From: Hongyu Wang <hongyu.wang@intel.com>
Date: Tue, 6 Dec 2022 01:53:35 +0000 (+0800)
Subject: i386: Avoid fma_chain for -march=alderlake and sapphirerapids.
X-Git-Tag: basepoints/gcc-14~2673
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3a1a141f79c83ad38f7db3a21d8a4dcfe625c176;p=thirdparty%2Fgcc.git

i386: Avoid fma_chain for -march=alderlake and sapphirerapids.

For Alderlake there is similar issue like PR 81616, enable
avoid_fma256_chain will also benefit on Intel latest platforms
Alderlake and Sapphire Rapids.

gcc/ChangeLog:

	* config/i386/x86-tune.def (X86_TUNE_AVOID_256FMA_CHAINS): Add
	m_SAPPHIRERAPIDS, m_ALDERLAKE and m_CORE_ATOM.
---

diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index cd66f3351137..db85de20bae1 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -499,7 +499,8 @@ DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER)
 
 /* X86_TUNE_AVOID_256FMA_CHAINS: Avoid creating loops with tight 256bit or
    smaller FMA chain.  */
-DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 | m_ZNVER3)
+DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 | m_ZNVER3
+	  | m_ALDERLAKE | m_SAPPHIRERAPIDS | m_CORE_ATOM)
 
 /* X86_TUNE_V2DF_REDUCTION_PREFER_PHADDPD: Prefer haddpd
    for v2df vector reduction.  */