Properly handle 256bit load cast.

gcc/

2011-05-18  H.J. Lu  <hongjiu.lu@intel.com>

	PR target/49002
	* config/i386/sse.md (avx_<ssemodesuffix><avxsizesuffix>_<ssemodesuffix>):
	Properly handle load cast.

gcc/testsuite/

2011-05-18  H.J. Lu  <hongjiu.lu@intel.com>

	PR target/49002
	* gcc.target/i386/pr49002-1.c: New test.
	* gcc.target/i386/pr49002-2.c: Likewise.

From-SVN: r173880
This commit is contained in:
H.J. Lu 2011-05-18 22:12:28 +00:00 committed by H.J. Lu
parent 137b5a4c68
commit 31f9eb59e5
5 changed files with 47 additions and 4 deletions

View File

@ -1,3 +1,9 @@
2011-05-18 H.J. Lu <hongjiu.lu@intel.com>
PR target/49002
* config/i386/sse.md (avx_<ssemodesuffix><avxsizesuffix>_<ssemodesuffix>):
Properly handle load cast.
2011-05-18 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/49039

View File

@ -10294,12 +10294,13 @@
"&& reload_completed"
[(const_int 0)]
{
rtx op0 = operands[0];
rtx op1 = operands[1];
if (REG_P (op1))
if (REG_P (op0))
op0 = gen_rtx_REG (<ssehalfvecmode>mode, REGNO (op0));
else
op1 = gen_rtx_REG (<MODE>mode, REGNO (op1));
else
op1 = gen_lowpart (<MODE>mode, op1);
emit_move_insn (operands[0], op1);
emit_move_insn (op0, op1);
DONE;
})

View File

@ -1,3 +1,9 @@
2011-05-18 H.J. Lu <hongjiu.lu@intel.com>
PR target/49002
* gcc.target/i386/pr49002-1.c: New test.
* gcc.target/i386/pr49002-2.c: Likewise.
2011-05-18 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/49039

View File

@ -0,0 +1,16 @@
/* PR target/49002 */
/* { dg-do compile } */
/* { dg-options "-O -mavx" } */
#include <immintrin.h>
void foo(const __m128d *from, __m256d *to, int s)
{
__m256d var = _mm256_castpd128_pd256(from[0]);
var = _mm256_insertf128_pd(var, from[s], 1);
to[0] = var;
}
/* Ensure we load into xmm, not ymm. */
/* { dg-final { scan-assembler-not "vmovapd\[\t \]*\[^,\]*,\[\t \]*%ymm" } } */
/* { dg-final { scan-assembler "vmovapd\[\t \]*\[^,\]*,\[\t \]*%xmm" } } */

View File

@ -0,0 +1,14 @@
/* PR target/49002 */
/* { dg-do compile } */
/* { dg-options "-O -mavx" } */
#include <immintrin.h>
void foo(const __m128d from, __m256d *to)
{
*to = _mm256_castpd128_pd256(from);
}
/* Ensure we store ymm, not xmm. */
/* { dg-final { scan-assembler-not "vmovapd\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
/* { dg-final { scan-assembler "vmovapd\[\t \]*%ymm\[0-9\]\+,\[^,\]*" } } */