https://gcc.gnu.org/g:c45ef5ee8da4de239bf7f5b66a45f7e6e797f954
commit r15-3965-gc45ef5ee8da4de239bf7f5b66a45f7e6e797f954
Author: Victor Do Nascimento <victor.donascime...@arm.com>
Date: Tue Jun 4 17:11:07 2024 +0100
i386: Fix dot_prod backend patterns for mmx and sse targets
Following the migration of the dot_prod optab from a direct to a
conversion-type optab, ensure all back-end patterns incorporate the
second machine mode into pattern names.
gcc/ChangeLog:
* config/i386/mmx.md (usdot_prodv8qi): Renamed to...
(usdot_prodv2siv8qi): ...this.
(sdot_prodv8qi): Renamed to...
(sdot_prodv2siv8qi): ...this.
(udot_prodv8qi): Renamed to...
(udot_prodv2siv8qi): ...this.
(usdot_prodv4hi): Renamed to...
(usdot_prodv2siv4hi): ...this.
(udot_prodv4hi): Renamed to...
(udot_prodv2siv4hi): ...this.
(sdot_prodv4hi): Renamed to...
(sdot_prodv2siv4hi): ...this.
* config/i386/sse.md (sdot_prod<mode>): Renamed to...
(sdot_prod<sseunpackmodelower><mode>): ...this.
(sdot_prodv4si): Renamed to...
(sdot_prodv2div4si): ...this.
(usdot_prod<mode>): Renamed to...
(usdot_prod<ssedvecmodelower><mode>): ...this.
(sdot_prod<mode>): Renamed to...
(sdot_prod<ssedvecmodelower><mode>): ...this.
(sdot_prodv64qi): Renamed to...
(sdot_prodv16siv64qi): ...this.
(udot_prod<mode>): Renamed to...
(udot_prod<ssedvecmodelower><mode>): ...this.
(udot_prodv64qi): Renamed to...
(udot_prodv16qiv64qi): ...this.
(usdot_prod<mode>): Renamed to...
(usdot_prod<sseunpackmodelower><mode>): ...this.
(udot_prod<mode>): Renamed to...
(udot_prod<sseunpackmodelower><mode>): ...this.
Diff:
---
gcc/config/i386/mmx.md | 30 +++++++++++++++---------------
gcc/config/i386/sse.md | 41 ++++++++++++++++++++++-------------------
2 files changed, 37 insertions(+), 34 deletions(-)
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index ca768b95df79..9d2a82c598e5 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -6504,7 +6504,7 @@
DONE;
})
-(define_expand "usdot_prodv8qi"
+(define_expand "usdot_prodv2siv8qi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V8QI 1 "register_operand")
(match_operand:V8QI 2 "register_operand")
@@ -6523,7 +6523,7 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_usdot_prodv16qi (op0, op1, op2, op3));
+ emit_insn (gen_usdot_prodv4siv16qi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
}
else
@@ -6537,7 +6537,7 @@
emit_move_insn (op3, CONST0_RTX (V4SImode));
emit_insn (gen_zero_extendv8qiv8hi2 (op1, operands[1]));
emit_insn (gen_extendv8qiv8hi2 (op2, operands[2]));
- emit_insn (gen_sdot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_sdot_prodv4siv8hi (op0, op1, op2, op3));
/* vec_perm (op0, 2, 3, 0, 1); */
emit_insn (gen_sse2_pshufd (op0_1, op0, GEN_INT (78)));
@@ -6548,7 +6548,7 @@
DONE;
})
-(define_expand "sdot_prodv8qi"
+(define_expand "sdot_prodv2siv8qi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V8QI 1 "register_operand")
(match_operand:V8QI 2 "register_operand")
@@ -6566,7 +6566,7 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_sdot_prodv16qi (op0, op1, op2, op3));
+ emit_insn (gen_sdot_prodv4siv16qi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
}
else
@@ -6580,7 +6580,7 @@
emit_move_insn (op3, CONST0_RTX (V4SImode));
emit_insn (gen_extendv8qiv8hi2 (op1, operands[1]));
emit_insn (gen_extendv8qiv8hi2 (op2, operands[2]));
- emit_insn (gen_sdot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_sdot_prodv4siv8hi (op0, op1, op2, op3));
/* vec_perm (op0, 2, 3, 0, 1); */
emit_insn (gen_sse2_pshufd (op0_1, op0, GEN_INT (78)));
@@ -6592,7 +6592,7 @@
})
-(define_expand "udot_prodv8qi"
+(define_expand "udot_prodv2siv8qi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V8QI 1 "register_operand")
(match_operand:V8QI 2 "register_operand")
@@ -6610,7 +6610,7 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_udot_prodv16qi (op0, op1, op2, op3));
+ emit_insn (gen_udot_prodv4siv16qi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
}
else
@@ -6624,7 +6624,7 @@
emit_move_insn (op3, CONST0_RTX (V4SImode));
emit_insn (gen_zero_extendv8qiv8hi2 (op1, operands[1]));
emit_insn (gen_zero_extendv8qiv8hi2 (op2, operands[2]));
- emit_insn (gen_sdot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_sdot_prodv4siv8hi (op0, op1, op2, op3));
/* vec_perm (op0, 2, 3, 0, 1); */
emit_insn (gen_sse2_pshufd (op0_1, op0, GEN_INT (78)));
@@ -6636,7 +6636,7 @@
})
-(define_expand "usdot_prodv4hi"
+(define_expand "usdot_prodv2siv4hi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V4HI 1 "register_operand")
(match_operand:V4HI 2 "register_operand")
@@ -6652,12 +6652,12 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_usdot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_usdot_prodv4siv8hi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
DONE;
})
-(define_expand "udot_prodv4hi"
+(define_expand "udot_prodv2siv4hi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V4HI 1 "register_operand")
(match_operand:V4HI 2 "register_operand")
@@ -6673,12 +6673,12 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_udot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_udot_prodv4siv8hi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
DONE;
})
-(define_expand "sdot_prodv4hi"
+(define_expand "sdot_prodv2siv4hi"
[(match_operand:V2SI 0 "register_operand")
(match_operand:V4HI 1 "register_operand")
(match_operand:V4HI 2 "register_operand")
@@ -6694,7 +6694,7 @@
rtx op3 = lowpart_subreg (V4SImode, operands[3], V2SImode);
rtx op0 = gen_reg_rtx (V4SImode);
- emit_insn (gen_sdot_prodv8hi (op0, op1, op2, op3));
+ emit_insn (gen_sdot_prodv4siv8hi (op0, op1, op2, op3));
emit_move_insn (operands[0], lowpart_subreg (V2SImode, op0, V4SImode));
DONE;
})
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 29b0ea3507d5..183c1953f913 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -16975,7 +16975,7 @@
(define_mode_attr SDOT_VPDP_SUF
[(V32HI "v16si") (V16HI "v8si") (V8HI "v4si")])
-(define_expand "sdot_prod<mode>"
+(define_expand "sdot_prod<sseunpackmodelower><mode>"
[(match_operand:<sseunpackmode> 0 "register_operand")
(match_operand:VI2_AVX512VNNIBW 1 "register_operand")
(match_operand:VI2_AVX512VNNIBW 2 "register_operand")
@@ -17010,7 +17010,7 @@
;; Normally we use widen_mul_even/odd, but combine can't quite get it all
;; back together when madd is available.
-(define_expand "sdot_prodv4si"
+(define_expand "sdot_prodv2div4si"
[(match_operand:V2DI 0 "register_operand")
(match_operand:V4SI 1 "register_operand")
(match_operand:V4SI 2 "register_operand")
@@ -30471,7 +30471,7 @@
[(set_attr ("prefix") ("evex"))
(set_attr "mode" "<sseinsnmode>")])
-(define_expand "usdot_prod<mode>"
+(define_expand "usdot_prod<ssedvecmodelower><mode>"
[(match_operand:<ssedvecmode> 0 "register_operand")
(match_operand:VI1_AVX512 1 "register_operand")
(match_operand:VI1_AVX512 2 "register_operand")
@@ -30509,10 +30509,11 @@
rtx sum = gen_reg_rtx (<ssedvecmode>mode);
emit_move_insn (sum, CONST0_RTX (<ssedvecmode>mode));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res1, op1_lo,
- op2_lo, sum));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res2, op1_hi,
- op2_hi, operands[3]));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res1,
+ op1_lo, op2_lo, sum));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res2,
+ op1_hi, op2_hi,
+ operands[3]));
emit_insn (gen_add<ssedvecmodelower>3 (operands[0], res1, res2));
}
DONE;
@@ -31336,7 +31337,7 @@
(UNSPEC_VPDPBSUD "bsud") (UNSPEC_VPDPBSUDS "bsuds")
(UNSPEC_VPDPBUUD "buud") (UNSPEC_VPDPBUUDS "buuds")])
-(define_expand "sdot_prod<mode>"
+(define_expand "sdot_prod<ssedvecmodelower><mode>"
[(match_operand:<ssedvecmode> 0 "register_operand")
(match_operand:VI1_AVX512VNNIBW 1 "register_operand")
(match_operand:VI1_AVX512VNNIBW 2 "register_operand")
@@ -31373,17 +31374,18 @@
rtx sum = gen_reg_rtx (<ssedvecmode>mode);
emit_move_insn (sum, CONST0_RTX (<ssedvecmode>mode));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res1, op1_lo,
- op2_lo, sum));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res2, op1_hi,
- op2_hi, operands[3]));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res1,
+ op1_lo, op2_lo, sum));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res2,
+ op1_hi, op2_hi,
+ operands[3]));
emit_insn (gen_add<ssedvecmodelower>3 (operands[0], res1, res2));
}
DONE;
})
-(define_expand "udot_prod<mode>"
+(define_expand "udot_prod<ssedvecmodelower><mode>"
[(match_operand:<ssedvecmode> 0 "register_operand")
(match_operand:VI1_AVX512VNNIBW 1 "register_operand")
(match_operand:VI1_AVX512VNNIBW 2 "register_operand")
@@ -31420,10 +31422,11 @@
rtx sum = gen_reg_rtx (<ssedvecmode>mode);
emit_move_insn (sum, CONST0_RTX (<ssedvecmode>mode));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res1, op1_lo,
- op2_lo, sum));
- emit_insn (gen_sdot_prod<sseunpackmodelower> (res2, op1_hi,
- op2_hi, operands[3]));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res1,
+ op1_lo, op2_lo, sum));
+ emit_insn (gen_sdot_prod<ssedvecmodelower><sseunpackmodelower> (res2,
+ op1_hi, op2_hi,
+ operands[3]));
emit_insn (gen_add<ssedvecmodelower>3 (operands[0], res1, res2));
}
@@ -31803,7 +31806,7 @@
(UNSPEC_VPDPWSUD "wsud") (UNSPEC_VPDPWSUDS "wsuds")
(UNSPEC_VPDPWUUD "wuud") (UNSPEC_VPDPWUUDS "wuuds")])
-(define_expand "usdot_prod<mode>"
+(define_expand "usdot_prod<sseunpackmodelower><mode>"
[(match_operand:<sseunpackmode> 0 "register_operand")
(match_operand:VI2_AVX10_2 1 "register_operand")
(match_operand:VI2_AVX10_2 2 "register_operand")
@@ -31821,7 +31824,7 @@
DONE;
})
-(define_expand "udot_prod<mode>"
+(define_expand "udot_prod<sseunpackmodelower><mode>"
[(match_operand:<sseunpackmode> 0 "register_operand")
(match_operand:VI2_AVX10_2 1 "register_operand")
(match_operand:VI2_AVX10_2 2 "register_operand")
