forked from OSchip/llvm-project
111 lines
5.0 KiB
LLVM
111 lines
5.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin8.7.2 -mattr=+sse,+sse2,+sse4.1 | FileCheck %s
|
|
|
|
target datalayout = "e-p:32:32"
|
|
|
|
define i16 @test1(float %f) nounwind {
|
|
; CHECK-LABEL: test1:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; CHECK-NEXT: xorps %xmm1, %xmm1
|
|
; CHECK-NEXT: subss LCPI0_0, %xmm0
|
|
; CHECK-NEXT: mulss LCPI0_1, %xmm0
|
|
; CHECK-NEXT: minss LCPI0_2, %xmm0
|
|
; CHECK-NEXT: maxss %xmm1, %xmm0
|
|
; CHECK-NEXT: cvttss2si %xmm0, %eax
|
|
; CHECK-NEXT: retl
|
|
%tmp = insertelement <4 x float> undef, float %f, i32 0 ; <<4 x float>> [#uses=1]
|
|
%tmp10 = insertelement <4 x float> %tmp, float 0.000000e+00, i32 1 ; <<4 x float>> [#uses=1]
|
|
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 2 ; <<4 x float>> [#uses=1]
|
|
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, i32 3 ; <<4 x float>> [#uses=1]
|
|
%tmp28 = tail call <4 x float> @llvm.x86.sse.sub.ss( <4 x float> %tmp12, <4 x float> < float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
|
|
%tmp37 = tail call <4 x float> @llvm.x86.sse.mul.ss( <4 x float> %tmp28, <4 x float> < float 5.000000e-01, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
|
|
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp37, <4 x float> < float 6.553500e+04, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
|
|
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> zeroinitializer ) ; <<4 x float>> [#uses=1]
|
|
%tmp.upgrd.1 = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
|
|
%tmp69 = trunc i32 %tmp.upgrd.1 to i16 ; <i16> [#uses=1]
|
|
ret i16 %tmp69
|
|
}
|
|
|
|
define i16 @test2(float %f) nounwind {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; CHECK-NEXT: addss LCPI1_0, %xmm0
|
|
; CHECK-NEXT: mulss LCPI1_1, %xmm0
|
|
; CHECK-NEXT: minss LCPI1_2, %xmm0
|
|
; CHECK-NEXT: xorps %xmm1, %xmm1
|
|
; CHECK-NEXT: maxss %xmm1, %xmm0
|
|
; CHECK-NEXT: cvttss2si %xmm0, %eax
|
|
; CHECK-NEXT: retl
|
|
%tmp28 = fsub float %f, 1.000000e+00 ; <float> [#uses=1]
|
|
%tmp37 = fmul float %tmp28, 5.000000e-01 ; <float> [#uses=1]
|
|
%tmp375 = insertelement <4 x float> undef, float %tmp37, i32 0 ; <<4 x float>> [#uses=1]
|
|
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp375, <4 x float> < float 6.553500e+04, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
|
|
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> < float 0.000000e+00, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
|
|
%tmp = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
|
|
%tmp69 = trunc i32 %tmp to i16 ; <i16> [#uses=1]
|
|
ret i16 %tmp69
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>)
|
|
|
|
declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>)
|
|
|
|
declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>)
|
|
|
|
declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>)
|
|
|
|
declare i32 @llvm.x86.sse.cvttss2si(<4 x float>)
|
|
|
|
declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32)
|
|
|
|
declare <4 x float> @f()
|
|
|
|
define <4 x float> @test3(<4 x float> %A, float *%b, i32 %C) nounwind {
|
|
; CHECK-LABEL: test3:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; CHECK-NEXT: roundss $4, (%eax), %xmm0
|
|
; CHECK-NEXT: retl
|
|
%a = load float , float *%b
|
|
%B = insertelement <4 x float> undef, float %a, i32 0
|
|
%X = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %A, <4 x float> %B, i32 4)
|
|
ret <4 x float> %X
|
|
}
|
|
|
|
define <4 x float> @test4(<4 x float> %A, float *%b, i32 %C) nounwind {
|
|
; CHECK-LABEL: test4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: subl $28, %esp
|
|
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; CHECK-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; CHECK-NEXT: movaps %xmm0, (%esp) ## 16-byte Spill
|
|
; CHECK-NEXT: calll L_f$stub
|
|
; CHECK-NEXT: movaps (%esp), %xmm1 ## 16-byte Reload
|
|
; CHECK-NEXT: roundss $4, %xmm1, %xmm0
|
|
; CHECK-NEXT: addl $28, %esp
|
|
; CHECK-NEXT: retl
|
|
%a = load float , float *%b
|
|
%B = insertelement <4 x float> undef, float %a, i32 0
|
|
%q = call <4 x float> @f()
|
|
%X = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %q, <4 x float> %B, i32 4)
|
|
ret <4 x float> %X
|
|
}
|
|
|
|
; PR13576
|
|
define <2 x double> @test5() nounwind uwtable readnone noinline {
|
|
; CHECK-LABEL: test5:
|
|
; CHECK: ## BB#0: ## %entry
|
|
; CHECK-NEXT: movaps {{.*#+}} xmm0 = [4.569870e+02,1.233210e+02]
|
|
; CHECK-NEXT: movl $128, %eax
|
|
; CHECK-NEXT: cvtsi2sdl %eax, %xmm0
|
|
; CHECK-NEXT: retl
|
|
entry:
|
|
%0 = tail call <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double> <double
|
|
4.569870e+02, double 1.233210e+02>, i32 128) nounwind readnone
|
|
ret <2 x double> %0
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double>, i32) nounwind readnone
|