[x86] add test/run for mayLoadFold with alignment; NFC

This commit is contained in:
Sanjay Patel 2021-10-26 10:44:19 -04:00
parent 622150ad5f
commit 4f423e9127
1 changed files with 34 additions and 1 deletions
llvm/test/CodeGen/X86

View File

@ -1,6 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-unknown -mattr=+sse2,+ssse3 | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2,+ssse3 | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2,+ssse3 | FileCheck %s --check-prefixes=X64,ALIGN
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2,+ssse3,sse-unaligned-mem | FileCheck %s --check-prefixes=X64,UNALIGN
; There are no MMX operations in @t1
@ -92,6 +93,38 @@ define <4 x float> @t4(<4 x float>* %P) nounwind {
ret <4 x float> %tmp2
}
define <4 x float> @t4_under_aligned(<4 x float>* %P) nounwind {
; X32-LABEL: t4_under_aligned:
; X32: # %bb.0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movups (%eax), %xmm1
; X32-NEXT: xorps %xmm2, %xmm2
; X32-NEXT: xorps %xmm0, %xmm0
; X32-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],xmm1[3,0]
; X32-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[2,3]
; X32-NEXT: retl
;
; ALIGN-LABEL: t4_under_aligned:
; ALIGN: # %bb.0:
; ALIGN-NEXT: movups (%rdi), %xmm1
; ALIGN-NEXT: xorps %xmm2, %xmm2
; ALIGN-NEXT: xorps %xmm0, %xmm0
; ALIGN-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],xmm1[3,0]
; ALIGN-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[2,3]
; ALIGN-NEXT: retq
;
; UNALIGN-LABEL: t4_under_aligned:
; UNALIGN: # %bb.0:
; UNALIGN-NEXT: xorps %xmm1, %xmm1
; UNALIGN-NEXT: xorps %xmm0, %xmm0
; UNALIGN-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],mem[3,0]
; UNALIGN-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm1[2,3]
; UNALIGN-NEXT: retq
%tmp1 = load <4 x float>, <4 x float>* %P, align 4
%tmp2 = shufflevector <4 x float> zeroinitializer, <4 x float> %tmp1, <4 x i32> < i32 7, i32 0, i32 0, i32 0 >
ret <4 x float> %tmp2
}
define <16 x i8> @t5(<16 x i8> %x) nounwind {
; X32-LABEL: t5:
; X32: # %bb.0: