diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86Subtarget.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86Subtarget.cpp | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/llvm/lib/Target/X86/X86Subtarget.cpp b/llvm/lib/Target/X86/X86Subtarget.cpp index 8543d189cdb..0f995404618 100644 --- a/llvm/lib/Target/X86/X86Subtarget.cpp +++ b/llvm/lib/Target/X86/X86Subtarget.cpp @@ -270,14 +270,13 @@ void X86Subtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) { isTargetKFreeBSD() || In64BitMode) stackAlignment = 16; - // Gather is available since Haswell (AVX2 set). So technically, we can - // generate Gathers on all AVX2 processors. But the overhead on HSW is high. - // Skylake Client processor has faster Gathers than HSW and performance is - // similar to Skylake Server (AVX-512). The specified overhead is relative to - // the Load operation. "2" is the number provided by Intel architects. This + // Some CPUs have more overhead for gather. The specified overhead is relative + // to the Load operation. "2" is the number provided by Intel architects. This // parameter is used for cost estimation of Gather Op and comparison with // other alternatives. - if (X86ProcFamily == IntelSkylake || hasAVX512()) + // TODO: Remove the explicit hasAVX512()?, That would mean we would only + // enable gather with a -march. + if (hasAVX512() || (hasAVX2() && hasFastGather())) GatherOverhead = 2; if (hasAVX512()) ScatterOverhead = 2; @@ -345,6 +344,7 @@ void X86Subtarget::initializeEnvironment() { HasCmpxchg16b = false; UseLeaForSP = false; HasFastPartialYMMorZMMWrite = false; + HasFastGather = false; HasFastScalarFSQRT = false; HasFastVectorFSQRT = false; HasFastLZCNT = false; |
