qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 00/11] Lower TCG vector ops to LSX
@ 2023-08-28 15:19 Jiajie Chen
  2023-08-28 15:19 ` [PATCH 01/11] tcg/loongarch64: Import LSX instructions Jiajie Chen
                   ` (11 more replies)
  0 siblings, 12 replies; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen

This patch series allows qemu to utilize LSX instructions on LoongArch
machines to execute TCG vector ops.

Jiajie Chen (11):
  tcg/loongarch64: Import LSX instructions
  tcg/loongarch64: Lower basic tcg vec ops to LSX
  tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt
  tcg/loongarch64: Lower add/sub_vec to vadd/vsub
  tcg/loongarch64: Lower vector bitwise operations
  tcg/loongarch64: Lower neg_vec to vneg
  tcg/loongarch64: Lower mul_vec to vmul
  tcg/loongarch64: Lower vector min max ops
  tcg/loongarch64: Lower vector saturated ops
  tcg/loongarch64: Lower vector shift vector ops
  tcg/loongarch64: Lower bitsel_vec to vbitsel

 tcg/loongarch64/tcg-insn-defs.c.inc  | 6251 +++++++++++++++++++++++++-
 tcg/loongarch64/tcg-target-con-set.h |    5 +
 tcg/loongarch64/tcg-target-con-str.h |    1 +
 tcg/loongarch64/tcg-target.c.inc     |  414 +-
 tcg/loongarch64/tcg-target.h         |   37 +-
 tcg/loongarch64/tcg-target.opc.h     |   12 +
 6 files changed, 6601 insertions(+), 119 deletions(-)
 create mode 100644 tcg/loongarch64/tcg-target.opc.h

-- 
2.42.0



^ permalink raw reply	[flat|nested] 25+ messages in thread

* [PATCH 01/11] tcg/loongarch64: Import LSX instructions
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 15:19 ` [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
                   ` (10 subsequent siblings)
  11 siblings, 0 replies; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Add opcodes and encoder functions for LSX.

Generated from
https://github.com/jiegec/loongarch-opcodes/tree/qemu-lsx.

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-insn-defs.c.inc | 6251 ++++++++++++++++++++++++++-
 1 file changed, 6134 insertions(+), 117 deletions(-)

diff --git a/tcg/loongarch64/tcg-insn-defs.c.inc b/tcg/loongarch64/tcg-insn-defs.c.inc
index b5bb0c5e73..ee3b483b02 100644
--- a/tcg/loongarch64/tcg-insn-defs.c.inc
+++ b/tcg/loongarch64/tcg-insn-defs.c.inc
@@ -4,7 +4,7 @@
  *
  * This file is auto-generated by genqemutcgdefs from
  * https://github.com/loongson-community/loongarch-opcodes,
- * from commit 25ca7effe9d88101c1cf96c4005423643386d81f.
+ * from commit 8027da9a8157a8b47fc48ff1def292e09c5668bd.
  * DO NOT EDIT.
  */
 
@@ -74,6 +74,60 @@ typedef enum {
     OPC_ANDI = 0x03400000,
     OPC_ORI = 0x03800000,
     OPC_XORI = 0x03c00000,
+    OPC_VFMADD_S = 0x09100000,
+    OPC_VFMADD_D = 0x09200000,
+    OPC_VFMSUB_S = 0x09500000,
+    OPC_VFMSUB_D = 0x09600000,
+    OPC_VFNMADD_S = 0x09900000,
+    OPC_VFNMADD_D = 0x09a00000,
+    OPC_VFNMSUB_S = 0x09d00000,
+    OPC_VFNMSUB_D = 0x09e00000,
+    OPC_VFCMP_CAF_S = 0x0c500000,
+    OPC_VFCMP_SAF_S = 0x0c508000,
+    OPC_VFCMP_CLT_S = 0x0c510000,
+    OPC_VFCMP_SLT_S = 0x0c518000,
+    OPC_VFCMP_CEQ_S = 0x0c520000,
+    OPC_VFCMP_SEQ_S = 0x0c528000,
+    OPC_VFCMP_CLE_S = 0x0c530000,
+    OPC_VFCMP_SLE_S = 0x0c538000,
+    OPC_VFCMP_CUN_S = 0x0c540000,
+    OPC_VFCMP_SUN_S = 0x0c548000,
+    OPC_VFCMP_CULT_S = 0x0c550000,
+    OPC_VFCMP_SULT_S = 0x0c558000,
+    OPC_VFCMP_CUEQ_S = 0x0c560000,
+    OPC_VFCMP_SUEQ_S = 0x0c568000,
+    OPC_VFCMP_CULE_S = 0x0c570000,
+    OPC_VFCMP_SULE_S = 0x0c578000,
+    OPC_VFCMP_CNE_S = 0x0c580000,
+    OPC_VFCMP_SNE_S = 0x0c588000,
+    OPC_VFCMP_COR_S = 0x0c5a0000,
+    OPC_VFCMP_SOR_S = 0x0c5a8000,
+    OPC_VFCMP_CUNE_S = 0x0c5c0000,
+    OPC_VFCMP_SUNE_S = 0x0c5c8000,
+    OPC_VFCMP_CAF_D = 0x0c600000,
+    OPC_VFCMP_SAF_D = 0x0c608000,
+    OPC_VFCMP_CLT_D = 0x0c610000,
+    OPC_VFCMP_SLT_D = 0x0c618000,
+    OPC_VFCMP_CEQ_D = 0x0c620000,
+    OPC_VFCMP_SEQ_D = 0x0c628000,
+    OPC_VFCMP_CLE_D = 0x0c630000,
+    OPC_VFCMP_SLE_D = 0x0c638000,
+    OPC_VFCMP_CUN_D = 0x0c640000,
+    OPC_VFCMP_SUN_D = 0x0c648000,
+    OPC_VFCMP_CULT_D = 0x0c650000,
+    OPC_VFCMP_SULT_D = 0x0c658000,
+    OPC_VFCMP_CUEQ_D = 0x0c660000,
+    OPC_VFCMP_SUEQ_D = 0x0c668000,
+    OPC_VFCMP_CULE_D = 0x0c670000,
+    OPC_VFCMP_SULE_D = 0x0c678000,
+    OPC_VFCMP_CNE_D = 0x0c680000,
+    OPC_VFCMP_SNE_D = 0x0c688000,
+    OPC_VFCMP_COR_D = 0x0c6a0000,
+    OPC_VFCMP_SOR_D = 0x0c6a8000,
+    OPC_VFCMP_CUNE_D = 0x0c6c0000,
+    OPC_VFCMP_SUNE_D = 0x0c6c8000,
+    OPC_VBITSEL_V = 0x0d100000,
+    OPC_VSHUF_B = 0x0d500000,
     OPC_ADDU16I_D = 0x10000000,
     OPC_LU12I_W = 0x14000000,
     OPC_CU32I_D = 0x16000000,
@@ -92,6 +146,16 @@ typedef enum {
     OPC_LD_BU = 0x2a000000,
     OPC_LD_HU = 0x2a400000,
     OPC_LD_WU = 0x2a800000,
+    OPC_VLD = 0x2c000000,
+    OPC_VST = 0x2c400000,
+    OPC_VLDREPL_D = 0x30100000,
+    OPC_VLDREPL_W = 0x30200000,
+    OPC_VLDREPL_H = 0x30400000,
+    OPC_VLDREPL_B = 0x30800000,
+    OPC_VSTELM_D = 0x31100000,
+    OPC_VSTELM_W = 0x31200000,
+    OPC_VSTELM_H = 0x31400000,
+    OPC_VSTELM_B = 0x31800000,
     OPC_LDX_B = 0x38000000,
     OPC_LDX_H = 0x38040000,
     OPC_LDX_W = 0x38080000,
@@ -103,6 +167,8 @@ typedef enum {
     OPC_LDX_BU = 0x38200000,
     OPC_LDX_HU = 0x38240000,
     OPC_LDX_WU = 0x38280000,
+    OPC_VLDX = 0x38400000,
+    OPC_VSTX = 0x38440000,
     OPC_DBAR = 0x38720000,
     OPC_JIRL = 0x4c000000,
     OPC_B = 0x50000000,
@@ -113,6 +179,652 @@ typedef enum {
     OPC_BLE = 0x64000000,
     OPC_BGTU = 0x68000000,
     OPC_BLEU = 0x6c000000,
+    OPC_VSEQ_B = 0x70000000,
+    OPC_VSEQ_H = 0x70008000,
+    OPC_VSEQ_W = 0x70010000,
+    OPC_VSEQ_D = 0x70018000,
+    OPC_VSLE_B = 0x70020000,
+    OPC_VSLE_H = 0x70028000,
+    OPC_VSLE_W = 0x70030000,
+    OPC_VSLE_D = 0x70038000,
+    OPC_VSLE_BU = 0x70040000,
+    OPC_VSLE_HU = 0x70048000,
+    OPC_VSLE_WU = 0x70050000,
+    OPC_VSLE_DU = 0x70058000,
+    OPC_VSLT_B = 0x70060000,
+    OPC_VSLT_H = 0x70068000,
+    OPC_VSLT_W = 0x70070000,
+    OPC_VSLT_D = 0x70078000,
+    OPC_VSLT_BU = 0x70080000,
+    OPC_VSLT_HU = 0x70088000,
+    OPC_VSLT_WU = 0x70090000,
+    OPC_VSLT_DU = 0x70098000,
+    OPC_VADD_B = 0x700a0000,
+    OPC_VADD_H = 0x700a8000,
+    OPC_VADD_W = 0x700b0000,
+    OPC_VADD_D = 0x700b8000,
+    OPC_VSUB_B = 0x700c0000,
+    OPC_VSUB_H = 0x700c8000,
+    OPC_VSUB_W = 0x700d0000,
+    OPC_VSUB_D = 0x700d8000,
+    OPC_VADDWEV_H_B = 0x701e0000,
+    OPC_VADDWEV_W_H = 0x701e8000,
+    OPC_VADDWEV_D_W = 0x701f0000,
+    OPC_VADDWEV_Q_D = 0x701f8000,
+    OPC_VSUBWEV_H_B = 0x70200000,
+    OPC_VSUBWEV_W_H = 0x70208000,
+    OPC_VSUBWEV_D_W = 0x70210000,
+    OPC_VSUBWEV_Q_D = 0x70218000,
+    OPC_VADDWOD_H_B = 0x70220000,
+    OPC_VADDWOD_W_H = 0x70228000,
+    OPC_VADDWOD_D_W = 0x70230000,
+    OPC_VADDWOD_Q_D = 0x70238000,
+    OPC_VSUBWOD_H_B = 0x70240000,
+    OPC_VSUBWOD_W_H = 0x70248000,
+    OPC_VSUBWOD_D_W = 0x70250000,
+    OPC_VSUBWOD_Q_D = 0x70258000,
+    OPC_VADDWEV_H_BU = 0x702e0000,
+    OPC_VADDWEV_W_HU = 0x702e8000,
+    OPC_VADDWEV_D_WU = 0x702f0000,
+    OPC_VADDWEV_Q_DU = 0x702f8000,
+    OPC_VSUBWEV_H_BU = 0x70300000,
+    OPC_VSUBWEV_W_HU = 0x70308000,
+    OPC_VSUBWEV_D_WU = 0x70310000,
+    OPC_VSUBWEV_Q_DU = 0x70318000,
+    OPC_VADDWOD_H_BU = 0x70320000,
+    OPC_VADDWOD_W_HU = 0x70328000,
+    OPC_VADDWOD_D_WU = 0x70330000,
+    OPC_VADDWOD_Q_DU = 0x70338000,
+    OPC_VSUBWOD_H_BU = 0x70340000,
+    OPC_VSUBWOD_W_HU = 0x70348000,
+    OPC_VSUBWOD_D_WU = 0x70350000,
+    OPC_VSUBWOD_Q_DU = 0x70358000,
+    OPC_VADDWEV_H_BU_B = 0x703e0000,
+    OPC_VADDWEV_W_HU_H = 0x703e8000,
+    OPC_VADDWEV_D_WU_W = 0x703f0000,
+    OPC_VADDWEV_Q_DU_D = 0x703f8000,
+    OPC_VADDWOD_H_BU_B = 0x70400000,
+    OPC_VADDWOD_W_HU_H = 0x70408000,
+    OPC_VADDWOD_D_WU_W = 0x70410000,
+    OPC_VADDWOD_Q_DU_D = 0x70418000,
+    OPC_VSADD_B = 0x70460000,
+    OPC_VSADD_H = 0x70468000,
+    OPC_VSADD_W = 0x70470000,
+    OPC_VSADD_D = 0x70478000,
+    OPC_VSSUB_B = 0x70480000,
+    OPC_VSSUB_H = 0x70488000,
+    OPC_VSSUB_W = 0x70490000,
+    OPC_VSSUB_D = 0x70498000,
+    OPC_VSADD_BU = 0x704a0000,
+    OPC_VSADD_HU = 0x704a8000,
+    OPC_VSADD_WU = 0x704b0000,
+    OPC_VSADD_DU = 0x704b8000,
+    OPC_VSSUB_BU = 0x704c0000,
+    OPC_VSSUB_HU = 0x704c8000,
+    OPC_VSSUB_WU = 0x704d0000,
+    OPC_VSSUB_DU = 0x704d8000,
+    OPC_VHADDW_H_B = 0x70540000,
+    OPC_VHADDW_W_H = 0x70548000,
+    OPC_VHADDW_D_W = 0x70550000,
+    OPC_VHADDW_Q_D = 0x70558000,
+    OPC_VHSUBW_H_B = 0x70560000,
+    OPC_VHSUBW_W_H = 0x70568000,
+    OPC_VHSUBW_D_W = 0x70570000,
+    OPC_VHSUBW_Q_D = 0x70578000,
+    OPC_VHADDW_HU_BU = 0x70580000,
+    OPC_VHADDW_WU_HU = 0x70588000,
+    OPC_VHADDW_DU_WU = 0x70590000,
+    OPC_VHADDW_QU_DU = 0x70598000,
+    OPC_VHSUBW_HU_BU = 0x705a0000,
+    OPC_VHSUBW_WU_HU = 0x705a8000,
+    OPC_VHSUBW_DU_WU = 0x705b0000,
+    OPC_VHSUBW_QU_DU = 0x705b8000,
+    OPC_VADDA_B = 0x705c0000,
+    OPC_VADDA_H = 0x705c8000,
+    OPC_VADDA_W = 0x705d0000,
+    OPC_VADDA_D = 0x705d8000,
+    OPC_VABSD_B = 0x70600000,
+    OPC_VABSD_H = 0x70608000,
+    OPC_VABSD_W = 0x70610000,
+    OPC_VABSD_D = 0x70618000,
+    OPC_VABSD_BU = 0x70620000,
+    OPC_VABSD_HU = 0x70628000,
+    OPC_VABSD_WU = 0x70630000,
+    OPC_VABSD_DU = 0x70638000,
+    OPC_VAVG_B = 0x70640000,
+    OPC_VAVG_H = 0x70648000,
+    OPC_VAVG_W = 0x70650000,
+    OPC_VAVG_D = 0x70658000,
+    OPC_VAVG_BU = 0x70660000,
+    OPC_VAVG_HU = 0x70668000,
+    OPC_VAVG_WU = 0x70670000,
+    OPC_VAVG_DU = 0x70678000,
+    OPC_VAVGR_B = 0x70680000,
+    OPC_VAVGR_H = 0x70688000,
+    OPC_VAVGR_W = 0x70690000,
+    OPC_VAVGR_D = 0x70698000,
+    OPC_VAVGR_BU = 0x706a0000,
+    OPC_VAVGR_HU = 0x706a8000,
+    OPC_VAVGR_WU = 0x706b0000,
+    OPC_VAVGR_DU = 0x706b8000,
+    OPC_VMAX_B = 0x70700000,
+    OPC_VMAX_H = 0x70708000,
+    OPC_VMAX_W = 0x70710000,
+    OPC_VMAX_D = 0x70718000,
+    OPC_VMIN_B = 0x70720000,
+    OPC_VMIN_H = 0x70728000,
+    OPC_VMIN_W = 0x70730000,
+    OPC_VMIN_D = 0x70738000,
+    OPC_VMAX_BU = 0x70740000,
+    OPC_VMAX_HU = 0x70748000,
+    OPC_VMAX_WU = 0x70750000,
+    OPC_VMAX_DU = 0x70758000,
+    OPC_VMIN_BU = 0x70760000,
+    OPC_VMIN_HU = 0x70768000,
+    OPC_VMIN_WU = 0x70770000,
+    OPC_VMIN_DU = 0x70778000,
+    OPC_VMUL_B = 0x70840000,
+    OPC_VMUL_H = 0x70848000,
+    OPC_VMUL_W = 0x70850000,
+    OPC_VMUL_D = 0x70858000,
+    OPC_VMUH_B = 0x70860000,
+    OPC_VMUH_H = 0x70868000,
+    OPC_VMUH_W = 0x70870000,
+    OPC_VMUH_D = 0x70878000,
+    OPC_VMUH_BU = 0x70880000,
+    OPC_VMUH_HU = 0x70888000,
+    OPC_VMUH_WU = 0x70890000,
+    OPC_VMUH_DU = 0x70898000,
+    OPC_VMULWEV_H_B = 0x70900000,
+    OPC_VMULWEV_W_H = 0x70908000,
+    OPC_VMULWEV_D_W = 0x70910000,
+    OPC_VMULWEV_Q_D = 0x70918000,
+    OPC_VMULWOD_H_B = 0x70920000,
+    OPC_VMULWOD_W_H = 0x70928000,
+    OPC_VMULWOD_D_W = 0x70930000,
+    OPC_VMULWOD_Q_D = 0x70938000,
+    OPC_VMULWEV_H_BU = 0x70980000,
+    OPC_VMULWEV_W_HU = 0x70988000,
+    OPC_VMULWEV_D_WU = 0x70990000,
+    OPC_VMULWEV_Q_DU = 0x70998000,
+    OPC_VMULWOD_H_BU = 0x709a0000,
+    OPC_VMULWOD_W_HU = 0x709a8000,
+    OPC_VMULWOD_D_WU = 0x709b0000,
+    OPC_VMULWOD_Q_DU = 0x709b8000,
+    OPC_VMULWEV_H_BU_B = 0x70a00000,
+    OPC_VMULWEV_W_HU_H = 0x70a08000,
+    OPC_VMULWEV_D_WU_W = 0x70a10000,
+    OPC_VMULWEV_Q_DU_D = 0x70a18000,
+    OPC_VMULWOD_H_BU_B = 0x70a20000,
+    OPC_VMULWOD_W_HU_H = 0x70a28000,
+    OPC_VMULWOD_D_WU_W = 0x70a30000,
+    OPC_VMULWOD_Q_DU_D = 0x70a38000,
+    OPC_VMADD_B = 0x70a80000,
+    OPC_VMADD_H = 0x70a88000,
+    OPC_VMADD_W = 0x70a90000,
+    OPC_VMADD_D = 0x70a98000,
+    OPC_VMSUB_B = 0x70aa0000,
+    OPC_VMSUB_H = 0x70aa8000,
+    OPC_VMSUB_W = 0x70ab0000,
+    OPC_VMSUB_D = 0x70ab8000,
+    OPC_VMADDWEV_H_B = 0x70ac0000,
+    OPC_VMADDWEV_W_H = 0x70ac8000,
+    OPC_VMADDWEV_D_W = 0x70ad0000,
+    OPC_VMADDWEV_Q_D = 0x70ad8000,
+    OPC_VMADDWOD_H_B = 0x70ae0000,
+    OPC_VMADDWOD_W_H = 0x70ae8000,
+    OPC_VMADDWOD_D_W = 0x70af0000,
+    OPC_VMADDWOD_Q_D = 0x70af8000,
+    OPC_VMADDWEV_H_BU = 0x70b40000,
+    OPC_VMADDWEV_W_HU = 0x70b48000,
+    OPC_VMADDWEV_D_WU = 0x70b50000,
+    OPC_VMADDWEV_Q_DU = 0x70b58000,
+    OPC_VMADDWOD_H_BU = 0x70b60000,
+    OPC_VMADDWOD_W_HU = 0x70b68000,
+    OPC_VMADDWOD_D_WU = 0x70b70000,
+    OPC_VMADDWOD_Q_DU = 0x70b78000,
+    OPC_VMADDWEV_H_BU_B = 0x70bc0000,
+    OPC_VMADDWEV_W_HU_H = 0x70bc8000,
+    OPC_VMADDWEV_D_WU_W = 0x70bd0000,
+    OPC_VMADDWEV_Q_DU_D = 0x70bd8000,
+    OPC_VMADDWOD_H_BU_B = 0x70be0000,
+    OPC_VMADDWOD_W_HU_H = 0x70be8000,
+    OPC_VMADDWOD_D_WU_W = 0x70bf0000,
+    OPC_VMADDWOD_Q_DU_D = 0x70bf8000,
+    OPC_VDIV_B = 0x70e00000,
+    OPC_VDIV_H = 0x70e08000,
+    OPC_VDIV_W = 0x70e10000,
+    OPC_VDIV_D = 0x70e18000,
+    OPC_VMOD_B = 0x70e20000,
+    OPC_VMOD_H = 0x70e28000,
+    OPC_VMOD_W = 0x70e30000,
+    OPC_VMOD_D = 0x70e38000,
+    OPC_VDIV_BU = 0x70e40000,
+    OPC_VDIV_HU = 0x70e48000,
+    OPC_VDIV_WU = 0x70e50000,
+    OPC_VDIV_DU = 0x70e58000,
+    OPC_VMOD_BU = 0x70e60000,
+    OPC_VMOD_HU = 0x70e68000,
+    OPC_VMOD_WU = 0x70e70000,
+    OPC_VMOD_DU = 0x70e78000,
+    OPC_VSLL_B = 0x70e80000,
+    OPC_VSLL_H = 0x70e88000,
+    OPC_VSLL_W = 0x70e90000,
+    OPC_VSLL_D = 0x70e98000,
+    OPC_VSRL_B = 0x70ea0000,
+    OPC_VSRL_H = 0x70ea8000,
+    OPC_VSRL_W = 0x70eb0000,
+    OPC_VSRL_D = 0x70eb8000,
+    OPC_VSRA_B = 0x70ec0000,
+    OPC_VSRA_H = 0x70ec8000,
+    OPC_VSRA_W = 0x70ed0000,
+    OPC_VSRA_D = 0x70ed8000,
+    OPC_VROTR_B = 0x70ee0000,
+    OPC_VROTR_H = 0x70ee8000,
+    OPC_VROTR_W = 0x70ef0000,
+    OPC_VROTR_D = 0x70ef8000,
+    OPC_VSRLR_B = 0x70f00000,
+    OPC_VSRLR_H = 0x70f08000,
+    OPC_VSRLR_W = 0x70f10000,
+    OPC_VSRLR_D = 0x70f18000,
+    OPC_VSRAR_B = 0x70f20000,
+    OPC_VSRAR_H = 0x70f28000,
+    OPC_VSRAR_W = 0x70f30000,
+    OPC_VSRAR_D = 0x70f38000,
+    OPC_VSRLN_B_H = 0x70f48000,
+    OPC_VSRLN_H_W = 0x70f50000,
+    OPC_VSRLN_W_D = 0x70f58000,
+    OPC_VSRAN_B_H = 0x70f68000,
+    OPC_VSRAN_H_W = 0x70f70000,
+    OPC_VSRAN_W_D = 0x70f78000,
+    OPC_VSRLRN_B_H = 0x70f88000,
+    OPC_VSRLRN_H_W = 0x70f90000,
+    OPC_VSRLRN_W_D = 0x70f98000,
+    OPC_VSRARN_B_H = 0x70fa8000,
+    OPC_VSRARN_H_W = 0x70fb0000,
+    OPC_VSRARN_W_D = 0x70fb8000,
+    OPC_VSSRLN_B_H = 0x70fc8000,
+    OPC_VSSRLN_H_W = 0x70fd0000,
+    OPC_VSSRLN_W_D = 0x70fd8000,
+    OPC_VSSRAN_B_H = 0x70fe8000,
+    OPC_VSSRAN_H_W = 0x70ff0000,
+    OPC_VSSRAN_W_D = 0x70ff8000,
+    OPC_VSSRLRN_B_H = 0x71008000,
+    OPC_VSSRLRN_H_W = 0x71010000,
+    OPC_VSSRLRN_W_D = 0x71018000,
+    OPC_VSSRARN_B_H = 0x71028000,
+    OPC_VSSRARN_H_W = 0x71030000,
+    OPC_VSSRARN_W_D = 0x71038000,
+    OPC_VSSRLN_BU_H = 0x71048000,
+    OPC_VSSRLN_HU_W = 0x71050000,
+    OPC_VSSRLN_WU_D = 0x71058000,
+    OPC_VSSRAN_BU_H = 0x71068000,
+    OPC_VSSRAN_HU_W = 0x71070000,
+    OPC_VSSRAN_WU_D = 0x71078000,
+    OPC_VSSRLRN_BU_H = 0x71088000,
+    OPC_VSSRLRN_HU_W = 0x71090000,
+    OPC_VSSRLRN_WU_D = 0x71098000,
+    OPC_VSSRARN_BU_H = 0x710a8000,
+    OPC_VSSRARN_HU_W = 0x710b0000,
+    OPC_VSSRARN_WU_D = 0x710b8000,
+    OPC_VBITCLR_B = 0x710c0000,
+    OPC_VBITCLR_H = 0x710c8000,
+    OPC_VBITCLR_W = 0x710d0000,
+    OPC_VBITCLR_D = 0x710d8000,
+    OPC_VBITSET_B = 0x710e0000,
+    OPC_VBITSET_H = 0x710e8000,
+    OPC_VBITSET_W = 0x710f0000,
+    OPC_VBITSET_D = 0x710f8000,
+    OPC_VBITREV_B = 0x71100000,
+    OPC_VBITREV_H = 0x71108000,
+    OPC_VBITREV_W = 0x71110000,
+    OPC_VBITREV_D = 0x71118000,
+    OPC_VPACKEV_B = 0x71160000,
+    OPC_VPACKEV_H = 0x71168000,
+    OPC_VPACKEV_W = 0x71170000,
+    OPC_VPACKEV_D = 0x71178000,
+    OPC_VPACKOD_B = 0x71180000,
+    OPC_VPACKOD_H = 0x71188000,
+    OPC_VPACKOD_W = 0x71190000,
+    OPC_VPACKOD_D = 0x71198000,
+    OPC_VILVL_B = 0x711a0000,
+    OPC_VILVL_H = 0x711a8000,
+    OPC_VILVL_W = 0x711b0000,
+    OPC_VILVL_D = 0x711b8000,
+    OPC_VILVH_B = 0x711c0000,
+    OPC_VILVH_H = 0x711c8000,
+    OPC_VILVH_W = 0x711d0000,
+    OPC_VILVH_D = 0x711d8000,
+    OPC_VPICKEV_B = 0x711e0000,
+    OPC_VPICKEV_H = 0x711e8000,
+    OPC_VPICKEV_W = 0x711f0000,
+    OPC_VPICKEV_D = 0x711f8000,
+    OPC_VPICKOD_B = 0x71200000,
+    OPC_VPICKOD_H = 0x71208000,
+    OPC_VPICKOD_W = 0x71210000,
+    OPC_VPICKOD_D = 0x71218000,
+    OPC_VREPLVE_B = 0x71220000,
+    OPC_VREPLVE_H = 0x71228000,
+    OPC_VREPLVE_W = 0x71230000,
+    OPC_VREPLVE_D = 0x71238000,
+    OPC_VAND_V = 0x71260000,
+    OPC_VOR_V = 0x71268000,
+    OPC_VXOR_V = 0x71270000,
+    OPC_VNOR_V = 0x71278000,
+    OPC_VANDN_V = 0x71280000,
+    OPC_VORN_V = 0x71288000,
+    OPC_VFRSTP_B = 0x712b0000,
+    OPC_VFRSTP_H = 0x712b8000,
+    OPC_VADD_Q = 0x712d0000,
+    OPC_VSUB_Q = 0x712d8000,
+    OPC_VSIGNCOV_B = 0x712e0000,
+    OPC_VSIGNCOV_H = 0x712e8000,
+    OPC_VSIGNCOV_W = 0x712f0000,
+    OPC_VSIGNCOV_D = 0x712f8000,
+    OPC_VFADD_S = 0x71308000,
+    OPC_VFADD_D = 0x71310000,
+    OPC_VFSUB_S = 0x71328000,
+    OPC_VFSUB_D = 0x71330000,
+    OPC_VFMUL_S = 0x71388000,
+    OPC_VFMUL_D = 0x71390000,
+    OPC_VFDIV_S = 0x713a8000,
+    OPC_VFDIV_D = 0x713b0000,
+    OPC_VFMAX_S = 0x713c8000,
+    OPC_VFMAX_D = 0x713d0000,
+    OPC_VFMIN_S = 0x713e8000,
+    OPC_VFMIN_D = 0x713f0000,
+    OPC_VFMAXA_S = 0x71408000,
+    OPC_VFMAXA_D = 0x71410000,
+    OPC_VFMINA_S = 0x71428000,
+    OPC_VFMINA_D = 0x71430000,
+    OPC_VFCVT_H_S = 0x71460000,
+    OPC_VFCVT_S_D = 0x71468000,
+    OPC_VFFINT_S_L = 0x71480000,
+    OPC_VFTINT_W_D = 0x71498000,
+    OPC_VFTINTRM_W_D = 0x714a0000,
+    OPC_VFTINTRP_W_D = 0x714a8000,
+    OPC_VFTINTRZ_W_D = 0x714b0000,
+    OPC_VFTINTRNE_W_D = 0x714b8000,
+    OPC_VSHUF_H = 0x717a8000,
+    OPC_VSHUF_W = 0x717b0000,
+    OPC_VSHUF_D = 0x717b8000,
+    OPC_VSEQI_B = 0x72800000,
+    OPC_VSEQI_H = 0x72808000,
+    OPC_VSEQI_W = 0x72810000,
+    OPC_VSEQI_D = 0x72818000,
+    OPC_VSLEI_B = 0x72820000,
+    OPC_VSLEI_H = 0x72828000,
+    OPC_VSLEI_W = 0x72830000,
+    OPC_VSLEI_D = 0x72838000,
+    OPC_VSLEI_BU = 0x72840000,
+    OPC_VSLEI_HU = 0x72848000,
+    OPC_VSLEI_WU = 0x72850000,
+    OPC_VSLEI_DU = 0x72858000,
+    OPC_VSLTI_B = 0x72860000,
+    OPC_VSLTI_H = 0x72868000,
+    OPC_VSLTI_W = 0x72870000,
+    OPC_VSLTI_D = 0x72878000,
+    OPC_VSLTI_BU = 0x72880000,
+    OPC_VSLTI_HU = 0x72888000,
+    OPC_VSLTI_WU = 0x72890000,
+    OPC_VSLTI_DU = 0x72898000,
+    OPC_VADDI_BU = 0x728a0000,
+    OPC_VADDI_HU = 0x728a8000,
+    OPC_VADDI_WU = 0x728b0000,
+    OPC_VADDI_DU = 0x728b8000,
+    OPC_VSUBI_BU = 0x728c0000,
+    OPC_VSUBI_HU = 0x728c8000,
+    OPC_VSUBI_WU = 0x728d0000,
+    OPC_VSUBI_DU = 0x728d8000,
+    OPC_VBSLL_V = 0x728e0000,
+    OPC_VBSRL_V = 0x728e8000,
+    OPC_VMAXI_B = 0x72900000,
+    OPC_VMAXI_H = 0x72908000,
+    OPC_VMAXI_W = 0x72910000,
+    OPC_VMAXI_D = 0x72918000,
+    OPC_VMINI_B = 0x72920000,
+    OPC_VMINI_H = 0x72928000,
+    OPC_VMINI_W = 0x72930000,
+    OPC_VMINI_D = 0x72938000,
+    OPC_VMAXI_BU = 0x72940000,
+    OPC_VMAXI_HU = 0x72948000,
+    OPC_VMAXI_WU = 0x72950000,
+    OPC_VMAXI_DU = 0x72958000,
+    OPC_VMINI_BU = 0x72960000,
+    OPC_VMINI_HU = 0x72968000,
+    OPC_VMINI_WU = 0x72970000,
+    OPC_VMINI_DU = 0x72978000,
+    OPC_VFRSTPI_B = 0x729a0000,
+    OPC_VFRSTPI_H = 0x729a8000,
+    OPC_VCLO_B = 0x729c0000,
+    OPC_VCLO_H = 0x729c0400,
+    OPC_VCLO_W = 0x729c0800,
+    OPC_VCLO_D = 0x729c0c00,
+    OPC_VCLZ_B = 0x729c1000,
+    OPC_VCLZ_H = 0x729c1400,
+    OPC_VCLZ_W = 0x729c1800,
+    OPC_VCLZ_D = 0x729c1c00,
+    OPC_VPCNT_B = 0x729c2000,
+    OPC_VPCNT_H = 0x729c2400,
+    OPC_VPCNT_W = 0x729c2800,
+    OPC_VPCNT_D = 0x729c2c00,
+    OPC_VNEG_B = 0x729c3000,
+    OPC_VNEG_H = 0x729c3400,
+    OPC_VNEG_W = 0x729c3800,
+    OPC_VNEG_D = 0x729c3c00,
+    OPC_VMSKLTZ_B = 0x729c4000,
+    OPC_VMSKLTZ_H = 0x729c4400,
+    OPC_VMSKLTZ_W = 0x729c4800,
+    OPC_VMSKLTZ_D = 0x729c4c00,
+    OPC_VMSKGEZ_B = 0x729c5000,
+    OPC_VMSKNZ_B = 0x729c6000,
+    OPC_VSETEQZ_V = 0x729c9800,
+    OPC_VSETNEZ_V = 0x729c9c00,
+    OPC_VSETANYEQZ_B = 0x729ca000,
+    OPC_VSETANYEQZ_H = 0x729ca400,
+    OPC_VSETANYEQZ_W = 0x729ca800,
+    OPC_VSETANYEQZ_D = 0x729cac00,
+    OPC_VSETALLNEZ_B = 0x729cb000,
+    OPC_VSETALLNEZ_H = 0x729cb400,
+    OPC_VSETALLNEZ_W = 0x729cb800,
+    OPC_VSETALLNEZ_D = 0x729cbc00,
+    OPC_VFLOGB_S = 0x729cc400,
+    OPC_VFLOGB_D = 0x729cc800,
+    OPC_VFCLASS_S = 0x729cd400,
+    OPC_VFCLASS_D = 0x729cd800,
+    OPC_VFSQRT_S = 0x729ce400,
+    OPC_VFSQRT_D = 0x729ce800,
+    OPC_VFRECIP_S = 0x729cf400,
+    OPC_VFRECIP_D = 0x729cf800,
+    OPC_VFRSQRT_S = 0x729d0400,
+    OPC_VFRSQRT_D = 0x729d0800,
+    OPC_VFRINT_S = 0x729d3400,
+    OPC_VFRINT_D = 0x729d3800,
+    OPC_VFRINTRM_S = 0x729d4400,
+    OPC_VFRINTRM_D = 0x729d4800,
+    OPC_VFRINTRP_S = 0x729d5400,
+    OPC_VFRINTRP_D = 0x729d5800,
+    OPC_VFRINTRZ_S = 0x729d6400,
+    OPC_VFRINTRZ_D = 0x729d6800,
+    OPC_VFRINTRNE_S = 0x729d7400,
+    OPC_VFRINTRNE_D = 0x729d7800,
+    OPC_VFCVTL_S_H = 0x729de800,
+    OPC_VFCVTH_S_H = 0x729dec00,
+    OPC_VFCVTL_D_S = 0x729df000,
+    OPC_VFCVTH_D_S = 0x729df400,
+    OPC_VFFINT_S_W = 0x729e0000,
+    OPC_VFFINT_S_WU = 0x729e0400,
+    OPC_VFFINT_D_L = 0x729e0800,
+    OPC_VFFINT_D_LU = 0x729e0c00,
+    OPC_VFFINTL_D_W = 0x729e1000,
+    OPC_VFFINTH_D_W = 0x729e1400,
+    OPC_VFTINT_W_S = 0x729e3000,
+    OPC_VFTINT_L_D = 0x729e3400,
+    OPC_VFTINTRM_W_S = 0x729e3800,
+    OPC_VFTINTRM_L_D = 0x729e3c00,
+    OPC_VFTINTRP_W_S = 0x729e4000,
+    OPC_VFTINTRP_L_D = 0x729e4400,
+    OPC_VFTINTRZ_W_S = 0x729e4800,
+    OPC_VFTINTRZ_L_D = 0x729e4c00,
+    OPC_VFTINTRNE_W_S = 0x729e5000,
+    OPC_VFTINTRNE_L_D = 0x729e5400,
+    OPC_VFTINT_WU_S = 0x729e5800,
+    OPC_VFTINT_LU_D = 0x729e5c00,
+    OPC_VFTINTRZ_WU_S = 0x729e7000,
+    OPC_VFTINTRZ_LU_D = 0x729e7400,
+    OPC_VFTINTL_L_S = 0x729e8000,
+    OPC_VFTINTH_L_S = 0x729e8400,
+    OPC_VFTINTRML_L_S = 0x729e8800,
+    OPC_VFTINTRMH_L_S = 0x729e8c00,
+    OPC_VFTINTRPL_L_S = 0x729e9000,
+    OPC_VFTINTRPH_L_S = 0x729e9400,
+    OPC_VFTINTRZL_L_S = 0x729e9800,
+    OPC_VFTINTRZH_L_S = 0x729e9c00,
+    OPC_VFTINTRNEL_L_S = 0x729ea000,
+    OPC_VFTINTRNEH_L_S = 0x729ea400,
+    OPC_VEXTH_H_B = 0x729ee000,
+    OPC_VEXTH_W_H = 0x729ee400,
+    OPC_VEXTH_D_W = 0x729ee800,
+    OPC_VEXTH_Q_D = 0x729eec00,
+    OPC_VEXTH_HU_BU = 0x729ef000,
+    OPC_VEXTH_WU_HU = 0x729ef400,
+    OPC_VEXTH_DU_WU = 0x729ef800,
+    OPC_VEXTH_QU_DU = 0x729efc00,
+    OPC_VREPLGR2VR_B = 0x729f0000,
+    OPC_VREPLGR2VR_H = 0x729f0400,
+    OPC_VREPLGR2VR_W = 0x729f0800,
+    OPC_VREPLGR2VR_D = 0x729f0c00,
+    OPC_VROTRI_B = 0x72a02000,
+    OPC_VROTRI_H = 0x72a04000,
+    OPC_VROTRI_W = 0x72a08000,
+    OPC_VROTRI_D = 0x72a10000,
+    OPC_VSRLRI_B = 0x72a42000,
+    OPC_VSRLRI_H = 0x72a44000,
+    OPC_VSRLRI_W = 0x72a48000,
+    OPC_VSRLRI_D = 0x72a50000,
+    OPC_VSRARI_B = 0x72a82000,
+    OPC_VSRARI_H = 0x72a84000,
+    OPC_VSRARI_W = 0x72a88000,
+    OPC_VSRARI_D = 0x72a90000,
+    OPC_VINSGR2VR_B = 0x72eb8000,
+    OPC_VINSGR2VR_H = 0x72ebc000,
+    OPC_VINSGR2VR_W = 0x72ebe000,
+    OPC_VINSGR2VR_D = 0x72ebf000,
+    OPC_VPICKVE2GR_B = 0x72ef8000,
+    OPC_VPICKVE2GR_H = 0x72efc000,
+    OPC_VPICKVE2GR_W = 0x72efe000,
+    OPC_VPICKVE2GR_D = 0x72eff000,
+    OPC_VPICKVE2GR_BU = 0x72f38000,
+    OPC_VPICKVE2GR_HU = 0x72f3c000,
+    OPC_VPICKVE2GR_WU = 0x72f3e000,
+    OPC_VPICKVE2GR_DU = 0x72f3f000,
+    OPC_VREPLVEI_B = 0x72f78000,
+    OPC_VREPLVEI_H = 0x72f7c000,
+    OPC_VREPLVEI_W = 0x72f7e000,
+    OPC_VREPLVEI_D = 0x72f7f000,
+    OPC_VSLLWIL_H_B = 0x73082000,
+    OPC_VSLLWIL_W_H = 0x73084000,
+    OPC_VSLLWIL_D_W = 0x73088000,
+    OPC_VEXTL_Q_D = 0x73090000,
+    OPC_VSLLWIL_HU_BU = 0x730c2000,
+    OPC_VSLLWIL_WU_HU = 0x730c4000,
+    OPC_VSLLWIL_DU_WU = 0x730c8000,
+    OPC_VEXTL_QU_DU = 0x730d0000,
+    OPC_VBITCLRI_B = 0x73102000,
+    OPC_VBITCLRI_H = 0x73104000,
+    OPC_VBITCLRI_W = 0x73108000,
+    OPC_VBITCLRI_D = 0x73110000,
+    OPC_VBITSETI_B = 0x73142000,
+    OPC_VBITSETI_H = 0x73144000,
+    OPC_VBITSETI_W = 0x73148000,
+    OPC_VBITSETI_D = 0x73150000,
+    OPC_VBITREVI_B = 0x73182000,
+    OPC_VBITREVI_H = 0x73184000,
+    OPC_VBITREVI_W = 0x73188000,
+    OPC_VBITREVI_D = 0x73190000,
+    OPC_VSAT_B = 0x73242000,
+    OPC_VSAT_H = 0x73244000,
+    OPC_VSAT_W = 0x73248000,
+    OPC_VSAT_D = 0x73250000,
+    OPC_VSAT_BU = 0x73282000,
+    OPC_VSAT_HU = 0x73284000,
+    OPC_VSAT_WU = 0x73288000,
+    OPC_VSAT_DU = 0x73290000,
+    OPC_VSLLI_B = 0x732c2000,
+    OPC_VSLLI_H = 0x732c4000,
+    OPC_VSLLI_W = 0x732c8000,
+    OPC_VSLLI_D = 0x732d0000,
+    OPC_VSRLI_B = 0x73302000,
+    OPC_VSRLI_H = 0x73304000,
+    OPC_VSRLI_W = 0x73308000,
+    OPC_VSRLI_D = 0x73310000,
+    OPC_VSRAI_B = 0x73342000,
+    OPC_VSRAI_H = 0x73344000,
+    OPC_VSRAI_W = 0x73348000,
+    OPC_VSRAI_D = 0x73350000,
+    OPC_VSRLNI_B_H = 0x73404000,
+    OPC_VSRLNI_H_W = 0x73408000,
+    OPC_VSRLNI_W_D = 0x73410000,
+    OPC_VSRLNI_D_Q = 0x73420000,
+    OPC_VSRLRNI_B_H = 0x73444000,
+    OPC_VSRLRNI_H_W = 0x73448000,
+    OPC_VSRLRNI_W_D = 0x73450000,
+    OPC_VSRLRNI_D_Q = 0x73460000,
+    OPC_VSSRLNI_B_H = 0x73484000,
+    OPC_VSSRLNI_H_W = 0x73488000,
+    OPC_VSSRLNI_W_D = 0x73490000,
+    OPC_VSSRLNI_D_Q = 0x734a0000,
+    OPC_VSSRLNI_BU_H = 0x734c4000,
+    OPC_VSSRLNI_HU_W = 0x734c8000,
+    OPC_VSSRLNI_WU_D = 0x734d0000,
+    OPC_VSSRLNI_DU_Q = 0x734e0000,
+    OPC_VSSRLRNI_B_H = 0x73504000,
+    OPC_VSSRLRNI_H_W = 0x73508000,
+    OPC_VSSRLRNI_W_D = 0x73510000,
+    OPC_VSSRLRNI_D_Q = 0x73520000,
+    OPC_VSSRLRNI_BU_H = 0x73544000,
+    OPC_VSSRLRNI_HU_W = 0x73548000,
+    OPC_VSSRLRNI_WU_D = 0x73550000,
+    OPC_VSSRLRNI_DU_Q = 0x73560000,
+    OPC_VSRANI_B_H = 0x73584000,
+    OPC_VSRANI_H_W = 0x73588000,
+    OPC_VSRANI_W_D = 0x73590000,
+    OPC_VSRANI_D_Q = 0x735a0000,
+    OPC_VSRARNI_B_H = 0x735c4000,
+    OPC_VSRARNI_H_W = 0x735c8000,
+    OPC_VSRARNI_W_D = 0x735d0000,
+    OPC_VSRARNI_D_Q = 0x735e0000,
+    OPC_VSSRANI_B_H = 0x73604000,
+    OPC_VSSRANI_H_W = 0x73608000,
+    OPC_VSSRANI_W_D = 0x73610000,
+    OPC_VSSRANI_D_Q = 0x73620000,
+    OPC_VSSRANI_BU_H = 0x73644000,
+    OPC_VSSRANI_HU_W = 0x73648000,
+    OPC_VSSRANI_WU_D = 0x73650000,
+    OPC_VSSRANI_DU_Q = 0x73660000,
+    OPC_VSSRARNI_B_H = 0x73684000,
+    OPC_VSSRARNI_H_W = 0x73688000,
+    OPC_VSSRARNI_W_D = 0x73690000,
+    OPC_VSSRARNI_D_Q = 0x736a0000,
+    OPC_VSSRARNI_BU_H = 0x736c4000,
+    OPC_VSSRARNI_HU_W = 0x736c8000,
+    OPC_VSSRARNI_WU_D = 0x736d0000,
+    OPC_VSSRARNI_DU_Q = 0x736e0000,
+    OPC_VEXTRINS_D = 0x73800000,
+    OPC_VEXTRINS_W = 0x73840000,
+    OPC_VEXTRINS_H = 0x73880000,
+    OPC_VEXTRINS_B = 0x738c0000,
+    OPC_VSHUF4I_B = 0x73900000,
+    OPC_VSHUF4I_H = 0x73940000,
+    OPC_VSHUF4I_W = 0x73980000,
+    OPC_VSHUF4I_D = 0x739c0000,
+    OPC_VBITSELI_B = 0x73c40000,
+    OPC_VANDI_B = 0x73d00000,
+    OPC_VORI_B = 0x73d40000,
+    OPC_VXORI_B = 0x73d80000,
+    OPC_VNORI_B = 0x73dc0000,
+    OPC_VLDI = 0x73e00000,
+    OPC_VPERMI_W = 0x73e40000,
 } LoongArchInsn;
 
 static int32_t __attribute__((unused))
@@ -133,6 +845,13 @@ encode_djk_slots(LoongArchInsn opc, uint32_t d, uint32_t j, uint32_t k)
     return opc | d | j << 5 | k << 10;
 }
 
+static int32_t __attribute__((unused))
+encode_djka_slots(LoongArchInsn opc, uint32_t d, uint32_t j, uint32_t k,
+                  uint32_t a)
+{
+    return opc | d | j << 5 | k << 10 | a << 15;
+}
+
 static int32_t __attribute__((unused))
 encode_djkm_slots(LoongArchInsn opc, uint32_t d, uint32_t j, uint32_t k,
                   uint32_t m)
@@ -140,12 +859,27 @@ encode_djkm_slots(LoongArchInsn opc, uint32_t d, uint32_t j, uint32_t k,
     return opc | d | j << 5 | k << 10 | m << 16;
 }
 
+static int32_t __attribute__((unused))
+encode_djkn_slots(LoongArchInsn opc, uint32_t d, uint32_t j, uint32_t k,
+                  uint32_t n)
+{
+    return opc | d | j << 5 | k << 10 | n << 18;
+}
+
 static int32_t __attribute__((unused))
 encode_dk_slots(LoongArchInsn opc, uint32_t d, uint32_t k)
 {
     return opc | d | k << 10;
 }
 
+static int32_t __attribute__((unused))
+encode_cdvj_insn(LoongArchInsn opc, TCGReg cd, TCGReg vj)
+{
+    tcg_debug_assert(cd >= 0 && cd <= 0x7);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    return encode_dj_slots(opc, cd, vj & 0x1f);
+}
+
 static int32_t __attribute__((unused))
 encode_dj_insn(LoongArchInsn opc, TCGReg d, TCGReg j)
 {
@@ -238,6 +972,42 @@ encode_dsj20_insn(LoongArchInsn opc, TCGReg d, int32_t sj20)
     return encode_dj_slots(opc, d, sj20 & 0xfffff);
 }
 
+static int32_t __attribute__((unused))
+encode_dvjuk1_insn(LoongArchInsn opc, TCGReg d, TCGReg vj, uint32_t uk1)
+{
+    tcg_debug_assert(d >= 0 && d <= 0x1f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk1 <= 0x1);
+    return encode_djk_slots(opc, d, vj & 0x1f, uk1);
+}
+
+static int32_t __attribute__((unused))
+encode_dvjuk2_insn(LoongArchInsn opc, TCGReg d, TCGReg vj, uint32_t uk2)
+{
+    tcg_debug_assert(d >= 0 && d <= 0x1f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk2 <= 0x3);
+    return encode_djk_slots(opc, d, vj & 0x1f, uk2);
+}
+
+static int32_t __attribute__((unused))
+encode_dvjuk3_insn(LoongArchInsn opc, TCGReg d, TCGReg vj, uint32_t uk3)
+{
+    tcg_debug_assert(d >= 0 && d <= 0x1f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk3 <= 0x7);
+    return encode_djk_slots(opc, d, vj & 0x1f, uk3);
+}
+
+static int32_t __attribute__((unused))
+encode_dvjuk4_insn(LoongArchInsn opc, TCGReg d, TCGReg vj, uint32_t uk4)
+{
+    tcg_debug_assert(d >= 0 && d <= 0x1f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk4 <= 0xf);
+    return encode_djk_slots(opc, d, vj & 0x1f, uk4);
+}
+
 static int32_t __attribute__((unused))
 encode_sd10k16_insn(LoongArchInsn opc, int32_t sd10k16)
 {
@@ -252,6 +1022,265 @@ encode_ud15_insn(LoongArchInsn opc, uint32_t ud15)
     return encode_d_slot(opc, ud15);
 }
 
+static int32_t __attribute__((unused))
+encode_vdj_insn(LoongArchInsn opc, TCGReg vd, TCGReg j)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    return encode_dj_slots(opc, vd & 0x1f, j);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjk_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, TCGReg k)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(k >= 0 && k <= 0x1f);
+    return encode_djk_slots(opc, vd & 0x1f, j, k);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk10_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk10)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk10 >= -0x200 && sk10 <= 0x1ff);
+    return encode_djk_slots(opc, vd & 0x1f, j, sk10 & 0x3ff);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk11_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk11)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk11 >= -0x400 && sk11 <= 0x3ff);
+    return encode_djk_slots(opc, vd & 0x1f, j, sk11 & 0x7ff);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk12_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk12)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk12 >= -0x800 && sk12 <= 0x7ff);
+    return encode_djk_slots(opc, vd & 0x1f, j, sk12 & 0xfff);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk8un1_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk8,
+                      uint32_t un1)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk8 >= -0x80 && sk8 <= 0x7f);
+    tcg_debug_assert(un1 <= 0x1);
+    return encode_djkn_slots(opc, vd & 0x1f, j, sk8 & 0xff, un1);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk8un2_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk8,
+                      uint32_t un2)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk8 >= -0x80 && sk8 <= 0x7f);
+    tcg_debug_assert(un2 <= 0x3);
+    return encode_djkn_slots(opc, vd & 0x1f, j, sk8 & 0xff, un2);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk8un3_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk8,
+                      uint32_t un3)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk8 >= -0x80 && sk8 <= 0x7f);
+    tcg_debug_assert(un3 <= 0x7);
+    return encode_djkn_slots(opc, vd & 0x1f, j, sk8 & 0xff, un3);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk8un4_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk8,
+                      uint32_t un4)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk8 >= -0x80 && sk8 <= 0x7f);
+    tcg_debug_assert(un4 <= 0xf);
+    return encode_djkn_slots(opc, vd & 0x1f, j, sk8 & 0xff, un4);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjsk9_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, int32_t sk9)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(sk9 >= -0x100 && sk9 <= 0xff);
+    return encode_djk_slots(opc, vd & 0x1f, j, sk9 & 0x1ff);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjuk1_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, uint32_t uk1)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(uk1 <= 0x1);
+    return encode_djk_slots(opc, vd & 0x1f, j, uk1);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjuk2_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, uint32_t uk2)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(uk2 <= 0x3);
+    return encode_djk_slots(opc, vd & 0x1f, j, uk2);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjuk3_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, uint32_t uk3)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(uk3 <= 0x7);
+    return encode_djk_slots(opc, vd & 0x1f, j, uk3);
+}
+
+static int32_t __attribute__((unused))
+encode_vdjuk4_insn(LoongArchInsn opc, TCGReg vd, TCGReg j, uint32_t uk4)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(j >= 0 && j <= 0x1f);
+    tcg_debug_assert(uk4 <= 0xf);
+    return encode_djk_slots(opc, vd & 0x1f, j, uk4);
+}
+
+static int32_t __attribute__((unused))
+encode_vdsj13_insn(LoongArchInsn opc, TCGReg vd, int32_t sj13)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(sj13 >= -0x1000 && sj13 <= 0xfff);
+    return encode_dj_slots(opc, vd & 0x1f, sj13 & 0x1fff);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvj_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    return encode_dj_slots(opc, vd & 0x1f, vj & 0x1f);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjk_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, TCGReg k)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(k >= 0 && k <= 0x1f);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, k);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjsk5_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(sk5 >= -0x10 && sk5 <= 0xf);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, sk5 & 0x1f);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk1_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk1)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk1 <= 0x1);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk1);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk2_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk2)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk2 <= 0x3);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk2);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk3_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk3 <= 0x7);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk3);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk4_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk4 <= 0xf);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk4);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk5_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk5 <= 0x1f);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk5);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk6_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk6 <= 0x3f);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk6);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk7_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk7 <= 0x7f);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk7);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjuk8_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(uk8 <= 0xff);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, uk8);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjvk_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(vk >= 0x20 && vk <= 0x3f);
+    return encode_djk_slots(opc, vd & 0x1f, vj & 0x1f, vk & 0x1f);
+}
+
+static int32_t __attribute__((unused))
+encode_vdvjvkva_insn(LoongArchInsn opc, TCGReg vd, TCGReg vj, TCGReg vk,
+                     TCGReg va)
+{
+    tcg_debug_assert(vd >= 0x20 && vd <= 0x3f);
+    tcg_debug_assert(vj >= 0x20 && vj <= 0x3f);
+    tcg_debug_assert(vk >= 0x20 && vk <= 0x3f);
+    tcg_debug_assert(va >= 0x20 && va <= 0x3f);
+    return encode_djka_slots(opc, vd & 0x1f, vj & 0x1f, vk & 0x1f, va & 0x1f);
+}
+
 /* Emits the `clz.w d, j` instruction.  */
 static void __attribute__((unused))
 tcg_out_opc_clz_w(TCGContext *s, TCGReg d, TCGReg j)
@@ -711,277 +1740,5265 @@ tcg_out_opc_xori(TCGContext *s, TCGReg d, TCGReg j, uint32_t uk12)
     tcg_out32(s, encode_djuk12_insn(OPC_XORI, d, j, uk12));
 }
 
-/* Emits the `addu16i.d d, j, sk16` instruction.  */
+/* Emits the `vfmadd.s vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_addu16i_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vfmadd_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_ADDU16I_D, d, j, sk16));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFMADD_S, vd, vj, vk, va));
 }
 
-/* Emits the `lu12i.w d, sj20` instruction.  */
+/* Emits the `vfmadd.d vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_lu12i_w(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfmadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_LU12I_W, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFMADD_D, vd, vj, vk, va));
 }
 
-/* Emits the `cu32i.d d, sj20` instruction.  */
+/* Emits the `vfmsub.s vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_cu32i_d(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfmsub_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_CU32I_D, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFMSUB_S, vd, vj, vk, va));
 }
 
-/* Emits the `pcaddu2i d, sj20` instruction.  */
+/* Emits the `vfmsub.d vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_pcaddu2i(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfmsub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU2I, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFMSUB_D, vd, vj, vk, va));
 }
 
-/* Emits the `pcalau12i d, sj20` instruction.  */
+/* Emits the `vfnmadd.s vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_pcalau12i(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfnmadd_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_PCALAU12I, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFNMADD_S, vd, vj, vk, va));
 }
 
-/* Emits the `pcaddu12i d, sj20` instruction.  */
+/* Emits the `vfnmadd.d vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_pcaddu12i(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfnmadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU12I, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFNMADD_D, vd, vj, vk, va));
 }
 
-/* Emits the `pcaddu18i d, sj20` instruction.  */
+/* Emits the `vfnmsub.s vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_pcaddu18i(TCGContext *s, TCGReg d, int32_t sj20)
+tcg_out_opc_vfnmsub_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU18I, d, sj20));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFNMSUB_S, vd, vj, vk, va));
 }
 
-/* Emits the `ld.b d, j, sk12` instruction.  */
+/* Emits the `vfnmsub.d vd, vj, vk, va` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_b(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfnmsub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_B, d, j, sk12));
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VFNMSUB_D, vd, vj, vk, va));
 }
 
-/* Emits the `ld.h d, j, sk12` instruction.  */
+/* Emits the `vfcmp.caf.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_h(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_caf_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_H, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CAF_S, vd, vj, vk));
 }
 
-/* Emits the `ld.w d, j, sk12` instruction.  */
+/* Emits the `vfcmp.saf.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_w(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_saf_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_W, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SAF_S, vd, vj, vk));
 }
 
-/* Emits the `ld.d d, j, sk12` instruction.  */
+/* Emits the `vfcmp.clt.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_clt_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_D, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CLT_S, vd, vj, vk));
 }
 
-/* Emits the `st.b d, j, sk12` instruction.  */
+/* Emits the `vfcmp.slt.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_st_b(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_slt_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_ST_B, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SLT_S, vd, vj, vk));
 }
 
-/* Emits the `st.h d, j, sk12` instruction.  */
+/* Emits the `vfcmp.ceq.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_st_h(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_ceq_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_ST_H, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CEQ_S, vd, vj, vk));
 }
 
-/* Emits the `st.w d, j, sk12` instruction.  */
+/* Emits the `vfcmp.seq.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_st_w(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_seq_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_ST_W, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SEQ_S, vd, vj, vk));
 }
 
-/* Emits the `st.d d, j, sk12` instruction.  */
+/* Emits the `vfcmp.cle.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_st_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_cle_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_ST_D, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CLE_S, vd, vj, vk));
 }
 
-/* Emits the `ld.bu d, j, sk12` instruction.  */
+/* Emits the `vfcmp.sle.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_bu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_sle_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_BU, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SLE_S, vd, vj, vk));
 }
 
-/* Emits the `ld.hu d, j, sk12` instruction.  */
+/* Emits the `vfcmp.cun.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_hu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_cun_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_HU, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUN_S, vd, vj, vk));
 }
 
-/* Emits the `ld.wu d, j, sk12` instruction.  */
+/* Emits the `vfcmp.sun.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ld_wu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+tcg_out_opc_vfcmp_sun_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk12_insn(OPC_LD_WU, d, j, sk12));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUN_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.b d, j, k` instruction.  */
+/* Emits the `vfcmp.cult.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_b(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cult_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_B, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CULT_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.h d, j, k` instruction.  */
+/* Emits the `vfcmp.sult.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_h(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_sult_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_H, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SULT_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.w d, j, k` instruction.  */
+/* Emits the `vfcmp.cueq.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_w(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cueq_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_W, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUEQ_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.d d, j, k` instruction.  */
+/* Emits the `vfcmp.sueq.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_d(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_sueq_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_D, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUEQ_S, vd, vj, vk));
 }
 
-/* Emits the `stx.b d, j, k` instruction.  */
+/* Emits the `vfcmp.cule.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_stx_b(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cule_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_STX_B, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CULE_S, vd, vj, vk));
 }
 
-/* Emits the `stx.h d, j, k` instruction.  */
+/* Emits the `vfcmp.sule.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_stx_h(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_sule_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_STX_H, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SULE_S, vd, vj, vk));
 }
 
-/* Emits the `stx.w d, j, k` instruction.  */
+/* Emits the `vfcmp.cne.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_stx_w(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cne_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_STX_W, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CNE_S, vd, vj, vk));
 }
 
-/* Emits the `stx.d d, j, k` instruction.  */
+/* Emits the `vfcmp.sne.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_stx_d(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_sne_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_STX_D, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SNE_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.bu d, j, k` instruction.  */
+/* Emits the `vfcmp.cor.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_bu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cor_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_BU, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_COR_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.hu d, j, k` instruction.  */
+/* Emits the `vfcmp.sor.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_hu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_sor_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_HU, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SOR_S, vd, vj, vk));
 }
 
-/* Emits the `ldx.wu d, j, k` instruction.  */
+/* Emits the `vfcmp.cune.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ldx_wu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+tcg_out_opc_vfcmp_cune_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djk_insn(OPC_LDX_WU, d, j, k));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUNE_S, vd, vj, vk));
 }
 
-/* Emits the `dbar ud15` instruction.  */
+/* Emits the `vfcmp.sune.s vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_dbar(TCGContext *s, uint32_t ud15)
+tcg_out_opc_vfcmp_sune_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_ud15_insn(OPC_DBAR, ud15));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUNE_S, vd, vj, vk));
 }
 
-/* Emits the `jirl d, j, sk16` instruction.  */
+/* Emits the `vfcmp.caf.d vd, vj, vk` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_jirl(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vfcmp_caf_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_JIRL, d, j, sk16));
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CAF_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.saf.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_saf_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SAF_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.clt.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_clt_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CLT_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.slt.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_slt_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SLT_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.ceq.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_ceq_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CEQ_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.seq.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_seq_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SEQ_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cle.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cle_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CLE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sle.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sle_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SLE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cun.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cun_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUN_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sun.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sun_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUN_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cult.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cult_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CULT_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sult.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sult_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SULT_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cueq.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cueq_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUEQ_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sueq.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sueq_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUEQ_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cule.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cule_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CULE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sule.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sule_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SULE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cne.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cne_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CNE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sne.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sne_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SNE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cor.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cor_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_COR_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sor.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sor_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SOR_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.cune.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_cune_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_CUNE_D, vd, vj, vk));
+}
+
+/* Emits the `vfcmp.sune.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcmp_sune_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCMP_SUNE_D, vd, vj, vk));
+}
+
+/* Emits the `vbitsel.v vd, vj, vk, va` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitsel_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
+{
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VBITSEL_V, vd, vj, vk, va));
+}
+
+/* Emits the `vshuf.b vd, vj, vk, va` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk, TCGReg va)
+{
+    tcg_out32(s, encode_vdvjvkva_insn(OPC_VSHUF_B, vd, vj, vk, va));
+}
+
+/* Emits the `addu16i.d d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_addu16i_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_ADDU16I_D, d, j, sk16));
+}
+
+/* Emits the `lu12i.w d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_lu12i_w(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_LU12I_W, d, sj20));
+}
+
+/* Emits the `cu32i.d d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_cu32i_d(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_CU32I_D, d, sj20));
+}
+
+/* Emits the `pcaddu2i d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_pcaddu2i(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU2I, d, sj20));
+}
+
+/* Emits the `pcalau12i d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_pcalau12i(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_PCALAU12I, d, sj20));
+}
+
+/* Emits the `pcaddu12i d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_pcaddu12i(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU12I, d, sj20));
+}
+
+/* Emits the `pcaddu18i d, sj20` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_pcaddu18i(TCGContext *s, TCGReg d, int32_t sj20)
+{
+    tcg_out32(s, encode_dsj20_insn(OPC_PCADDU18I, d, sj20));
+}
+
+/* Emits the `ld.b d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_b(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_B, d, j, sk12));
+}
+
+/* Emits the `ld.h d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_h(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_H, d, j, sk12));
+}
+
+/* Emits the `ld.w d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_w(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_W, d, j, sk12));
+}
+
+/* Emits the `ld.d d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_D, d, j, sk12));
+}
+
+/* Emits the `st.b d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_st_b(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_ST_B, d, j, sk12));
+}
+
+/* Emits the `st.h d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_st_h(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_ST_H, d, j, sk12));
+}
+
+/* Emits the `st.w d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_st_w(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_ST_W, d, j, sk12));
+}
+
+/* Emits the `st.d d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_st_d(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_ST_D, d, j, sk12));
+}
+
+/* Emits the `ld.bu d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_bu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_BU, d, j, sk12));
+}
+
+/* Emits the `ld.hu d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_hu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_HU, d, j, sk12));
+}
+
+/* Emits the `ld.wu d, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ld_wu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_djsk12_insn(OPC_LD_WU, d, j, sk12));
+}
+
+/* Emits the `vld vd, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vld(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_vdjsk12_insn(OPC_VLD, vd, j, sk12));
+}
+
+/* Emits the `vst vd, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vst(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_vdjsk12_insn(OPC_VST, vd, j, sk12));
+}
+
+/* Emits the `vldrepl.d vd, j, sk9` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldrepl_d(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk9)
+{
+    tcg_out32(s, encode_vdjsk9_insn(OPC_VLDREPL_D, vd, j, sk9));
+}
+
+/* Emits the `vldrepl.w vd, j, sk10` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldrepl_w(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk10)
+{
+    tcg_out32(s, encode_vdjsk10_insn(OPC_VLDREPL_W, vd, j, sk10));
+}
+
+/* Emits the `vldrepl.h vd, j, sk11` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldrepl_h(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk11)
+{
+    tcg_out32(s, encode_vdjsk11_insn(OPC_VLDREPL_H, vd, j, sk11));
+}
+
+/* Emits the `vldrepl.b vd, j, sk12` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldrepl_b(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk12)
+{
+    tcg_out32(s, encode_vdjsk12_insn(OPC_VLDREPL_B, vd, j, sk12));
+}
+
+/* Emits the `vstelm.d vd, j, sk8, un1` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vstelm_d(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk8,
+                     uint32_t un1)
+{
+    tcg_out32(s, encode_vdjsk8un1_insn(OPC_VSTELM_D, vd, j, sk8, un1));
+}
+
+/* Emits the `vstelm.w vd, j, sk8, un2` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vstelm_w(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk8,
+                     uint32_t un2)
+{
+    tcg_out32(s, encode_vdjsk8un2_insn(OPC_VSTELM_W, vd, j, sk8, un2));
+}
+
+/* Emits the `vstelm.h vd, j, sk8, un3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vstelm_h(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk8,
+                     uint32_t un3)
+{
+    tcg_out32(s, encode_vdjsk8un3_insn(OPC_VSTELM_H, vd, j, sk8, un3));
+}
+
+/* Emits the `vstelm.b vd, j, sk8, un4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vstelm_b(TCGContext *s, TCGReg vd, TCGReg j, int32_t sk8,
+                     uint32_t un4)
+{
+    tcg_out32(s, encode_vdjsk8un4_insn(OPC_VSTELM_B, vd, j, sk8, un4));
+}
+
+/* Emits the `ldx.b d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_b(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_B, d, j, k));
+}
+
+/* Emits the `ldx.h d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_h(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_H, d, j, k));
+}
+
+/* Emits the `ldx.w d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_w(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_W, d, j, k));
+}
+
+/* Emits the `ldx.d d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_d(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_D, d, j, k));
+}
+
+/* Emits the `stx.b d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_stx_b(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_STX_B, d, j, k));
+}
+
+/* Emits the `stx.h d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_stx_h(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_STX_H, d, j, k));
+}
+
+/* Emits the `stx.w d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_stx_w(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_STX_W, d, j, k));
+}
+
+/* Emits the `stx.d d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_stx_d(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_STX_D, d, j, k));
+}
+
+/* Emits the `ldx.bu d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_bu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_BU, d, j, k));
+}
+
+/* Emits the `ldx.hu d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_hu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_HU, d, j, k));
+}
+
+/* Emits the `ldx.wu d, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ldx_wu(TCGContext *s, TCGReg d, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_djk_insn(OPC_LDX_WU, d, j, k));
+}
+
+/* Emits the `vldx vd, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldx(TCGContext *s, TCGReg vd, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_vdjk_insn(OPC_VLDX, vd, j, k));
+}
+
+/* Emits the `vstx vd, j, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vstx(TCGContext *s, TCGReg vd, TCGReg j, TCGReg k)
+{
+    tcg_out32(s, encode_vdjk_insn(OPC_VSTX, vd, j, k));
+}
+
+/* Emits the `dbar ud15` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_dbar(TCGContext *s, uint32_t ud15)
+{
+    tcg_out32(s, encode_ud15_insn(OPC_DBAR, ud15));
+}
+
+/* Emits the `jirl d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_jirl(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_JIRL, d, j, sk16));
 }
 
 /* Emits the `b sd10k16` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_b(TCGContext *s, int32_t sd10k16)
+tcg_out_opc_b(TCGContext *s, int32_t sd10k16)
+{
+    tcg_out32(s, encode_sd10k16_insn(OPC_B, sd10k16));
+}
+
+/* Emits the `bl sd10k16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_bl(TCGContext *s, int32_t sd10k16)
+{
+    tcg_out32(s, encode_sd10k16_insn(OPC_BL, sd10k16));
+}
+
+/* Emits the `beq d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_beq(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BEQ, d, j, sk16));
+}
+
+/* Emits the `bne d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_bne(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BNE, d, j, sk16));
+}
+
+/* Emits the `bgt d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_bgt(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BGT, d, j, sk16));
+}
+
+/* Emits the `ble d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_ble(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BLE, d, j, sk16));
+}
+
+/* Emits the `bgtu d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_bgtu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BGTU, d, j, sk16));
+}
+
+/* Emits the `bleu d, j, sk16` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_bleu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+{
+    tcg_out32(s, encode_djsk16_insn(OPC_BLEU, d, j, sk16));
+}
+
+/* Emits the `vseq.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseq_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSEQ_B, vd, vj, vk));
+}
+
+/* Emits the `vseq.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseq_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSEQ_H, vd, vj, vk));
+}
+
+/* Emits the `vseq.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseq_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSEQ_W, vd, vj, vk));
+}
+
+/* Emits the `vseq.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseq_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSEQ_D, vd, vj, vk));
+}
+
+/* Emits the `vsle.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_B, vd, vj, vk));
+}
+
+/* Emits the `vsle.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_H, vd, vj, vk));
+}
+
+/* Emits the `vsle.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_W, vd, vj, vk));
+}
+
+/* Emits the `vsle.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_D, vd, vj, vk));
+}
+
+/* Emits the `vsle.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_BU, vd, vj, vk));
+}
+
+/* Emits the `vsle.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_HU, vd, vj, vk));
+}
+
+/* Emits the `vsle.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_WU, vd, vj, vk));
+}
+
+/* Emits the `vsle.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsle_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLE_DU, vd, vj, vk));
+}
+
+/* Emits the `vslt.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_B, vd, vj, vk));
+}
+
+/* Emits the `vslt.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_H, vd, vj, vk));
+}
+
+/* Emits the `vslt.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_W, vd, vj, vk));
+}
+
+/* Emits the `vslt.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_D, vd, vj, vk));
+}
+
+/* Emits the `vslt.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_BU, vd, vj, vk));
+}
+
+/* Emits the `vslt.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_HU, vd, vj, vk));
+}
+
+/* Emits the `vslt.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_WU, vd, vj, vk));
+}
+
+/* Emits the `vslt.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslt_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLT_DU, vd, vj, vk));
+}
+
+/* Emits the `vadd.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadd_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADD_B, vd, vj, vk));
+}
+
+/* Emits the `vadd.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadd_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADD_H, vd, vj, vk));
+}
+
+/* Emits the `vadd.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadd_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADD_W, vd, vj, vk));
+}
+
+/* Emits the `vadd.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADD_D, vd, vj, vk));
+}
+
+/* Emits the `vsub.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsub_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUB_B, vd, vj, vk));
+}
+
+/* Emits the `vsub.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsub_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUB_H, vd, vj, vk));
+}
+
+/* Emits the `vsub.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsub_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUB_W, vd, vj, vk));
+}
+
+/* Emits the `vsub.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUB_D, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_H_B, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_W_H, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_D_W, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_H_B, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_W_H, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_D_W, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_H_B, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_W_H, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_D_W, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_H_B, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_W_H, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_D_W, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vsubwev.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwev_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWEV_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vsubwod.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubwod_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUBWOD_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vaddwev.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwev_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWEV_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vaddwod.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddwod_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDWOD_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vsadd.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_B, vd, vj, vk));
+}
+
+/* Emits the `vsadd.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_H, vd, vj, vk));
+}
+
+/* Emits the `vsadd.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_W, vd, vj, vk));
+}
+
+/* Emits the `vsadd.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_D, vd, vj, vk));
+}
+
+/* Emits the `vssub.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_B, vd, vj, vk));
+}
+
+/* Emits the `vssub.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_H, vd, vj, vk));
+}
+
+/* Emits the `vssub.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_W, vd, vj, vk));
+}
+
+/* Emits the `vssub.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_D, vd, vj, vk));
+}
+
+/* Emits the `vsadd.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_BU, vd, vj, vk));
+}
+
+/* Emits the `vsadd.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_HU, vd, vj, vk));
+}
+
+/* Emits the `vsadd.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_WU, vd, vj, vk));
+}
+
+/* Emits the `vsadd.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsadd_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSADD_DU, vd, vj, vk));
+}
+
+/* Emits the `vssub.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_BU, vd, vj, vk));
+}
+
+/* Emits the `vssub.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_HU, vd, vj, vk));
+}
+
+/* Emits the `vssub.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_WU, vd, vj, vk));
+}
+
+/* Emits the `vssub.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssub_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSUB_DU, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_H_B, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_W_H, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_D_W, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_H_B, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_W_H, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_D_W, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.hu.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_hu_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_HU_BU, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.wu.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_wu_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_WU_HU, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.du.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_du_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_DU_WU, vd, vj, vk));
+}
+
+/* Emits the `vhaddw.qu.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhaddw_qu_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHADDW_QU_DU, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.hu.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_hu_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_HU_BU, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.wu.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_wu_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_WU_HU, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.du.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_du_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_DU_WU, vd, vj, vk));
+}
+
+/* Emits the `vhsubw.qu.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vhsubw_qu_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VHSUBW_QU_DU, vd, vj, vk));
+}
+
+/* Emits the `vadda.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadda_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDA_B, vd, vj, vk));
+}
+
+/* Emits the `vadda.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadda_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDA_H, vd, vj, vk));
+}
+
+/* Emits the `vadda.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadda_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDA_W, vd, vj, vk));
+}
+
+/* Emits the `vadda.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadda_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADDA_D, vd, vj, vk));
+}
+
+/* Emits the `vabsd.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_B, vd, vj, vk));
+}
+
+/* Emits the `vabsd.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_H, vd, vj, vk));
+}
+
+/* Emits the `vabsd.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_W, vd, vj, vk));
+}
+
+/* Emits the `vabsd.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_D, vd, vj, vk));
+}
+
+/* Emits the `vabsd.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_BU, vd, vj, vk));
+}
+
+/* Emits the `vabsd.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_HU, vd, vj, vk));
+}
+
+/* Emits the `vabsd.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_WU, vd, vj, vk));
+}
+
+/* Emits the `vabsd.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vabsd_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VABSD_DU, vd, vj, vk));
+}
+
+/* Emits the `vavg.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_B, vd, vj, vk));
+}
+
+/* Emits the `vavg.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_H, vd, vj, vk));
+}
+
+/* Emits the `vavg.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_W, vd, vj, vk));
+}
+
+/* Emits the `vavg.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_D, vd, vj, vk));
+}
+
+/* Emits the `vavg.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_BU, vd, vj, vk));
+}
+
+/* Emits the `vavg.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_HU, vd, vj, vk));
+}
+
+/* Emits the `vavg.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_WU, vd, vj, vk));
+}
+
+/* Emits the `vavg.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavg_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVG_DU, vd, vj, vk));
+}
+
+/* Emits the `vavgr.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_B, vd, vj, vk));
+}
+
+/* Emits the `vavgr.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_H, vd, vj, vk));
+}
+
+/* Emits the `vavgr.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_W, vd, vj, vk));
+}
+
+/* Emits the `vavgr.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_D, vd, vj, vk));
+}
+
+/* Emits the `vavgr.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_BU, vd, vj, vk));
+}
+
+/* Emits the `vavgr.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_HU, vd, vj, vk));
+}
+
+/* Emits the `vavgr.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_WU, vd, vj, vk));
+}
+
+/* Emits the `vavgr.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vavgr_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAVGR_DU, vd, vj, vk));
+}
+
+/* Emits the `vmax.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_B, vd, vj, vk));
+}
+
+/* Emits the `vmax.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_H, vd, vj, vk));
+}
+
+/* Emits the `vmax.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_W, vd, vj, vk));
+}
+
+/* Emits the `vmax.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_D, vd, vj, vk));
+}
+
+/* Emits the `vmin.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_B, vd, vj, vk));
+}
+
+/* Emits the `vmin.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_H, vd, vj, vk));
+}
+
+/* Emits the `vmin.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_W, vd, vj, vk));
+}
+
+/* Emits the `vmin.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_D, vd, vj, vk));
+}
+
+/* Emits the `vmax.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_BU, vd, vj, vk));
+}
+
+/* Emits the `vmax.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_HU, vd, vj, vk));
+}
+
+/* Emits the `vmax.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_WU, vd, vj, vk));
+}
+
+/* Emits the `vmax.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmax_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMAX_DU, vd, vj, vk));
+}
+
+/* Emits the `vmin.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_BU, vd, vj, vk));
+}
+
+/* Emits the `vmin.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_HU, vd, vj, vk));
+}
+
+/* Emits the `vmin.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_WU, vd, vj, vk));
+}
+
+/* Emits the `vmin.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmin_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMIN_DU, vd, vj, vk));
+}
+
+/* Emits the `vmul.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmul_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUL_B, vd, vj, vk));
+}
+
+/* Emits the `vmul.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmul_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUL_H, vd, vj, vk));
+}
+
+/* Emits the `vmul.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmul_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUL_W, vd, vj, vk));
+}
+
+/* Emits the `vmul.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmul_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUL_D, vd, vj, vk));
+}
+
+/* Emits the `vmuh.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_B, vd, vj, vk));
+}
+
+/* Emits the `vmuh.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_H, vd, vj, vk));
+}
+
+/* Emits the `vmuh.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_W, vd, vj, vk));
+}
+
+/* Emits the `vmuh.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_D, vd, vj, vk));
+}
+
+/* Emits the `vmuh.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_BU, vd, vj, vk));
+}
+
+/* Emits the `vmuh.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_HU, vd, vj, vk));
+}
+
+/* Emits the `vmuh.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_WU, vd, vj, vk));
+}
+
+/* Emits the `vmuh.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmuh_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMUH_DU, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_H_B, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_W_H, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_D_W, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_H_B, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_W_H, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_D_W, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vmulwev.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwev_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWEV_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vmulwod.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmulwod_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMULWOD_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vmadd.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmadd_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADD_B, vd, vj, vk));
+}
+
+/* Emits the `vmadd.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmadd_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADD_H, vd, vj, vk));
+}
+
+/* Emits the `vmadd.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmadd_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADD_W, vd, vj, vk));
+}
+
+/* Emits the `vmadd.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADD_D, vd, vj, vk));
+}
+
+/* Emits the `vmsub.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmsub_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMSUB_B, vd, vj, vk));
+}
+
+/* Emits the `vmsub.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmsub_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMSUB_H, vd, vj, vk));
+}
+
+/* Emits the `vmsub.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmsub_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMSUB_W, vd, vj, vk));
+}
+
+/* Emits the `vmsub.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmsub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMSUB_D, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_H_B, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_W_H, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_D_W, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.h.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_h_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_H_B, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.w.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_w_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_W_H, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.d.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_d_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_D_W, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.q.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_q_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_Q_D, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.h.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_h_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_H_BU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.w.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_w_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_W_HU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.d.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_d_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_D_WU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.q.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_q_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_Q_DU, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vmaddwev.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwev_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWEV_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.h.bu.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_h_bu_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_H_BU_B, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.w.hu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_w_hu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_W_HU_H, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.d.wu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_d_wu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_D_WU_W, vd, vj, vk));
+}
+
+/* Emits the `vmaddwod.q.du.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaddwod_q_du_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMADDWOD_Q_DU_D, vd, vj, vk));
+}
+
+/* Emits the `vdiv.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_B, vd, vj, vk));
+}
+
+/* Emits the `vdiv.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_H, vd, vj, vk));
+}
+
+/* Emits the `vdiv.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_W, vd, vj, vk));
+}
+
+/* Emits the `vdiv.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_D, vd, vj, vk));
+}
+
+/* Emits the `vmod.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_B, vd, vj, vk));
+}
+
+/* Emits the `vmod.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_H, vd, vj, vk));
+}
+
+/* Emits the `vmod.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_W, vd, vj, vk));
+}
+
+/* Emits the `vmod.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_D, vd, vj, vk));
+}
+
+/* Emits the `vdiv.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_BU, vd, vj, vk));
+}
+
+/* Emits the `vdiv.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_HU, vd, vj, vk));
+}
+
+/* Emits the `vdiv.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_WU, vd, vj, vk));
+}
+
+/* Emits the `vdiv.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vdiv_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VDIV_DU, vd, vj, vk));
+}
+
+/* Emits the `vmod.bu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_bu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_BU, vd, vj, vk));
+}
+
+/* Emits the `vmod.hu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_hu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_HU, vd, vj, vk));
+}
+
+/* Emits the `vmod.wu vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_wu(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_WU, vd, vj, vk));
+}
+
+/* Emits the `vmod.du vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmod_du(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VMOD_DU, vd, vj, vk));
+}
+
+/* Emits the `vsll.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsll_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLL_B, vd, vj, vk));
+}
+
+/* Emits the `vsll.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsll_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLL_H, vd, vj, vk));
+}
+
+/* Emits the `vsll.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsll_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLL_W, vd, vj, vk));
+}
+
+/* Emits the `vsll.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsll_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSLL_D, vd, vj, vk));
+}
+
+/* Emits the `vsrl.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrl_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRL_B, vd, vj, vk));
+}
+
+/* Emits the `vsrl.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrl_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRL_H, vd, vj, vk));
+}
+
+/* Emits the `vsrl.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrl_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRL_W, vd, vj, vk));
+}
+
+/* Emits the `vsrl.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrl_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRL_D, vd, vj, vk));
+}
+
+/* Emits the `vsra.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsra_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRA_B, vd, vj, vk));
+}
+
+/* Emits the `vsra.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsra_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRA_H, vd, vj, vk));
+}
+
+/* Emits the `vsra.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsra_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRA_W, vd, vj, vk));
+}
+
+/* Emits the `vsra.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsra_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRA_D, vd, vj, vk));
+}
+
+/* Emits the `vrotr.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotr_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VROTR_B, vd, vj, vk));
+}
+
+/* Emits the `vrotr.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotr_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VROTR_H, vd, vj, vk));
+}
+
+/* Emits the `vrotr.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotr_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VROTR_W, vd, vj, vk));
+}
+
+/* Emits the `vrotr.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotr_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VROTR_D, vd, vj, vk));
+}
+
+/* Emits the `vsrlr.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlr_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLR_B, vd, vj, vk));
+}
+
+/* Emits the `vsrlr.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlr_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLR_H, vd, vj, vk));
+}
+
+/* Emits the `vsrlr.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlr_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLR_W, vd, vj, vk));
+}
+
+/* Emits the `vsrlr.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlr_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLR_D, vd, vj, vk));
+}
+
+/* Emits the `vsrar.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrar_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAR_B, vd, vj, vk));
+}
+
+/* Emits the `vsrar.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrar_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAR_H, vd, vj, vk));
+}
+
+/* Emits the `vsrar.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrar_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAR_W, vd, vj, vk));
+}
+
+/* Emits the `vsrar.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrar_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAR_D, vd, vj, vk));
+}
+
+/* Emits the `vsrln.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrln_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vsrln.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrln_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vsrln.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrln_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vsran.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsran_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vsran.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsran_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vsran.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsran_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRAN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vsrlrn.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrn_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLRN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vsrlrn.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrn_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLRN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vsrlrn.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrn_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRLRN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vsrarn.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarn_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRARN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vsrarn.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarn_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRARN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vsrarn.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarn_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSRARN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vssrln.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vssrln.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vssrln.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vssran.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vssran.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vssran.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.b.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_b_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_B_H, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.h.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_h_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_H_W, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_W_D, vd, vj, vk));
+}
+
+/* Emits the `vssrln.bu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_BU_H, vd, vj, vk));
+}
+
+/* Emits the `vssrln.hu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_HU_W, vd, vj, vk));
+}
+
+/* Emits the `vssrln.wu.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrln_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLN_WU_D, vd, vj, vk));
+}
+
+/* Emits the `vssran.bu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_BU_H, vd, vj, vk));
+}
+
+/* Emits the `vssran.hu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_HU_W, vd, vj, vk));
+}
+
+/* Emits the `vssran.wu.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssran_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRAN_WU_D, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.bu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_BU_H, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.hu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_HU_W, vd, vj, vk));
+}
+
+/* Emits the `vssrlrn.wu.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrn_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRLRN_WU_D, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.bu.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_BU_H, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.hu.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_HU_W, vd, vj, vk));
+}
+
+/* Emits the `vssrarn.wu.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarn_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSSRARN_WU_D, vd, vj, vk));
+}
+
+/* Emits the `vbitclr.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclr_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITCLR_B, vd, vj, vk));
+}
+
+/* Emits the `vbitclr.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclr_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITCLR_H, vd, vj, vk));
+}
+
+/* Emits the `vbitclr.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclr_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITCLR_W, vd, vj, vk));
+}
+
+/* Emits the `vbitclr.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclr_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITCLR_D, vd, vj, vk));
+}
+
+/* Emits the `vbitset.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitset_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITSET_B, vd, vj, vk));
+}
+
+/* Emits the `vbitset.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitset_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITSET_H, vd, vj, vk));
+}
+
+/* Emits the `vbitset.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitset_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITSET_W, vd, vj, vk));
+}
+
+/* Emits the `vbitset.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitset_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITSET_D, vd, vj, vk));
+}
+
+/* Emits the `vbitrev.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrev_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITREV_B, vd, vj, vk));
+}
+
+/* Emits the `vbitrev.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrev_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITREV_H, vd, vj, vk));
+}
+
+/* Emits the `vbitrev.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrev_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITREV_W, vd, vj, vk));
+}
+
+/* Emits the `vbitrev.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrev_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VBITREV_D, vd, vj, vk));
+}
+
+/* Emits the `vpackev.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackev_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKEV_B, vd, vj, vk));
+}
+
+/* Emits the `vpackev.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackev_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKEV_H, vd, vj, vk));
+}
+
+/* Emits the `vpackev.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackev_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKEV_W, vd, vj, vk));
+}
+
+/* Emits the `vpackev.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackev_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKEV_D, vd, vj, vk));
+}
+
+/* Emits the `vpackod.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackod_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKOD_B, vd, vj, vk));
+}
+
+/* Emits the `vpackod.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackod_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKOD_H, vd, vj, vk));
+}
+
+/* Emits the `vpackod.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackod_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKOD_W, vd, vj, vk));
+}
+
+/* Emits the `vpackod.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpackod_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPACKOD_D, vd, vj, vk));
+}
+
+/* Emits the `vilvl.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvl_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVL_B, vd, vj, vk));
+}
+
+/* Emits the `vilvl.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvl_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVL_H, vd, vj, vk));
+}
+
+/* Emits the `vilvl.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvl_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVL_W, vd, vj, vk));
+}
+
+/* Emits the `vilvl.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvl_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVL_D, vd, vj, vk));
+}
+
+/* Emits the `vilvh.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvh_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVH_B, vd, vj, vk));
+}
+
+/* Emits the `vilvh.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvh_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVH_H, vd, vj, vk));
+}
+
+/* Emits the `vilvh.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvh_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVH_W, vd, vj, vk));
+}
+
+/* Emits the `vilvh.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vilvh_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VILVH_D, vd, vj, vk));
+}
+
+/* Emits the `vpickev.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickev_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKEV_B, vd, vj, vk));
+}
+
+/* Emits the `vpickev.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickev_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKEV_H, vd, vj, vk));
+}
+
+/* Emits the `vpickev.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickev_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKEV_W, vd, vj, vk));
+}
+
+/* Emits the `vpickev.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickev_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKEV_D, vd, vj, vk));
+}
+
+/* Emits the `vpickod.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickod_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKOD_B, vd, vj, vk));
+}
+
+/* Emits the `vpickod.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickod_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKOD_H, vd, vj, vk));
+}
+
+/* Emits the `vpickod.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickod_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKOD_W, vd, vj, vk));
+}
+
+/* Emits the `vpickod.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickod_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VPICKOD_D, vd, vj, vk));
+}
+
+/* Emits the `vreplve.b vd, vj, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplve_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg k)
+{
+    tcg_out32(s, encode_vdvjk_insn(OPC_VREPLVE_B, vd, vj, k));
+}
+
+/* Emits the `vreplve.h vd, vj, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplve_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg k)
+{
+    tcg_out32(s, encode_vdvjk_insn(OPC_VREPLVE_H, vd, vj, k));
+}
+
+/* Emits the `vreplve.w vd, vj, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplve_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg k)
+{
+    tcg_out32(s, encode_vdvjk_insn(OPC_VREPLVE_W, vd, vj, k));
+}
+
+/* Emits the `vreplve.d vd, vj, k` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplve_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg k)
+{
+    tcg_out32(s, encode_vdvjk_insn(OPC_VREPLVE_D, vd, vj, k));
+}
+
+/* Emits the `vand.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vand_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VAND_V, vd, vj, vk));
+}
+
+/* Emits the `vor.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vor_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VOR_V, vd, vj, vk));
+}
+
+/* Emits the `vxor.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vxor_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VXOR_V, vd, vj, vk));
+}
+
+/* Emits the `vnor.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vnor_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VNOR_V, vd, vj, vk));
+}
+
+/* Emits the `vandn.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vandn_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VANDN_V, vd, vj, vk));
+}
+
+/* Emits the `vorn.v vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vorn_v(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VORN_V, vd, vj, vk));
+}
+
+/* Emits the `vfrstp.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrstp_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFRSTP_B, vd, vj, vk));
+}
+
+/* Emits the `vfrstp.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrstp_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFRSTP_H, vd, vj, vk));
+}
+
+/* Emits the `vadd.q vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vadd_q(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VADD_Q, vd, vj, vk));
+}
+
+/* Emits the `vsub.q vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsub_q(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSUB_Q, vd, vj, vk));
+}
+
+/* Emits the `vsigncov.b vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsigncov_b(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSIGNCOV_B, vd, vj, vk));
+}
+
+/* Emits the `vsigncov.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsigncov_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSIGNCOV_H, vd, vj, vk));
+}
+
+/* Emits the `vsigncov.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsigncov_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSIGNCOV_W, vd, vj, vk));
+}
+
+/* Emits the `vsigncov.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsigncov_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSIGNCOV_D, vd, vj, vk));
+}
+
+/* Emits the `vfadd.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfadd_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFADD_S, vd, vj, vk));
+}
+
+/* Emits the `vfadd.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfadd_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFADD_D, vd, vj, vk));
+}
+
+/* Emits the `vfsub.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfsub_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFSUB_S, vd, vj, vk));
+}
+
+/* Emits the `vfsub.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfsub_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFSUB_D, vd, vj, vk));
+}
+
+/* Emits the `vfmul.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmul_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMUL_S, vd, vj, vk));
+}
+
+/* Emits the `vfmul.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmul_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMUL_D, vd, vj, vk));
+}
+
+/* Emits the `vfdiv.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfdiv_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFDIV_S, vd, vj, vk));
+}
+
+/* Emits the `vfdiv.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfdiv_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFDIV_D, vd, vj, vk));
+}
+
+/* Emits the `vfmax.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmax_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMAX_S, vd, vj, vk));
+}
+
+/* Emits the `vfmax.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmax_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMAX_D, vd, vj, vk));
+}
+
+/* Emits the `vfmin.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmin_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMIN_S, vd, vj, vk));
+}
+
+/* Emits the `vfmin.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmin_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMIN_D, vd, vj, vk));
+}
+
+/* Emits the `vfmaxa.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmaxa_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMAXA_S, vd, vj, vk));
+}
+
+/* Emits the `vfmaxa.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmaxa_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMAXA_D, vd, vj, vk));
+}
+
+/* Emits the `vfmina.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmina_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMINA_S, vd, vj, vk));
+}
+
+/* Emits the `vfmina.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfmina_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFMINA_D, vd, vj, vk));
+}
+
+/* Emits the `vfcvt.h.s vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvt_h_s(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCVT_H_S, vd, vj, vk));
+}
+
+/* Emits the `vfcvt.s.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvt_s_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFCVT_S_D, vd, vj, vk));
+}
+
+/* Emits the `vffint.s.l vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffint_s_l(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFFINT_S_L, vd, vj, vk));
+}
+
+/* Emits the `vftint.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftint_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFTINT_W_D, vd, vj, vk));
+}
+
+/* Emits the `vftintrm.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrm_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFTINTRM_W_D, vd, vj, vk));
+}
+
+/* Emits the `vftintrp.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrp_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFTINTRP_W_D, vd, vj, vk));
+}
+
+/* Emits the `vftintrz.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrz_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFTINTRZ_W_D, vd, vj, vk));
+}
+
+/* Emits the `vftintrne.w.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrne_w_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VFTINTRNE_W_D, vd, vj, vk));
+}
+
+/* Emits the `vshuf.h vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf_h(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSHUF_H, vd, vj, vk));
+}
+
+/* Emits the `vshuf.w vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf_w(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSHUF_W, vd, vj, vk));
+}
+
+/* Emits the `vshuf.d vd, vj, vk` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf_d(TCGContext *s, TCGReg vd, TCGReg vj, TCGReg vk)
+{
+    tcg_out32(s, encode_vdvjvk_insn(OPC_VSHUF_D, vd, vj, vk));
+}
+
+/* Emits the `vseqi.b vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseqi_b(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSEQI_B, vd, vj, sk5));
+}
+
+/* Emits the `vseqi.h vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseqi_h(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSEQI_H, vd, vj, sk5));
+}
+
+/* Emits the `vseqi.w vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseqi_w(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSEQI_W, vd, vj, sk5));
+}
+
+/* Emits the `vseqi.d vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseqi_d(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSEQI_D, vd, vj, sk5));
+}
+
+/* Emits the `vslei.b vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_b(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLEI_B, vd, vj, sk5));
+}
+
+/* Emits the `vslei.h vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_h(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLEI_H, vd, vj, sk5));
+}
+
+/* Emits the `vslei.w vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_w(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLEI_W, vd, vj, sk5));
+}
+
+/* Emits the `vslei.d vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_d(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLEI_D, vd, vj, sk5));
+}
+
+/* Emits the `vslei.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLEI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vslei.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLEI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vslei.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLEI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vslei.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslei_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLEI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vslti.b vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_b(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLTI_B, vd, vj, sk5));
+}
+
+/* Emits the `vslti.h vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_h(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLTI_H, vd, vj, sk5));
+}
+
+/* Emits the `vslti.w vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_w(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLTI_W, vd, vj, sk5));
+}
+
+/* Emits the `vslti.d vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_d(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VSLTI_D, vd, vj, sk5));
+}
+
+/* Emits the `vslti.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLTI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vslti.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLTI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vslti.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLTI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vslti.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslti_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLTI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vaddi.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddi_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VADDI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vaddi.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddi_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VADDI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vaddi.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddi_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VADDI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vaddi.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vaddi_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VADDI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vsubi.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubi_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSUBI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vsubi.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubi_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSUBI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vsubi.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubi_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSUBI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vsubi.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsubi_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSUBI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vbsll.v vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbsll_v(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VBSLL_V, vd, vj, uk5));
+}
+
+/* Emits the `vbsrl.v vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbsrl_v(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VBSRL_V, vd, vj, uk5));
+}
+
+/* Emits the `vmaxi.b vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_b(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMAXI_B, vd, vj, sk5));
+}
+
+/* Emits the `vmaxi.h vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_h(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMAXI_H, vd, vj, sk5));
+}
+
+/* Emits the `vmaxi.w vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_w(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMAXI_W, vd, vj, sk5));
+}
+
+/* Emits the `vmaxi.d vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_d(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMAXI_D, vd, vj, sk5));
+}
+
+/* Emits the `vmini.b vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_b(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMINI_B, vd, vj, sk5));
+}
+
+/* Emits the `vmini.h vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_h(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMINI_H, vd, vj, sk5));
+}
+
+/* Emits the `vmini.w vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_w(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMINI_W, vd, vj, sk5));
+}
+
+/* Emits the `vmini.d vd, vj, sk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_d(TCGContext *s, TCGReg vd, TCGReg vj, int32_t sk5)
+{
+    tcg_out32(s, encode_vdvjsk5_insn(OPC_VMINI_D, vd, vj, sk5));
+}
+
+/* Emits the `vmaxi.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMAXI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vmaxi.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMAXI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vmaxi.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMAXI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vmaxi.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmaxi_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMAXI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vmini.bu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMINI_BU, vd, vj, uk5));
+}
+
+/* Emits the `vmini.hu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMINI_HU, vd, vj, uk5));
+}
+
+/* Emits the `vmini.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMINI_WU, vd, vj, uk5));
+}
+
+/* Emits the `vmini.du vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmini_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VMINI_DU, vd, vj, uk5));
+}
+
+/* Emits the `vfrstpi.b vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrstpi_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VFRSTPI_B, vd, vj, uk5));
+}
+
+/* Emits the `vfrstpi.h vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrstpi_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VFRSTPI_H, vd, vj, uk5));
+}
+
+/* Emits the `vclo.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclo_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLO_B, vd, vj));
+}
+
+/* Emits the `vclo.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclo_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLO_H, vd, vj));
+}
+
+/* Emits the `vclo.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclo_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLO_W, vd, vj));
+}
+
+/* Emits the `vclo.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclo_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLO_D, vd, vj));
+}
+
+/* Emits the `vclz.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclz_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLZ_B, vd, vj));
+}
+
+/* Emits the `vclz.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclz_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLZ_H, vd, vj));
+}
+
+/* Emits the `vclz.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclz_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLZ_W, vd, vj));
+}
+
+/* Emits the `vclz.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vclz_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VCLZ_D, vd, vj));
+}
+
+/* Emits the `vpcnt.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpcnt_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VPCNT_B, vd, vj));
+}
+
+/* Emits the `vpcnt.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpcnt_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VPCNT_H, vd, vj));
+}
+
+/* Emits the `vpcnt.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpcnt_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VPCNT_W, vd, vj));
+}
+
+/* Emits the `vpcnt.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpcnt_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VPCNT_D, vd, vj));
+}
+
+/* Emits the `vneg.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vneg_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VNEG_B, vd, vj));
+}
+
+/* Emits the `vneg.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vneg_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VNEG_H, vd, vj));
+}
+
+/* Emits the `vneg.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vneg_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VNEG_W, vd, vj));
+}
+
+/* Emits the `vneg.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vneg_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VNEG_D, vd, vj));
+}
+
+/* Emits the `vmskltz.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmskltz_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKLTZ_B, vd, vj));
+}
+
+/* Emits the `vmskltz.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmskltz_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKLTZ_H, vd, vj));
+}
+
+/* Emits the `vmskltz.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmskltz_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKLTZ_W, vd, vj));
+}
+
+/* Emits the `vmskltz.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmskltz_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKLTZ_D, vd, vj));
+}
+
+/* Emits the `vmskgez.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmskgez_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKGEZ_B, vd, vj));
+}
+
+/* Emits the `vmsknz.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vmsknz_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VMSKNZ_B, vd, vj));
+}
+
+/* Emits the `vseteqz.v cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vseteqz_v(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETEQZ_V, cd, vj));
+}
+
+/* Emits the `vsetnez.v cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetnez_v(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETNEZ_V, cd, vj));
+}
+
+/* Emits the `vsetanyeqz.b cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetanyeqz_b(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETANYEQZ_B, cd, vj));
+}
+
+/* Emits the `vsetanyeqz.h cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetanyeqz_h(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETANYEQZ_H, cd, vj));
+}
+
+/* Emits the `vsetanyeqz.w cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetanyeqz_w(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETANYEQZ_W, cd, vj));
+}
+
+/* Emits the `vsetanyeqz.d cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetanyeqz_d(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETANYEQZ_D, cd, vj));
+}
+
+/* Emits the `vsetallnez.b cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetallnez_b(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETALLNEZ_B, cd, vj));
+}
+
+/* Emits the `vsetallnez.h cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetallnez_h(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETALLNEZ_H, cd, vj));
+}
+
+/* Emits the `vsetallnez.w cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetallnez_w(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETALLNEZ_W, cd, vj));
+}
+
+/* Emits the `vsetallnez.d cd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsetallnez_d(TCGContext *s, TCGReg cd, TCGReg vj)
+{
+    tcg_out32(s, encode_cdvj_insn(OPC_VSETALLNEZ_D, cd, vj));
+}
+
+/* Emits the `vflogb.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vflogb_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFLOGB_S, vd, vj));
+}
+
+/* Emits the `vflogb.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vflogb_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFLOGB_D, vd, vj));
+}
+
+/* Emits the `vfclass.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfclass_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCLASS_S, vd, vj));
+}
+
+/* Emits the `vfclass.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfclass_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCLASS_D, vd, vj));
+}
+
+/* Emits the `vfsqrt.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfsqrt_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFSQRT_S, vd, vj));
+}
+
+/* Emits the `vfsqrt.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfsqrt_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFSQRT_D, vd, vj));
+}
+
+/* Emits the `vfrecip.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrecip_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRECIP_S, vd, vj));
+}
+
+/* Emits the `vfrecip.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrecip_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRECIP_D, vd, vj));
+}
+
+/* Emits the `vfrsqrt.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrsqrt_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRSQRT_S, vd, vj));
+}
+
+/* Emits the `vfrsqrt.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrsqrt_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRSQRT_D, vd, vj));
+}
+
+/* Emits the `vfrint.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrint_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINT_S, vd, vj));
+}
+
+/* Emits the `vfrint.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrint_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINT_D, vd, vj));
+}
+
+/* Emits the `vfrintrm.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrm_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRM_S, vd, vj));
+}
+
+/* Emits the `vfrintrm.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrm_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRM_D, vd, vj));
+}
+
+/* Emits the `vfrintrp.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrp_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRP_S, vd, vj));
+}
+
+/* Emits the `vfrintrp.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrp_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRP_D, vd, vj));
+}
+
+/* Emits the `vfrintrz.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrz_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRZ_S, vd, vj));
+}
+
+/* Emits the `vfrintrz.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrz_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRZ_D, vd, vj));
+}
+
+/* Emits the `vfrintrne.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrne_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRNE_S, vd, vj));
+}
+
+/* Emits the `vfrintrne.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfrintrne_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFRINTRNE_D, vd, vj));
+}
+
+/* Emits the `vfcvtl.s.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvtl_s_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCVTL_S_H, vd, vj));
+}
+
+/* Emits the `vfcvth.s.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvth_s_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCVTH_S_H, vd, vj));
+}
+
+/* Emits the `vfcvtl.d.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvtl_d_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCVTL_D_S, vd, vj));
+}
+
+/* Emits the `vfcvth.d.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vfcvth_d_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFCVTH_D_S, vd, vj));
+}
+
+/* Emits the `vffint.s.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffint_s_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINT_S_W, vd, vj));
+}
+
+/* Emits the `vffint.s.wu vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffint_s_wu(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINT_S_WU, vd, vj));
+}
+
+/* Emits the `vffint.d.l vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffint_d_l(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINT_D_L, vd, vj));
+}
+
+/* Emits the `vffint.d.lu vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffint_d_lu(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINT_D_LU, vd, vj));
+}
+
+/* Emits the `vffintl.d.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffintl_d_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINTL_D_W, vd, vj));
+}
+
+/* Emits the `vffinth.d.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vffinth_d_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFFINTH_D_W, vd, vj));
+}
+
+/* Emits the `vftint.w.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftint_w_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINT_W_S, vd, vj));
+}
+
+/* Emits the `vftint.l.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftint_l_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINT_L_D, vd, vj));
+}
+
+/* Emits the `vftintrm.w.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrm_w_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRM_W_S, vd, vj));
+}
+
+/* Emits the `vftintrm.l.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrm_l_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRM_L_D, vd, vj));
+}
+
+/* Emits the `vftintrp.w.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrp_w_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRP_W_S, vd, vj));
+}
+
+/* Emits the `vftintrp.l.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrp_l_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRP_L_D, vd, vj));
+}
+
+/* Emits the `vftintrz.w.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrz_w_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZ_W_S, vd, vj));
+}
+
+/* Emits the `vftintrz.l.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrz_l_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZ_L_D, vd, vj));
+}
+
+/* Emits the `vftintrne.w.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrne_w_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRNE_W_S, vd, vj));
+}
+
+/* Emits the `vftintrne.l.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrne_l_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRNE_L_D, vd, vj));
+}
+
+/* Emits the `vftint.wu.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftint_wu_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINT_WU_S, vd, vj));
+}
+
+/* Emits the `vftint.lu.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftint_lu_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINT_LU_D, vd, vj));
+}
+
+/* Emits the `vftintrz.wu.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrz_wu_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZ_WU_S, vd, vj));
+}
+
+/* Emits the `vftintrz.lu.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrz_lu_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZ_LU_D, vd, vj));
+}
+
+/* Emits the `vftintl.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintl_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTL_L_S, vd, vj));
+}
+
+/* Emits the `vftinth.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftinth_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTH_L_S, vd, vj));
+}
+
+/* Emits the `vftintrml.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrml_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRML_L_S, vd, vj));
+}
+
+/* Emits the `vftintrmh.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrmh_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRMH_L_S, vd, vj));
+}
+
+/* Emits the `vftintrpl.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrpl_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRPL_L_S, vd, vj));
+}
+
+/* Emits the `vftintrph.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrph_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRPH_L_S, vd, vj));
+}
+
+/* Emits the `vftintrzl.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrzl_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZL_L_S, vd, vj));
+}
+
+/* Emits the `vftintrzh.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrzh_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRZH_L_S, vd, vj));
+}
+
+/* Emits the `vftintrnel.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrnel_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRNEL_L_S, vd, vj));
+}
+
+/* Emits the `vftintrneh.l.s vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vftintrneh_l_s(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VFTINTRNEH_L_S, vd, vj));
+}
+
+/* Emits the `vexth.h.b vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_h_b(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_H_B, vd, vj));
+}
+
+/* Emits the `vexth.w.h vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_w_h(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_W_H, vd, vj));
+}
+
+/* Emits the `vexth.d.w vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_d_w(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_D_W, vd, vj));
+}
+
+/* Emits the `vexth.q.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_q_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_Q_D, vd, vj));
+}
+
+/* Emits the `vexth.hu.bu vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_hu_bu(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_HU_BU, vd, vj));
+}
+
+/* Emits the `vexth.wu.hu vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_wu_hu(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_WU_HU, vd, vj));
+}
+
+/* Emits the `vexth.du.wu vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_du_wu(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_DU_WU, vd, vj));
+}
+
+/* Emits the `vexth.qu.du vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vexth_qu_du(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTH_QU_DU, vd, vj));
+}
+
+/* Emits the `vreplgr2vr.b vd, j` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplgr2vr_b(TCGContext *s, TCGReg vd, TCGReg j)
+{
+    tcg_out32(s, encode_vdj_insn(OPC_VREPLGR2VR_B, vd, j));
+}
+
+/* Emits the `vreplgr2vr.h vd, j` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplgr2vr_h(TCGContext *s, TCGReg vd, TCGReg j)
+{
+    tcg_out32(s, encode_vdj_insn(OPC_VREPLGR2VR_H, vd, j));
+}
+
+/* Emits the `vreplgr2vr.w vd, j` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplgr2vr_w(TCGContext *s, TCGReg vd, TCGReg j)
+{
+    tcg_out32(s, encode_vdj_insn(OPC_VREPLGR2VR_W, vd, j));
+}
+
+/* Emits the `vreplgr2vr.d vd, j` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplgr2vr_d(TCGContext *s, TCGReg vd, TCGReg j)
+{
+    tcg_out32(s, encode_vdj_insn(OPC_VREPLGR2VR_D, vd, j));
+}
+
+/* Emits the `vrotri.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotri_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VROTRI_B, vd, vj, uk3));
+}
+
+/* Emits the `vrotri.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotri_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VROTRI_H, vd, vj, uk4));
+}
+
+/* Emits the `vrotri.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotri_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VROTRI_W, vd, vj, uk5));
+}
+
+/* Emits the `vrotri.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vrotri_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VROTRI_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrlri.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlri_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSRLRI_B, vd, vj, uk3));
+}
+
+/* Emits the `vsrlri.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlri_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRLRI_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrlri.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlri_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRLRI_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrlri.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlri_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRLRI_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrari.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrari_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSRARI_B, vd, vj, uk3));
+}
+
+/* Emits the `vsrari.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrari_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRARI_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrari.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrari_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRARI_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrari.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrari_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRARI_D, vd, vj, uk6));
+}
+
+/* Emits the `vinsgr2vr.b vd, j, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vinsgr2vr_b(TCGContext *s, TCGReg vd, TCGReg j, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdjuk4_insn(OPC_VINSGR2VR_B, vd, j, uk4));
+}
+
+/* Emits the `vinsgr2vr.h vd, j, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vinsgr2vr_h(TCGContext *s, TCGReg vd, TCGReg j, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdjuk3_insn(OPC_VINSGR2VR_H, vd, j, uk3));
+}
+
+/* Emits the `vinsgr2vr.w vd, j, uk2` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vinsgr2vr_w(TCGContext *s, TCGReg vd, TCGReg j, uint32_t uk2)
+{
+    tcg_out32(s, encode_vdjuk2_insn(OPC_VINSGR2VR_W, vd, j, uk2));
+}
+
+/* Emits the `vinsgr2vr.d vd, j, uk1` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vinsgr2vr_d(TCGContext *s, TCGReg vd, TCGReg j, uint32_t uk1)
+{
+    tcg_out32(s, encode_vdjuk1_insn(OPC_VINSGR2VR_D, vd, j, uk1));
+}
+
+/* Emits the `vpickve2gr.b d, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_b(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_dvjuk4_insn(OPC_VPICKVE2GR_B, d, vj, uk4));
+}
+
+/* Emits the `vpickve2gr.h d, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_h(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_dvjuk3_insn(OPC_VPICKVE2GR_H, d, vj, uk3));
+}
+
+/* Emits the `vpickve2gr.w d, vj, uk2` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_w(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk2)
+{
+    tcg_out32(s, encode_dvjuk2_insn(OPC_VPICKVE2GR_W, d, vj, uk2));
+}
+
+/* Emits the `vpickve2gr.d d, vj, uk1` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_d(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk1)
+{
+    tcg_out32(s, encode_dvjuk1_insn(OPC_VPICKVE2GR_D, d, vj, uk1));
+}
+
+/* Emits the `vpickve2gr.bu d, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_bu(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_dvjuk4_insn(OPC_VPICKVE2GR_BU, d, vj, uk4));
+}
+
+/* Emits the `vpickve2gr.hu d, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_hu(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_dvjuk3_insn(OPC_VPICKVE2GR_HU, d, vj, uk3));
+}
+
+/* Emits the `vpickve2gr.wu d, vj, uk2` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_wu(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk2)
+{
+    tcg_out32(s, encode_dvjuk2_insn(OPC_VPICKVE2GR_WU, d, vj, uk2));
+}
+
+/* Emits the `vpickve2gr.du d, vj, uk1` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpickve2gr_du(TCGContext *s, TCGReg d, TCGReg vj, uint32_t uk1)
+{
+    tcg_out32(s, encode_dvjuk1_insn(OPC_VPICKVE2GR_DU, d, vj, uk1));
+}
+
+/* Emits the `vreplvei.b vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplvei_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VREPLVEI_B, vd, vj, uk4));
+}
+
+/* Emits the `vreplvei.h vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplvei_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VREPLVEI_H, vd, vj, uk3));
+}
+
+/* Emits the `vreplvei.w vd, vj, uk2` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplvei_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk2)
+{
+    tcg_out32(s, encode_vdvjuk2_insn(OPC_VREPLVEI_W, vd, vj, uk2));
+}
+
+/* Emits the `vreplvei.d vd, vj, uk1` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vreplvei_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk1)
+{
+    tcg_out32(s, encode_vdvjuk1_insn(OPC_VREPLVEI_D, vd, vj, uk1));
+}
+
+/* Emits the `vsllwil.h.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_h_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSLLWIL_H_B, vd, vj, uk3));
+}
+
+/* Emits the `vsllwil.w.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_w_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSLLWIL_W_H, vd, vj, uk4));
+}
+
+/* Emits the `vsllwil.d.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_d_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLLWIL_D_W, vd, vj, uk5));
+}
+
+/* Emits the `vextl.q.d vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextl_q_d(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTL_Q_D, vd, vj));
+}
+
+/* Emits the `vsllwil.hu.bu vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_hu_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSLLWIL_HU_BU, vd, vj, uk3));
+}
+
+/* Emits the `vsllwil.wu.hu vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_wu_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSLLWIL_WU_HU, vd, vj, uk4));
+}
+
+/* Emits the `vsllwil.du.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsllwil_du_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLLWIL_DU_WU, vd, vj, uk5));
+}
+
+/* Emits the `vextl.qu.du vd, vj` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextl_qu_du(TCGContext *s, TCGReg vd, TCGReg vj)
+{
+    tcg_out32(s, encode_vdvj_insn(OPC_VEXTL_QU_DU, vd, vj));
+}
+
+/* Emits the `vbitclri.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclri_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VBITCLRI_B, vd, vj, uk3));
+}
+
+/* Emits the `vbitclri.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclri_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VBITCLRI_H, vd, vj, uk4));
+}
+
+/* Emits the `vbitclri.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclri_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VBITCLRI_W, vd, vj, uk5));
+}
+
+/* Emits the `vbitclri.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitclri_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VBITCLRI_D, vd, vj, uk6));
+}
+
+/* Emits the `vbitseti.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitseti_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VBITSETI_B, vd, vj, uk3));
+}
+
+/* Emits the `vbitseti.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitseti_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VBITSETI_H, vd, vj, uk4));
+}
+
+/* Emits the `vbitseti.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitseti_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VBITSETI_W, vd, vj, uk5));
+}
+
+/* Emits the `vbitseti.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitseti_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VBITSETI_D, vd, vj, uk6));
+}
+
+/* Emits the `vbitrevi.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrevi_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VBITREVI_B, vd, vj, uk3));
+}
+
+/* Emits the `vbitrevi.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrevi_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VBITREVI_H, vd, vj, uk4));
+}
+
+/* Emits the `vbitrevi.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrevi_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VBITREVI_W, vd, vj, uk5));
+}
+
+/* Emits the `vbitrevi.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitrevi_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VBITREVI_D, vd, vj, uk6));
+}
+
+/* Emits the `vsat.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSAT_B, vd, vj, uk3));
+}
+
+/* Emits the `vsat.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSAT_H, vd, vj, uk4));
+}
+
+/* Emits the `vsat.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSAT_W, vd, vj, uk5));
+}
+
+/* Emits the `vsat.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSAT_D, vd, vj, uk6));
+}
+
+/* Emits the `vsat.bu vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_bu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSAT_BU, vd, vj, uk3));
+}
+
+/* Emits the `vsat.hu vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_hu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSAT_HU, vd, vj, uk4));
+}
+
+/* Emits the `vsat.wu vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_wu(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSAT_WU, vd, vj, uk5));
+}
+
+/* Emits the `vsat.du vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsat_du(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSAT_DU, vd, vj, uk6));
+}
+
+/* Emits the `vslli.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslli_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSLLI_B, vd, vj, uk3));
+}
+
+/* Emits the `vslli.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslli_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSLLI_H, vd, vj, uk4));
+}
+
+/* Emits the `vslli.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslli_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSLLI_W, vd, vj, uk5));
+}
+
+/* Emits the `vslli.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vslli_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSLLI_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrli.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrli_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSRLI_B, vd, vj, uk3));
+}
+
+/* Emits the `vsrli.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrli_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRLI_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrli.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrli_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRLI_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrli.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrli_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRLI_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrai.b vd, vj, uk3` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrai_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk3)
+{
+    tcg_out32(s, encode_vdvjuk3_insn(OPC_VSRAI_B, vd, vj, uk3));
+}
+
+/* Emits the `vsrai.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrai_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
 {
-    tcg_out32(s, encode_sd10k16_insn(OPC_B, sd10k16));
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRAI_H, vd, vj, uk4));
 }
 
-/* Emits the `bl sd10k16` instruction.  */
+/* Emits the `vsrai.w vd, vj, uk5` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_bl(TCGContext *s, int32_t sd10k16)
+tcg_out_opc_vsrai_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
 {
-    tcg_out32(s, encode_sd10k16_insn(OPC_BL, sd10k16));
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRAI_W, vd, vj, uk5));
 }
 
-/* Emits the `beq d, j, sk16` instruction.  */
+/* Emits the `vsrai.d vd, vj, uk6` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_beq(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrai_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BEQ, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRAI_D, vd, vj, uk6));
 }
 
-/* Emits the `bne d, j, sk16` instruction.  */
+/* Emits the `vsrlni.b.h vd, vj, uk4` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_bne(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrlni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BNE, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRLNI_B_H, vd, vj, uk4));
 }
 
-/* Emits the `bgt d, j, sk16` instruction.  */
+/* Emits the `vsrlni.h.w vd, vj, uk5` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_bgt(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrlni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BGT, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRLNI_H_W, vd, vj, uk5));
 }
 
-/* Emits the `ble d, j, sk16` instruction.  */
+/* Emits the `vsrlni.w.d vd, vj, uk6` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_ble(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrlni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BLE, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRLNI_W_D, vd, vj, uk6));
 }
 
-/* Emits the `bgtu d, j, sk16` instruction.  */
+/* Emits the `vsrlni.d.q vd, vj, uk7` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_bgtu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrlni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BGTU, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSRLNI_D_Q, vd, vj, uk7));
 }
 
-/* Emits the `bleu d, j, sk16` instruction.  */
+/* Emits the `vsrlrni.b.h vd, vj, uk4` instruction.  */
 static void __attribute__((unused))
-tcg_out_opc_bleu(TCGContext *s, TCGReg d, TCGReg j, int32_t sk16)
+tcg_out_opc_vsrlrni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
 {
-    tcg_out32(s, encode_djsk16_insn(OPC_BLEU, d, j, sk16));
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRLRNI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrlrni.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRLRNI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrlrni.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRLRNI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrlrni.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrlrni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSRLRNI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrlni.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRLNI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrlni.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRLNI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrlni.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRLNI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrlni.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRLNI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrlni.bu.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRLNI_BU_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrlni.hu.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRLNI_HU_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrlni.wu.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRLNI_WU_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrlni.du.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlni_du_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRLNI_DU_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrlrni.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRLRNI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrlrni.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRLRNI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrlrni.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRLRNI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrlrni.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRLRNI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrlrni.bu.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRLRNI_BU_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrlrni.hu.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRLRNI_HU_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrlrni.wu.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRLRNI_WU_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrlrni.du.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrlrni_du_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRLRNI_DU_Q, vd, vj, uk7));
+}
+
+/* Emits the `vsrani.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrani_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRANI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrani.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrani_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRANI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrani.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrani_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRANI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrani.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrani_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSRANI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vsrarni.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSRARNI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vsrarni.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSRARNI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vsrarni.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSRARNI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vsrarni.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vsrarni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSRARNI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrani.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRANI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrani.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRANI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrani.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRANI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrani.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRANI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrani.bu.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRANI_BU_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrani.hu.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRANI_HU_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrani.wu.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRANI_WU_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrani.du.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrani_du_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRANI_DU_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrarni.b.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_b_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRARNI_B_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrarni.h.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_h_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRARNI_H_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrarni.w.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_w_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRARNI_W_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrarni.d.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_d_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRARNI_D_Q, vd, vj, uk7));
+}
+
+/* Emits the `vssrarni.bu.h vd, vj, uk4` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_bu_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk4)
+{
+    tcg_out32(s, encode_vdvjuk4_insn(OPC_VSSRARNI_BU_H, vd, vj, uk4));
+}
+
+/* Emits the `vssrarni.hu.w vd, vj, uk5` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_hu_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk5)
+{
+    tcg_out32(s, encode_vdvjuk5_insn(OPC_VSSRARNI_HU_W, vd, vj, uk5));
+}
+
+/* Emits the `vssrarni.wu.d vd, vj, uk6` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_wu_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk6)
+{
+    tcg_out32(s, encode_vdvjuk6_insn(OPC_VSSRARNI_WU_D, vd, vj, uk6));
+}
+
+/* Emits the `vssrarni.du.q vd, vj, uk7` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vssrarni_du_q(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk7)
+{
+    tcg_out32(s, encode_vdvjuk7_insn(OPC_VSSRARNI_DU_Q, vd, vj, uk7));
+}
+
+/* Emits the `vextrins.d vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextrins_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VEXTRINS_D, vd, vj, uk8));
+}
+
+/* Emits the `vextrins.w vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextrins_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VEXTRINS_W, vd, vj, uk8));
+}
+
+/* Emits the `vextrins.h vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextrins_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VEXTRINS_H, vd, vj, uk8));
+}
+
+/* Emits the `vextrins.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vextrins_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VEXTRINS_B, vd, vj, uk8));
+}
+
+/* Emits the `vshuf4i.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf4i_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VSHUF4I_B, vd, vj, uk8));
+}
+
+/* Emits the `vshuf4i.h vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf4i_h(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VSHUF4I_H, vd, vj, uk8));
+}
+
+/* Emits the `vshuf4i.w vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf4i_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VSHUF4I_W, vd, vj, uk8));
+}
+
+/* Emits the `vshuf4i.d vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vshuf4i_d(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VSHUF4I_D, vd, vj, uk8));
+}
+
+/* Emits the `vbitseli.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vbitseli_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VBITSELI_B, vd, vj, uk8));
+}
+
+/* Emits the `vandi.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vandi_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VANDI_B, vd, vj, uk8));
+}
+
+/* Emits the `vori.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vori_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VORI_B, vd, vj, uk8));
+}
+
+/* Emits the `vxori.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vxori_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VXORI_B, vd, vj, uk8));
+}
+
+/* Emits the `vnori.b vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vnori_b(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VNORI_B, vd, vj, uk8));
+}
+
+/* Emits the `vldi vd, sj13` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vldi(TCGContext *s, TCGReg vd, int32_t sj13)
+{
+    tcg_out32(s, encode_vdsj13_insn(OPC_VLDI, vd, sj13));
+}
+
+/* Emits the `vpermi.w vd, vj, uk8` instruction.  */
+static void __attribute__((unused))
+tcg_out_opc_vpermi_w(TCGContext *s, TCGReg vd, TCGReg vj, uint32_t uk8)
+{
+    tcg_out32(s, encode_vdvjuk8_insn(OPC_VPERMI_W, vd, vj, uk8));
 }
 
 /* End of generated code.  */
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
  2023-08-28 15:19 ` [PATCH 01/11] tcg/loongarch64: Import LSX instructions Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 16:57   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
                   ` (9 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

LSX support on host cpu is detected via hwcap.

Lower the following ops to LSX:

- dup_vec
- dupi_vec
- dupm_vec
- ld_vec
- st_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |   2 +
 tcg/loongarch64/tcg-target-con-str.h |   1 +
 tcg/loongarch64/tcg-target.c.inc     | 223 ++++++++++++++++++++++++++-
 tcg/loongarch64/tcg-target.h         |  37 ++++-
 tcg/loongarch64/tcg-target.opc.h     |  12 ++
 5 files changed, 273 insertions(+), 2 deletions(-)
 create mode 100644 tcg/loongarch64/tcg-target.opc.h

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index c2bde44613..37b3f80bf9 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -17,7 +17,9 @@
 C_O0_I1(r)
 C_O0_I2(rZ, r)
 C_O0_I2(rZ, rZ)
+C_O0_I2(w, r)
 C_O1_I1(r, r)
+C_O1_I1(w, r)
 C_O1_I2(r, r, rC)
 C_O1_I2(r, r, ri)
 C_O1_I2(r, r, rI)
diff --git a/tcg/loongarch64/tcg-target-con-str.h b/tcg/loongarch64/tcg-target-con-str.h
index 6e9ccca3ad..81b8d40278 100644
--- a/tcg/loongarch64/tcg-target-con-str.h
+++ b/tcg/loongarch64/tcg-target-con-str.h
@@ -14,6 +14,7 @@
  * REGS(letter, register_mask)
  */
 REGS('r', ALL_GENERAL_REGS)
+REGS('w', ALL_VECTOR_REGS)
 
 /*
  * Define constraint letters for constants:
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index baf5fc3819..0f9427572c 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -32,6 +32,8 @@
 #include "../tcg-ldst.c.inc"
 #include <asm/hwcap.h>
 
+bool use_lsx_instructions;
+
 #ifdef CONFIG_DEBUG_TCG
 static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
     "zero",
@@ -65,7 +67,39 @@ static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
     "s5",
     "s6",
     "s7",
-    "s8"
+    "s8",
+    "vr0",
+    "vr1",
+    "vr2",
+    "vr3",
+    "vr4",
+    "vr5",
+    "vr6",
+    "vr7",
+    "vr8",
+    "vr9",
+    "vr10",
+    "vr11",
+    "vr12",
+    "vr13",
+    "vr14",
+    "vr15",
+    "vr16",
+    "vr17",
+    "vr18",
+    "vr19",
+    "vr20",
+    "vr21",
+    "vr22",
+    "vr23",
+    "vr24",
+    "vr25",
+    "vr26",
+    "vr27",
+    "vr28",
+    "vr29",
+    "vr30",
+    "vr31",
 };
 #endif
 
@@ -102,6 +136,15 @@ static const int tcg_target_reg_alloc_order[] = {
     TCG_REG_A2,
     TCG_REG_A1,
     TCG_REG_A0,
+
+    /* Vector registers */
+    TCG_REG_V0, TCG_REG_V1, TCG_REG_V2, TCG_REG_V3,
+    TCG_REG_V4, TCG_REG_V5, TCG_REG_V6, TCG_REG_V7,
+    TCG_REG_V8, TCG_REG_V9, TCG_REG_V10, TCG_REG_V11,
+    TCG_REG_V12, TCG_REG_V13, TCG_REG_V14, TCG_REG_V15,
+    TCG_REG_V16, TCG_REG_V17, TCG_REG_V18, TCG_REG_V19,
+    TCG_REG_V20, TCG_REG_V21, TCG_REG_V22, TCG_REG_V23,
+    /* V24 - V31 are caller-saved, and skipped.  */
 };
 
 static const int tcg_target_call_iarg_regs[] = {
@@ -135,6 +178,7 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot)
 #define TCG_CT_CONST_WSZ   0x2000
 
 #define ALL_GENERAL_REGS   MAKE_64BIT_MASK(0, 32)
+#define ALL_VECTOR_REGS    MAKE_64BIT_MASK(32, 32)
 
 static inline tcg_target_long sextreg(tcg_target_long val, int pos, int len)
 {
@@ -1486,6 +1530,159 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     }
 }
 
+static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
+                            TCGReg rd, TCGReg rs)
+{
+    switch (vece) {
+    case MO_8:
+        tcg_out_opc_vreplgr2vr_b(s, rd, rs);
+        break;
+    case MO_16:
+        tcg_out_opc_vreplgr2vr_h(s, rd, rs);
+        break;
+    case MO_32:
+        tcg_out_opc_vreplgr2vr_w(s, rd, rs);
+        break;
+    case MO_64:
+        tcg_out_opc_vreplgr2vr_d(s, rd, rs);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    return true;
+}
+
+static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
+                             TCGReg r, TCGReg base, intptr_t offset)
+{
+    /* Handle imm overflow and division (vldrepl.d imm is divided by 8) */
+    if (offset < -0x800 || offset > 0x7ff || \
+        (offset & ((1 << vece) - 1)) != 0) {
+        tcg_out_addi(s, TCG_TYPE_I64, TCG_REG_TMP0, base, offset);
+        base = TCG_REG_TMP0;
+        offset = 0;
+    }
+    offset >>= vece;
+
+    switch (vece) {
+    case MO_8:
+        tcg_out_opc_vldrepl_b(s, r, base, offset);
+        break;
+    case MO_16:
+        tcg_out_opc_vldrepl_h(s, r, base, offset);
+        break;
+    case MO_32:
+        tcg_out_opc_vldrepl_w(s, r, base, offset);
+        break;
+    case MO_64:
+        tcg_out_opc_vldrepl_d(s, r, base, offset);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    return true;
+}
+
+static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
+                             TCGReg rd, int64_t v64)
+{
+    /* Try vldi if imm can fit */
+    if (vece <= MO_32 && (-0x200 <= v64 && v64 <= 0x1FF)) {
+        uint32_t imm = (vece << 10) | ((uint32_t)v64 & 0x3FF);
+        tcg_out_opc_vldi(s, rd, imm);
+        return;
+    }
+
+    /* Fallback to vreplgr2vr */
+    tcg_out_movi(s, type, TCG_REG_TMP0, v64);
+    switch (vece) {
+    case MO_8:
+        tcg_out_opc_vreplgr2vr_b(s, rd, TCG_REG_TMP0);
+        break;
+    case MO_16:
+        tcg_out_opc_vreplgr2vr_h(s, rd, TCG_REG_TMP0);
+        break;
+    case MO_32:
+        tcg_out_opc_vreplgr2vr_w(s, rd, TCG_REG_TMP0);
+        break;
+    case MO_64:
+        tcg_out_opc_vreplgr2vr_d(s, rd, TCG_REG_TMP0);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
+                           unsigned vecl, unsigned vece,
+                           const TCGArg args[TCG_MAX_OP_ARGS],
+                           const int const_args[TCG_MAX_OP_ARGS])
+{
+    TCGType type = vecl + TCG_TYPE_V64;
+    TCGArg a0, a1, a2;
+    TCGReg base;
+    TCGReg temp = TCG_REG_TMP0;
+    int32_t offset;
+
+    a0 = args[0];
+    a1 = args[1];
+    a2 = args[2];
+
+    /* Currently only supports V128 */
+    tcg_debug_assert(type == TCG_TYPE_V128);
+
+    switch (opc) {
+    case INDEX_op_st_vec:
+        /* Try to fit vst imm */
+        if (-0x800 <= a2 && a2 <= 0x7ff) {
+            base = a1;
+            offset = a2;
+        } else {
+            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
+            base = temp;
+            offset = 0;
+        }
+        tcg_out_opc_vst(s, a0, base, offset);
+        break;
+    case INDEX_op_ld_vec:
+        /* Try to fit vld imm */
+        if (-0x800 <= a2 && a2 <= 0x7ff) {
+            base = a1;
+            offset = a2;
+        } else {
+            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
+            base = temp;
+            offset = 0;
+        }
+        tcg_out_opc_vld(s, a0, base, offset);
+        break;
+    case INDEX_op_dupm_vec:
+        tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
+{
+    switch (opc) {
+    case INDEX_op_ld_vec:
+    case INDEX_op_st_vec:
+    case INDEX_op_dup_vec:
+    case INDEX_op_dupm_vec:
+        return 1;
+    default:
+        return 0;
+    }
+}
+
+void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
+                       TCGArg a0, ...)
+{
+    g_assert_not_reached();
+}
+
 static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
 {
     switch (op) {
@@ -1627,6 +1824,14 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_movcond_i64:
         return C_O1_I4(r, rZ, rJ, rZ, rZ);
 
+    case INDEX_op_ld_vec:
+    case INDEX_op_dupm_vec:
+    case INDEX_op_dup_vec:
+        return C_O1_I1(w, r);
+
+    case INDEX_op_st_vec:
+        return C_O0_I2(w, r);
+
     default:
         g_assert_not_reached();
     }
@@ -1708,6 +1913,10 @@ static void tcg_target_init(TCGContext *s)
         exit(EXIT_FAILURE);
     }
 
+    if (hwcap & HWCAP_LOONGARCH_LSX) {
+        use_lsx_instructions = 1;
+    }
+
     tcg_target_available_regs[TCG_TYPE_I32] = ALL_GENERAL_REGS;
     tcg_target_available_regs[TCG_TYPE_I64] = ALL_GENERAL_REGS;
 
@@ -1723,6 +1932,18 @@ static void tcg_target_init(TCGContext *s)
     tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_S8);
     tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_S9);
 
+    if (use_lsx_instructions) {
+        tcg_target_available_regs[TCG_TYPE_V128] = ALL_VECTOR_REGS;
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V24);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V25);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V26);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V27);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V28);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V29);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V30);
+        tcg_regset_reset_reg(tcg_target_call_clobber_regs, TCG_REG_V31);
+    }
+
     s->reserved_regs = 0;
     tcg_regset_set_reg(s->reserved_regs, TCG_REG_ZERO);
     tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP0);
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 26f1aab780..be9343ded9 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -30,7 +30,7 @@
 #define LOONGARCH_TCG_TARGET_H
 
 #define TCG_TARGET_INSN_UNIT_SIZE 4
-#define TCG_TARGET_NB_REGS 32
+#define TCG_TARGET_NB_REGS 64
 
 #define MAX_CODE_GEN_BUFFER_SIZE  ((size_t)-1)
 
@@ -68,6 +68,15 @@ typedef enum {
     TCG_REG_S7,
     TCG_REG_S8,
 
+    TCG_REG_V0 = 32, TCG_REG_V1, TCG_REG_V2, TCG_REG_V3,
+    TCG_REG_V4, TCG_REG_V5, TCG_REG_V6, TCG_REG_V7,
+    TCG_REG_V8, TCG_REG_V9, TCG_REG_V10, TCG_REG_V11,
+    TCG_REG_V12, TCG_REG_V13, TCG_REG_V14, TCG_REG_V15,
+    TCG_REG_V16, TCG_REG_V17, TCG_REG_V18, TCG_REG_V19,
+    TCG_REG_V20, TCG_REG_V21, TCG_REG_V22, TCG_REG_V23,
+    TCG_REG_V24, TCG_REG_V25, TCG_REG_V26, TCG_REG_V27,
+    TCG_REG_V28, TCG_REG_V29, TCG_REG_V30, TCG_REG_V31,
+
     /* aliases */
     TCG_AREG0    = TCG_REG_S0,
     TCG_REG_TMP0 = TCG_REG_T8,
@@ -75,6 +84,8 @@ typedef enum {
     TCG_REG_TMP2 = TCG_REG_T6,
 } TCGReg;
 
+extern bool use_lsx_instructions;
+
 /* used for function call generation */
 #define TCG_REG_CALL_STACK              TCG_REG_SP
 #define TCG_TARGET_STACK_ALIGN          16
@@ -159,6 +170,30 @@ typedef enum {
 #define TCG_TARGET_HAS_mulsh_i64        1
 #define TCG_TARGET_HAS_qemu_ldst_i128   0
 
+#define TCG_TARGET_HAS_v64              0
+#define TCG_TARGET_HAS_v128             use_lsx_instructions
+#define TCG_TARGET_HAS_v256             0
+
+#define TCG_TARGET_HAS_not_vec          0
+#define TCG_TARGET_HAS_neg_vec          0
+#define TCG_TARGET_HAS_abs_vec          0
+#define TCG_TARGET_HAS_andc_vec         0
+#define TCG_TARGET_HAS_orc_vec          0
+#define TCG_TARGET_HAS_nand_vec         0
+#define TCG_TARGET_HAS_nor_vec          0
+#define TCG_TARGET_HAS_eqv_vec          0
+#define TCG_TARGET_HAS_mul_vec          0
+#define TCG_TARGET_HAS_shi_vec          0
+#define TCG_TARGET_HAS_shs_vec          0
+#define TCG_TARGET_HAS_shv_vec          0
+#define TCG_TARGET_HAS_roti_vec         0
+#define TCG_TARGET_HAS_rots_vec         0
+#define TCG_TARGET_HAS_rotv_vec         0
+#define TCG_TARGET_HAS_sat_vec          0
+#define TCG_TARGET_HAS_minmax_vec       0
+#define TCG_TARGET_HAS_bitsel_vec       0
+#define TCG_TARGET_HAS_cmpsel_vec       0
+
 #define TCG_TARGET_DEFAULT_MO (0)
 
 #define TCG_TARGET_NEED_LDST_LABELS
diff --git a/tcg/loongarch64/tcg-target.opc.h b/tcg/loongarch64/tcg-target.opc.h
new file mode 100644
index 0000000000..fd1a40b7fd
--- /dev/null
+++ b/tcg/loongarch64/tcg-target.opc.h
@@ -0,0 +1,12 @@
+/*
+ * Copyright (c) 2023 Jiajie Chen
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ *
+ * Target-specific opcodes for host vector expansion.  These will be
+ * emitted by tcg_expand_vec_op.  For those familiar with GCC internals,
+ * consider these to be UNSPEC with names.
+ */
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
  2023-08-28 15:19 ` [PATCH 01/11] tcg/loongarch64: Import LSX instructions Jiajie Chen
  2023-08-28 15:19 ` [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:08   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Jiajie Chen
                   ` (8 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |  1 +
 tcg/loongarch64/tcg-target.c.inc     | 25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index 37b3f80bf9..e80fc7f3f7 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -31,4 +31,5 @@ C_O1_I2(r, 0, rZ)
 C_O1_I2(r, rZ, ri)
 C_O1_I2(r, rZ, rJ)
 C_O1_I2(r, rZ, rZ)
+C_O1_I2(w, w, w)
 C_O1_I4(r, rZ, rJ, rZ, rZ)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 0f9427572c..cc80e5fa20 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1624,6 +1624,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     TCGReg temp = TCG_REG_TMP0;
     int32_t offset;
 
+    static const LoongArchInsn cmp_vec_insn[16][4] = {
+        [TCG_COND_EQ] = {OPC_VSEQ_B, OPC_VSEQ_H, OPC_VSEQ_W, OPC_VSEQ_D},
+        [TCG_COND_LE] = {OPC_VSLE_B, OPC_VSLE_H, OPC_VSLE_W, OPC_VSLE_D},
+        [TCG_COND_LEU] = {OPC_VSLE_BU, OPC_VSLE_HU, OPC_VSLE_WU, OPC_VSLE_DU},
+        [TCG_COND_LT] = {OPC_VSLT_B, OPC_VSLT_H, OPC_VSLT_W, OPC_VSLT_D},
+        [TCG_COND_LTU] = {OPC_VSLT_BU, OPC_VSLT_HU, OPC_VSLT_WU, OPC_VSLT_DU},
+    };
+    LoongArchInsn insn;
+
     a0 = args[0];
     a1 = args[1];
     a2 = args[2];
@@ -1656,6 +1665,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         }
         tcg_out_opc_vld(s, a0, base, offset);
         break;
+    case INDEX_op_cmp_vec:
+        TCGCond cond = args[3];
+        insn = cmp_vec_insn[cond][vece];
+        if (insn == 0) {
+            TCGArg t;
+            t = a1, a1 = a2, a2 = t;
+            cond = tcg_swap_cond(cond);
+            insn = cmp_vec_insn[cond][vece];
+            tcg_debug_assert(insn != 0);
+        }
+        tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1671,6 +1692,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_st_vec:
     case INDEX_op_dup_vec:
     case INDEX_op_dupm_vec:
+    case INDEX_op_cmp_vec:
         return 1;
     default:
         return 0;
@@ -1832,6 +1854,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_st_vec:
         return C_O0_I2(w, r);
 
+    case INDEX_op_cmp_vec:
+        return C_O1_I2(w, w, w);
+
     default:
         g_assert_not_reached();
     }
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (2 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:13   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
                   ` (7 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Lower the following ops:

- add_vec
- sub_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index cc80e5fa20..eb340a6493 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1632,6 +1632,12 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         [TCG_COND_LTU] = {OPC_VSLT_BU, OPC_VSLT_HU, OPC_VSLT_WU, OPC_VSLT_DU},
     };
     LoongArchInsn insn;
+    static const LoongArchInsn add_vec_insn[4] = {
+        OPC_VADD_B, OPC_VADD_H, OPC_VADD_W, OPC_VADD_D
+    };
+    static const LoongArchInsn sub_vec_insn[4] = {
+        OPC_VSUB_B, OPC_VSUB_H, OPC_VSUB_W, OPC_VSUB_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1677,6 +1683,12 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         }
         tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
         break;
+    case INDEX_op_add_vec:
+        tcg_out32(s, encode_vdvjvk_insn(add_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sub_vec:
+        tcg_out32(s, encode_vdvjvk_insn(sub_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1693,6 +1705,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_dup_vec:
     case INDEX_op_dupm_vec:
     case INDEX_op_cmp_vec:
+    case INDEX_op_add_vec:
+    case INDEX_op_sub_vec:
         return 1;
     default:
         return 0;
@@ -1855,6 +1869,8 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
         return C_O0_I2(w, r);
 
     case INDEX_op_cmp_vec:
+    case INDEX_op_add_vec:
+    case INDEX_op_sub_vec:
         return C_O1_I2(w, w, w);
 
     default:
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (3 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:17   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
                   ` (6 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Lower the following ops:

- and_vec
- andc_vec
- or_vec
- orc_vec
- xor_vec
- nor_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 35 ++++++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  6 +++---
 2 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index eb340a6493..fe741ef045 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1671,6 +1671,29 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         }
         tcg_out_opc_vld(s, a0, base, offset);
         break;
+    case INDEX_op_and_vec:
+        tcg_out_opc_vand_v(s, a0, a1, a2);
+        break;
+    case INDEX_op_andc_vec:
+        /*
+         * vandn vd, vj, vk: vd = vk & ~vj
+         * andc_vec vd, vj, vk: vd = vj & ~vk
+         * vk and vk are swapped
+         */
+        tcg_out_opc_vandn_v(s, a0, a2, a1);
+        break;
+    case INDEX_op_or_vec:
+        tcg_out_opc_vor_v(s, a0, a1, a2);
+        break;
+    case INDEX_op_orc_vec:
+        tcg_out_opc_vorn_v(s, a0, a1, a2);
+        break;
+    case INDEX_op_xor_vec:
+        tcg_out_opc_vxor_v(s, a0, a1, a2);
+        break;
+    case INDEX_op_nor_vec:
+        tcg_out_opc_vnor_v(s, a0, a1, a2);
+        break;
     case INDEX_op_cmp_vec:
         TCGCond cond = args[3];
         insn = cmp_vec_insn[cond][vece];
@@ -1707,6 +1730,12 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_cmp_vec:
     case INDEX_op_add_vec:
     case INDEX_op_sub_vec:
+    case INDEX_op_and_vec:
+    case INDEX_op_andc_vec:
+    case INDEX_op_or_vec:
+    case INDEX_op_orc_vec:
+    case INDEX_op_xor_vec:
+    case INDEX_op_nor_vec:
         return 1;
     default:
         return 0;
@@ -1871,6 +1900,12 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_cmp_vec:
     case INDEX_op_add_vec:
     case INDEX_op_sub_vec:
+    case INDEX_op_and_vec:
+    case INDEX_op_andc_vec:
+    case INDEX_op_or_vec:
+    case INDEX_op_orc_vec:
+    case INDEX_op_xor_vec:
+    case INDEX_op_nor_vec:
         return C_O1_I2(w, w, w);
 
     default:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index be9343ded9..4ca685e752 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -177,10 +177,10 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_not_vec          0
 #define TCG_TARGET_HAS_neg_vec          0
 #define TCG_TARGET_HAS_abs_vec          0
-#define TCG_TARGET_HAS_andc_vec         0
-#define TCG_TARGET_HAS_orc_vec          0
+#define TCG_TARGET_HAS_andc_vec         1
+#define TCG_TARGET_HAS_orc_vec          1
 #define TCG_TARGET_HAS_nand_vec         0
-#define TCG_TARGET_HAS_nor_vec          0
+#define TCG_TARGET_HAS_nor_vec          1
 #define TCG_TARGET_HAS_eqv_vec          0
 #define TCG_TARGET_HAS_mul_vec          0
 #define TCG_TARGET_HAS_shi_vec          0
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (4 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:18   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
                   ` (5 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |  1 +
 tcg/loongarch64/tcg-target.c.inc     | 10 ++++++++++
 tcg/loongarch64/tcg-target.h         |  2 +-
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index e80fc7f3f7..9fce856012 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -20,6 +20,7 @@ C_O0_I2(rZ, rZ)
 C_O0_I2(w, r)
 C_O1_I1(r, r)
 C_O1_I1(w, r)
+C_O1_I1(w, w)
 C_O1_I2(r, r, rC)
 C_O1_I2(r, r, ri)
 C_O1_I2(r, r, rI)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index fe741ef045..819dcdba77 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1638,6 +1638,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn sub_vec_insn[4] = {
         OPC_VSUB_B, OPC_VSUB_H, OPC_VSUB_W, OPC_VSUB_D
     };
+    static const LoongArchInsn neg_vec_insn[4] = {
+        OPC_VNEG_B, OPC_VNEG_H, OPC_VNEG_W, OPC_VNEG_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1712,6 +1715,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_sub_vec:
         tcg_out32(s, encode_vdvjvk_insn(sub_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_neg_vec:
+        tcg_out32(s, encode_vdvj_insn(neg_vec_insn[vece], a0, a1));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1736,6 +1742,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_orc_vec:
     case INDEX_op_xor_vec:
     case INDEX_op_nor_vec:
+    case INDEX_op_neg_vec:
         return 1;
     default:
         return 0;
@@ -1908,6 +1915,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_nor_vec:
         return C_O1_I2(w, w, w);
 
+    case INDEX_op_neg_vec:
+        return C_O1_I1(w, w);
+
     default:
         g_assert_not_reached();
     }
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 4ca685e752..6a8147875a 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -175,7 +175,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_v256             0
 
 #define TCG_TARGET_HAS_not_vec          0
-#define TCG_TARGET_HAS_neg_vec          0
+#define TCG_TARGET_HAS_neg_vec          1
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_andc_vec         1
 #define TCG_TARGET_HAS_orc_vec          1
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (5 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:18   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 08/11] tcg/loongarch64: Lower vector min max ops Jiajie Chen
                   ` (4 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 8 ++++++++
 tcg/loongarch64/tcg-target.h     | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 819dcdba77..bca24b6a20 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1641,6 +1641,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn neg_vec_insn[4] = {
         OPC_VNEG_B, OPC_VNEG_H, OPC_VNEG_W, OPC_VNEG_D
     };
+    static const LoongArchInsn mul_vec_insn[4] = {
+        OPC_VMUL_B, OPC_VMUL_H, OPC_VMUL_W, OPC_VMUL_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1718,6 +1721,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_neg_vec:
         tcg_out32(s, encode_vdvj_insn(neg_vec_insn[vece], a0, a1));
         break;
+    case INDEX_op_mul_vec:
+        tcg_out32(s, encode_vdvjvk_insn(mul_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1743,6 +1749,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_xor_vec:
     case INDEX_op_nor_vec:
     case INDEX_op_neg_vec:
+    case INDEX_op_mul_vec:
         return 1;
     default:
         return 0;
@@ -1913,6 +1920,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_orc_vec:
     case INDEX_op_xor_vec:
     case INDEX_op_nor_vec:
+    case INDEX_op_mul_vec:
         return C_O1_I2(w, w, w);
 
     case INDEX_op_neg_vec:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 6a8147875a..6b97abcb5b 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -182,7 +182,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_nand_vec         0
 #define TCG_TARGET_HAS_nor_vec          1
 #define TCG_TARGET_HAS_eqv_vec          0
-#define TCG_TARGET_HAS_mul_vec          0
+#define TCG_TARGET_HAS_mul_vec          1
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
 #define TCG_TARGET_HAS_shv_vec          0
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 08/11] tcg/loongarch64: Lower vector min max ops
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (6 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:19   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
                   ` (3 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Lower the following ops:

- smin_vec
- smax_vec
- umin_vec
- umax_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index bca24b6a20..91049a80b6 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1644,6 +1644,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn mul_vec_insn[4] = {
         OPC_VMUL_B, OPC_VMUL_H, OPC_VMUL_W, OPC_VMUL_D
     };
+    static const LoongArchInsn smin_vec_insn[4] = {
+        OPC_VMIN_B, OPC_VMIN_H, OPC_VMIN_W, OPC_VMIN_D
+    };
+    static const LoongArchInsn umin_vec_insn[4] = {
+        OPC_VMIN_BU, OPC_VMIN_HU, OPC_VMIN_WU, OPC_VMIN_DU
+    };
+    static const LoongArchInsn smax_vec_insn[4] = {
+        OPC_VMAX_B, OPC_VMAX_H, OPC_VMAX_W, OPC_VMAX_D
+    };
+    static const LoongArchInsn umax_vec_insn[4] = {
+        OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1724,6 +1736,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_mul_vec:
         tcg_out32(s, encode_vdvjvk_insn(mul_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_smin_vec:
+        tcg_out32(s, encode_vdvjvk_insn(smin_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_smax_vec:
+        tcg_out32(s, encode_vdvjvk_insn(smax_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_umin_vec:
+        tcg_out32(s, encode_vdvjvk_insn(umin_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_umax_vec:
+        tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1750,6 +1774,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_nor_vec:
     case INDEX_op_neg_vec:
     case INDEX_op_mul_vec:
+    case INDEX_op_smin_vec:
+    case INDEX_op_smax_vec:
+    case INDEX_op_umin_vec:
+    case INDEX_op_umax_vec:
         return 1;
     default:
         return 0;
@@ -1921,6 +1949,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_xor_vec:
     case INDEX_op_nor_vec:
     case INDEX_op_mul_vec:
+    case INDEX_op_smin_vec:
+    case INDEX_op_smax_vec:
+    case INDEX_op_umin_vec:
+    case INDEX_op_umax_vec:
         return C_O1_I2(w, w, w);
 
     case INDEX_op_neg_vec:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 6b97abcb5b..97af7f8631 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -190,7 +190,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_sat_vec          0
-#define TCG_TARGET_HAS_minmax_vec       0
+#define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       0
 
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (7 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 08/11] tcg/loongarch64: Lower vector min max ops Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:20   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
                   ` (2 subsequent siblings)
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Lower the following ops:

- ssadd_vec
- usadd_vec
- sssub_vec
- ussub_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 91049a80b6..21d2365987 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1656,6 +1656,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn umax_vec_insn[4] = {
         OPC_VMAX_BU, OPC_VMAX_HU, OPC_VMAX_WU, OPC_VMAX_DU
     };
+    static const LoongArchInsn ssadd_vec_insn[4] = {
+        OPC_VSADD_B, OPC_VSADD_H, OPC_VSADD_W, OPC_VSADD_D
+    };
+    static const LoongArchInsn usadd_vec_insn[4] = {
+        OPC_VSADD_BU, OPC_VSADD_HU, OPC_VSADD_WU, OPC_VSADD_DU
+    };
+    static const LoongArchInsn sssub_vec_insn[4] = {
+        OPC_VSSUB_B, OPC_VSSUB_H, OPC_VSSUB_W, OPC_VSSUB_D
+    };
+    static const LoongArchInsn ussub_vec_insn[4] = {
+        OPC_VSSUB_BU, OPC_VSSUB_HU, OPC_VSSUB_WU, OPC_VSSUB_DU
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1748,6 +1760,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_umax_vec:
         tcg_out32(s, encode_vdvjvk_insn(umax_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_ssadd_vec:
+        tcg_out32(s, encode_vdvjvk_insn(ssadd_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_usadd_vec:
+        tcg_out32(s, encode_vdvjvk_insn(usadd_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sssub_vec:
+        tcg_out32(s, encode_vdvjvk_insn(sssub_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_ussub_vec:
+        tcg_out32(s, encode_vdvjvk_insn(ussub_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1778,6 +1802,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_smax_vec:
     case INDEX_op_umin_vec:
     case INDEX_op_umax_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_ussub_vec:
         return 1;
     default:
         return 0;
@@ -1953,6 +1981,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_smax_vec:
     case INDEX_op_umin_vec:
     case INDEX_op_umax_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_ussub_vec:
         return C_O1_I2(w, w, w);
 
     case INDEX_op_neg_vec:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 97af7f8631..4c90a1cf51 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -189,7 +189,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_roti_vec         0
 #define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
-#define TCG_TARGET_HAS_sat_vec          0
+#define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       0
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (8 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:21   ` Richard Henderson
  2023-08-28 15:19 ` [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
  2023-08-28 17:29 ` [PATCH 00/11] Lower TCG vector ops to LSX Richard Henderson
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Lower the following ops:

- shlv_vec
- shrv_vec
- sarv_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target.c.inc | 24 ++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h     |  2 +-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 21d2365987..caf2a7a563 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1668,6 +1668,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const LoongArchInsn ussub_vec_insn[4] = {
         OPC_VSSUB_BU, OPC_VSSUB_HU, OPC_VSSUB_WU, OPC_VSSUB_DU
     };
+    static const LoongArchInsn shlv_vec_insn[4] = {
+        OPC_VSLL_B, OPC_VSLL_H, OPC_VSLL_W, OPC_VSLL_D
+    };
+    static const LoongArchInsn shrv_vec_insn[4] = {
+        OPC_VSRL_B, OPC_VSRL_H, OPC_VSRL_W, OPC_VSRL_D
+    };
+    static const LoongArchInsn sarv_vec_insn[4] = {
+        OPC_VSRA_B, OPC_VSRA_H, OPC_VSRA_W, OPC_VSRA_D
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1772,6 +1781,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ussub_vec:
         tcg_out32(s, encode_vdvjvk_insn(ussub_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_shlv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(shlv_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_shrv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(shrv_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sarv_vec:
+        tcg_out32(s, encode_vdvjvk_insn(sarv_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1806,6 +1824,9 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_usadd_vec:
     case INDEX_op_sssub_vec:
     case INDEX_op_ussub_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return 1;
     default:
         return 0;
@@ -1985,6 +2006,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_usadd_vec:
     case INDEX_op_sssub_vec:
     case INDEX_op_ussub_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return C_O1_I2(w, w, w);
 
     case INDEX_op_neg_vec:
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 4c90a1cf51..771545b021 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -185,7 +185,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_mul_vec          1
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
-#define TCG_TARGET_HAS_shv_vec          0
+#define TCG_TARGET_HAS_shv_vec          1
 #define TCG_TARGET_HAS_roti_vec         0
 #define TCG_TARGET_HAS_rots_vec         0
 #define TCG_TARGET_HAS_rotv_vec         0
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (9 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
@ 2023-08-28 15:19 ` Jiajie Chen
  2023-08-28 17:22   ` Richard Henderson
  2023-08-28 17:29 ` [PATCH 00/11] Lower TCG vector ops to LSX Richard Henderson
  11 siblings, 1 reply; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 15:19 UTC (permalink / raw)
  To: qemu-devel; +Cc: richard.henderson, gaosong, Jiajie Chen, WANG Xuerui

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |  1 +
 tcg/loongarch64/tcg-target.c.inc     | 11 ++++++++++-
 tcg/loongarch64/tcg-target.h         |  2 +-
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index 9fce856012..0f709113f0 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -33,4 +33,5 @@ C_O1_I2(r, rZ, ri)
 C_O1_I2(r, rZ, rJ)
 C_O1_I2(r, rZ, rZ)
 C_O1_I2(w, w, w)
+C_O1_I3(w, w, w, w)
 C_O1_I4(r, rZ, rJ, rZ, rZ)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index caf2a7a563..14826fad5a 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1619,7 +1619,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
                            const int const_args[TCG_MAX_OP_ARGS])
 {
     TCGType type = vecl + TCG_TYPE_V64;
-    TCGArg a0, a1, a2;
+    TCGArg a0, a1, a2, a3;
     TCGReg base;
     TCGReg temp = TCG_REG_TMP0;
     int32_t offset;
@@ -1681,6 +1681,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     a0 = args[0];
     a1 = args[1];
     a2 = args[2];
+    a3 = args[3];
 
     /* Currently only supports V128 */
     tcg_debug_assert(type == TCG_TYPE_V128);
@@ -1790,6 +1791,10 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_sarv_vec:
         tcg_out32(s, encode_vdvjvk_insn(sarv_vec_insn[vece], a0, a1, a2));
         break;
+    case INDEX_op_bitsel_vec:
+        /* vbitsel vd, vj, vk, va = bitsel_vec vd, va, vk, vj */
+        tcg_out_opc_vbitsel_v(s, a0, a3, a2, a1);
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1827,6 +1832,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_shlv_vec:
     case INDEX_op_shrv_vec:
     case INDEX_op_sarv_vec:
+    case INDEX_op_bitsel_vec:
         return 1;
     default:
         return 0;
@@ -2014,6 +2020,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_neg_vec:
         return C_O1_I1(w, w);
 
+    case INDEX_op_bitsel_vec:
+        return C_O1_I3(w, w, w, w);
+
     default:
         g_assert_not_reached();
     }
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 771545b021..aafd770356 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -191,7 +191,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_rotv_vec         0
 #define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
-#define TCG_TARGET_HAS_bitsel_vec       0
+#define TCG_TARGET_HAS_bitsel_vec       1
 #define TCG_TARGET_HAS_cmpsel_vec       0
 
 #define TCG_TARGET_DEFAULT_MO (0)
-- 
2.42.0



^ permalink raw reply related	[flat|nested] 25+ messages in thread

* Re: [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX
  2023-08-28 15:19 ` [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
@ 2023-08-28 16:57   ` Richard Henderson
  2023-08-28 17:04     ` Jiajie Chen
  0 siblings, 1 reply; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 16:57 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> +static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
> +                             TCGReg rd, int64_t v64)
> +{
> +    /* Try vldi if imm can fit */
> +    if (vece <= MO_32 && (-0x200 <= v64 && v64 <= 0x1FF)) {
> +        uint32_t imm = (vece << 10) | ((uint32_t)v64 & 0x3FF);
> +        tcg_out_opc_vldi(s, rd, imm);
> +        return;
> +    }

v64 has the value replicated across 64 bits.
In order to do the comparison above, you'll want

     int64_t vale = sextract64(v64, 0, 8 << vece);
     if (-0x200 <= vale && vale <= 0x1ff)
         ...

Since the only documentation for LSX is qemu's own translator code, why are you testing 
vece <= MO_32?  MO_64 should be available as well?  Or is there a bug in trans_vldi()?

It might be nice to leave a to-do for vldi imm bit 12 set, for the patterns expanded by 
vldi_get_value().  In particular, mode == 9 is likely to be useful, and modes {1,2,3,5} 
are easy to test for.


> +
> +    /* Fallback to vreplgr2vr */
> +    tcg_out_movi(s, type, TCG_REG_TMP0, v64);

type is a vector type; you can't use it here.
Correct would be TCG_TYPE_I64.

Better to load vale instead, since that will take fewer insns in tcg_out_movi.


> +static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
> +                           unsigned vecl, unsigned vece,
> +                           const TCGArg args[TCG_MAX_OP_ARGS],
> +                           const int const_args[TCG_MAX_OP_ARGS])
> +{
> +    TCGType type = vecl + TCG_TYPE_V64;
> +    TCGArg a0, a1, a2;
> +    TCGReg base;
> +    TCGReg temp = TCG_REG_TMP0;
> +    int32_t offset;
> +
> +    a0 = args[0];
> +    a1 = args[1];
> +    a2 = args[2];
> +
> +    /* Currently only supports V128 */
> +    tcg_debug_assert(type == TCG_TYPE_V128);
> +
> +    switch (opc) {
> +    case INDEX_op_st_vec:
> +        /* Try to fit vst imm */
> +        if (-0x800 <= a2 && a2 <= 0x7ff) {
> +            base = a1;
> +            offset = a2;
> +        } else {
> +            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
> +            base = temp;
> +            offset = 0;
> +        }
> +        tcg_out_opc_vst(s, a0, base, offset);
> +        break;
> +    case INDEX_op_ld_vec:
> +        /* Try to fit vld imm */
> +        if (-0x800 <= a2 && a2 <= 0x7ff) {
> +            base = a1;
> +            offset = a2;
> +        } else {
> +            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
> +            base = temp;
> +            offset = 0;
> +        }
> +        tcg_out_opc_vld(s, a0, base, offset);

tcg_out_addi has a hole in bits [15:12], and can take an extra insn if those bits are set. 
  Better to load the offset with tcg_out_movi and then use VLDX/VSTX instead of VLD/VST.

> @@ -159,6 +170,30 @@ typedef enum {
>   #define TCG_TARGET_HAS_mulsh_i64        1
>   #define TCG_TARGET_HAS_qemu_ldst_i128   0
>   
> +#define TCG_TARGET_HAS_v64              0
> +#define TCG_TARGET_HAS_v128             use_lsx_instructions
> +#define TCG_TARGET_HAS_v256             0

Perhaps reserve for a follow-up, but TCG_TARGET_HAS_v64 can easily be supported using the 
same instructions.

The only difference is load/store, where you could use FLD.D/FST.D to load the lower 
64-bits of the fp/vector register, or VLDREPL.D to load and initialize all bits and 
VSTELM.D to store the lower 64-bits.

I tend to think the float insns are more flexible, having a larger displacement, and the 
availability of FLDX/FSTX as well.


r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX
  2023-08-28 16:57   ` Richard Henderson
@ 2023-08-28 17:04     ` Jiajie Chen
  0 siblings, 0 replies; 25+ messages in thread
From: Jiajie Chen @ 2023-08-28 17:04 UTC (permalink / raw)
  To: Richard Henderson, qemu-devel; +Cc: gaosong, WANG Xuerui

There seems to some problem with the email server, try my another email 
address to send this email.


On 2023/8/29 00:57, Richard Henderson wrote:
> On 8/28/23 08:19, Jiajie Chen wrote:
>> +static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned 
>> vece,
>> +                             TCGReg rd, int64_t v64)
>> +{
>> +    /* Try vldi if imm can fit */
>> +    if (vece <= MO_32 && (-0x200 <= v64 && v64 <= 0x1FF)) {
>> +        uint32_t imm = (vece << 10) | ((uint32_t)v64 & 0x3FF);
>> +        tcg_out_opc_vldi(s, rd, imm);
>> +        return;
>> +    }
>
> v64 has the value replicated across 64 bits.
> In order to do the comparison above, you'll want
>
>     int64_t vale = sextract64(v64, 0, 8 << vece);
>     if (-0x200 <= vale && vale <= 0x1ff)
>         ...
>
> Since the only documentation for LSX is qemu's own translator code, 
> why are you testing vece <= MO_32?  MO_64 should be available as 
> well?  Or is there a bug in trans_vldi()?


Sorry, my mistake. I was messing MO_64 with bit 12 in vldi imm.


>
> It might be nice to leave a to-do for vldi imm bit 12 set, for the 
> patterns expanded by vldi_get_value().  In particular, mode == 9 is 
> likely to be useful, and modes {1,2,3,5} are easy to test for.
>

Sure, I was thinking about the complexity of pattern matching on those 
modes, and decided to skip the hard part in the first patch series.


>
>> +
>> +    /* Fallback to vreplgr2vr */
>> +    tcg_out_movi(s, type, TCG_REG_TMP0, v64);
>
> type is a vector type; you can't use it here.
> Correct would be TCG_TYPE_I64.
>
> Better to load vale instead, since that will take fewer insns in 
> tcg_out_movi.


Sure.


>
>
>> +static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
>> +                           unsigned vecl, unsigned vece,
>> +                           const TCGArg args[TCG_MAX_OP_ARGS],
>> +                           const int const_args[TCG_MAX_OP_ARGS])
>> +{
>> +    TCGType type = vecl + TCG_TYPE_V64;
>> +    TCGArg a0, a1, a2;
>> +    TCGReg base;
>> +    TCGReg temp = TCG_REG_TMP0;
>> +    int32_t offset;
>> +
>> +    a0 = args[0];
>> +    a1 = args[1];
>> +    a2 = args[2];
>> +
>> +    /* Currently only supports V128 */
>> +    tcg_debug_assert(type == TCG_TYPE_V128);
>> +
>> +    switch (opc) {
>> +    case INDEX_op_st_vec:
>> +        /* Try to fit vst imm */
>> +        if (-0x800 <= a2 && a2 <= 0x7ff) {
>> +            base = a1;
>> +            offset = a2;
>> +        } else {
>> +            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
>> +            base = temp;
>> +            offset = 0;
>> +        }
>> +        tcg_out_opc_vst(s, a0, base, offset);
>> +        break;
>> +    case INDEX_op_ld_vec:
>> +        /* Try to fit vld imm */
>> +        if (-0x800 <= a2 && a2 <= 0x7ff) {
>> +            base = a1;
>> +            offset = a2;
>> +        } else {
>> +            tcg_out_addi(s, TCG_TYPE_I64, temp, a1, a2);
>> +            base = temp;
>> +            offset = 0;
>> +        }
>> +        tcg_out_opc_vld(s, a0, base, offset);
>
> tcg_out_addi has a hole in bits [15:12], and can take an extra insn if 
> those bits are set.  Better to load the offset with tcg_out_movi and 
> then use VLDX/VSTX instead of VLD/VST.


Sure.


>
>> @@ -159,6 +170,30 @@ typedef enum {
>>   #define TCG_TARGET_HAS_mulsh_i64        1
>>   #define TCG_TARGET_HAS_qemu_ldst_i128   0
>>   +#define TCG_TARGET_HAS_v64              0
>> +#define TCG_TARGET_HAS_v128             use_lsx_instructions
>> +#define TCG_TARGET_HAS_v256             0
>
> Perhaps reserve for a follow-up, but TCG_TARGET_HAS_v64 can easily be 
> supported using the same instructions.
>
> The only difference is load/store, where you could use FLD.D/FST.D to 
> load the lower 64-bits of the fp/vector register, or VLDREPL.D to load 
> and initialize all bits and VSTELM.D to store the lower 64-bits.
>
> I tend to think the float insns are more flexible, having a larger 
> displacement, and the availability of FLDX/FSTX as well.


Sure.


>
>
> r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt
  2023-08-28 15:19 ` [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
@ 2023-08-28 17:08   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:08 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Signed-off-by: Jiajie Chen <c@jia.je>
> ---
>   tcg/loongarch64/tcg-target-con-set.h |  1 +
>   tcg/loongarch64/tcg-target.c.inc     | 25 +++++++++++++++++++++++++
>   2 files changed, 26 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

> @@ -1624,6 +1624,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
>       TCGReg temp = TCG_REG_TMP0;
>       int32_t offset;
>   
> +    static const LoongArchInsn cmp_vec_insn[16][4] = {
> +        [TCG_COND_EQ] = {OPC_VSEQ_B, OPC_VSEQ_H, OPC_VSEQ_W, OPC_VSEQ_D},
> +        [TCG_COND_LE] = {OPC_VSLE_B, OPC_VSLE_H, OPC_VSLE_W, OPC_VSLE_D},
> +        [TCG_COND_LEU] = {OPC_VSLE_BU, OPC_VSLE_HU, OPC_VSLE_WU, OPC_VSLE_DU},
> +        [TCG_COND_LT] = {OPC_VSLT_B, OPC_VSLT_H, OPC_VSLT_W, OPC_VSLT_D},
> +        [TCG_COND_LTU] = {OPC_VSLT_BU, OPC_VSLT_HU, OPC_VSLT_WU, OPC_VSLT_DU},
> +    };
> +    LoongArchInsn insn;
> +
>       a0 = args[0];
>       a1 = args[1];
>       a2 = args[2];
> @@ -1656,6 +1665,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
>           }
>           tcg_out_opc_vld(s, a0, base, offset);
>           break;
> +    case INDEX_op_cmp_vec:
> +        TCGCond cond = args[3];
> +        insn = cmp_vec_insn[cond][vece];
> +        if (insn == 0) {
> +            TCGArg t;
> +            t = a1, a1 = a2, a2 = t;
> +            cond = tcg_swap_cond(cond);
> +            insn = cmp_vec_insn[cond][vece];
> +            tcg_debug_assert(insn != 0);
> +        }
> +        tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
> +        break;
>       case INDEX_op_dupm_vec:
>           tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
>           break;
> @@ -1671,6 +1692,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
>       case INDEX_op_st_vec:
>       case INDEX_op_dup_vec:
>       case INDEX_op_dupm_vec:
> +    case INDEX_op_cmp_vec:
>           return 1;
>       default:
>           return 0;
> @@ -1832,6 +1854,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
>       case INDEX_op_st_vec:
>           return C_O0_I2(w, r);
>   
> +    case INDEX_op_cmp_vec:
> +        return C_O1_I2(w, w, w);

Further improvement can be done with VS*I, and its 5-bit signed immediate.
While you can't swap operands for GT/GE in that case, you can invert, e.g.
GT -> LE, then invert the result using VNOR.

Comparing vs zero is especially common...


r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub
  2023-08-28 15:19 ` [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Jiajie Chen
@ 2023-08-28 17:13   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:13 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Lower the following ops:
> 
> - add_vec
> - sub_vec
> 
> Signed-off-by: Jiajie Chen <c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 16 ++++++++++++++++
>   1 file changed, 16 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

For further improvement, VADDI and VSUBI have a 5-bit unsigned immediate,
giving you a range of [-0x1f, 0x1f].


r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations
  2023-08-28 15:19 ` [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
@ 2023-08-28 17:17   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:17 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Lower the following ops:
> 
> - and_vec
> - andc_vec
> - or_vec
> - orc_vec
> - xor_vec
> - nor_vec
> 
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 35 ++++++++++++++++++++++++++++++++
>   tcg/loongarch64/tcg-target.h     |  6 +++---
>   2 files changed, 38 insertions(+), 3 deletions(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg
  2023-08-28 15:19 ` [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
@ 2023-08-28 17:18   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:18 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target-con-set.h |  1 +
>   tcg/loongarch64/tcg-target.c.inc     | 10 ++++++++++
>   tcg/loongarch64/tcg-target.h         |  2 +-
>   3 files changed, 12 insertions(+), 1 deletion(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul
  2023-08-28 15:19 ` [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
@ 2023-08-28 17:18   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:18 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 8 ++++++++
>   tcg/loongarch64/tcg-target.h     | 2 +-
>   2 files changed, 9 insertions(+), 1 deletion(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 08/11] tcg/loongarch64: Lower vector min max ops
  2023-08-28 15:19 ` [PATCH 08/11] tcg/loongarch64: Lower vector min max ops Jiajie Chen
@ 2023-08-28 17:19   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:19 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Lower the following ops:
> 
> - smin_vec
> - smax_vec
> - umin_vec
> - umax_vec
> 
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
>   tcg/loongarch64/tcg-target.h     |  2 +-
>   2 files changed, 33 insertions(+), 1 deletion(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops
  2023-08-28 15:19 ` [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
@ 2023-08-28 17:20   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:20 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Lower the following ops:
> 
> - ssadd_vec
> - usadd_vec
> - sssub_vec
> - ussub_vec
> 
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 32 ++++++++++++++++++++++++++++++++
>   tcg/loongarch64/tcg-target.h     |  2 +-
>   2 files changed, 33 insertions(+), 1 deletion(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops
  2023-08-28 15:19 ` [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
@ 2023-08-28 17:21   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:21 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Lower the following ops:
> 
> - shlv_vec
> - shrv_vec
> - sarv_vec
> 
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target.c.inc | 24 ++++++++++++++++++++++++
>   tcg/loongarch64/tcg-target.h     |  2 +-
>   2 files changed, 25 insertions(+), 1 deletion(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel
  2023-08-28 15:19 ` [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
@ 2023-08-28 17:22   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:22 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong, WANG Xuerui

On 8/28/23 08:19, Jiajie Chen wrote:
> Signed-off-by: Jiajie Chen<c@jia.je>
> ---
>   tcg/loongarch64/tcg-target-con-set.h |  1 +
>   tcg/loongarch64/tcg-target.c.inc     | 11 ++++++++++-
>   tcg/loongarch64/tcg-target.h         |  2 +-
>   3 files changed, 12 insertions(+), 2 deletions(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 00/11] Lower TCG vector ops to LSX
  2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
                   ` (10 preceding siblings ...)
  2023-08-28 15:19 ` [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
@ 2023-08-28 17:29 ` Richard Henderson
  2023-08-28 19:39   ` Richard Henderson
  11 siblings, 1 reply; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 17:29 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong

On 8/28/23 08:19, Jiajie Chen wrote:
> This patch series allows qemu to utilize LSX instructions on LoongArch
> machines to execute TCG vector ops.
> 
> Jiajie Chen (11):
>    tcg/loongarch64: Import LSX instructions
>    tcg/loongarch64: Lower basic tcg vec ops to LSX
>    tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt
>    tcg/loongarch64: Lower add/sub_vec to vadd/vsub
>    tcg/loongarch64: Lower vector bitwise operations
>    tcg/loongarch64: Lower neg_vec to vneg
>    tcg/loongarch64: Lower mul_vec to vmul
>    tcg/loongarch64: Lower vector min max ops
>    tcg/loongarch64: Lower vector saturated ops
>    tcg/loongarch64: Lower vector shift vector ops
>    tcg/loongarch64: Lower bitsel_vec to vbitsel
> 
>   tcg/loongarch64/tcg-insn-defs.c.inc  | 6251 +++++++++++++++++++++++++-
>   tcg/loongarch64/tcg-target-con-set.h |    5 +
>   tcg/loongarch64/tcg-target-con-str.h |    1 +
>   tcg/loongarch64/tcg-target.c.inc     |  414 +-
>   tcg/loongarch64/tcg-target.h         |   37 +-
>   tcg/loongarch64/tcg-target.opc.h     |   12 +
>   6 files changed, 6601 insertions(+), 119 deletions(-)
>   create mode 100644 tcg/loongarch64/tcg-target.opc.h

Looks very good at a first pass.

We should probably improve tcg_gen_not_vec to try NOR.  This would support loongarch64, 
and allow the special expansion in PPC and S390X to be removed.

It would be good to support TCG_TARGET_HAS_shi_vec using VSLLI/VSRLI/VSRAI.

It would be good to support TCG_TARGET_HAS_roti_vec and TCG_TARGET_HAS_rotv_vec.



r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

* Re: [PATCH 00/11] Lower TCG vector ops to LSX
  2023-08-28 17:29 ` [PATCH 00/11] Lower TCG vector ops to LSX Richard Henderson
@ 2023-08-28 19:39   ` Richard Henderson
  0 siblings, 0 replies; 25+ messages in thread
From: Richard Henderson @ 2023-08-28 19:39 UTC (permalink / raw)
  To: Jiajie Chen, qemu-devel; +Cc: gaosong

On 8/28/23 10:29, Richard Henderson wrote:
> We should probably improve tcg_gen_not_vec to try NOR.  This would support loongarch64, 
> and allow the special expansion in PPC and S390X to be removed.

Hmm, no.  The tcg optimizer does better when NOT is supported directly.
There is a whole series of fold_*_to_not patterns.

It's what I get for looking at this for a long time.

Anyway, it would be good for LSX to expand NOT(x) via NOR(x,x).


r~


^ permalink raw reply	[flat|nested] 25+ messages in thread

end of thread, other threads:[~2023-08-28 19:39 UTC | newest]

Thread overview: 25+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-08-28 15:19 [PATCH 00/11] Lower TCG vector ops to LSX Jiajie Chen
2023-08-28 15:19 ` [PATCH 01/11] tcg/loongarch64: Import LSX instructions Jiajie Chen
2023-08-28 15:19 ` [PATCH 02/11] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
2023-08-28 16:57   ` Richard Henderson
2023-08-28 17:04     ` Jiajie Chen
2023-08-28 15:19 ` [PATCH 03/11] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
2023-08-28 17:08   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 04/11] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Jiajie Chen
2023-08-28 17:13   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 05/11] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
2023-08-28 17:17   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 06/11] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
2023-08-28 17:18   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 07/11] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
2023-08-28 17:18   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 08/11] tcg/loongarch64: Lower vector min max ops Jiajie Chen
2023-08-28 17:19   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 09/11] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
2023-08-28 17:20   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 10/11] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
2023-08-28 17:21   ` Richard Henderson
2023-08-28 15:19 ` [PATCH 11/11] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
2023-08-28 17:22   ` Richard Henderson
2023-08-28 17:29 ` [PATCH 00/11] Lower TCG vector ops to LSX Richard Henderson
2023-08-28 19:39   ` Richard Henderson

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).