Enable AVX512 memcmp()

[davezarzycki]

Summary

Unless I'm missing something, the "TODO" is stale.

[craig.topper]

LGTM

[davezarzycki]

r373706

lib/Target/X86/X86TargetTransformInfo.cpp

 X86TTIImpl::TTI::MemCmpExpansionOptions
 X86TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
   TTI::MemCmpExpansionOptions Options;
   Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
   Options.NumLoadsPerBlock = 2;
   if (IsZeroCmp) {
     // Only enable vector loads for equality comparison. Right now the vector
     // version is not as fast for three way compare (see #33329).
-    // TODO: enable AVX512 when the DAG is ready.
-    // if (ST->hasAVX512()) Options.LoadSizes.push_back(64);
     const unsigned PreferredWidth = ST->getPreferVectorWidth();
+    if (PreferredWidth >= 512 && ST->hasAVX512()) Options.LoadSizes.push_back(64);
     if (PreferredWidth >= 256 && ST->hasAVX2()) Options.LoadSizes.push_back(32);
     if (PreferredWidth >= 128 && ST->hasSSE2()) Options.LoadSizes.push_back(16);
     // All GPR and vector loads can be unaligned. SIMD compare requires integer
     // vectors (SSE2/AVX2).
     Options.AllowOverlappingLoads = true;
   }
   if (ST->is64Bit()) {
     Options.LoadSizes.push_back(8);

test/CodeGen/X86/memcmp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=cmov   | FileCheck %s --check-prefix=X86 --check-prefix=X86-NOSSE
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse   | FileCheck %s --check-prefix=X86 --check-prefix=SSE --check-prefix=X86-SSE1
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2  | FileCheck %s --check-prefix=X86 --check-prefix=SSE --check-prefix=X86-SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown             | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx  | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX512F
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512bw | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX512F --check-prefix=X64-AVX512BW
 
 ; This tests codegen time inlining/optimization of memcmp
 ; rdar://6480398
 
 @.str = private constant [65 x i8] c"0123456789012345678901234567890123456789012345678901234567890123\00", align 1
 
 declare i32 @memcmp(i8*, i8*, i64)
 

 ; X64-AVX2-NEXT:    vpcmpeqb 32(%rsi), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
 ; X64-AVX2-NEXT:    setne %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
+;
+; X64-AVX512F-LABEL: length64_eq:
+; X64-AVX512F:       # %bb.0:
+; X64-AVX512F-NEXT:    vmovdqu64 (%rdi), %zmm0
+; X64-AVX512F-NEXT:    vpcmpeqd (%rsi), %zmm0, %k0
+; X64-AVX512F-NEXT:    kortestw %k0, %k0
+; X64-AVX512F-NEXT:    setae %al
+; X64-AVX512F-NEXT:    vzeroupper
+; X64-AVX512F-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 64) nounwind
   %cmp = icmp ne i32 %call, 0
   ret i1 %cmp
 }
 
 define i1 @length64_eq_const(i8* %X) nounwind {
 ; X86-LABEL: length64_eq_const:
 ; X86:       # %bb.0:

 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
 ; X64-AVX2-NEXT:    sete %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
+;
+; X64-AVX512F-LABEL: length64_eq_const:
+; X64-AVX512F:       # %bb.0:
+; X64-AVX512F-NEXT:    vmovdqu64 (%rdi), %zmm0
+; X64-AVX512F-NEXT:    vpcmpeqd {{.*}}(%rip), %zmm0, %k0
+; X64-AVX512F-NEXT:    kortestw %k0, %k0
+; X64-AVX512F-NEXT:    setb %al
+; X64-AVX512F-NEXT:    vzeroupper
+; X64-AVX512F-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 64) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 
 ; This checks that we do not do stupid things with huge sizes.
 define i32 @huge_length(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: huge_length: