From f762c7b32f33f9fe984c229c9fe7f178ba657c95 Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Tue, 24 Oct 2017 15:27:47 +0000
Subject: [PATCH] [x86] add more vector ISA variants for memcmp expansion; NFC

...because every swiss cheese has different holes.

llvm-svn: 316446
---
 llvm/test/CodeGen/X86/memcmp.ll | 66 +++++++++++++++++++++++++++++++--
 1 file changed, 62 insertions(+), 4 deletions(-)

diff --git a/llvm/test/CodeGen/X86/memcmp.ll b/llvm/test/CodeGen/X86/memcmp.ll
index a269529b646c..b4d5148f046b 100644
--- a/llvm/test/CodeGen/X86/memcmp.ll
+++ b/llvm/test/CodeGen/X86/memcmp.ll
@@ -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) nounwind {
 ; 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) nounwind {
 ; 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) nounwind {
 ; 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) nounwind {
 ; 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