[X86] Regenerate memcmp tests and add X64-AVX512 common prefix

Should help make the changes in D69157 clearer

llvm-svn: 375215

llvm/test/CodeGen/X86/memcmp.ll

@@ -1,12 +1,12 @@
 ; 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=cmov   | FileCheck %s --check-prefixes=X86,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=+sse   | FileCheck %s --check-prefixes=X86,SSE,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=i686-unknown-unknown -mattr=+sse2  | FileCheck %s --check-prefixes=X86,SSE,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             | FileCheck %s --check-prefixes=X64,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=avx  | FileCheck %s --check-prefixes=X64,X64-AVX,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=avx2 | FileCheck %s --check-prefixes=X64,X64-AVX,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=avx512f | FileCheck %s --check-prefixes=X64,X64-AVX512,X64-AVX512F
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512bw | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512bw | FileCheck %s --check-prefixes=X64,X64-AVX512,X64-AVX512BW
 
 ; This tests codegen time inlining/optimization of memcmp
 ; rdar://6480398
@@ -1007,6 +1007,14 @@ define i1 @length16_eq(i8* %x, i8* %y) nounwind {
 ; X64-AVX-NEXT:    vptest %xmm0, %xmm0
 ; X64-AVX-NEXT:    setne %al
 ; X64-AVX-NEXT:    retq
+;
+; X64-AVX512-LABEL: length16_eq:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX512-NEXT:    vpxor (%rsi), %xmm0, %xmm0
+; X64-AVX512-NEXT:    vptest %xmm0, %xmm0
+; X64-AVX512-NEXT:    setne %al
+; X64-AVX512-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16) nounwind
   %cmp = icmp ne i32 %call, 0
   ret i1 %cmp
@@ -1063,6 +1071,14 @@ define i1 @length16_eq_const(i8* %X) nounwind {
 ; X64-AVX-NEXT:    vptest %xmm0, %xmm0
 ; X64-AVX-NEXT:    sete %al
 ; X64-AVX-NEXT:    retq
+;
+; X64-AVX512-LABEL: length16_eq_const:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX512-NEXT:    vptest %xmm0, %xmm0
+; X64-AVX512-NEXT:    sete %al
+; X64-AVX512-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 16) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
@@ -1147,14 +1163,26 @@ define i1 @length24_eq(i8* %x, i8* %y) nounwind {
 ; X64-AVX-LABEL: length24_eq:
 ; X64-AVX:       # %bb.0:
 ; X64-AVX-NEXT:    vmovdqu (%rdi), %xmm0
-; X64-AVX-NEXT:    vmovq 16(%rdi), %xmm1
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
-; X64-AVX-NEXT:    vmovq 16(%rsi), %xmm2
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
 ; X64-AVX-NEXT:    vpxor %xmm2, %xmm1, %xmm1
 ; X64-AVX-NEXT:    vpxor (%rsi), %xmm0, %xmm0
 ; X64-AVX-NEXT:    vpor %xmm1, %xmm0, %xmm0
 ; X64-AVX-NEXT:    vptest %xmm0, %xmm0
 ; X64-AVX-NEXT:    sete %al
 ; X64-AVX-NEXT:    retq
+;
+; X64-AVX512-LABEL: length24_eq:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX512-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX512-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
+; X64-AVX512-NEXT:    vpxor %xmm2, %xmm1, %xmm1
+; X64-AVX512-NEXT:    vpxor (%rsi), %xmm0, %xmm0
+; X64-AVX512-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; X64-AVX512-NEXT:    vptest %xmm0, %xmm0
+; X64-AVX512-NEXT:    sete %al
+; X64-AVX512-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 24) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
@@ -1213,13 +1241,24 @@ define i1 @length24_eq_const(i8* %X) nounwind {
 ; X64-AVX-LABEL: length24_eq_const:
 ; X64-AVX:       # %bb.0:
 ; X64-AVX-NEXT:    vmovdqu (%rdi), %xmm0
-; X64-AVX-NEXT:    vmovq 16(%rdi), %xmm1
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
 ; X64-AVX-NEXT:    vpxor {{.*}}(%rip), %xmm1, %xmm1
 ; X64-AVX-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
 ; X64-AVX-NEXT:    vpor %xmm1, %xmm0, %xmm0
 ; X64-AVX-NEXT:    vptest %xmm0, %xmm0
 ; X64-AVX-NEXT:    setne %al
 ; X64-AVX-NEXT:    retq
+;
+; X64-AVX512-LABEL: length24_eq_const:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX512-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm1, %xmm1
+; X64-AVX512-NEXT:    vpxor {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX512-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; X64-AVX512-NEXT:    vptest %xmm0, %xmm0
+; X64-AVX512-NEXT:    setne %al
+; X64-AVX512-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 24) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
@@ -1315,11 +1354,20 @@ define i1 @length32_eq(i8* %x, i8* %y) nounwind {
 ; X64-AVX2-LABEL: length32_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
-; X64-AVX2-NEXT:    vpxor   (%rsi), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpxor (%rsi), %ymm0, %ymm0
-; X64-AVX2-NEXT:    vptest  %ymm0, %ymm0
+; X64-AVX2-NEXT:    vptest %ymm0, %ymm0
 ; X64-AVX2-NEXT:    sete %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
+;
+; X64-AVX512-LABEL: length32_eq:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX512-NEXT:    vpxor (%rsi), %ymm0, %ymm0
+; X64-AVX512-NEXT:    vptest %ymm0, %ymm0
+; X64-AVX512-NEXT:    sete %al
+; X64-AVX512-NEXT:    vzeroupper
+; X64-AVX512-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
@@ -1390,6 +1438,17 @@ define i1 @length32_eq_prefer128(i8* %x, i8* %y) nounwind "prefer-vector-width"=
 ; X64-AVX-NEXT:    vptest %xmm0, %xmm0
 ; X64-AVX-NEXT:    sete %al
 ; X64-AVX-NEXT:    retq
+;
+; X64-AVX512-LABEL: length32_eq_prefer128:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX512-NEXT:    vmovdqu 16(%rdi), %xmm1
+; X64-AVX512-NEXT:    vpxor 16(%rsi), %xmm1, %xmm1
+; X64-AVX512-NEXT:    vpxor (%rsi), %xmm0, %xmm0
+; X64-AVX512-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; X64-AVX512-NEXT:    vptest %xmm0, %xmm0
+; X64-AVX512-NEXT:    sete %al
+; X64-AVX512-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
@@ -1464,6 +1523,15 @@ define i1 @length32_eq_const(i8* %X) nounwind {
 ; X64-AVX2-NEXT:    setne %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
+;
+; X64-AVX512-LABEL: length32_eq_const:
+; X64-AVX512:       # %bb.0:
+; X64-AVX512-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX512-NEXT:    vpxor {{.*}}(%rip), %ymm0, %ymm0
+; X64-AVX512-NEXT:    vptest %ymm0, %ymm0
+; X64-AVX512-NEXT:    setne %al
+; X64-AVX512-NEXT:    vzeroupper
+; X64-AVX512-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 32) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
@@ -1666,7 +1734,6 @@ define i1 @huge_length_eq(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    sete %al
 ; X64-NEXT:    popq %rcx
 ; X64-NEXT:    retq
-
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 9223372036854775807) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c