mirror/gcc
2
0
Fork 0
mirror of git://gcc.gnu.org/git/gcc.git synced 2025-04-19 22:31:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

[AArch64] PR84114: Avoid reassociating FMA

Browse Source 
As discussed in the PR, the reassociation phase runs before FMAs are formed
and so can significantly reduce FMA opportunities.  Although reassociation
could be switched off, it helps in many cases, so a better alternative is to
only avoid reassociation of floating point additions.  This fixes the testcase
and gives 1% speedup on SPECFP2017, fixing the performance regression.

    gcc/
	PR tree-optimization/84114
	* config/aarch64/aarch64.c (aarch64_reassociation_width)
	Avoid reassociation of FLOAT_MODE addition.

From-SVN: r258248
This commit is contained in:
Wilco Dijkstra 2018-03-05 14:40:55 +00:00 committed by Wilco Dijkstra
parent 13b93d4b89
commit b5b33e1134
2 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gcc/ChangeLog
View File

@ -1,3 +1,9 @@
2018-03-05 Wilco Dijkstra <wdijkstr@arm.com>
PR tree-optimization/84114
* config/aarch64/aarch64.c (aarch64_reassociation_width)
Avoid reassociation of FLOAT_MODE addition.
2018-03-05 Olga Makhotina <olga.makhotina@intel.com>
* common/config/i386/i386-common.c (OPTION_MASK_ISA_PCONFIG_SET,

7
gcc/config/aarch64/aarch64.c
View File

@ -1094,15 +1094,16 @@ aarch64_min_divisions_for_recip_mul (machine_mode mode)
return aarch64_tune_params.min_div_recip_mul_df;
}
/* Return the reassociation width of treeop OPC with mode MODE. */
static int
aarch64_reassociation_width (unsigned opc ATTRIBUTE_UNUSED,
machine_mode mode)
aarch64_reassociation_width (unsigned opc, machine_mode mode)
{
if (VECTOR_MODE_P (mode))
return aarch64_tune_params.vec_reassoc_width;
if (INTEGRAL_MODE_P (mode))
return aarch64_tune_params.int_reassoc_width;
if (FLOAT_MODE_P (mode))
/* Avoid reassociating floating point addition so we emit more FMAs. */
if (FLOAT_MODE_P (mode) && opc != PLUS_EXPR)
return aarch64_tune_params.fp_reassoc_width;
return 1;
}