[PATCH, i386, AVX-512] Split out mask version for vec_extract_hi_<mode>.
Kirill Yukhin
kirill.yukhin@gmail.com
Mon Dec 28 13:17:00 GMT 2015
Hello,
On 02 Dec 20:00, Kirill Yukhin wrote:
> Hello,
> On 30 Nov 13:46, Kirill Yukhin wrote:
> > Hello,
> > Patch in the bottom splits masked version of vec_extract_hi_<mode>
> > to block AVX-1512VL insn generation for KNL and cures ICE on spec2k6/450.soplex.
> >
> > Bootstrapped and regtesed.
> >
> > If no objections - I'll commit on Wednesday.
> >
> > gcc/
> > * config/i386/sse.md (define_insn "vec_extract_hi_<mode>_maskm"):
> > Remove "prefix_extra".
> > (define_insn "vec_extract_hi_<mode>_mask"): New.
> > (define_insn "vec_extract_hi_<mode>"): Remove masking.
> > gcc/testsuite/
> > * gcc.target/i386/avx512vl-vextractf32x4-1.c: Fix scan pattern.
Similar patch is needed to make spec2k6/465.tonto working for gcc-5.
Is patch in the bottom ok for gcc-5-branch if bootstrapped and regtested?
It cures spec2k6/465.tonto illegal insn emit.
--
Thanks, K
commit 3d5942b7d30d173d7d44ceb657b6ba93212cf0af
Author: kyukhin <kyukhin@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Wed Dec 2 11:07:42 2015 +0000
AVX-512. Split out mask version for vec_extract_hi_<mode>.
gcc/
* config/i386/sse.md (define_insn "vec_extract_hi_<mode>_maskm"):
New.
(define_insn "vec_extract_hi_<mode>_mask"): New.
(define_insn "vec_extract_hi_<mode>"): Remove masking.
gcc/testsuite/
* gcc.target/i386/avx512vl-vextractf64x2-1.c: Fix scan pattern.
* gcc.target/i386/avx512vl-vextracti64x2-1.c: Ditto.
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index dc7f6a7..6757e56 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -7018,28 +7018,50 @@
DONE;
})
-(define_insn "vec_extract_hi_<mode><mask_name>"
- [(set (match_operand:<ssehalfvecmode> 0 "<store_mask_predicate>" "=v,<store_mask_constraint>")
+(define_insn "vec_extract_hi_<mode>_maskm"
+ [(set (match_operand:<ssehalfvecmode> 0 "memory_operand" "=m")
+ (vec_merge:<ssehalfvecmode>
+ (vec_select:<ssehalfvecmode>
+ (match_operand:VI8F_256 1 "register_operand" "v")
+ (parallel [(const_int 2) (const_int 3)]))
+ (match_operand:<ssehalfvecmode> 2 "memory_operand" "0")
+ (match_operand:<ssehalfvecmode> 3 "register_operand" "k")))]
+ "TARGET_AVX512DQ && TARGET_AVX512VL
+ && rtx_equal_p (operands[2], operands[0])"
+ "vextract<shuffletype>64x2\t{$0x1, %1, %0%{%3%}|%0%{%3%}, %1, 0x1}"
+ [(set_attr "type" "sselog1")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "vec_extract_hi_<mode>_mask"
+ [(set (match_operand:<ssehalfvecmode> 0 "register_operand" "=v")
+ (vec_merge:<ssehalfvecmode>
+ (vec_select:<ssehalfvecmode>
+ (match_operand:VI8F_256 1 "register_operand" "v")
+ (parallel [(const_int 2) (const_int 3)]))
+ (match_operand:<ssehalfvecmode> 2 "vector_move_operand" "0C")
+ (match_operand:<avx512fmaskmode> 3 "register_operand" "Yk")))]
+ "TARGET_AVX512VL && TARGET_AVX512DQ"
+ "vextract<shuffletype>64x2\t{$0x1, %1, %0%{%3%}%N2|%0%{%3%}%N2, %1, 0x1}"
+ [(set_attr "type" "sselog1")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "vec_extract_hi_<mode>"
+ [(set (match_operand:<ssehalfvecmode> 0 "nonimmediate_operand" "=xm, vm")
(vec_select:<ssehalfvecmode>
- (match_operand:VI8F_256 1 "register_operand" "v,v")
+ (match_operand:VI8F_256 1 "register_operand" "x, v")
(parallel [(const_int 2) (const_int 3)])))]
- "TARGET_AVX && <mask_avx512vl_condition> && <mask_avx512dq_condition>"
-{
- if (TARGET_AVX512VL)
- {
- if (TARGET_AVX512DQ)
- return "vextract<shuffletype>64x2\t{$0x1, %1, %0<mask_operand2>|%0<mask_operand2>, %1, 0x1}";
- else
- return "vextract<shuffletype>32x4\t{$0x1, %1, %0|%0, %1, 0x1}";
- }
- else
- return "vextract<i128>\t{$0x1, %1, %0|%0, %1, 0x1}";
-}
- [(set_attr "type" "sselog")
- (set_attr "prefix_extra" "1")
+ "TARGET_AVX"
+ "@
+ vextract<i128>\t{$0x1, %1, %0|%0, %1, 0x1}
+ vextract<shuffletype>64x2\t{$0x1, %1, %0|%0, %1, 0x1}"
+ [(set_attr "isa" "*, avx512dq")
+ (set_attr "prefix" "vex, evex")
+ (set_attr "type" "sselog1")
(set_attr "length_immediate" "1")
- (set_attr "memory" "none,store")
- (set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
(define_split
diff --git a/gcc/testsuite/gcc.target/i386/avx512dq-vextractf64x2-1.c b/gcc/testsuite/gcc.target/i386/avx512dq-vextractf64x2-1.c
index c8cce51..dd7e30b 100644
--- a/gcc/testsuite/gcc.target/i386/avx512dq-vextractf64x2-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512dq-vextractf64x2-1.c
@@ -3,7 +3,7 @@
/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
-/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vextractf(?:128|64x2)\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextractf64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
diff --git a/gcc/testsuite/gcc.target/i386/avx512dq-vextracti64x2-1.c b/gcc/testsuite/gcc.target/i386/avx512dq-vextracti64x2-1.c
index d49b0c0..a3f3224 100644
--- a/gcc/testsuite/gcc.target/i386/avx512dq-vextracti64x2-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512dq-vextracti64x2-1.c
@@ -3,7 +3,7 @@
/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+.{7}\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
-/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vextracti(?:128|64x2)\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vextracti64x2\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+.{7}\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
More information about the Gcc-patches
mailing list