From 2aa97c0da4a62d3cf41942e8803d049dee4fcf13 Mon Sep 17 00:00:00 2001 From: Haochen Jiang Date: Mon, 16 Oct 2023 13:51:02 +0800 Subject: x86: Add m_CORE_HYBRID for hybrid clients tuning gcc/Changelog: * config/i386/i386-options.cc (m_CORE_HYBRID): New. * config/i386/x86-tune.def: Replace hybrid client tune to m_CORE_HYBRID. --- gcc/config/i386/i386-options.cc | 1 + gcc/config/i386/x86-tune.def | 113 ++++++++++++++++++---------------------- 2 files changed, 52 insertions(+), 62 deletions(-) diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc index 1d28258..952cfe5 100644 --- a/gcc/config/i386/i386-options.cc +++ b/gcc/config/i386/i386-options.cc @@ -143,6 +143,7 @@ along with GCC; see the file COPYING3. If not see #define m_ARROWLAKE_S (HOST_WIDE_INT_1U<> (W-1) ^ x) - @@ -386,8 +381,7 @@ DEF_TUNE (X86_TUNE_USE_SIMODE_FIOP, "use_simode_fiop", ~(m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_AMD_MULTIPLE | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT - | m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM - | m_GENERIC)) + | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC)) /* X86_TUNE_USE_FFREEP: Use freep instruction instead of fstp. */ DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI) @@ -396,8 +390,8 @@ DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI) DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_LUJIAZUI - | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE | m_ARROWLAKE - | m_ARROWLAKE_S | m_CORE_ATOM | m_GENERIC) + | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID + | m_CORE_ATOM | m_GENERIC) /*****************************************************************************/ /* SSE instruction selection tuning */ @@ -412,17 +406,16 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill", of a sequence loading registers by parts. */ DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM - | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM | m_AMDFAM10 | m_BDVER - | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GENERIC) + | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID + | m_CORE_ATOM | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI + | m_GENERIC) /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores instead of a sequence loading registers by parts. */ DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM - | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S| m_CORE_ATOM | m_BDVER | m_ZNVER - | m_LUJIAZUI | m_GENERIC) + | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID + | m_CORE_ATOM | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC) /* X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL: Use packed single precision 128bit instructions instead of double where possible. */ @@ -431,15 +424,14 @@ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optim /* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores. */ DEF_TUNE (X86_TUNE_SSE_TYPELESS_STORES, "sse_typeless_stores", - m_AMD_MULTIPLE | m_LUJIAZUI | m_CORE_ALL | m_TREMONT | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM | m_GENERIC) + m_AMD_MULTIPLE | m_LUJIAZUI | m_CORE_ALL | m_TREMONT | m_CORE_HYBRID + | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SSE_LOAD0_BY_PXOR: Always use pxor to load0 as opposed to xorps/xorpd and other variants. */ DEF_TUNE (X86_TUNE_SSE_LOAD0_BY_PXOR, "sse_load0_by_pxor", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BDVER | m_BTVER | m_ZNVER - | m_LUJIAZUI | m_TREMONT | m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S - | m_CORE_ATOM | m_GENERIC) + | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_INTER_UNIT_MOVES_TO_VEC: Enable moves in from integer to SSE registers. If disabled, the moves will be done by storing @@ -485,14 +477,14 @@ DEF_TUNE (X86_TUNE_SLOW_PSHUFB, "slow_pshufb", /* X86_TUNE_AVOID_4BYTE_PREFIXES: Avoid instructions requiring 4+ bytes of prefixes. */ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes", - m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM | m_INTEL) + m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID + | m_CORE_ATOM | m_INTEL) /* X86_TUNE_USE_GATHER_2PARTS: Use gather instructions for vectors with 2 elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts", - ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM | m_GENERIC | m_GDS)) + ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_CORE_HYBRID + | m_CORE_ATOM | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER_2PARTS: Use scater instructions for vectors with 2 elements. */ @@ -502,8 +494,8 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_2PARTS, "use_scatter_2parts", /* X86_TUNE_USE_GATHER_4PARTS: Use gather instructions for vectors with 4 elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts", - ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE - | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_ATOM | m_GENERIC | m_GDS)) + ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_CORE_HYBRID + | m_CORE_ATOM | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER_4PARTS: Use scater instructions for vectors with 4 elements. */ @@ -513,8 +505,8 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_4PARTS, "use_scatter_4parts", /* X86_TUNE_USE_GATHER: Use gather instructions for vectors with 8 or more elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_8PARTS, "use_gather_8parts", - ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_ALDERLAKE | m_ARROWLAKE - | m_ARROWLAKE_S | m_CORE_ATOM | m_GENERIC | m_GDS)) + ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_CORE_HYBRID | m_CORE_ATOM + | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER: Use scater instructions for vectors with 8 or more elements. */ @@ -528,8 +520,7 @@ DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 | m_ZNVER2 /* 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 - | m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S | m_SAPPHIRERAPIDS - | m_CORE_ATOM) + | m_CORE_HYBRID | m_SAPPHIRERAPIDS | m_CORE_ATOM) /* X86_TUNE_AVOID_512FMA_CHAINS: Avoid creating loops with tight 512bit or smaller FMA chain. */ @@ -573,14 +564,12 @@ DEF_TUNE (X86_TUNE_AVX512_SPLIT_REGS, "avx512_split_regs", m_ZNVER4) /* X86_TUNE_AVX256_MOVE_BY_PIECES: Optimize move_by_pieces with 256-bit AVX instructions. */ DEF_TUNE (X86_TUNE_AVX256_MOVE_BY_PIECES, "avx256_move_by_pieces", - m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_AVX2 | m_ZNVER1 - | m_ZNVER2 | m_ZNVER3) + m_CORE_HYBRID | m_CORE_AVX2 | m_ZNVER1 | m_ZNVER2 | m_ZNVER3) /* X86_TUNE_AVX256_STORE_BY_PIECES: Optimize store_by_pieces with 256-bit AVX instructions. */ DEF_TUNE (X86_TUNE_AVX256_STORE_BY_PIECES, "avx256_store_by_pieces", - m_ALDERLAKE | m_ARROWLAKE | m_ARROWLAKE_S | m_CORE_AVX2 | m_ZNVER1 - | m_ZNVER2 | m_ZNVER3) + m_CORE_HYBRID | m_CORE_AVX2 | m_ZNVER1 | m_ZNVER2 | m_ZNVER3) /* X86_TUNE_AVX512_MOVE_BY_PIECES: Optimize move_by_pieces with 512-bit AVX instructions. */ -- cgit v1.1