From 3217e694854fe50be13091f071283f47aad9b348 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Thu, 31 May 2018 15:37:22 +0000 Subject: [PATCH] x86: Re-enable partial_reg_dependency and movx for Haswell r254152 disabled partial_reg_dependency and movx for Haswell and newer Intel processors. r258972 restored them for skylake-avx512. For Haswell, movx improves performance. But partial_reg_stall may be better than partial_reg_dependency in theory. We will investigate performance impact of partial_reg_stall vs partial_reg_dependency on Haswell for GCC 9. In the meantime, this patch restores both partial_reg_dependency and mox for Haswell in GCC 8. On Haswell, improvements for EEMBC benchmarks with -mtune-ctrl=movx,partial_reg_dependency -Ofast -march=haswell vs -Ofast -mtune=haswell are automotive ========= aifftr01 (default) - goodperf: Runtime improvement of 2.6% (time). aiifft01 (default) - goodperf: Runtime improvement of 2.2% (time). networking ========= ip_pktcheckb1m (default) - goodperf: Runtime improvement of 3.8% (time). ip_pktcheckb2m (default) - goodperf: Runtime improvement of 5.2% (time). ip_pktcheckb4m (default) - goodperf: Runtime improvement of 4.4% (time). ip_pktcheckb512k (default) - goodperf: Runtime improvement of 4.2% (time). telecom ========= fft00data_1 (default) - goodperf: Runtime improvement of 8.4% (time). fft00data_2 (default) - goodperf: Runtime improvement of 8.6% (time). fft00data_3 (default) - goodperf: Runtime improvement of 9.0% (time). PR target/85829 * config/i386/x86-tune.def: Re-enable partial_reg_dependency and movx for Haswell. From-SVN: r261028 --- gcc/ChangeLog | 6 ++++++ gcc/config/i386/x86-tune.def | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index c9cf570..36c7a86 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,9 @@ +2018-05-31 H.J. Lu + + PR target/85829 + * config/i386/x86-tune.def: Re-enable partial_reg_dependency + and movx for Haswell. + 2018-05-31 Chung-Lin Tang Cesar Philippidis diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def index 77d9934..f95c070 100644 --- a/gcc/config/i386/x86-tune.def +++ b/gcc/config/i386/x86-tune.def @@ -49,7 +49,7 @@ DEF_TUNE (X86_TUNE_SCHEDULE, "schedule", over partial stores. For example preffer MOVZBL or MOVQ to load 8bit value over movb. */ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency", - m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE + m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL | m_KNL | m_KNM | m_AMD_MULTIPLE | m_SKYLAKE_AVX512 | m_GENERIC) @@ -87,7 +87,7 @@ DEF_TUNE (X86_TUNE_MOVX, "movx", m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_KNL | m_KNM | m_INTEL | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_SKYLAKE_AVX512 - | m_GENERIC) + | m_HASWELL | m_GENERIC) /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by full sized loads. */ -- 2.7.4