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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=slp-vectorizer -S -mcpu=cascadelake -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
define void @foo(i1 %arg) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CONV:%.*]] = uitofp i16 0 to float
; CHECK-NEXT: [[SUB:%.*]] = fsub float 6.553500e+04, 0.000000e+00
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x float> <float poison, float poison, float 0.000000e+00, float 0.000000e+00>, float [[SUB]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x float> [[TMP0]], float [[CONV]], i32 1
; CHECK-NEXT: br label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[TMP2:%.*]] = phi <4 x float> [ [[TMP1]], [[BB1]] ], [ [[TMP14:%.*]], [[BB3:%.*]] ]
; CHECK-NEXT: [[TMP3:%.*]] = load double, ptr null, align 8
; CHECK-NEXT: br i1 [[ARG:%.*]], label [[BB3]], label [[BB4:%.*]]
; CHECK: bb4:
; CHECK-NEXT: [[TMP4:%.*]] = fpext <4 x float> [[TMP2]] to <4 x double>
; CHECK-NEXT: [[CONV2:%.*]] = uitofp i16 0 to double
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x double> <double 0.000000e+00, double poison>, double [[TMP3]], i32 1
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x double> <double 0.000000e+00, double poison>, double [[CONV2]], i32 1
; CHECK-NEXT: [[TMP7:%.*]] = fsub <2 x double> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = fadd <2 x double> [[TMP5]], [[TMP6]]
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x double> [[TMP7]], <2 x double> [[TMP8]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <2 x double> [[TMP9]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x double> <double poison, double poison, double 0.000000e+00, double 0.000000e+00>, <4 x double> [[TMP15]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: [[TMP11:%.*]] = fcmp ogt <4 x double> [[TMP10]], [[TMP4]]
; CHECK-NEXT: [[TMP12:%.*]] = fptrunc <4 x double> [[TMP10]] to <4 x float>
; CHECK-NEXT: [[TMP13:%.*]] = select <4 x i1> [[TMP11]], <4 x float> [[TMP2]], <4 x float> [[TMP12]]
; CHECK-NEXT: br label [[BB3]]
; CHECK: bb3:
; CHECK-NEXT: [[TMP14]] = phi <4 x float> [ [[TMP13]], [[BB4]] ], [ [[TMP2]], [[BB2]] ]
; CHECK-NEXT: br label [[BB2]]
;
entry:
%conv = uitofp i16 zeroinitializer to float
%sub = fsub float 6.553500e+04, zeroinitializer
br label %bb1
bb1:
br label %bb2
bb2:
%0 = phi float [ %sub, %bb1 ], [ %9, %bb3 ]
%1 = phi float [ %conv, %bb1 ], [ %10, %bb3 ]
%2 = phi float [ zeroinitializer, %bb1 ], [ %11, %bb3 ]
%3 = phi float [ zeroinitializer, %bb1 ], [ %12, %bb3 ]
%4 = load double, ptr zeroinitializer, align 8
br i1 %arg, label %bb3, label %bb4
bb4:
%ext = fpext float %3 to double
%cmp1 = fcmp ogt double zeroinitializer, %ext
%5 = fptrunc double zeroinitializer to float
%sel1 = select i1 %cmp1, float %3, float %5
%ext2 = fpext float %2 to double
%cmp2 = fcmp ogt double zeroinitializer, %ext2
%6 = fptrunc double zeroinitializer to float
%sel2 = select i1 %cmp2, float %2, float %6
%ext3 = fpext float %1 to double
%conv2 = uitofp i16 zeroinitializer to double
%add1 = fadd double %4, %conv2
%cmp3 = fcmp ogt double %add1, %ext3
%7 = fptrunc double %add1 to float
%sel3 = select i1 %cmp3, float %1, float %7
%ext4 = fpext float %0 to double
%sub1 = fsub double zeroinitializer, zeroinitializer
%cmp4 = fcmp ogt double %sub1, %ext4
%8 = fptrunc double %sub1 to float
%sel4 = select i1 %cmp4, float %0, float %8
br label %bb3
bb3:
%9 = phi float [ %sel4, %bb4 ], [ %0, %bb2 ]
%10 = phi float [ %sel3, %bb4 ], [ %1, %bb2 ]
%11 = phi float [ %sel2, %bb4 ], [ %2, %bb2 ]
%12 = phi float [ %sel1, %bb4 ], [ %3, %bb2 ]
br label %bb2
}
|
