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
|
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s
; Verify that we're folding the load into the math instruction.
; FIXME: The folding should also happen without the avx attribute;
; ie, when generating SSE (non-VEX-prefixed) instructions.
define float @rcpss(float* %a) {
; CHECK-LABEL: rcpss:
; CHECK: vrcpss (%rdi), %xmm0, %xmm0
%ld = load float, float* %a
%ins = insertelement <4 x float> undef, float %ld, i32 0
%res = tail call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %ins)
%ext = extractelement <4 x float> %res, i32 0
ret float %ext
}
define float @rsqrtss(float* %a) {
; CHECK-LABEL: rsqrtss:
; CHECK: vrsqrtss (%rdi), %xmm0, %xmm0
%ld = load float, float* %a
%ins = insertelement <4 x float> undef, float %ld, i32 0
%res = tail call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %ins)
%ext = extractelement <4 x float> %res, i32 0
ret float %ext
}
define float @sqrtss(float* %a) {
; CHECK-LABEL: sqrtss:
; CHECK: vsqrtss (%rdi), %xmm0, %xmm0
%ld = load float, float* %a
%ins = insertelement <4 x float> undef, float %ld, i32 0
%res = tail call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %ins)
%ext = extractelement <4 x float> %res, i32 0
ret float %ext
}
define double @sqrtsd(double* %a) {
; CHECK-LABEL: sqrtsd:
; CHECK: vsqrtsd (%rdi), %xmm0, %xmm0
%ld = load double, double* %a
%ins = insertelement <2 x double> undef, double %ld, i32 0
%res = tail call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %ins)
%ext = extractelement <2 x double> %res, i32 0
ret double %ext
}
declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
|
