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.
OK for GCC 8? H.J. --- PR target/85829 * config/i386/x86-tune.def: Re-enable partial_reg_dependency and movx for Haswell. --- gcc/config/i386/x86-tune.def | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def index 5649fdcf416..60625668236 100644 --- a/gcc/config/i386/x86-tune.def +++ b/gcc/config/i386/x86-tune.def @@ -48,7 +48,7 @@ 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_INTEL | m_KNL | m_KNM | m_AMD_MULTIPLE | m_SKYLAKE_AVX512 | m_GENERIC) @@ -84,7 +84,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_FLAG_REG_STALL, "partial_flag_reg_stall", partial dependencies. */ DEF_TUNE (X86_TUNE_MOVX, "movx", m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE - | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL + | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_HASWELL | m_GEODE | m_AMD_MULTIPLE | m_SKYLAKE_AVX512 | m_GENERIC) /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by -- 2.17.0