maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

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

...because every swiss cheese has different holes.

llvm-svn: 316446
This commit is contained in:
Sanjay Patel 2017-10-24 15:27:47 +00:00
parent 25bd602b7a
commit f762c7b32f
1 changed files with 62 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
llvm/test/CodeGen/X86/memcmp.ll
View File

@ -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