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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,X86,SSE,X86-SSE,SSE2,X86-SSE2
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=CHECK,X86,SSE,X86-SSE,SSE41,X86-SSE41
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=CHECK,X86,AVX,X86-AVX,AVX1,X86-AVX1
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,X86,AVX,X86-AVX,AVX512,X86-AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,X64,SSE,X64-SSE,SSE2,X64-SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=CHECK,X64,SSE,X64-SSE,SSE41,X64-SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=CHECK,X64,AVX,X64-AVX,AVX1,X64-AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,X64,AVX,X64-AVX,AVX512,X64-AVX512
; PR21507 - https://llvm.org/bugs/show_bug.cgi?id=21507
; Each function should be a single math op; no extra moves.
define <4 x float> @recip(<4 x float> %x) {
; SSE-LABEL: recip:
; SSE: # %bb.0:
; SSE-NEXT: rcpss %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: recip:
; AVX: # %bb.0:
; AVX-NEXT: vrcpss %xmm0, %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%y = tail call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %x)
%shuf = shufflevector <4 x float> %y, <4 x float> %x, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuf
}
define <4 x float> @recip_square_root(<4 x float> %x) {
; SSE-LABEL: recip_square_root:
; SSE: # %bb.0:
; SSE-NEXT: rsqrtss %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: recip_square_root:
; AVX: # %bb.0:
; AVX-NEXT: vrsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%y = tail call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %x)
%shuf = shufflevector <4 x float> %y, <4 x float> %x, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuf
}
define <4 x float> @square_root(<4 x float> %x) {
; SSE-LABEL: square_root:
; SSE: # %bb.0:
; SSE-NEXT: sqrtss %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: square_root:
; AVX: # %bb.0:
; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%y = tail call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %x)
%shuf = shufflevector <4 x float> %y, <4 x float> %x, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuf
}
define <2 x double> @square_root_double(<2 x double> %x) {
; SSE-LABEL: square_root_double:
; SSE: # %bb.0:
; SSE-NEXT: sqrtsd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: square_root_double:
; AVX: # %bb.0:
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%y = tail call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %x)
%shuf = shufflevector <2 x double> %y, <2 x double> %x, <2 x i32> <i32 0, i32 3>
ret <2 x double> %shuf
}
declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>)
declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>)
declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>)
declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>)
|