Fold single imm use of a FMA if it is a negation [PR95060]

match.pd already has simplifications for negation of a FMA (FMS, FNMA, FNMS)
call if it is single use, but when the widening_mul pass discovers FMAs,
nothing folds the statements anymore.

So, the following patch adjusts the widening_mul pass to handle that.

I had to adjust quite a lot of tests, because they have in them nested FMAs
(one FMA feeding another one) and the patch results in some (equivalent) changes
in the chosen instructions, previously the negation of one FMA's result
would result in the dependent FMA being adjusted for the negation, but now
instead the first FMA is adjusted.

2020-05-13  Jakub Jelinek  <jakub@redhat.com>

	PR tree-optimization/95060
	* tree-ssa-math-opts.c (convert_mult_to_fma_1): Fold a NEGATE_EXPR
	if it is the single use of the FMA internal builtin.

	* gcc.target/i386/avx512f-pr95060.c: New test.
	* gcc.target/i386/fma_double_1.c: Adjust expected insn counts.
	* gcc.target/i386/fma_double_2.c: Likewise.
	* gcc.target/i386/fma_double_3.c: Likewise.
	* gcc.target/i386/fma_double_4.c: Likewise.
	* gcc.target/i386/fma_double_5.c: Likewise.
	* gcc.target/i386/fma_double_6.c: Likewise.
	* gcc.target/i386/fma_float_1.c: Likewise.
	* gcc.target/i386/fma_float_2.c: Likewise.
	* gcc.target/i386/fma_float_3.c: Likewise.
	* gcc.target/i386/fma_float_4.c: Likewise.
	* gcc.target/i386/fma_float_5.c: Likewise.
	* gcc.target/i386/fma_float_6.c: Likewise.
	* gcc.target/i386/l_fma_double_1.c: Likewise.
	* gcc.target/i386/l_fma_double_2.c: Likewise.
	* gcc.target/i386/l_fma_double_3.c: Likewise.
	* gcc.target/i386/l_fma_double_4.c: Likewise.
	* gcc.target/i386/l_fma_double_5.c: Likewise.
	* gcc.target/i386/l_fma_double_6.c: Likewise.
	* gcc.target/i386/l_fma_float_1.c: Likewise.
	* gcc.target/i386/l_fma_float_2.c: Likewise.
	* gcc.target/i386/l_fma_float_3.c: Likewise.
	* gcc.target/i386/l_fma_float_4.c: Likewise.
	* gcc.target/i386/l_fma_float_5.c: Likewise.
	* gcc.target/i386/l_fma_float_6.c: Likewise.
This commit is contained in:
Jakub Jelinek 2020-05-13 11:21:02 +02:00
parent f884bef21c
commit c0c39a765b
28 changed files with 226 additions and 144 deletions

View File

@ -1,3 +1,9 @@
2020-05-13 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/95060
* tree-ssa-math-opts.c (convert_mult_to_fma_1): Fold a NEGATE_EXPR
if it is the single use of the FMA internal builtin.
2020-05-13 Bin Cheng <bin.cheng@linux.alibaba.com>
PR tree-optimization/94969

View File

@ -1,3 +1,32 @@
2020-05-13 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/95060
* gcc.target/i386/avx512f-pr95060.c: New test.
* gcc.target/i386/fma_double_1.c: Adjust expected insn counts.
* gcc.target/i386/fma_double_2.c: Likewise.
* gcc.target/i386/fma_double_3.c: Likewise.
* gcc.target/i386/fma_double_4.c: Likewise.
* gcc.target/i386/fma_double_5.c: Likewise.
* gcc.target/i386/fma_double_6.c: Likewise.
* gcc.target/i386/fma_float_1.c: Likewise.
* gcc.target/i386/fma_float_2.c: Likewise.
* gcc.target/i386/fma_float_3.c: Likewise.
* gcc.target/i386/fma_float_4.c: Likewise.
* gcc.target/i386/fma_float_5.c: Likewise.
* gcc.target/i386/fma_float_6.c: Likewise.
* gcc.target/i386/l_fma_double_1.c: Likewise.
* gcc.target/i386/l_fma_double_2.c: Likewise.
* gcc.target/i386/l_fma_double_3.c: Likewise.
* gcc.target/i386/l_fma_double_4.c: Likewise.
* gcc.target/i386/l_fma_double_5.c: Likewise.
* gcc.target/i386/l_fma_double_6.c: Likewise.
* gcc.target/i386/l_fma_float_1.c: Likewise.
* gcc.target/i386/l_fma_float_2.c: Likewise.
* gcc.target/i386/l_fma_float_3.c: Likewise.
* gcc.target/i386/l_fma_float_4.c: Likewise.
* gcc.target/i386/l_fma_float_5.c: Likewise.
* gcc.target/i386/l_fma_float_6.c: Likewise.
2020-05-13 Martin Liska <mliska@suse.cz>
PR sanitizer/95051

View File

@ -0,0 +1,22 @@
/* PR tree-optimization/95060 */
/* { dg-do compile } */
/* { dg-options "-O3 -ffast-math -mavx512f" } */
/* { dg-final { scan-assembler "\tvfnmsub" } } */
/* { dg-final { scan-assembler-not "\tvfmadd" } } */
#define N 32
float r[N], a[N], b[N], c[N];
void
foo (void)
{
for (int i = 0; i < N; i++)
r[i] = -(a[i] * b[i]) - c[i];
}
void
bar (void)
{
for (int i = 0; i < N; i++)
r[i] = -(a[i] * b[i] + c[i]);
}

View File

@ -8,11 +8,9 @@
#include "fma_1.h"
/* { dg-final { scan-assembler-times "vfmadd132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd231sd" 4 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub231sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmadd231sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231sd" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_2.h"
/* { dg-final { scan-assembler-times "vfmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_3.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+sd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+sd" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_4.h"
/* { dg-final { scan-assembler-times "vfmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_5.h"
/* { dg-final { scan-assembler-times "vfmadd\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[132\]+sd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+sd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+sd" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_6.h"
/* { dg-final { scan-assembler-times "vfmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132sd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132sd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132sd" 4 } } */

View File

@ -8,11 +8,9 @@
#include "fma_1.h"
/* { dg-final { scan-assembler-times "vfmadd132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd231ss" 4 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub231ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmadd231ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231ss" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_2.h"
/* { dg-final { scan-assembler-times "vfmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_3.h"
/* { dg-final { scan-assembler-times "vfmadd\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[132\]+ss" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+ss" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+ss" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_4.h"
/* { dg-final { scan-assembler-times "vfmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_5.h"
/* { dg-final { scan-assembler-times "vfmadd\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[132\]+ss" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[132\]+ss" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[132\]+ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[132\]+ss" 4 } } */

View File

@ -8,7 +8,7 @@
#include "fma_6.h"
/* { dg-final { scan-assembler-times "vfmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub132ss" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ss" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ss" 4 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_1.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_2.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_3.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_4.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_5.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -11,11 +11,11 @@ typedef double adouble __attribute__((aligned(sizeof (double))));
#include "l_fma_6.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 32 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+pd" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+pd" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+sd" 48 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+sd" 16 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+sd" 16 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_1.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_2.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_3.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_4.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_5.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -10,11 +10,11 @@
#include "l_fma_6.h"
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 8 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 64 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ps" 12 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ps" 4 } } */
/* { dg-final { scan-assembler-times "vfmadd\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfmsub\[123\]+ss" 96 } } */
/* { dg-final { scan-assembler-times "vfnmadd\[123\]+ss" 32 } } */
/* { dg-final { scan-assembler-times "vfnmsub\[123\]+ss" 32 } } */

View File

@ -2930,6 +2930,35 @@ convert_mult_to_fma_1 (tree mul_result, tree op1, tree op2)
fprintf (dump_file, "\n");
}
/* If the FMA result is negated in a single use, fold the negation
too. */
orig_stmt = gsi_stmt (gsi);
use_operand_p use_p;
gimple *neg_stmt;
if (is_gimple_call (orig_stmt)
&& gimple_call_internal_p (orig_stmt)
&& gimple_call_lhs (orig_stmt)
&& TREE_CODE (gimple_call_lhs (orig_stmt)) == SSA_NAME
&& single_imm_use (gimple_call_lhs (orig_stmt), &use_p, &neg_stmt)
&& is_gimple_assign (neg_stmt)
&& gimple_assign_rhs_code (neg_stmt) == NEGATE_EXPR
&& !stmt_could_throw_p (cfun, neg_stmt))
{
gsi = gsi_for_stmt (neg_stmt);
if (fold_stmt (&gsi, follow_all_ssa_edges))
{
if (maybe_clean_or_replace_eh_stmt (neg_stmt, gsi_stmt (gsi)))
gcc_unreachable ();
update_stmt (gsi_stmt (gsi));
if (dump_file && (dump_flags & TDF_DETAILS))
{
fprintf (dump_file, "Folded FMA negation ");
print_gimple_stmt (dump_file, gsi_stmt (gsi), 0, TDF_NONE);
fprintf (dump_file, "\n");
}
}
}
widen_mul_stats.fmas_inserted++;
}
}