llvm-project/llvm/test/CodeGen/X86/sse4a-upgrade.ll

40 lines
1.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=+sse4a | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=+sse4a,+avx | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4a | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4a,+avx | FileCheck %s --check-prefix=X64
define void @test_movntss(i8* %p, <4 x float> %a) nounwind optsize ssp {
; X32-LABEL: test_movntss:
; X32: # %bb.0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movntss %xmm0, (%eax)
; X32-NEXT: retl
;
; X64-LABEL: test_movntss:
; X64: # %bb.0:
; X64-NEXT: movntss %xmm0, (%rdi)
; X64-NEXT: retq
tail call void @llvm.x86.sse4a.movnt.ss(i8* %p, <4 x float> %a) nounwind
ret void
}
declare void @llvm.x86.sse4a.movnt.ss(i8*, <4 x float>)
define void @test_movntsd(i8* %p, <2 x double> %a) nounwind optsize ssp {
; X32-LABEL: test_movntsd:
; X32: # %bb.0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movntsd %xmm0, (%eax)
; X32-NEXT: retl
;
; X64-LABEL: test_movntsd:
; X64: # %bb.0:
; X64-NEXT: movntsd %xmm0, (%rdi)
; X64-NEXT: retq
tail call void @llvm.x86.sse4a.movnt.sd(i8* %p, <2 x double> %a) nounwind
ret void
}
declare void @llvm.x86.sse4a.movnt.sd(i8*, <2 x double>)