On 10/20/18, Uros Bizjak <[email protected]> wrote:
> On Fri, Oct 19, 2018 at 11:08 PM H.J. Lu <[email protected]> wrote:
>>
>> Many AVX512 vector operations can broadcast from a scalar memory source.
>> This patch enables memory broadcast for FP mul operations.
>>
>> gcc/
>>
>> PR target/72782
>> * config/i386/sse.md (*mul<mode>3<mask_name>_bcst_1): New.
>> (*mul<mode>3<mask_name>_bcst_2): Likewise.
>>
>> gcc/testsuite/
>>
>> PR target/72782
>> * gcc.target/i386/avx512f-mul-df-zmm-1.c: New test.
>> * gcc.target/i386/avx512f-mul-sf-zmm-1.c: Likewise.
>> * gcc.target/i386/avx512f-mul-sf-zmm-2.c: Likewise.
>> * gcc.target/i386/avx512f-mul-sf-zmm-3.c: Likewise.
>> * gcc.target/i386/avx512f-mul-sf-zmm-4.c: Likewise.
>> * gcc.target/i386/avx512f-mul-sf-zmm-5.c: Likewise.
>> * gcc.target/i386/avx512f-mul-sf-zmm-6.c: Likewise.
>> * gcc.target/i386/avx512vl-mul-sf-xmm-1.c: Likewise.
>> * gcc.target/i386/avx512vl-mul-sf-ymm-1.c: Likewise.
>> ---
>> gcc/config/i386/sse.md | 24 +++++++++++++++++++
>> .../gcc.target/i386/avx512f-mul-df-zmm-1.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-1.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-2.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-3.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-4.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-5.c | 12 ++++++++++
>> .../gcc.target/i386/avx512f-mul-sf-zmm-6.c | 12 ++++++++++
>> .../gcc.target/i386/avx512vl-mul-sf-xmm-1.c | 12 ++++++++++
>> .../gcc.target/i386/avx512vl-mul-sf-ymm-1.c | 12 ++++++++++
>> 10 files changed, 132 insertions(+)
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-df-zmm-1.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-1.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-2.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-3.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-4.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-5.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-6.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-xmm-1.c
>> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-ymm-1.c
>>
>> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
>> index 411c78ae8d3..a73659e6bd2 100644
>> --- a/gcc/config/i386/sse.md
>> +++ b/gcc/config/i386/sse.md
>> @@ -1754,6 +1754,30 @@
>> (set_attr "btver2_decode" "direct,double")
>> (set_attr "mode" "<MODE>")])
>>
>> +(define_insn "*mul<mode>3<mask_name>_bcst_1"
>> + [(set (match_operand:VF_AVX512 0 "register_operand" "=v")
>> + (mult:VF_AVX512
>> + (match_operand:VF_AVX512 1 "register_operand" "v")
>> + (vec_duplicate:VF_AVX512
>> + (match_operand:<ssescalarmode> 2 "memory_operand" "m"))))]
>> + "TARGET_AVX512F && <mask_mode512bit_condition>"
>> + "vmul<ssemodesuffix>\t{%2<avx512bcst>, %1,
>> %0<mask_operand3>|%0<mask_operand3>, %1, %2<<avx512bcst>>}"
>> + [(set_attr "prefix" "evex")
>> + (set_attr "type" "ssemul")
>> + (set_attr "mode" "<MODE>")])
>> +
>> +(define_insn "*mul<mode>3<mask_name>_bcst_2"
>> + [(set (match_operand:VF_AVX512 0 "register_operand" "=v")
>> + (mult:VF_AVX512
>> + (vec_duplicate:VF_AVX512
>> + (match_operand:<ssescalarmode> 1 "memory_operand" "m"))
>> + (match_operand:VF_AVX512 2 "register_operand" "v")))]
>> + "TARGET_AVX512F && <mask_mode512bit_condition>"
>> + "vmul<ssemodesuffix>\t{%1<avx512bcst>, %2,
>> %0<mask_operand3>|%0<mask_operand3>, %2, %1<<avx512bcst>>}"
>> + [(set_attr "prefix" "evex")
>> + (set_attr "type" "ssemul")
>> + (set_attr "mode" "<MODE>")])
>
> Do we really need two patterns here? IIRC, the compiler canonicalizes
> commutative binops so that they have memory operand in the second
> place. We have vec_duplicate here, so this may not be the case, but
> please investigate if we really need two patterns for commutative
> binops.
>
Only one pattern is needed. For
(set (reg:V16SF 89) (vec_duplicate:V16SF (reg:SF 91)))
(set (reg:V16SF 95) (mult:V16SF (reg:V16SF 87) (reg:V16SF 89)))
combiner prefers
(set (reg:V16SF 95)
(mult:V16SF
(vec_duplicate:V16SF (reg:SF 91))
(reg:V16SF 87)))
instead of
(set (reg:V16SF 95)
(mult:V16SF
(reg:V16SF 87)
(vec_duplicate:V16SF (reg:SF 91))))
commutation is performed at
(set (reg:V16SF 95) (mult:V16SF (reg:V16SF 87) (reg:V16SF 89)))
Here is the updated patch. OK for trunk?
Thanks.
--
H.J.
From 1262c47632de9cff9cdeaea792b107a18ceefa25 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <[email protected]>
Date: Wed, 3 Oct 2018 09:37:43 -0700
Subject: [PATCH] i386: Enable AVX512 memory broadcast for FP mul
Many AVX512 vector operations can broadcast from a scalar memory source.
This patch enables memory broadcast for FP mul operations.
gcc/
PR target/72782
* config/i386/sse.md (*mul<mode>3<mask_name>_bcst): New.
gcc/testsuite/
PR target/72782
* gcc.target/i386/avx512f-mul-df-zmm-1.c: New test.
* gcc.target/i386/avx512f-mul-sf-zmm-1.c: Likewise.
* gcc.target/i386/avx512f-mul-sf-zmm-2.c: Likewise.
* gcc.target/i386/avx512f-mul-sf-zmm-3.c: Likewise.
* gcc.target/i386/avx512f-mul-sf-zmm-4.c: Likewise.
* gcc.target/i386/avx512f-mul-sf-zmm-5.c: Likewise.
* gcc.target/i386/avx512f-mul-sf-zmm-6.c: Likewise.
* gcc.target/i386/avx512vl-mul-sf-xmm-1.c: Likewise.
* gcc.target/i386/avx512vl-mul-sf-ymm-1.c: Likewise.
---
gcc/config/i386/sse.md | 25 +++++++++++++++++++
.../gcc.target/i386/avx512f-mul-df-zmm-1.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-1.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-2.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-3.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-4.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-5.c | 12 +++++++++
.../gcc.target/i386/avx512f-mul-sf-zmm-6.c | 12 +++++++++
.../gcc.target/i386/avx512vl-mul-sf-xmm-1.c | 12 +++++++++
.../gcc.target/i386/avx512vl-mul-sf-ymm-1.c | 12 +++++++++
10 files changed, 133 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-df-zmm-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-2.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-3.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-4.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-5.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-6.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-xmm-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-ymm-1.c
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 1b41aa5088b..22707927274 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -1754,6 +1754,31 @@
(set_attr "btver2_decode" "direct,double")
(set_attr "mode" "<MODE>")])
+;; For
+;; (set (reg:V16SF 89) (vec_duplicate:V16SF (reg:SF 91)))
+;; (set (reg:V16SF 95) (mult:V16SF (reg:V16SF 87) (reg:V16SF 89)))
+;; combiner prefers
+;; (set (reg:V16SF 95)
+;; (mult:V16SF
+;; (vec_duplicate:V16SF (reg:SF 91))
+;; (reg:V16SF 87)))
+;; instead of
+;; (set (reg:V16SF 95)
+;; (mult:V16SF
+;; (reg:V16SF 87)
+;; (vec_duplicate:V16SF (reg:SF 91))))
+(define_insn "*mul<mode>3<mask_name>_bcst"
+ [(set (match_operand:VF_AVX512 0 "register_operand" "=v")
+ (mult:VF_AVX512
+ (vec_duplicate:VF_AVX512
+ (match_operand:<ssescalarmode> 1 "memory_operand" "m"))
+ (match_operand:VF_AVX512 2 "register_operand" "v")))]
+ "TARGET_AVX512F && <mask_mode512bit_condition>"
+ "vmul<ssemodesuffix>\t{%1<avx512bcst>, %2, %0<mask_operand3>|%0<mask_operand3>, %2, %1<<avx512bcst>>}"
+ [(set_attr "prefix" "evex")
+ (set_attr "type" "ssemul")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "<sse>_vm<multdiv_mnemonic><mode>3<mask_scalar_name><round_scalar_name>"
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
(vec_merge:VF_128
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-df-zmm-1.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-df-zmm-1.c
new file mode 100644
index 00000000000..e3c51986fe2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-df-zmm-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmulpd\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastsd\[^\n\]*%zmm\[0-9\]+" } } */
+
+#define type __m512d
+#define vec 512
+#define op mul
+#define suffix pd
+#define SCALAR double
+
+#include "avx512-binop-1.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-1.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-1.c
new file mode 100644
index 00000000000..14bccca276a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-1.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-2.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-2.c
new file mode 100644
index 00000000000..8293324084b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-2.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-3.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-3.c
new file mode 100644
index 00000000000..cb768db2cb4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "vmulps\[^\n\]*%zmm\[0-9\]+" 1 } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-3.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-4.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-4.c
new file mode 100644
index 00000000000..7626192ed3d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-4.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+%zmm\[0-9\]+, %zmm\[0-9\]+, %zmm0" 1 } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-4.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-5.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-5.c
new file mode 100644
index 00000000000..b2ad8054d98
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-5.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-5.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-6.c b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-6.c
new file mode 100644
index 00000000000..d8dde860fe7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-mul-sf-zmm-6.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
+
+#define type __m512
+#define vec 512
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-6.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-xmm-1.c b/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-xmm-1.c
new file mode 100644
index 00000000000..bbb0041613b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-xmm-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512vl -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%xmm\[0-9\]+" } } */
+
+#define type __m128
+#define vec
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-1.h"
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-ymm-1.c b/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-ymm-1.c
new file mode 100644
index 00000000000..35810b220c3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-mul-sf-ymm-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512vl -O2" } */
+/* { dg-final { scan-assembler-times "vmulps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %ymm\[0-9\]+, %ymm0" 1 } } */
+/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%ymm\[0-9\]+" } } */
+
+#define type __m256
+#define vec 256
+#define op mul
+#define suffix ps
+#define SCALAR float
+
+#include "avx512-binop-1.h"
--
2.17.2
