mirror/gcc
2
0
Fork 0
mirror of git://gcc.gnu.org/git/gcc.git synced 2025-02-01 04:29:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

Allow propagations from inner loop to outer loop.

Browse Source 
NULL is considered as an outer loop of any other loop.

gcc/ChangeLog:

	PR rtl-optimization/103750
	* fwprop.c (forward_propagate_into): Allow propagations from
	inner loop to outer loop.

gcc/testsuite/ChangeLog:

	* g++.target/i386/pr103750-fwprop-1.C: New test.
This commit is contained in:
liuhongt 2021-12-20 11:13:38 +08:00
parent 659f8161f6
commit e7a7dbb5ca
3 changed files with 31 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
build.log Normal file
View File

7
gcc/fwprop.c
View File

@ -866,10 +866,13 @@ forward_propagate_into (use_info *use, bool reg_prop_only = false)
rtx src = SET_SRC (def_set);
/* Allow propagations into a loop only for reg-to-reg copies, since
replacing one register by another shouldn't increase the cost. */
replacing one register by another shouldn't increase the cost.
Propagations from inner loop to outer loop should also be ok. */
struct loop *def_loop = def_insn->bb ()->cfg_bb ()->loop_father;
struct loop *use_loop = use->bb ()->cfg_bb ()->loop_father;
if ((reg_prop_only || def_loop != use_loop)
if ((reg_prop_only
|| (def_loop != use_loop
&& !flow_loop_nested_p (use_loop, def_loop)))
&& (!reg_single_def_p (dest) || !reg_single_def_p (src)))
return false;

26
gcc/testsuite/g++.target/i386/pr103750-fwprop-1.C Normal file
View File

@ -0,0 +1,26 @@
/* PR target/103750. */
/* { dg-do compile } */
/* { dg-options "-O2 -std=c++1y -march=cannonlake -fdump-rtl-fwprop1" } */
/* { dg-final { scan-rtl-dump-not "subreg:HI\[ \\\(\]*reg:SI\[^\n]*\n\[^\n]*UNSPEC_TZCNT" "fwprop1" } } */
#include<immintrin.h>
const char16_t *qustrchr(char16_t *n, char16_t *e, char16_t c) noexcept
{
__m256i mch256 = _mm256_set1_epi16(c);
for ( ; n < e; n += 32) {
__m256i data1 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(n));
__m256i data2 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(n) + 1);
__mmask16 mask1 = _mm256_cmpeq_epu16_mask(data1, mch256);
__mmask16 mask2 = _mm256_cmpeq_epu16_mask(data2, mch256);
if (_kortestz_mask16_u8(mask1, mask2))
continue;
unsigned idx = _tzcnt_u32(mask1);
if (mask1 == 0) {
idx = __tzcnt_u16(mask2);
n += 16;
}
return n + idx;
}
return e;
}