[PATCH v3 45/60] target/riscv: vector wideing integer reduction instructions

[PATCH v3 45/60] target/riscv: vector wideing integer reduction instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  7 +++++++
 target/riscv/insn32.decode              |  2 ++
 target/riscv/insn_trans/trans_rvv.inc.c |  4 ++++
 target/riscv/vector_helper.c            | 11 +++++++++++
 4 files changed, 24 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index cc1eb55404..76435f90a9 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1054,3 +1054,10 @@ DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vwredsumu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsumu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 2419ef97e7..e6a354c134 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -531,6 +531,8 @@ vredminu_vs     000100 . ..... ..... 010 ..... 1010111 @r_vm
 vredmin_vs      000101 . ..... ..... 010 ..... 1010111 @r_vm
 vredmaxu_vs     000110 . ..... ..... 010 ..... 1010111 @r_vm
 vredmax_vs      000111 . ..... ..... 010 ..... 1010111 @r_vm
+vwredsumu_vs    110000 . ..... ..... 000 ..... 1010111 @r_vm
+vwredsum_vs     110001 . ..... ..... 000 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 3f6951abd5..195c460cb8 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2040,3 +2040,7 @@ GEN_OPIVV_TRANS(vredmin_vs, reduction_check)
 GEN_OPIVV_TRANS(vredand_vs, reduction_check)
 GEN_OPIVV_TRANS(vredor_vs, reduction_check)
 GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
+
+/* Vector Widening Integer Reduction Instructions */
+GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check)
+GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 789be79b5a..f2ded5adc6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4138,3 +4138,14 @@ GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb)
 GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh)
 GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl)
 GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq)
+
+/* Vector Widening Integer Reduction Instructions */
+/* signed sum reduction into double-width accumulator */
+GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD, clearh)
+GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD, clearl)
+GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq)
+
+/* Unsigned sum reduction into double-width accumulator */
+GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh)
+GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl)
+GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq)
-- 
2.23.0

[PATCH v3 16/60] target/riscv: vector integer min/max instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   | 33 ++++++++++++
 target/riscv/insn32.decode              |  8 +++
 target/riscv/insn_trans/trans_rvv.inc.c | 10 ++++
 target/riscv/vector_helper.c            | 71 +++++++++++++++++++++++++
 4 files changed, 122 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 4e6c47c2d2..c7d4ff185a 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -492,3 +492,36 @@ DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 525b2fa442..a7619f4e3d 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -354,6 +354,14 @@ vmsgtu_vx       011110 . ..... ..... 100 ..... 1010111 @r_vm
 vmsgtu_vi       011110 . ..... ..... 011 ..... 1010111 @r_vm
 vmsgt_vx        011111 . ..... ..... 100 ..... 1010111 @r_vm
 vmsgt_vi        011111 . ..... ..... 011 ..... 1010111 @r_vm
+vminu_vv        000100 . ..... ..... 000 ..... 1010111 @r_vm
+vminu_vx        000100 . ..... ..... 100 ..... 1010111 @r_vm
+vmin_vv         000101 . ..... ..... 000 ..... 1010111 @r_vm
+vmin_vx         000101 . ..... ..... 100 ..... 1010111 @r_vm
+vmaxu_vv        000110 . ..... ..... 000 ..... 1010111 @r_vm
+vmaxu_vx        000110 . ..... ..... 100 ..... 1010111 @r_vm
+vmax_vv         000111 . ..... ..... 000 ..... 1010111 @r_vm
+vmax_vx         000111 . ..... ..... 100 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 078d275af6..4437a77878 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1424,3 +1424,13 @@ GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check)
+
+/* Vector Integer Min/Max Instructions */
+GEN_OPIVV_GVEC_TRANS(vminu_vv, umin)
+GEN_OPIVV_GVEC_TRANS(vmin_vv,  smin)
+GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax)
+GEN_OPIVV_GVEC_TRANS(vmax_vv,  smax)
+GEN_OPIVX_TRANS(vminu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmin_vx,  opivx_check)
+GEN_OPIVX_TRANS(vmaxu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmax_vx,  opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index e7a4e99f46..03e001262f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -849,6 +849,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl)
 #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
 #define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
 #define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
+#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
 
 /* operation of two vector elements */
 #define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
@@ -1479,3 +1483,70 @@ GEN_VEXT_CMP_VX(vmsgt_vx_b, int8_t,  H1, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_h, int16_t, H2, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_w, int32_t, H4, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_d, int64_t, H8, DO_MSGT)
+
+/* Vector Integer Min/Max Instructions */
+RVVCALL(OPIVV2, vminu_vv_b, OP_UUU_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_h, OP_UUU_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_w, OP_UUU_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_d, OP_UUU_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_b, OP_SSS_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_h, OP_SSS_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_w, OP_SSS_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_d, OP_SSS_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmaxu_vv_b, OP_UUU_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_h, OP_UUU_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_w, OP_UUU_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_d, OP_UUU_D, H8, H8, H8, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
+GEN_VEXT_VV(vminu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vminu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vminu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vminu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmin_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmin_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmin_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmin_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmaxu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmaxu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmaxu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmaxu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmax_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmax_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmax_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmax_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_w, OP_UUU_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_d, OP_UUU_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_b, OP_SSS_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_h, OP_SSS_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_w, OP_SSS_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_d, OP_SSS_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmaxu_vx_b, OP_UUU_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_h, OP_UUU_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_w, OP_UUU_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_d, OP_UUU_D, H8, H8, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
+GEN_VEXT_VX(vminu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vminu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vminu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vminu_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmin_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmin_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmin_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmin_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmaxu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmaxu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmaxu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmaxu_vx_d, 8, 8,  clearq)
+GEN_VEXT_VX(vmax_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmax_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmax_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmax_vx_d, 8, 8, clearq)
-- 
2.23.0

[PATCH v3 44/60] target/riscv: vector single-width integer reduction instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   | 33 +++++++++++
 target/riscv/insn32.decode              |  8 +++
 target/riscv/insn_trans/trans_rvv.inc.c | 17 ++++++
 target/riscv/vector_helper.c            | 76 +++++++++++++++++++++++++
 4 files changed, 134 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 008c5b9868..cc1eb55404 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1021,3 +1021,36 @@ DEF_HELPER_5(vfncvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index ffc58698c6..2419ef97e7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -523,6 +523,14 @@ vfncvt_x_f_v    100010 . ..... 10001 001 ..... 1010111 @r2_vm
 vfncvt_f_xu_v   100010 . ..... 10010 001 ..... 1010111 @r2_vm
 vfncvt_f_x_v    100010 . ..... 10011 001 ..... 1010111 @r2_vm
 vfncvt_f_f_v    100010 . ..... 10100 001 ..... 1010111 @r2_vm
+vredsum_vs      000000 . ..... ..... 010 ..... 1010111 @r_vm
+vredand_vs      000001 . ..... ..... 010 ..... 1010111 @r_vm
+vredor_vs       000010 . ..... ..... 010 ..... 1010111 @r_vm
+vredxor_vs      000011 . ..... ..... 010 ..... 1010111 @r_vm
+vredminu_vs     000100 . ..... ..... 010 ..... 1010111 @r_vm
+vredmin_vs      000101 . ..... ..... 010 ..... 1010111 @r_vm
+vredmaxu_vs     000110 . ..... ..... 010 ..... 1010111 @r_vm
+vredmax_vs      000111 . ..... ..... 010 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index bdb765bf13..3f6951abd5 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2023,3 +2023,20 @@ GEN_OPFV_NARROW_TRANS(vfncvt_x_f_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_xu_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_x_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_f_v)
+
+/*
+ *** Vector Reduction Operations
+ */
+/* Vector Single-Width Integer Reduction Instructions */
+static bool reduction_check(DisasContext *s, arg_rmrr *a)
+{
+    return vext_check_isa_ill(s, RVV) && vext_check_reg(s, a->rs2, false);
+}
+GEN_OPIVV_TRANS(vredsum_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmaxu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmax_vs, reduction_check)
+GEN_OPIVV_TRANS(vredminu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmin_vs, reduction_check)
+GEN_OPIVV_TRANS(vredand_vs, reduction_check)
+GEN_OPIVV_TRANS(vredor_vs, reduction_check)
+GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index bb143b9216..789be79b5a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4062,3 +4062,79 @@ RVVCALL(OPFVV1, vfncvt_f_f_v_h, NOP_UU_H, H2, H4, vfncvtffv16)
 RVVCALL(OPFVV1, vfncvt_f_f_v_w, NOP_UU_W, H4, H8, vfncvtffv32)
 GEN_VEXT_V_ENV(vfncvt_f_f_v_h, 2, 2, clearh)
 GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl)
+
+/*
+ *** Vector Reduction Operations
+ */
+/* Vector Single-Width Integer Reduction Instructions */
+#define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\
+void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
+        void *vs2, CPURISCVState *env, uint32_t desc)     \
+{                                                         \
+    uint32_t mlen = vext_mlen(desc);                      \
+    uint32_t vm = vext_vm(desc);                          \
+    uint32_t vl = env->vl;                                \
+    uint32_t i;                                           \
+    uint32_t tot = env_archcpu(env)->cfg.vlen / 8;        \
+                                                          \
+    TD s1 =  *((TD *)vs1 + HD(0));                        \
+    for (i = 0; i < vl; i++) {                            \
+        TS2 s2 = *((TS2 *)vs2 + HS2(i));                  \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {        \
+            continue;                                     \
+        }                                                 \
+        s1 = OP(s1, (TD)s2);                              \
+    }                                                     \
+    if (i != 0) {                                         \
+        *((TD *)vd + HD(0)) = s1;                         \
+        CLEAR_FN(vd, 1, sizeof(TD), tot);                 \
+    }                                                     \
+}
+
+/* vd[0] = sum(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredsum_vs_b, int8_t, int8_t, H1, H1, DO_ADD, clearb)
+GEN_VEXT_RED(vredsum_vs_h, int16_t, int16_t, H2, H2, DO_ADD, clearh)
+GEN_VEXT_RED(vredsum_vs_w, int32_t, int32_t, H4, H4, DO_ADD, clearl)
+GEN_VEXT_RED(vredsum_vs_d, int64_t, int64_t, H8, H8, DO_ADD, clearq)
+
+/* vd[0] = maxu(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmaxu_vs_b, uint8_t, uint8_t, H1, H1, DO_MAX, clearb)
+GEN_VEXT_RED(vredmaxu_vs_h, uint16_t, uint16_t, H2, H2, DO_MAX, clearh)
+GEN_VEXT_RED(vredmaxu_vs_w, uint32_t, uint32_t, H4, H4, DO_MAX, clearl)
+GEN_VEXT_RED(vredmaxu_vs_d, uint64_t, uint64_t, H8, H8, DO_MAX, clearq)
+
+/* vd[0] = max(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmax_vs_b, int8_t, int8_t, H1, H1, DO_MAX, clearb)
+GEN_VEXT_RED(vredmax_vs_h, int16_t, int16_t, H2, H2, DO_MAX, clearh)
+GEN_VEXT_RED(vredmax_vs_w, int32_t, int32_t, H4, H4, DO_MAX, clearl)
+GEN_VEXT_RED(vredmax_vs_d, int64_t, int64_t, H8, H8, DO_MAX, clearq)
+
+/* vd[0] = minu(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredminu_vs_b, uint8_t, uint8_t, H1, H1, DO_MIN, clearb)
+GEN_VEXT_RED(vredminu_vs_h, uint16_t, uint16_t, H2, H2, DO_MIN, clearh)
+GEN_VEXT_RED(vredminu_vs_w, uint32_t, uint32_t, H4, H4, DO_MIN, clearl)
+GEN_VEXT_RED(vredminu_vs_d, uint64_t, uint64_t, H8, H8, DO_MIN, clearq)
+
+/* vd[0] = min(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmin_vs_b, int8_t, int8_t, H1, H1, DO_MIN, clearb)
+GEN_VEXT_RED(vredmin_vs_h, int16_t, int16_t, H2, H2, DO_MIN, clearh)
+GEN_VEXT_RED(vredmin_vs_w, int32_t, int32_t, H4, H4, DO_MIN, clearl)
+GEN_VEXT_RED(vredmin_vs_d, int64_t, int64_t, H8, H8, DO_MIN, clearq)
+
+/* vd[0] = and(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredand_vs_b, int8_t, int8_t, H1, H1, DO_AND, clearb)
+GEN_VEXT_RED(vredand_vs_h, int16_t, int16_t, H2, H2, DO_AND, clearh)
+GEN_VEXT_RED(vredand_vs_w, int32_t, int32_t, H4, H4, DO_AND, clearl)
+GEN_VEXT_RED(vredand_vs_d, int64_t, int64_t, H8, H8, DO_AND, clearq)
+
+/* vd[0] = or(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredor_vs_b, int8_t, int8_t, H1, H1, DO_OR, clearb)
+GEN_VEXT_RED(vredor_vs_h, int16_t, int16_t, H2, H2, DO_OR, clearh)
+GEN_VEXT_RED(vredor_vs_w, int32_t, int32_t, H4, H4, DO_OR, clearl)
+GEN_VEXT_RED(vredor_vs_d, int64_t, int64_t, H8, H8, DO_OR, clearq)
+
+/* vd[0] = xor(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb)
+GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh)
+GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl)
+GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq)
-- 
2.23.0

[PATCH v3 45/60] target/riscv: vector wideing integer reduction instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  7 +++++++
 target/riscv/insn32.decode              |  2 ++
 target/riscv/insn_trans/trans_rvv.inc.c |  4 ++++
 target/riscv/vector_helper.c            | 11 +++++++++++
 4 files changed, 24 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index cc1eb55404..76435f90a9 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1054,3 +1054,10 @@ DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vwredsumu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsumu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 2419ef97e7..e6a354c134 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -531,6 +531,8 @@ vredminu_vs     000100 . ..... ..... 010 ..... 1010111 @r_vm
 vredmin_vs      000101 . ..... ..... 010 ..... 1010111 @r_vm
 vredmaxu_vs     000110 . ..... ..... 010 ..... 1010111 @r_vm
 vredmax_vs      000111 . ..... ..... 010 ..... 1010111 @r_vm
+vwredsumu_vs    110000 . ..... ..... 000 ..... 1010111 @r_vm
+vwredsum_vs     110001 . ..... ..... 000 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 3f6951abd5..195c460cb8 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2040,3 +2040,7 @@ GEN_OPIVV_TRANS(vredmin_vs, reduction_check)
 GEN_OPIVV_TRANS(vredand_vs, reduction_check)
 GEN_OPIVV_TRANS(vredor_vs, reduction_check)
 GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
+
+/* Vector Widening Integer Reduction Instructions */
+GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check)
+GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 789be79b5a..f2ded5adc6 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4138,3 +4138,14 @@ GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb)
 GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh)
 GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl)
 GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq)
+
+/* Vector Widening Integer Reduction Instructions */
+/* signed sum reduction into double-width accumulator */
+GEN_VEXT_RED(vwredsum_vs_b, int16_t, int8_t, H2, H1, DO_ADD, clearh)
+GEN_VEXT_RED(vwredsum_vs_h, int32_t, int16_t, H4, H2, DO_ADD, clearl)
+GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq)
+
+/* Unsigned sum reduction into double-width accumulator */
+GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh)
+GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl)
+GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq)
-- 
2.23.0

[PATCH v3 46/60] target/riscv: vector single-width floating-point reduction instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   | 10 +++++++
 target/riscv/insn32.decode              |  4 +++
 target/riscv/insn_trans/trans_rvv.inc.c |  5 ++++
 target/riscv/vector_helper.c            | 39 +++++++++++++++++++++++++
 4 files changed, 58 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 76435f90a9..0a1aa30514 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1061,3 +1061,13 @@ DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vfredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e6a354c134..294e55b7ae 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -533,6 +533,10 @@ vredmaxu_vs     000110 . ..... ..... 010 ..... 1010111 @r_vm
 vredmax_vs      000111 . ..... ..... 010 ..... 1010111 @r_vm
 vwredsumu_vs    110000 . ..... ..... 000 ..... 1010111 @r_vm
 vwredsum_vs     110001 . ..... ..... 000 ..... 1010111 @r_vm
+# Vector ordered and unordered reduction sum
+vfredsum_vs     0000-1 . ..... ..... 001 ..... 1010111 @r_vm
+vfredmin_vs     000101 . ..... ..... 001 ..... 1010111 @r_vm
+vfredmax_vs     000111 . ..... ..... 001 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 195c460cb8..d66ec4a1e4 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2044,3 +2044,8 @@ GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
 /* Vector Widening Integer Reduction Instructions */
 GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check)
 GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
+
+/* Vector Single-Width Floating-Point Reduction Instructions */
+GEN_OPFVV_TRANS(vfredsum_vs, reduction_check)
+GEN_OPFVV_TRANS(vfredmax_vs, reduction_check)
+GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index f2ded5adc6..948135f60b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4149,3 +4149,42 @@ GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4, DO_ADD, clearq)
 GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh)
 GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl)
 GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq)
+
+/* Vector Single-Width Floating-Point Reduction Instructions */
+#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\
+void HELPER(NAME)(void *vd, void *v0, void *vs1,           \
+        void *vs2, CPURISCVState *env, uint32_t desc)      \
+{                                                          \
+    uint32_t mlen = vext_mlen(desc);                       \
+    uint32_t vm = vext_vm(desc);                           \
+    uint32_t vl = env->vl;                                 \
+    uint32_t i;                                            \
+    uint32_t tot = env_archcpu(env)->cfg.vlen / 8;         \
+                                                           \
+    TD s1 =  *((TD *)vs1 + HD(0));                         \
+    for (i = 0; i < vl; i++) {                             \
+        TS2 s2 = *((TS2 *)vs2 + HS2(i));                   \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {         \
+            continue;                                      \
+        }                                                  \
+        s1 = OP(s1, (TD)s2, &env->fp_status);              \
+    }                                                      \
+    if (i != 0) {                                          \
+        *((TD *)vd + HD(0)) = s1;                          \
+        CLEAR_FN(vd, 1, sizeof(TD), tot);                  \
+    }                                                      \
+}
+/* Unordered sum */
+GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add, clearh)
+GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add, clearl)
+GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add, clearq)
+
+/* Maximum value */
+GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maxnum, clearh)
+GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maxnum, clearl)
+GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, clearq)
+
+/* Minimum value */
+GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh)
+GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl)
+GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq)
-- 
2.23.0

[PATCH v3 47/60] target/riscv: vector widening floating-point reduction instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  3 ++
 target/riscv/insn32.decode              |  2 +
 target/riscv/insn_trans/trans_rvv.inc.c |  3 ++
 target/riscv/vector_helper.c            | 50 +++++++++++++++++++++++++
 4 files changed, 58 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 0a1aa30514..b0bb617b42 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1071,3 +1071,6 @@ DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 294e55b7ae..f1efc8886d 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -537,6 +537,8 @@ vwredsum_vs     110001 . ..... ..... 000 ..... 1010111 @r_vm
 vfredsum_vs     0000-1 . ..... ..... 001 ..... 1010111 @r_vm
 vfredmin_vs     000101 . ..... ..... 001 ..... 1010111 @r_vm
 vfredmax_vs     000111 . ..... ..... 001 ..... 1010111 @r_vm
+# Vector widening ordered and unordered float reduction sum
+vfwredsum_vs    1100-1 . ..... ..... 001 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index d66ec4a1e4..ad864c9742 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2049,3 +2049,6 @@ GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check)
 GEN_OPFVV_TRANS(vfredsum_vs, reduction_check)
 GEN_OPFVV_TRANS(vfredmax_vs, reduction_check)
 GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
+
+/* Vector Widening Floating-Point Reduction Instructions */
+GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 948135f60b..d325fe5e2e 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4188,3 +4188,53 @@ GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, clearq)
 GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, clearh)
 GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, clearl)
 GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq)
+
+/* Vector Widening Floating-Point Reduction Instructions */
+/* Unordered reduce 2*SEW = 2*SEW + sum(promote(SEW)) */
+void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1,
+        void *vs2, CPURISCVState *env, uint32_t desc)
+{
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    uint32_t i;
+    uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
+
+    uint32_t s1 =  *((uint32_t *)vs1 + H4(0));
+    for (i = 0; i < vl; i++) {
+        uint16_t s2 = *((uint16_t *)vs2 + H2(i));
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {
+            continue;
+        }
+        s1 = float32_add(s1, float16_to_float32(s2, true, &env->fp_status),
+                &env->fp_status);
+    }
+    if (i != 0) {
+        *((uint32_t *)vd + H4(0)) = s1;
+        clearl(vd, 1, sizeof(uint32_t), tot);
+    }
+}
+
+void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
+        void *vs2, CPURISCVState *env, uint32_t desc)
+{
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    uint32_t i;
+    uint32_t tot = env_archcpu(env)->cfg.vlen / 8;
+
+    uint64_t s1 =  *((uint64_t *)vs1);
+    for (i = 0; i < vl; i++) {
+        uint32_t s2 = *((uint32_t *)vs2 + H4(i));
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {
+            continue;
+        }
+        s1 = float64_add(s1, float32_to_float64(s2, &env->fp_status),
+                &env->fp_status);
+    }
+    if (i != 0) {
+        *((uint64_t *)vd) = s1;
+        clearq(vd, 1, sizeof(uint64_t), tot);
+    }
+}
-- 
2.23.0

[PATCH v3 48/60] target/riscv: vector mask-register logical instructions

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  9 ++++++
 target/riscv/insn32.decode              |  8 +++++
 target/riscv/insn_trans/trans_rvv.inc.c | 28 +++++++++++++++++
 target/riscv/vector_helper.c            | 40 +++++++++++++++++++++++++
 4 files changed, 85 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b0bb617b42..9301ce0e00 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1074,3 +1074,12 @@ DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vmand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmandnot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index f1efc8886d..76a9bae8bb 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -539,6 +539,14 @@ vfredmin_vs     000101 . ..... ..... 001 ..... 1010111 @r_vm
 vfredmax_vs     000111 . ..... ..... 001 ..... 1010111 @r_vm
 # Vector widening ordered and unordered float reduction sum
 vfwredsum_vs    1100-1 . ..... ..... 001 ..... 1010111 @r_vm
+vmand_mm        011001 - ..... ..... 010 ..... 1010111 @r
+vmnand_mm       011101 - ..... ..... 010 ..... 1010111 @r
+vmandnot_mm     011000 - ..... ..... 010 ..... 1010111 @r
+vmxor_mm        011011 - ..... ..... 010 ..... 1010111 @r
+vmor_mm         011010 - ..... ..... 010 ..... 1010111 @r
+vmnor_mm        011110 - ..... ..... 010 ..... 1010111 @r
+vmornot_mm      011100 - ..... ..... 010 ..... 1010111 @r
+vmxnor_mm       011111 - ..... ..... 010 ..... 1010111 @r
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index ad864c9742..065b415abb 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2052,3 +2052,31 @@ GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
 
 /* Vector Widening Floating-Point Reduction Instructions */
 GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)
+
+/*
+ *** Vector Mask Operations
+ */
+/* Vector Mask-Register Logical Instructions */
+#define GEN_MM_TRANS(NAME)                                         \
+static bool trans_##NAME(DisasContext *s, arg_r *a)                \
+{                                                                  \
+    if (vext_check_isa_ill(s, RVV)) {                              \
+        uint32_t data = 0;                                         \
+        gen_helper_gvec_4_ptr * fn = gen_helper_##NAME;            \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);             \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
+        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
+            vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),              \
+            cpu_env, 0, s->vlen / 8, data, fn);                    \
+        return true;                                               \
+    }                                                              \
+    return false;                                                  \
+}
+GEN_MM_TRANS(vmand_mm)
+GEN_MM_TRANS(vmnand_mm)
+GEN_MM_TRANS(vmandnot_mm)
+GEN_MM_TRANS(vmxor_mm)
+GEN_MM_TRANS(vmor_mm)
+GEN_MM_TRANS(vmnor_mm)
+GEN_MM_TRANS(vmornot_mm)
+GEN_MM_TRANS(vmxnor_mm)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d325fe5e2e..9e9d172cda 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4238,3 +4238,43 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
         clearq(vd, 1, sizeof(uint64_t), tot);
     }
 }
+
+/*
+ *** Vector Mask Operations
+ */
+/* Vector Mask-Register Logical Instructions */
+#define GEN_VEXT_MASK_VV(NAME, OP)                        \
+void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
+        void *vs2, CPURISCVState *env, uint32_t desc)     \
+{                                                         \
+    uint32_t mlen = vext_mlen(desc);                      \
+    uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;   \
+    uint32_t vl = env->vl;                                \
+    uint32_t i;                                           \
+    int a, b;                                             \
+    for (i = 0; i < vl; i++) {                            \
+        a = vext_elem_mask(vs1, mlen, i);                 \
+        b = vext_elem_mask(vs2, mlen, i);                 \
+        vext_set_elem_mask(vd, mlen, i, OP(b, a));        \
+    }                                                     \
+    if (i == 0) {                                         \
+        return;                                           \
+    }                                                     \
+    for (; i < vlmax; i++) {                              \
+        vext_set_elem_mask(vd, mlen, i, 0);               \
+    }                                                     \
+}
+#define DO_NAND(N, M)  (!(N & M))
+#define DO_ANDNOT(N, M)  (N & !M)
+#define DO_NOR(N, M)  (!(N | M))
+#define DO_ORNOT(N, M)  (N | !M)
+#define DO_XNOR(N, M)  (!(N ^ M))
+
+GEN_VEXT_MASK_VV(vmand_mm, DO_AND)
+GEN_VEXT_MASK_VV(vmnand_mm, DO_NAND)
+GEN_VEXT_MASK_VV(vmandnot_mm, DO_ANDNOT)
+GEN_VEXT_MASK_VV(vmxor_mm, DO_XOR)
+GEN_VEXT_MASK_VV(vmor_mm, DO_OR)
+GEN_VEXT_MASK_VV(vmnor_mm, DO_NOR)
+GEN_VEXT_MASK_VV(vmornot_mm, DO_ORNOT)
+GEN_VEXT_MASK_VV(vmxnor_mm, DO_XNOR)
-- 
2.23.0

[PATCH v3 49/60] target/riscv: vector mask population count vmpopc

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  2 ++
 target/riscv/insn32.decode              |  1 +
 target/riscv/insn_trans/trans_rvv.inc.c | 32 +++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 20 ++++++++++++++++
 4 files changed, 55 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 9301ce0e00..3f6b8ab451 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1083,3 +1083,5 @@ DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 76a9bae8bb..eac767ad82 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -547,6 +547,7 @@ vmor_mm         011010 - ..... ..... 010 ..... 1010111 @r
 vmnor_mm        011110 - ..... ..... 010 ..... 1010111 @r
 vmornot_mm      011100 - ..... ..... 010 ..... 1010111 @r
 vmxnor_mm       011111 - ..... ..... 010 ..... 1010111 @r
+vmpopc_m        010100 . ..... ----- 010 ..... 1010111 @r2_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 065b415abb..c56f30a257 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2080,3 +2080,35 @@ GEN_MM_TRANS(vmor_mm)
 GEN_MM_TRANS(vmnor_mm)
 GEN_MM_TRANS(vmornot_mm)
 GEN_MM_TRANS(vmxnor_mm)
+
+/* Vector mask population count vmpopc */
+static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a)
+{
+    if (vext_check_isa_ill(s, RVV)) {
+        TCGv_ptr src2, mask;
+        TCGv dst;
+        TCGv_i32 desc;
+        uint32_t data = 0;
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+        data = FIELD_DP32(data, VDATA, VM, a->vm);
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+
+        mask = tcg_temp_new_ptr();
+        src2 = tcg_temp_new_ptr();
+        dst = tcg_temp_new();
+        desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+        tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2));
+        tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+        gen_helper_vmpopc_m(dst, mask, src2, cpu_env, desc);
+        gen_set_gpr(a->rd, dst);
+
+        tcg_temp_free_ptr(mask);
+        tcg_temp_free_ptr(src2);
+        tcg_temp_free(dst);
+        tcg_temp_free_i32(desc);
+        return true;
+    }
+    return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 9e9d172cda..4bd901e826 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4278,3 +4278,23 @@ GEN_VEXT_MASK_VV(vmor_mm, DO_OR)
 GEN_VEXT_MASK_VV(vmnor_mm, DO_NOR)
 GEN_VEXT_MASK_VV(vmornot_mm, DO_ORNOT)
 GEN_VEXT_MASK_VV(vmxnor_mm, DO_XNOR)
+
+/* Vector mask population count vmpopc */
+target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env,
+        uint32_t desc)
+{
+    target_ulong cnt = 0;
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    int i;
+
+    for (i = 0; i < vl; i++) {
+        if (vm || vext_elem_mask(v0, mlen, i)) {
+            if (vext_elem_mask(vs2, mlen, i)) {
+                cnt++;
+            }
+        }
+    }
+    return cnt;
+}
-- 
2.23.0

[PATCH v3 50/60] target/riscv: vmfirst find-first-set mask bit

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  2 ++
 target/riscv/insn32.decode              |  1 +
 target/riscv/insn_trans/trans_rvv.inc.c | 32 +++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 19 +++++++++++++++
 4 files changed, 54 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3f6b8ab451..363bc52dc4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1085,3 +1085,5 @@ DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_4(vmpopc_m, tl, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vmfirst_m, tl, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index eac767ad82..328a6c75bb 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -548,6 +548,7 @@ vmnor_mm        011110 - ..... ..... 010 ..... 1010111 @r
 vmornot_mm      011100 - ..... ..... 010 ..... 1010111 @r
 vmxnor_mm       011111 - ..... ..... 010 ..... 1010111 @r
 vmpopc_m        010100 . ..... ----- 010 ..... 1010111 @r2_vm
+vmfirst_m       010101 . ..... ----- 010 ..... 1010111 @r2_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index c56f30a257..265d94245f 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2112,3 +2112,35 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a)
     }
     return false;
 }
+
+/* vmfirst find-first-set mask bit */
+static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a)
+{
+    if (vext_check_isa_ill(s, RVV)) {
+        TCGv_ptr src2, mask;
+        TCGv dst;
+        TCGv_i32 desc;
+        uint32_t data = 0;
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+        data = FIELD_DP32(data, VDATA, VM, a->vm);
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+
+        mask = tcg_temp_new_ptr();
+        src2 = tcg_temp_new_ptr();
+        dst = tcg_temp_new();
+        desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+
+        tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, a->rs2));
+        tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
+
+        gen_helper_vmfirst_m(dst, mask, src2, cpu_env, desc);
+        gen_set_gpr(a->rd, dst);
+
+        tcg_temp_free_ptr(mask);
+        tcg_temp_free_ptr(src2);
+        tcg_temp_free(dst);
+        tcg_temp_free_i32(desc);
+        return true;
+    }
+    return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 4bd901e826..8a3f8ccdec 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4298,3 +4298,22 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env,
     }
     return cnt;
 }
+
+/* vmfirst find-first-set mask bit*/
+target_ulong HELPER(vmfirst_m)(void *v0, void *vs2, CPURISCVState *env,
+        uint32_t desc)
+{
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+    int i;
+
+    for (i = 0; i < vl; i++) {
+        if (vm || vext_elem_mask(v0, mlen, i)) {
+            if (vext_elem_mask(vs2, mlen, i)) {
+               return i;
+            }
+        }
+    }
+    return -1LL;
+}
-- 
2.23.0