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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s --check-prefixes=AVX1
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefixes=AVX2
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512vl | FileCheck %s --check-prefixes=AVX512
; FIXME: Ensure when we merge broadcasts to different widths that they come from the same SDValue.
define i32 @PR48215(i32 %a0, i32 %a1) {
; AVX1-LABEL: PR48215:
; AVX1: ## %bb.0:
; AVX1-NEXT: movl %edi, %eax
; AVX1-NEXT: cltd
; AVX1-NEXT: idivl %esi
; AVX1-NEXT: vmovd %edx, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [4,5,6,7]
; AVX1-NEXT: vmovd %eax, %xmm2
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm3
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [0,1,2,3]
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm4, %xmm2
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
; AVX1-NEXT: vmovmskps %ymm2, %ecx
; AVX1-NEXT: vpcmpgtd %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vmovmskps %xmm0, %eax
; AVX1-NEXT: addl %ecx, %eax
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: PR48215:
; AVX2: ## %bb.0:
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: cltd
; AVX2-NEXT: idivl %esi
; AVX2-NEXT: vmovd %eax, %xmm0
; AVX2-NEXT: vpbroadcastd %xmm0, %ymm0
; AVX2-NEXT: vmovd %edx, %xmm1
; AVX2-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,2,3,4,5,6,7]
; AVX2-NEXT: vpcmpgtd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [4,5,6,7]
; AVX2-NEXT: vpcmpgtd %xmm1, %xmm2, %xmm1
; AVX2-NEXT: vmovmskps %ymm0, %ecx
; AVX2-NEXT: vmovmskps %xmm1, %eax
; AVX2-NEXT: addl %ecx, %eax
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: PR48215:
; AVX512: ## %bb.0:
; AVX512-NEXT: movl %edi, %eax
; AVX512-NEXT: cltd
; AVX512-NEXT: idivl %esi
; AVX512-NEXT: vpbroadcastd %eax, %ymm0
; AVX512-NEXT: vpbroadcastd %edx, %xmm1
; AVX512-NEXT: vpcmpltd {{.*}}(%rip), %ymm0, %k0
; AVX512-NEXT: vpcmpltd {{.*}}(%rip), %xmm1, %k1
; AVX512-NEXT: kmovw %k0, %eax
; AVX512-NEXT: movzbl %al, %ecx
; AVX512-NEXT: kmovw %k1, %eax
; AVX512-NEXT: andl $15, %eax
; AVX512-NEXT: addl %ecx, %eax
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%d = sdiv i32 %a0, %a1
%r = srem i32 %a0, %a1
%dv0 = insertelement <8 x i32> undef, i32 %d, i32 0
%rv0 = insertelement <4 x i32> undef, i32 %r, i32 0
%dv1 = shufflevector <8 x i32> %dv0, <8 x i32> undef, <8 x i32> zeroinitializer
%rv1 = shufflevector <4 x i32> %rv0, <4 x i32> undef, <4 x i32> zeroinitializer
%dc0 = icmp slt <8 x i32> %dv1, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%rc0 = icmp slt <4 x i32> %rv1, <i32 4, i32 5, i32 6, i32 7>
%db0 = bitcast <8 x i1> %dc0 to i8
%rb0 = bitcast <4 x i1> %rc0 to i4
%db1 = zext i8 %db0 to i32
%rb1 = zext i4 %rb0 to i32
%res = add i32 %db1, %rb1
ret i32 %res
}
|
GitWeb