Hi!
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with the
AVX arithmetics instructions. So say for -O2 -mavx -ftree-vectorize
void
f1 (int *__restrict e, int *__restrict f)
{
int i;
for (i = 0; i
On Wed, Oct 30, 2013 at 10:47:13AM +0100, Jakub Jelinek wrote:
Hi!
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with the
AVX arithmetics instructions. So say for -O2 -mavx -ftree-vectorize
void
On Wed, Oct 30, 2013 at 10:53:58AM +0100, Ondřej Bílka wrote:
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with the
AVX arithmetics instructions. So say for -O2 -mavx -ftree-vectorize
void
f1
On Wed, Oct 30, 2013 at 11:00:13AM +0100, Jakub Jelinek wrote:
But the above is 16 byte unaligned load. Furthermore, GCC supports
-mavx256-split-unaligned-load and can emit 32 byte loads either as an
unaligned 32 byte load, or merge of 16 byte unaligned loads. The patch
affects only the
On Wed, Oct 30, 2013 at 11:05:58AM +0100, Jakub Jelinek wrote:
On Wed, Oct 30, 2013 at 11:00:13AM +0100, Jakub Jelinek wrote:
But the above is 16 byte unaligned load. Furthermore, GCC supports
-mavx256-split-unaligned-load and can emit 32 byte loads either as an
unaligned 32 byte load, or
On Wed, Oct 30, 2013 at 10:47 AM, Jakub Jelinek ja...@redhat.com wrote:
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with the
AVX arithmetics instructions. So say for -O2 -mavx -ftree-vectorize
This
On Wed, Oct 30, 2013 at 11:55:44AM +0100, Uros Bizjak wrote:
On Wed, Oct 30, 2013 at 10:47 AM, Jakub Jelinek ja...@redhat.com wrote:
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with the
AVX
On 10/30/2013 02:47 AM, Jakub Jelinek wrote:
2013-10-30 Jakub Jelinek ja...@redhat.com
* config/i386/i386.c (ix86_avx256_split_vector_move_misalign): If
op1 is misaligned_operand, just use *movmode_internal insn
rather than UNSPEC_LOADU load.
On Wed, Oct 30, 2013 at 09:17:04AM -0700, Richard Henderson wrote:
On 10/30/2013 02:47 AM, Jakub Jelinek wrote:
2013-10-30 Jakub Jelinek ja...@redhat.com
* config/i386/i386.c (ix86_avx256_split_vector_move_misalign): If
op1 is misaligned_operand, just use *movmode_internal insn
On Wed, Oct 30, 2013 at 12:11 PM, Jakub Jelinek ja...@redhat.com wrote:
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with
the
AVX arithmetics instructions. So say for -O2 -mavx -ftree-vectorize
On Wed, Oct 30, 2013 at 6:42 PM, Uros Bizjak ubiz...@gmail.com wrote:
On Wed, Oct 30, 2013 at 12:11 PM, Jakub Jelinek ja...@redhat.com wrote:
Yesterday I've noticed that for AVX which allows unaligned operands in
AVX arithmetics instructions we still don't combine unaligned loads with
the
11 matches
Mail list logo