https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98856
--- Comment #14 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
WIP that implements that. Except that we need some permutation expansion
improvements, both for the SSE2 V4SImode permutation cases and for AVX2
V8SImode permutation cases.
--- gcc/config/i386/sse.md.jj 2021-02-05 14:32:44.175463716 +0100
+++ gcc/config/i386/sse.md 2021-02-05 18:49:29.621590903 +0100
@@ -12458,7 +12458,7 @@
(set_attr "prefix" "orig,vex")
(set_attr "mode" "<sseinsnmode>")])
-(define_insn "ashr<mode>3<mask_name>"
+(define_insn "<mask_codefor>ashr<mode>3<mask_name>"
[(set (match_operand:VI248_AVX512BW_AVX512VL 0 "register_operand" "=v,v")
(ashiftrt:VI248_AVX512BW_AVX512VL
(match_operand:VI248_AVX512BW_AVX512VL 1 "nonimmediate_operand"
"v,vm")
@@ -12472,6 +12472,125 @@
(const_string "0")))
(set_attr "mode" "<sseinsnmode>")])
+(define_expand "ashr<mode>3"
+ [(set (match_operand:VI248_AVX512BW 0 "register_operand")
+ (ashiftrt:VI248_AVX512BW
+ (match_operand:VI248_AVX512BW 1 "nonimmediate_operand")
+ (match_operand:DI 2 "nonmemory_operand")))]
+ "TARGET_AVX512F")
+
+(define_expand "ashrv4di3"
+ [(set (match_operand:V4DI 0 "register_operand")
+ (ashiftrt:V4DI
+ (match_operand:V4DI 1 "nonimmediate_operand")
+ (match_operand:DI 2 "nonmemory_operand")))]
+ "TARGET_AVX2"
+{
+ if (!TARGET_AVX512VL)
+ {
+ if (CONST_INT_P (operands[2]) && UINTVAL (operands[2]) >= 63)
+ {
+ rtx zero = force_reg (V4DImode, CONST0_RTX (V4DImode));
+ emit_insn (gen_avx2_gtv4di3 (operands[0], zero, operands[1]));
+ DONE;
+ }
+ if (operands[2] == const0_rtx)
+ {
+ emit_move_insn (operands[0], operands[1]);
+ DONE;
+ }
+ if (CONST_INT_P (operands[2]))
+ {
+ vec_perm_builder sel (8, 8, 1);
+ sel.quick_grow (8);
+ rtx arg0, arg1;
+ rtx op1 = lowpart_subreg (V8SImode, operands[1], V4DImode);
+ rtx target = gen_reg_rtx (V8SImode);
+ if (INTVAL (operands[2]) > 32)
+ {
+ arg0 = gen_reg_rtx (V8SImode);
+ arg1 = gen_reg_rtx (V8SImode);
+ emit_insn (gen_ashrv8si3 (arg1, op1, GEN_INT (31)));
+ emit_insn (gen_ashrv8si3 (arg0, op1,
+ GEN_INT (INTVAL (operands[2]) - 32)));
+ sel[0] = 1;
+ sel[1] = 9;
+ sel[2] = 3;
+ sel[3] = 11;
+ sel[4] = 5;
+ sel[5] = 13;
+ sel[6] = 7;
+ sel[7] = 15;
+ }
+ else if (INTVAL (operands[2]) == 32)
+ {
+ arg0 = op1;
+ arg1 = gen_reg_rtx (V8SImode);
+ emit_insn (gen_ashrv8si3 (arg1, op1, GEN_INT (31)));
+ sel[0] = 1;
+ sel[1] = 9;
+ sel[2] = 3;
+ sel[3] = 11;
+ sel[4] = 5;
+ sel[5] = 13;
+ sel[6] = 7;
+ sel[7] = 15;
+ }
+ else
+ {
+ arg0 = gen_reg_rtx (V2DImode);
+ arg1 = gen_reg_rtx (V4SImode);
+ emit_insn (gen_lshrv2di3 (arg0, operands[1], operands[2]));
+ emit_insn (gen_ashrv4si3 (arg1, op1, operands[2]));
+ arg0 = lowpart_subreg (V4SImode, arg0, V2DImode);
+ sel[0] = 0;
+ sel[1] = 9;
+ sel[2] = 2;
+ sel[3] = 11;
+ sel[4] = 4;
+ sel[5] = 13;
+ sel[6] = 6;
+ sel[7] = 15;
+ }
+ vec_perm_indices indices (sel, 2, 8);
+ bool ok = targetm.vectorize.vec_perm_const (V8SImode, target,
+ arg0, arg1, indices);
+ gcc_assert (ok);
+ emit_move_insn (operands[0],
+ lowpart_subreg (V4DImode, target, V8SImode));
+ DONE;
+ }
+
+ rtx zero = force_reg (V4DImode, CONST0_RTX (V4DImode));
+ rtx zero_or_all_ones = gen_reg_rtx (V4DImode);
+ emit_insn (gen_avx2_gtv4di3 (zero_or_all_ones, zero, operands[1]));
+ rtx lshr_res = gen_reg_rtx (V4DImode);
+ emit_insn (gen_lshrv4di3 (lshr_res, operands[1], operands[2]));
+ rtx ashl_res = gen_reg_rtx (V4DImode);
+ rtx amount;
+ if (TARGET_64BIT)
+ {
+ amount = gen_reg_rtx (DImode);
+ emit_insn (gen_subdi3 (amount, force_reg (DImode, GEN_INT (64)),
+ operands[2]));
+ }
+ else
+ {
+ rtx temp = gen_reg_rtx (SImode);
+ emit_insn (gen_subsi3 (temp, force_reg (SImode, GEN_INT (64)),
+ lowpart_subreg (SImode, operands[2],
+ DImode)));
+ amount = gen_reg_rtx (V4SImode);
+ emit_insn (gen_vec_setv4si_0 (amount, CONST0_RTX (V4SImode),
+ temp));
+ }
+ amount = lowpart_subreg (DImode, amount, GET_MODE (amount));
+ emit_insn (gen_ashlv4di3 (ashl_res, zero_or_all_ones, amount));
+ emit_insn (gen_iorv4di3 (operands[0], lshr_res, ashl_res));
+ DONE;
+ }
+})
+
(define_insn "<mask_codefor><insn><mode>3<mask_name>"
[(set (match_operand:VI248_AVX512BW_2 0 "register_operand" "=v,v")
(any_lshift:VI248_AVX512BW_2
@@ -20313,11 +20432,13 @@
(ashiftrt:V2DI
(match_operand:V2DI 1 "register_operand")
(match_operand:DI 2 "nonmemory_operand")))]
- "TARGET_SSE4_2"
+ "TARGET_SSE2"
{
if (!TARGET_AVX512VL)
{
- if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 63)
+ if (TARGET_SSE4_2
+ && CONST_INT_P (operands[2])
+ && UINTVAL (operands[2]) >= 63)
{
rtx zero = force_reg (V2DImode, CONST0_RTX (V2DImode));
emit_insn (gen_sse4_2_gtv2di3 (operands[0], zero, operands[1]));
@@ -20328,6 +20449,65 @@
emit_move_insn (operands[0], operands[1]);
DONE;
}
+ if (CONST_INT_P (operands[2])
+ && (!TARGET_XOP || UINTVAL (operands[2]) >= 63))
+ {
+ vec_perm_builder sel (4, 4, 1);
+ sel.quick_grow (4);
+ rtx arg0, arg1;
+ rtx op1 = lowpart_subreg (V4SImode, operands[1], V2DImode);
+ rtx target = gen_reg_rtx (V4SImode);
+ if (UINTVAL (operands[2]) >= 63)
+ {
+ arg0 = arg1 = gen_reg_rtx (V4SImode);
+ emit_insn (gen_ashrv4si3 (arg0, op1, GEN_INT (31)));
+ sel[0] = 1;
+ sel[1] = 1;
+ sel[2] = 3;
+ sel[3] = 3;
+ }
+ else if (INTVAL (operands[2]) > 32)
+ {
+ arg0 = gen_reg_rtx (V4SImode);
+ arg1 = gen_reg_rtx (V4SImode);
+ emit_insn (gen_ashrv4si3 (arg1, op1, GEN_INT (31)));
+ emit_insn (gen_ashrv4si3 (arg0, op1,
+ GEN_INT (INTVAL (operands[2]) - 32)));
+ sel[0] = 1;
+ sel[1] = 5;
+ sel[2] = 3;
+ sel[3] = 7;
+ }
+ else if (INTVAL (operands[2]) == 32)
+ {
+ arg0 = op1;
+ arg1 = gen_reg_rtx (V4SImode);
+ emit_insn (gen_ashrv4si3 (arg1, op1, GEN_INT (31)));
+ sel[0] = 1;
+ sel[1] = 5;
+ sel[2] = 3;
+ sel[3] = 7;
+ }
+ else
+ {
+ arg0 = gen_reg_rtx (V2DImode);
+ arg1 = gen_reg_rtx (V4SImode);
+ emit_insn (gen_lshrv2di3 (arg0, operands[1], operands[2]));
+ emit_insn (gen_ashrv4si3 (arg1, op1, operands[2]));
+ arg0 = lowpart_subreg (V4SImode, arg0, V2DImode);
+ sel[0] = 0;
+ sel[1] = 5;
+ sel[2] = 2;
+ sel[3] = 7;
+ }
+ vec_perm_indices indices (sel, arg0 != arg1 ? 2 : 1, 4);
+ bool ok = targetm.vectorize.vec_perm_const (V4SImode, target,
+ arg0, arg1, indices);
+ gcc_assert (ok);
+ emit_move_insn (operands[0],
+ lowpart_subreg (V2DImode, target, V4SImode));
+ DONE;
+ }
if (!TARGET_XOP)
{
rtx zero = force_reg (V2DImode, CONST0_RTX (V2DImode));
@@ -20337,9 +20517,7 @@
emit_insn (gen_lshrv2di3 (lshr_res, operands[1], operands[2]));
rtx ashl_res = gen_reg_rtx (V2DImode);
rtx amount;
- if (CONST_INT_P (operands[2]))
- amount = GEN_INT (64 - INTVAL (operands[2]));
- else if (TARGET_64BIT)
+ if (TARGET_64BIT)
{
amount = gen_reg_rtx (DImode);
emit_insn (gen_subdi3 (amount, force_reg (DImode, GEN_INT (64)),
@@ -20355,8 +20533,7 @@
emit_insn (gen_vec_setv4si_0 (amount, CONST0_RTX (V4SImode),
temp));
}
- if (!CONST_INT_P (operands[2]))
- amount = lowpart_subreg (DImode, amount, GET_MODE (amount));
+ amount = lowpart_subreg (DImode, amount, GET_MODE (amount));
emit_insn (gen_ashlv2di3 (ashl_res, zero_or_all_ones, amount));
emit_insn (gen_iorv2di3 (operands[0], lshr_res, ashl_res));
DONE;