[llvm] r316446 - [x86] add more vector ISA variants for memcmp expansion; NFC

[Sanjay Patel via llvm-commits]

Author: spatel
Date: Tue Oct 24 08:27:47 2017
New Revision: 316446

URL: http://llvm.org/viewvc/llvm-project?rev=316446&view=rev
Log:
[x86] add more vector ISA variants for memcmp expansion; NFC

...because every swiss cheese has different holes.

Modified:
    llvm/trunk/test/CodeGen/X86/memcmp.ll

Modified: llvm/trunk/test/CodeGen/X86/memcmp.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/memcmp.ll?rev=316446&r1=316445&r2=316446&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/memcmp.ll (original)
+++ llvm/trunk/test/CodeGen/X86/memcmp.ll Tue Oct 24 08:27:47 2017
@@ -1,8 +1,10 @@
 ; 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=+sse2 | FileCheck %s --check-prefix=X86 --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=avx2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX2
+; 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
 
 ; This tests codegen time inlining/optimization of memcmp
 ; rdar://6480398
@@ -584,6 +586,18 @@ define i1 @length16_eq(i8* %x, i8* %y) n
 ; X86-NOSSE-NEXT:    setne %al
 ; X86-NOSSE-NEXT:    retl
 ;
+; X86-SSE1-LABEL: length16_eq:
+; X86-SSE1:       # BB#0:
+; X86-SSE1-NEXT:    pushl $0
+; X86-SSE1-NEXT:    pushl $16
+; X86-SSE1-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT:    calll memcmp
+; X86-SSE1-NEXT:    addl $16, %esp
+; X86-SSE1-NEXT:    testl %eax, %eax
+; X86-SSE1-NEXT:    setne %al
+; X86-SSE1-NEXT:    retl
+;
 ; X86-SSE2-LABEL: length16_eq:
 ; X86-SSE2:       # BB#0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
@@ -630,6 +644,18 @@ define i1 @length16_eq_const(i8* %X) nou
 ; X86-NOSSE-NEXT:    sete %al
 ; X86-NOSSE-NEXT:    retl
 ;
+; X86-SSE1-LABEL: length16_eq_const:
+; X86-SSE1:       # BB#0:
+; X86-SSE1-NEXT:    pushl $0
+; X86-SSE1-NEXT:    pushl $16
+; X86-SSE1-NEXT:    pushl $.L.str
+; X86-SSE1-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT:    calll memcmp
+; X86-SSE1-NEXT:    addl $16, %esp
+; X86-SSE1-NEXT:    testl %eax, %eax
+; X86-SSE1-NEXT:    sete %al
+; X86-SSE1-NEXT:    retl
+;
 ; X86-SSE2-LABEL: length16_eq_const:
 ; X86-SSE2:       # BB#0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
@@ -781,6 +807,22 @@ define i1 @length32_eq(i8* %x, i8* %y) n
 ; X64-SSE2-NEXT:    popq %rcx
 ; X64-SSE2-NEXT:    retq
 ;
+; X64-AVX1-LABEL: length32_eq:
+; X64-AVX1:       # BB#0:
+; X64-AVX1-NEXT:    movq 16(%rdi), %rax
+; X64-AVX1-NEXT:    movq (%rdi), %rcx
+; X64-AVX1-NEXT:    movq 8(%rdi), %rdx
+; X64-AVX1-NEXT:    movq 24(%rdi), %rdi
+; X64-AVX1-NEXT:    xorq 24(%rsi), %rdi
+; X64-AVX1-NEXT:    xorq 8(%rsi), %rdx
+; X64-AVX1-NEXT:    orq %rdi, %rdx
+; X64-AVX1-NEXT:    xorq 16(%rsi), %rax
+; X64-AVX1-NEXT:    xorq (%rsi), %rcx
+; X64-AVX1-NEXT:    orq %rax, %rcx
+; X64-AVX1-NEXT:    orq %rdx, %rcx
+; X64-AVX1-NEXT:    sete %al
+; X64-AVX1-NEXT:    retq
+;
 ; X64-AVX2-LABEL: length32_eq:
 ; X64-AVX2:       # BB#0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
@@ -819,6 +861,22 @@ define i1 @length32_eq_const(i8* %X) nou
 ; X64-SSE2-NEXT:    popq %rcx
 ; X64-SSE2-NEXT:    retq
 ;
+; X64-AVX1-LABEL: length32_eq_const:
+; X64-AVX1:       # BB#0:
+; X64-AVX1-NEXT:    movabsq $3544395820347831604, %rax # imm = 0x3130393837363534
+; X64-AVX1-NEXT:    xorq 24(%rdi), %rax
+; X64-AVX1-NEXT:    movabsq $3833745473465760056, %rcx # imm = 0x3534333231303938
+; X64-AVX1-NEXT:    xorq 8(%rdi), %rcx
+; X64-AVX1-NEXT:    orq %rax, %rcx
+; X64-AVX1-NEXT:    movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-AVX1-NEXT:    xorq 16(%rdi), %rax
+; X64-AVX1-NEXT:    movabsq $3978425819141910832, %rdx # imm = 0x3736353433323130
+; X64-AVX1-NEXT:    xorq (%rdi), %rdx
+; X64-AVX1-NEXT:    orq %rax, %rdx
+; X64-AVX1-NEXT:    orq %rcx, %rdx
+; X64-AVX1-NEXT:    setne %al
+; X64-AVX1-NEXT:    retq
+;
 ; X64-AVX2-LABEL: length32_eq_const:
 ; X64-AVX2:       # BB#0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0