From f793ec847d5133a3411e0f2352be831de53fa4e6 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 16 May 2019 15:53:30 -0400 Subject: [PATCH] tcg/i386: Support vector variable shift opcodes Backports commit a2ce146a06807fe1d1a81e878b8f249ff1e14038 from qemu --- qemu/tcg/i386/tcg-target.h | 2 +- qemu/tcg/i386/tcg-target.inc.c | 35 ++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/qemu/tcg/i386/tcg-target.h b/qemu/tcg/i386/tcg-target.h index 9738a5cf..46153ac7 100644 --- a/qemu/tcg/i386/tcg-target.h +++ b/qemu/tcg/i386/tcg-target.h @@ -217,7 +217,7 @@ 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/qemu/tcg/i386/tcg-target.inc.c b/qemu/tcg/i386/tcg-target.inc.c index 909d9090..16a086ed 100644 --- a/qemu/tcg/i386/tcg-target.inc.c +++ b/qemu/tcg/i386/tcg-target.inc.c @@ -473,6 +473,11 @@ 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) @@ -2735,6 +2740,18 @@ 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; @@ -2787,6 +2804,15 @@ 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; @@ -3165,6 +3191,9 @@ 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: @@ -3222,6 +3251,12 @@ 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. */