OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

tcg/i386: Implement more logical operations for avx512

Browse Source 
AVX512VL has a general ternary logic operation, VPTERNLOGQ,
which can implement NOT, ORC, NAND, NOR, EQV.

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>
This commit is contained in:
Richard Henderson 2021-12-16 07:37:02 -08:00
parent 4c8b968683
commit 3143767b74
2 changed files with 39 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
tcg/i386/tcg-target.c.inc
View File

@ -448,6 +448,7 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
#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_VPTERNLOGQ (0x25 | P_EXT3A | P_DATA16 | P_VEXW | P_EVEX)
#define OPC_VZEROUPPER (0x77 | P_EXT)
#define OPC_XCHG_ax_r32 (0x90)
@ -3098,6 +3099,29 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
insn = vpshldi_insn[vece];
sub = args[3];
goto gen_simd_imm8;
case INDEX_op_not_vec:
insn = OPC_VPTERNLOGQ;
a2 = a1;
sub = 0x33; /* !B */
goto gen_simd_imm8;
case INDEX_op_nor_vec:
insn = OPC_VPTERNLOGQ;
sub = 0x11; /* norCB */
goto gen_simd_imm8;
case INDEX_op_nand_vec:
insn = OPC_VPTERNLOGQ;
sub = 0x77; /* nandCB */
goto gen_simd_imm8;
case INDEX_op_eqv_vec:
insn = OPC_VPTERNLOGQ;
sub = 0x99; /* xnorCB */
goto gen_simd_imm8;
case INDEX_op_orc_vec:
insn = OPC_VPTERNLOGQ;
sub = 0xdd; /* orB!C */
goto gen_simd_imm8;
gen_simd_imm8:
tcg_debug_assert(insn != OPC_UD2);
if (type == TCG_TYPE_V256) {
@ -3318,6 +3342,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
case INDEX_op_or_vec:
case INDEX_op_xor_vec:
case INDEX_op_andc_vec:
case INDEX_op_orc_vec:
case INDEX_op_nand_vec:
case INDEX_op_nor_vec:
case INDEX_op_eqv_vec:
case INDEX_op_ssadd_vec:
case INDEX_op_usadd_vec:
case INDEX_op_sssub_vec:
@ -3350,6 +3378,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
case INDEX_op_abs_vec:
case INDEX_op_dup_vec:
case INDEX_op_not_vec:
case INDEX_op_shli_vec:
case INDEX_op_shri_vec:
case INDEX_op_sari_vec:
@ -3378,6 +3407,11 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_or_vec:
case INDEX_op_xor_vec:
case INDEX_op_andc_vec:
case INDEX_op_orc_vec:
case INDEX_op_nand_vec:
case INDEX_op_nor_vec:
case INDEX_op_eqv_vec:
case INDEX_op_not_vec:
return 1;
case INDEX_op_cmp_vec:
case INDEX_op_cmpsel_vec:

10
tcg/i386/tcg-target.h
View File

@ -188,11 +188,11 @@ extern bool have_movbe;
#define TCG_TARGET_HAS_v256 have_avx2
#define TCG_TARGET_HAS_andc_vec 1
#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_not_vec 0
#define TCG_TARGET_HAS_orc_vec have_avx512vl
#define TCG_TARGET_HAS_nand_vec have_avx512vl
#define TCG_TARGET_HAS_nor_vec have_avx512vl
#define TCG_TARGET_HAS_eqv_vec have_avx512vl
#define TCG_TARGET_HAS_not_vec have_avx512vl
#define TCG_TARGET_HAS_neg_vec 0
#define TCG_TARGET_HAS_abs_vec 1
#define TCG_TARGET_HAS_roti_vec have_avx512vl