procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Eliminate redundant vec_select moves.

Browse source 
gcc/
        * rtlanal.c (set_noop_p): Return nonzero in case of redundant vec_select for
        overlapping register lanes.

testsuite/
        * config/gcc.dg/vect/vect-nop-move.c: New.

From-SVN: r205712
This commit is contained in:
Tejas Belagod 2013-12-05 17:24:52 +00:00 • committed by Tejas Belagod
parent 601a5921eb
commit 8c8952918b
4 changed files with 94 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
gcc/ChangeLog
View file

@ -1,3 +1,8 @@
2013-12-05 Tejas Belagod <tejas.belagod@arm.com>
* rtlanal.c (set_noop_p): Return nonzero in case of redundant vec_select
for overlapping register lanes.
2013-12-05 Kirill Yukhin <kirill.yukhin@intel.com>
* config/i386/i386.c (ix86_expand_builtin): Generate

21
gcc/rtlanal.c
View file

@ -1180,6 +1180,27 @@ set_noop_p (const_rtx set)
dst = SUBREG_REG (dst);
}
/* It is a NOOP if destination overlaps with selected src vector
elements. */
if (GET_CODE (src) == VEC_SELECT
&& REG_P (XEXP (src, 0)) && REG_P (dst)
&& HARD_REGISTER_P (XEXP (src, 0))
&& HARD_REGISTER_P (dst))
{
int i;
rtx par = XEXP (src, 1);
rtx src0 = XEXP (src, 0);
int c0 = INTVAL (XVECEXP (par, 0, 0));
HOST_WIDE_INT offset = GET_MODE_UNIT_SIZE (GET_MODE (src0)) * c0;
for (i = 1; i < XVECLEN (par, 0); i++)
if (INTVAL (XVECEXP (par, 0, i)) != c0 + i)
return 0;
return
simplify_subreg_regno (REGNO (src0), GET_MODE (src0),
offset, GET_MODE (dst)) == (int) REGNO (dst);
}
return (REG_P (src) && REG_P (dst)
&& REGNO (src) == REGNO (dst));
}

4
gcc/testsuite/ChangeLog
View file

@ -1,3 +1,7 @@
2013-12-05 Tejas Belagod <tejas.belagod@arm.com>
* gcc.dg/vect/vect-nop-move.c: New test.
2013-12-05 Max Ostapenko <m.ostapenko@partner.samsung.com>
* c-c++-common/tsan/atomic_stack.c: New test.

64
gcc/testsuite/gcc.dg/vect/vect-nop-move.c Normal file
View file

@ -0,0 +1,64 @@
/* { dg-do run } */
/* { dg-require-effective-target vect_float } */
/* { dg-options "-O3 -fdump-rtl-combine-details" } */
extern void abort (void);
#define NOINLINE __attribute__((noinline))
typedef float float32x4_t __attribute__ ((__vector_size__ (16)));
typedef float float32x2_t __attribute__ ((__vector_size__ (8)));
NOINLINE float
foo32x4_be (float32x4_t x)
{
return x[3];
}
NOINLINE float
foo32x4_le (float32x4_t x)
{
return x[0];
}
NOINLINE float
bar (float a)
{
return a;
}
NOINLINE float
foo32x2_be (float32x2_t x)
{
return bar (x[1]);
}
NOINLINE float
foo32x2_le (float32x2_t x)
{
return bar (x[0]);
}
int
main()
{
float32x4_t a = { 0.0f, 1.0f, 2.0f, 3.0f };
float32x2_t b = { 0.0f, 1.0f };
if (foo32x4_be (a) != 3.0f)
abort ();
if (foo32x4_le (a) != 0.0f)
abort ();
if (foo32x2_be (b) != 1.0f)
abort ();
if (foo32x2_le (b) != 0.0f)
abort ();
return 0;
}
/* { dg-final { scan-rtl-dump "deleting noop move" "combine" { target aarch64*-*-* } } } */
/* { dg-final { cleanup-rtl-dump "combine" } } */