[Qemu-devel] [PATCH 13/38] tcg/i386: Support vector variable shift opcodes

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/i386/tcg-target.h     |  2 +-
 tcg/i386/tcg-target.inc.c | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 241bf19413..b240633455 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -184,7 +184,7 @@ extern bool have_avx2;
 #define TCG_TARGET_HAS_neg_vec          0
 #define TCG_TARGET_HAS_shi_vec          1
 #define TCG_TARGET_HAS_shs_vec          0
-#define TCG_TARGET_HAS_shv_vec          0
+#define TCG_TARGET_HAS_shv_vec          have_avx2
 #define TCG_TARGET_HAS_cmp_vec          1
 #define TCG_TARGET_HAS_mul_vec          1
 #define TCG_TARGET_HAS_sat_vec          1
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 4c42a2430d..04e609c7b2 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -467,6 +467,11 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define OPC_VPBROADCASTQ (0x59 | P_EXT38 | P_DATA16)
 #define OPC_VPERMQ      (0x00 | P_EXT3A | P_DATA16 | P_REXW)
 #define OPC_VPERM2I128  (0x46 | P_EXT3A | P_DATA16 | P_VEXL)
+#define OPC_VPSLLVD     (0x47 | P_EXT38 | P_DATA16)
+#define OPC_VPSLLVQ     (0x47 | P_EXT38 | P_DATA16 | P_REXW)
+#define OPC_VPSRAVD     (0x46 | P_EXT38 | P_DATA16)
+#define OPC_VPSRLVD     (0x45 | P_EXT38 | P_DATA16)
+#define OPC_VPSRLVQ     (0x45 | P_EXT38 | P_DATA16 | P_REXW)
 #define OPC_VZEROUPPER  (0x77 | P_EXT)
 #define OPC_XCHG_ax_r32	(0x90)
 
@@ -2705,6 +2710,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static int const umax_insn[4] = {
         OPC_PMAXUB, OPC_PMAXUW, OPC_PMAXUD, OPC_UD2
     };
+    static int const shlv_insn[4] = {
+        /* TODO: AVX512 adds support for MO_16.  */
+        OPC_UD2, OPC_UD2, OPC_VPSLLVD, OPC_VPSLLVQ
+    };
+    static int const shrv_insn[4] = {
+        /* TODO: AVX512 adds support for MO_16.  */
+        OPC_UD2, OPC_UD2, OPC_VPSRLVD, OPC_VPSRLVQ
+    };
+    static int const sarv_insn[4] = {
+        /* TODO: AVX512 adds support for MO_16, MO_64.  */
+        OPC_UD2, OPC_UD2, OPC_VPSRAVD, OPC_UD2
+    };
 
     TCGType type = vecl + TCG_TYPE_V64;
     int insn, sub;
@@ -2757,6 +2774,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_umax_vec:
         insn = umax_insn[vece];
         goto gen_simd;
+    case INDEX_op_shlv_vec:
+        insn = shlv_insn[vece];
+        goto gen_simd;
+    case INDEX_op_shrv_vec:
+        insn = shrv_insn[vece];
+        goto gen_simd;
+    case INDEX_op_sarv_vec:
+        insn = sarv_insn[vece];
+        goto gen_simd;
     case INDEX_op_x86_punpckl_vec:
         insn = punpckl_insn[vece];
         goto gen_simd;
@@ -3134,6 +3160,9 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
     case INDEX_op_umin_vec:
     case INDEX_op_smax_vec:
     case INDEX_op_umax_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
     case INDEX_op_cmp_vec:
     case INDEX_op_x86_shufps_vec:
     case INDEX_op_x86_blend_vec:
@@ -3191,6 +3220,12 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
         }
         return 1;
 
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+        return have_avx2 && vece >= MO_32;
+    case INDEX_op_sarv_vec:
+        return have_avx2 && vece == MO_32;
+
     case INDEX_op_mul_vec:
         if (vece == MO_8) {
             /* We can expand the operation for MO_8.  */
-- 
2.17.1