diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2021-12-15 21:18:48 -0800 |
|---|---|---|
| committer | Richard Henderson <richard.henderson@linaro.org> | 2022-03-04 08:50:41 -1000 |
| commit | ef77ce0d5c4b2e738cd09b4425ce56e071a4aadc (patch) | |
| tree | 68cbf54ce55513f32101cdc053acf2dfb5821fd9 /tcg/i386 | |
| parent | 54e2d650ddea28968160dee6d51cccd4dbfc7aea (diff) | |
| download | qemu-ef77ce0d5c4b2e738cd09b4425ce56e071a4aadc.zip qemu-ef77ce0d5c4b2e738cd09b4425ce56e071a4aadc.tar.gz qemu-ef77ce0d5c4b2e738cd09b4425ce56e071a4aadc.tar.bz2 | |
tcg/i386: Implement avx512 variable shifts
AVX512VL has VPSRAVQ, and
AVX512BW has VPSLLVW, VPSRAVW, VPSRLVW.
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'tcg/i386')
| -rw-r--r-- | tcg/i386/tcg-target.c.inc | 32 |
1 files changed, 24 insertions, 8 deletions
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 6a53f37..055db88 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -419,9 +419,13 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct) #define OPC_VPBROADCASTQ (0x59 | P_EXT38 | P_DATA16) #define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_VEXW) #define OPC_VPERM2I128 (0x46 | P_EXT3A | P_DATA16 | P_VEXL) +#define OPC_VPSLLVW (0x12 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX) #define OPC_VPSLLVD (0x47 | P_EXT38 | P_DATA16) #define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_VEXW) +#define OPC_VPSRAVW (0x11 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX) #define OPC_VPSRAVD (0x46 | P_EXT38 | P_DATA16) +#define OPC_VPSRAVQ (0x46 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX) +#define OPC_VPSRLVW (0x10 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX) #define OPC_VPSRLVD (0x45 | P_EXT38 | P_DATA16) #define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_VEXW) #define OPC_VZEROUPPER (0x77 | P_EXT) @@ -2835,16 +2839,13 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, 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 + OPC_UD2, OPC_VPSLLVW, 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 + OPC_UD2, OPC_VPSRLVW, 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 + OPC_UD2, OPC_VPSRAVW, OPC_VPSRAVD, OPC_VPSRAVQ }; static int const shls_insn[4] = { OPC_UD2, OPC_PSLLW, OPC_PSLLD, OPC_PSLLQ @@ -3335,9 +3336,24 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) case INDEX_op_shlv_vec: case INDEX_op_shrv_vec: - return have_avx2 && vece >= MO_32; + switch (vece) { + case MO_16: + return have_avx512bw; + case MO_32: + case MO_64: + return have_avx2; + } + return 0; case INDEX_op_sarv_vec: - return have_avx2 && vece == MO_32; + switch (vece) { + case MO_16: + return have_avx512bw; + case MO_32: + return have_avx2; + case MO_64: + return have_avx512vl; + } + return 0; case INDEX_op_rotlv_vec: case INDEX_op_rotrv_vec: return have_avx2 && vece >= MO_32 ? -1 : 0; |