From: Di Zhao OS Date: Thu, 22 Jun 2023 14:16:57 +0000 (+0100) Subject: Change fma_reassoc_width tuning for ampere1 X-Git-Tag: basepoints/gcc-15~8106 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=4ced8363622b31910cda61796a28fe2cbf70faa7;p=thirdparty%2Fgcc.git Change fma_reassoc_width tuning for ampere1 This patch enables reassociation of floating-point additions on ampere1. This brings about 1% overall benefit on spec2017 fprate cases. (There are minor regressions in 510.parest_r and 508.namd_r, analyzed here: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110279 .) gcc/ChangeLog: * config/aarch64/aarch64.cc: Change fma_reassoc_width for ampere1. --- diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc index b99f12c99e9e..644ebdebc0e0 100644 --- a/gcc/config/aarch64/aarch64.cc +++ b/gcc/config/aarch64/aarch64.cc @@ -1929,7 +1929,7 @@ static const struct tune_params ampere1_tunings = "32:16", /* loop_align. */ 2, /* int_reassoc_width. */ 4, /* fp_reassoc_width. */ - 1, /* fma_reassoc_width. */ + 4, /* fma_reassoc_width. */ 2, /* vec_reassoc_width. */ 2, /* min_div_recip_mul_sf. */ 2, /* min_div_recip_mul_df. */