File: upgrade-vecreduce-intrinsics.ll

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 995,808 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (64 lines) | stat: -rw-r--r-- 2,937 bytes parent folder | download | duplicates (4)
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
; RUN: opt -S < %s | FileCheck %s
; RUN: llvm-dis < %s.bc | FileCheck %s

define float @fadd_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_acc
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float %acc, <4 x float> %in)
  %res = call float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float %acc, <4 x float> %in)
  ret float %res
}

define float @fadd_undef(<4 x float> %in) {
; CHECK-LABEL: @fadd_undef
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float undef, <4 x float> %in)
  %res = call float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float undef, <4 x float> %in)
  ret float %res
}

define float @fadd_fast_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_fast_acc
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %in)
  %res = call fast float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float %acc, <4 x float> %in)
  ret float %res
}

define float @fadd_fast_undef(<4 x float> %in) {
; CHECK-LABEL: @fadd_fast_undef
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %in)
  %res = call fast float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float undef, <4 x float> %in)
  ret float %res
}

define float @fmul_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_acc
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float %acc, <4 x float> %in)
  %res = call float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float %acc, <4 x float> %in)
  ret float %res
}

define float @fmul_undef(<4 x float> %in) {
; CHECK-LABEL: @fmul_undef
; CHECK: %res = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float undef, <4 x float> %in)
  %res = call float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float undef, <4 x float> %in)
  ret float %res
}

define float @fmul_fast_acc(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_fast_acc
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float 1.000000e+00, <4 x float> %in)
  %res = call fast float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float %acc, <4 x float> %in)
  ret float %res
}

define float @fmul_fast_undef(<4 x float> %in) {
; CHECK-LABEL: @fmul_fast_undef
; CHECK: %res = call fast float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float 1.000000e+00, <4 x float> %in)
  %res = call fast float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float undef, <4 x float> %in)
  ret float %res
}

declare float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
; CHECK: declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float, <4 x float>)

declare float @llvm.experimental.vector.reduce.fmul.f32.v4f32(float, <4 x float>)
; CHECK: declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float, <4 x float>)