re PR tree-optimization/59501 (Vector Gather with GCC 4.9 2013-12-08 Snapshot)

PR target/59501
	* config/i386/i386.c (ix86_save_reg): Don't return true for drap_reg
	if !crtl->stack_realign_needed.
	(ix86_finalize_stack_realign_flags): If drap_reg isn't live on entry
	and stack_realign_needed will be false, clear drap_reg and need_drap.
	Optimize leaf functions that don't need stack frame even if
	crtl->need_drap.

	* gcc.target/i386/pr59501-1.c: New test.
	* gcc.target/i386/pr59501-1a.c: New test.
	* gcc.target/i386/pr59501-2.c: New test.
	* gcc.target/i386/pr59501-2a.c: New test.
	* gcc.target/i386/pr59501-3.c: New test.
	* gcc.target/i386/pr59501-3a.c: New test.
	* gcc.target/i386/pr59501-4.c: New test.
	* gcc.target/i386/pr59501-4a.c: New test.
	* gcc.target/i386/pr59501-5.c: New test.
	* gcc.target/i386/pr59501-6.c: New test.

From-SVN: r206243
This commit is contained in:
Jakub Jelinek 2013-12-30 09:53:10 +01:00 committed by Jakub Jelinek
parent 5cf5a0e59b
commit 8e72847528
13 changed files with 215 additions and 2 deletions

View File

@ -1,3 +1,13 @@
2013-12-30 Jakub Jelinek <jakub@redhat.com>
PR target/59501
* config/i386/i386.c (ix86_save_reg): Don't return true for drap_reg
if !crtl->stack_realign_needed.
(ix86_finalize_stack_realign_flags): If drap_reg isn't live on entry
and stack_realign_needed will be false, clear drap_reg and need_drap.
Optimize leaf functions that don't need stack frame even if
crtl->need_drap.
2013-12-30 H.J. Lu <hongjiu.lu@intel.com>
PR target/59605

View File

@ -9189,7 +9189,9 @@ ix86_save_reg (unsigned int regno, bool maybe_eh_return)
}
}
if (crtl->drap_reg && regno == REGNO (crtl->drap_reg))
if (crtl->drap_reg
&& regno == REGNO (crtl->drap_reg)
&& crtl->stack_realign_needed)
return true;
return (df_regs_ever_live_p (regno)
@ -10427,12 +10429,23 @@ ix86_finalize_stack_realign_flags (void)
return;
}
/* If drap has been set, but it actually isn't live at the start
of the function and !stack_realign, there is no reason to set it up. */
if (crtl->drap_reg && !stack_realign)
{
basic_block bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
if (! REGNO_REG_SET_P (DF_LR_IN (bb), REGNO (crtl->drap_reg)))
{
crtl->drap_reg = NULL_RTX;
crtl->need_drap = false;
}
}
/* If the only reason for frame_pointer_needed is that we conservatively
assumed stack realignment might be needed, but in the end nothing that
needed the stack alignment had been spilled, clear frame_pointer_needed
and say we don't need stack realignment. */
if (stack_realign
&& !crtl->need_drap
&& frame_pointer_needed
&& crtl->is_leaf
&& flag_omit_frame_pointer
@ -10470,6 +10483,18 @@ ix86_finalize_stack_realign_flags (void)
}
}
/* If drap has been set, but it actually isn't live at the start
of the function, there is no reason to set it up. */
if (crtl->drap_reg)
{
basic_block bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
if (! REGNO_REG_SET_P (DF_LR_IN (bb), REGNO (crtl->drap_reg)))
{
crtl->drap_reg = NULL_RTX;
crtl->need_drap = false;
}
}
frame_pointer_needed = false;
stack_realign = false;
crtl->max_used_stack_slot_alignment = incoming_stack_boundary;

View File

@ -1,3 +1,17 @@
2013-12-30 Jakub Jelinek <jakub@redhat.com>
PR target/59501
* gcc.target/i386/pr59501-1.c: New test.
* gcc.target/i386/pr59501-1a.c: New test.
* gcc.target/i386/pr59501-2.c: New test.
* gcc.target/i386/pr59501-2a.c: New test.
* gcc.target/i386/pr59501-3.c: New test.
* gcc.target/i386/pr59501-3a.c: New test.
* gcc.target/i386/pr59501-4.c: New test.
* gcc.target/i386/pr59501-4a.c: New test.
* gcc.target/i386/pr59501-5.c: New test.
* gcc.target/i386/pr59501-6.c: New test.
2013-12-30 H.J. Lu <hongjiu.lu@intel.com>
PR target/59605

View File

@ -0,0 +1,30 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -mno-accumulate-outgoing-args" } */
#define CHECK_H "avx-check.h"
#define TEST avx_test
#include CHECK_H
typedef double V __attribute__ ((vector_size (32)));
__attribute__((noinline, noclone)) V
foo (double *x, unsigned *y)
{
V r = { x[y[0]], x[y[1]], x[y[2]], x[y[3]] };
return r;
}
static void
TEST (void)
{
double a[16];
unsigned b[4] = { 5, 0, 15, 7 };
int i;
for (i = 0; i < 16; i++)
a[i] = 0.5 + i;
V v = foo (a, b);
if (v[0] != 5.5 || v[1] != 0.5 || v[2] != 15.5 || v[3] != 7.5)
__builtin_abort ();
}

View File

@ -0,0 +1,17 @@
/* PR target/59501 */
/* { dg-do compile { target { ! ia32 } } } */
/* { dg-options "-O2 -mavx -mno-accumulate-outgoing-args" } */
typedef double V __attribute__ ((vector_size (32)));
V
foo (double *x, unsigned *y)
{
V r = { x[y[0]], x[y[1]], x[y[2]], x[y[3]] };
return r;
}
/* Verify no dynamic realignment is performed. */
/* { dg-final { scan-assembler-not "and\[^\n\r]*sp" } } */
/* And DRAP isn't needed either. */
/* { dg-final { scan-assembler-not "r10" } } */

View File

@ -0,0 +1,5 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -maccumulate-outgoing-args" } */
#include "pr59501-1.c"

View File

@ -0,0 +1,10 @@
/* PR target/59501 */
/* { dg-do compile { target { ! ia32 } } } */
/* { dg-options "-O2 -mavx -maccumulate-outgoing-args" } */
#include "pr59501-1a.c"
/* Verify no dynamic realignment is performed. */
/* { dg-final { scan-assembler-not "and\[^\n\r]*sp" } } */
/* And DRAP isn't needed either. */
/* { dg-final { scan-assembler-not "r10" } } */

View File

@ -0,0 +1,30 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -mno-accumulate-outgoing-args" } */
#define CHECK_H "avx-check.h"
#define TEST avx_test
#include CHECK_H
typedef double V __attribute__ ((vector_size (32)));
__attribute__((noinline, noclone)) V
foo (double *x, int a, int b, int c, int d, int e, int f, unsigned *y)
{
V r = { x[y[0]], x[y[1]], x[y[2]], x[y[3]] };
return r;
}
static void
TEST (void)
{
double a[16];
unsigned b[4] = { 5, 0, 15, 7 };
int i;
for (i = 0; i < 16; i++)
a[i] = 0.5 + i;
V v = foo (a, 0, 0, 0, 0, 0, 0, b);
if (v[0] != 5.5 || v[1] != 0.5 || v[2] != 15.5 || v[3] != 7.5)
__builtin_abort ();
}

View File

@ -0,0 +1,15 @@
/* PR target/59501 */
/* { dg-do compile { target { ! ia32 } } } */
/* { dg-options "-O2 -mavx -mno-accumulate-outgoing-args" } */
typedef double V __attribute__ ((vector_size (32)));
V
foo (double *x, int a, int b, int c, int d, int e, int f, unsigned *y)
{
V r = { x[y[0]], x[y[1]], x[y[2]], x[y[3]] };
return r;
}
/* Verify no dynamic realignment is performed. */
/* { dg-final { scan-assembler-not "and\[^\n\r]*sp" } } */

View File

@ -0,0 +1,5 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -maccumulate-outgoing-args" } */
#include "pr59501-3.c"

View File

@ -0,0 +1,8 @@
/* PR target/59501 */
/* { dg-do compile { target { ! ia32 } } } */
/* { dg-options "-O2 -mavx -maccumulate-outgoing-args" } */
#include "pr59501-3a.c"
/* Verify no dynamic realignment is performed. */
/* { dg-final { scan-assembler-not "and\[^\n\r]*sp" { xfail *-*-* } } } */

View File

@ -0,0 +1,39 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -mno-accumulate-outgoing-args" } */
#define CHECK_H "avx-check.h"
#define TEST avx_test
#include CHECK_H
typedef double V __attribute__ ((vector_size (32)));
__attribute__((noinline, noclone)) void
bar (char *p)
{
p[0] = 1;
p[37] = 2;
asm volatile ("" : : "r" (p) : "memory");
}
__attribute__((noinline, noclone)) V
foo (double *x, int a, int b, int c, int d, int e, int f, unsigned *y)
{
bar (__builtin_alloca (a + b + c + d + e + f));
V r = { x[y[0]], x[y[1]], x[y[2]], x[y[3]] };
return r;
}
static void
TEST (void)
{
double a[16];
unsigned b[4] = { 5, 0, 15, 7 };
int i;
for (i = 0; i < 16; i++)
a[i] = 0.5 + i;
V v = foo (a, 0, 30, 0, 0, 8, 0, b);
if (v[0] != 5.5 || v[1] != 0.5 || v[2] != 15.5 || v[3] != 7.5)
__builtin_abort ();
}

View File

@ -0,0 +1,5 @@
/* PR target/59501 */
/* { dg-do run } */
/* { dg-options "-O2 -mavx -maccumulate-outgoing-args" } */
#include "pr59501-5.c"