[PATCH AArch64] Prefer dup to zip for vec_perm_const; enable dup for bigendian; add testcase.

gcc/:
	* config/aarch64/aarch64.c (aarch64_evpc_dup): Enable for bigendian.
	(aarch64_expand_vec_perm_const): Check for dup before zip.

gcc/testsuite:

	* gcc.target/aarch64/vdup_n_2.c: New test.

From-SVN: r213659
This commit is contained in:
Alan Lawrence 2014-08-06 10:17:05 +00:00 committed by Alan Lawrence
parent 06e105fc9b
commit f901401e53
4 changed files with 40 additions and 7 deletions

View File

@ -1,3 +1,8 @@
2014-08-06 Alan Lawrence <alan.lawrence@arm.com>
* config/aarch64/aarch64.c (aarch64_evpc_dup): Enable for bigendian.
(aarch64_expand_vec_perm_const): Check for dup before zip.
2014-08-06 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* config/aarch64/aarch64.c (aarch64_classify_address): Use REG_P and

View File

@ -9378,10 +9378,6 @@ aarch64_evpc_dup (struct expand_vec_perm_d *d)
unsigned int i, elt, nelt = d->nelt;
rtx lane;
/* TODO: This may not be big-endian safe. */
if (BYTES_BIG_ENDIAN)
return false;
elt = d->perm[0];
for (i = 1; i < nelt; i++)
{
@ -9395,7 +9391,7 @@ aarch64_evpc_dup (struct expand_vec_perm_d *d)
use d->op0 and need not do any extra arithmetic to get the
correct lane number. */
in0 = d->op0;
lane = GEN_INT (elt);
lane = GEN_INT (elt); /* The pattern corrects for big-endian. */
switch (vmode)
{
@ -9476,14 +9472,14 @@ aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
return true;
else if (aarch64_evpc_ext (d))
return true;
else if (aarch64_evpc_dup (d))
return true;
else if (aarch64_evpc_zip (d))
return true;
else if (aarch64_evpc_uzp (d))
return true;
else if (aarch64_evpc_trn (d))
return true;
else if (aarch64_evpc_dup (d))
return true;
return aarch64_evpc_tbl (d);
}
return false;

View File

@ -1,3 +1,7 @@
2014-08-06 Alan Lawrence <alan.lawrence@arm.com>
* gcc.target/aarch64/vdup_n_2.c: New test.
2014-08-06 Maciej W. Rozycki <macro@codesourcery.com>
* gcc.dg/pr44194-1.c: Also exclude powerpc*-*-linux*, except if

View File

@ -0,0 +1,28 @@
/* { dg-do run } */
/* { dg-options "-O2 -fno-inline --save-temps" } */
extern void abort (void);
typedef float float32x2_t __attribute__ ((__vector_size__ ((8))));
typedef unsigned int uint32x2_t __attribute__ ((__vector_size__ ((8))));
float32x2_t
test_dup_1 (float32x2_t in)
{
return __builtin_shuffle (in, (uint32x2_t) {1, 1});
}
int
main (int argc, char **argv)
{
float32x2_t test = {2.718, 3.141};
float32x2_t res = test_dup_1 (test);
if (res[0] != test[1] || res[1] != test[1])
abort ();
return 0;
}
/* { dg-final { scan-assembler-times "\[ \t\]*dup\[ \t\]+v\[0-9\]+\.2s, ?v\[0-9\]+\.s\\\[\[01\]\\\]" 1 } } */
/* { dg-final { scan-assembler-not "zip" } } */
/* { dg-final { cleanup-saved-temps } } */