Hello,
This patch introduces "mask_scalar_merge" subst.
Is it ok to commit to main trunk?
Testing pass.
--
Thanks, K
---
gcc/config/i386/sse.md | 26 +++++++++++++-------------
gcc/config/i386/subst.md | 16 ++++++++++++++++
2 files changed, 29 insertions(+), 13 deletions(-)
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 1f0d6fa..f3cca59 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2153,7 +2153,7 @@
[(V16SF "const_0_to_31_operand") (V8DF "const_0_to_31_operand")
(V16SI "const_0_to_7_operand") (V8DI "const_0_to_7_operand")])
-(define_insn "avx512f_cmp<mode>3"
+(define_insn "avx512f_cmp<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48F_512 1 "register_operand" "v")
@@ -2161,13 +2161,13 @@
(match_operand:SI 3 "<cmp_imm_predicate>" "n")]
UNSPEC_PCMP))]
"TARGET_AVX512F"
- "v<sseintprefix>cmp<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ "v<sseintprefix>cmp<ssemodesuffix>\t{%3, %2, %1,
%0<mask_scalar_merge_operand4>|%0<mask_scalar_merge_operand4>, %1, %2, %3}"
[(set_attr "type" "ssecmp")
(set_attr "length_immediate" "1")
(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
-(define_insn "avx512f_ucmp<mode>3"
+(define_insn "avx512f_ucmp<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand" "v")
@@ -2175,7 +2175,7 @@
(match_operand:SI 3 "const_0_to_7_operand" "n")]
UNSPEC_UNSIGNED_PCMP))]
"TARGET_AVX512F"
- "vpcmpu<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ "vpcmpu<ssemodesuffix>\t{%3, %2, %1,
%0<mask_scalar_merge_operand4>|%0<mask_scalar_merge_operand4>, %1, %2, %3}"
[(set_attr "type" "ssecmp")
(set_attr "length_immediate" "1")
(set_attr "prefix" "evex")
@@ -8712,7 +8712,7 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
-(define_expand "avx512f_eq<mode>3"
+(define_expand "avx512f_eq<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand")
@@ -8721,14 +8721,14 @@
"TARGET_AVX512F"
"ix86_fixup_binary_operands_no_copy (EQ, <MODE>mode, operands);")
-(define_insn "avx512f_eq<mode>3_1"
+(define_insn "avx512f_eq<mode>3<mask_scalar_merge_name>_1"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand" "%v")
(match_operand:VI48_512 2 "nonimmediate_operand" "vm")]
UNSPEC_MASKED_EQ))]
"TARGET_AVX512F && ix86_binary_operator_ok (EQ, <MODE>mode, operands)"
- "vpcmpeq<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "vpcmpeq<ssemodesuffix>\t{%2, %1,
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %1, %2}"
[(set_attr "type" "ssecmp")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "evex")
@@ -8808,13 +8808,13 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
-(define_insn "avx512f_gt<mode>3"
+(define_insn "avx512f_gt<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand" "v")
(match_operand:VI48_512 2 "nonimmediate_operand" "vm")]
UNSPEC_MASKED_GT))]
"TARGET_AVX512F"
- "vpcmpgt<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "vpcmpgt<ssemodesuffix>\t{%2, %1,
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %1, %2}"
[(set_attr "type" "ssecmp")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "evex")
@@ -9208,25 +9208,25 @@
]
(const_string "<sseinsnmode>")))])
-(define_insn "avx512f_testm<mode>3"
+(define_insn "avx512f_testm<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand" "v")
(match_operand:VI48_512 2 "nonimmediate_operand" "vm")]
UNSPEC_TESTM))]
"TARGET_AVX512F"
- "vptestm<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "vptestm<ssemodesuffix>\t{%2, %1,
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %1, %2}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
-(define_insn "avx512f_testnm<mode>3"
+(define_insn "avx512f_testnm<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(unspec:<avx512fmaskmode>
[(match_operand:VI48_512 1 "register_operand" "v")
(match_operand:VI48_512 2 "nonimmediate_operand" "vm")]
UNSPEC_TESTNM))]
"TARGET_AVX512CD"
- "%vptestnm<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "%vptestnm<ssemodesuffix>\t{%2, %1,
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %1, %2}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
diff --git a/gcc/config/i386/subst.md b/gcc/config/i386/subst.md
index 532a3a1..b537c5e 100644
--- a/gcc/config/i386/subst.md
+++ b/gcc/config/i386/subst.md
@@ -27,6 +27,9 @@
V16SF V8SF V4SF
V8DF V4DF V2DF])
+(define_mode_iterator SUBST_S
+ [QI HI SI DI])
+
(define_subst_attr "mask_name" "mask" "" "_mask")
(define_subst_attr "mask_applied" "mask" "false" "true")
(define_subst_attr "mask_operand2" "mask" "" "%{%3%}%N2")
@@ -77,3 +80,16 @@
(match_operand:<avx512fmaskmode> 5 "register_operand" "k"))
(match_dup 2)
(const_int 1)))])
+
+(define_subst_attr "mask_scalar_merge_name" "mask_scalar_merge" "" "_mask")
+(define_subst_attr "mask_scalar_merge_operand3" "mask_scalar_merge" ""
"%{%3%}")
+(define_subst_attr "mask_scalar_merge_operand4" "mask_scalar_merge" ""
"%{%4%}")
+
+(define_subst "mask_scalar_merge"
+ [(set (match_operand:SUBST_S 0)
+ (match_operand:SUBST_S 1))]
+ "TARGET_AVX512F"
+ [(set (match_dup 0)
+ (and:SUBST_S
+ (match_dup 1)
+ (match_operand:SUBST_S 3 "register_operand" "k")))])
