1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
|
; RUN: opt < %s -instcombine -S | FileCheck %s
define i16 @test1(float %f) {
entry:
; CHECK: @test1
; CHECK: fmul float
; CHECK-NOT: insertelement {{.*}} 0.00
; CHECK-NOT: call {{.*}} @llvm.x86.sse.mul
; CHECK-NOT: call {{.*}} @llvm.x86.sse.sub
; CHECK: ret
%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 i32 @test2(float %f) {
; CHECK: @test2
; CHECK-NOT: insertelement
; CHECK-NOT: extractelement
; CHECK: ret
%tmp5 = fmul float %f, %f
%tmp9 = insertelement <4 x float> undef, float %tmp5, i32 0
%tmp10 = insertelement <4 x float> %tmp9, float 0.000000e+00, i32 1
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 2
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, i32 3
%tmp19 = bitcast <4 x float> %tmp12 to <4 x i32>
%tmp21 = extractelement <4 x i32> %tmp19, i32 0
ret i32 %tmp21
}
define void @get_image() nounwind {
; CHECK: @get_image
; CHECK-NOT: extractelement
; CHECK: unreachable
entry:
%0 = call i32 @fgetc(i8* null) nounwind ; <i32> [#uses=1]
%1 = trunc i32 %0 to i8 ; <i8> [#uses=1]
%tmp2 = insertelement <100 x i8> zeroinitializer, i8 %1, i32 1 ; <<100 x i8>> [#uses=1]
%tmp1 = extractelement <100 x i8> %tmp2, i32 0 ; <i8> [#uses=1]
%2 = icmp eq i8 %tmp1, 80 ; <i1> [#uses=1]
br i1 %2, label %bb2, label %bb3
bb2: ; preds = %entry
br label %bb3
bb3: ; preds = %bb2, %entry
unreachable
}
; PR4340
define void @vac(<4 x float>* nocapture %a) nounwind {
; CHECK: @vac
; CHECK-NOT: load
; CHECK: ret
entry:
%tmp1 = load <4 x float>* %a ; <<4 x float>> [#uses=1]
%vecins = insertelement <4 x float> %tmp1, float 0.000000e+00, i32 0 ; <<4 x float>> [#uses=1]
%vecins4 = insertelement <4 x float> %vecins, float 0.000000e+00, i32 1; <<4 x float>> [#uses=1]
%vecins6 = insertelement <4 x float> %vecins4, float 0.000000e+00, i32 2; <<4 x float>> [#uses=1]
%vecins8 = insertelement <4 x float> %vecins6, float 0.000000e+00, i32 3; <<4 x float>> [#uses=1]
store <4 x float> %vecins8, <4 x float>* %a
ret void
}
declare i32 @fgetc(i8*)
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>)
|
