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_llc_test_checks.py
; RUN: llc < %s -O0 -mtriple=x86_64-apple-darwin -mcpu=skx | FileCheck %s
; ModuleID = 'mask_set.c'
source_filename = "mask_set.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
declare void @llvm.dbg.declare(metadata, metadata, metadata)
; Function Attrs: nounwind uwtable
declare i64 @calc_expected_mask_val(i8* %valp, i32 %el_size, i32 %length)
; Function Attrs: nounwind uwtable
declare i32 @check_mask16(i16 zeroext %res_mask, i16 zeroext %exp_mask, i8* %fname, i8* %input)
; Function Attrs: nounwind uwtable
define void @test_xmm(i32 %shift, i32 %mulp, <2 x i64> %a,i8* %arraydecay,i8* %fname){
; CHECK-LABEL: test_xmm:
; CHECK: ## %bb.0:
; CHECK-NEXT: subq $56, %rsp
; CHECK-NEXT: .cfi_def_cfa_offset 64
; CHECK-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
; CHECK-NEXT: movq %rdx, %rdi
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
; CHECK-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
; CHECK-NEXT: vpmovw2m %xmm0, %k0
; CHECK-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) ## 2-byte Spill
; CHECK-NEXT: movl $2, %esi
; CHECK-NEXT: movl $8, %edx
; CHECK-NEXT: callq _calc_expected_mask_val
; CHECK-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 ## 2-byte Reload
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx ## 8-byte Reload
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
; CHECK-NEXT: ## kill: def $eax killed $eax killed $rax
; CHECK-NEXT: ## kill: def $ax killed $ax killed $eax
; CHECK-NEXT: movzwl %ax, %esi
; CHECK-NEXT: kmovb %k0, %edi
; CHECK-NEXT: callq _check_mask16
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdi ## 8-byte Reload
; CHECK-NEXT: vpmovd2m %xmm0, %k0
; CHECK-NEXT: ## kill: def $k1 killed $k0
; CHECK-NEXT: kmovd %k0, %eax
; CHECK-NEXT: ## kill: def $al killed $al killed $eax
; CHECK-NEXT: movzbl %al, %eax
; CHECK-NEXT: ## kill: def $ax killed $ax killed $eax
; CHECK-NEXT: movw %ax, {{[-0-9]+}}(%r{{[sb]}}p) ## 2-byte Spill
; CHECK-NEXT: movl $4, %edx
; CHECK-NEXT: movl %edx, %esi
; CHECK-NEXT: callq _calc_expected_mask_val
; CHECK-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %si ## 2-byte Reload
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx ## 8-byte Reload
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx ## 8-byte Reload
; CHECK-NEXT: ## kill: def $ax killed $ax killed $rax
; CHECK-NEXT: movzwl %si, %edi
; CHECK-NEXT: movzwl %ax, %esi
; CHECK-NEXT: callq _check_mask16
; CHECK-NEXT: addq $56, %rsp
; CHECK-NEXT: retq
%d2 = bitcast <2 x i64> %a to <8 x i16>
%m2 = call i8 @llvm.x86.avx512.cvtw2mask.128(<8 x i16> %d2)
%conv7 = zext i8 %m2 to i16
%call9 = call i64 @calc_expected_mask_val(i8* %arraydecay, i32 2, i32 8)
%conv10 = trunc i64 %call9 to i16
%call12 = call i32 @check_mask16(i16 zeroext %conv7, i16 zeroext %conv10, i8* %fname, i8* %arraydecay)
%d3 = bitcast <2 x i64> %a to <4 x i32>
%m3 = call i8 @llvm.x86.avx512.cvtd2mask.128(<4 x i32> %d3)
%conv14 = zext i8 %m3 to i16
%call16 = call i64 @calc_expected_mask_val(i8* %arraydecay, i32 4, i32 4)
%conv17 = trunc i64 %call16 to i16
%call19 = call i32 @check_mask16(i16 zeroext %conv14, i16 zeroext %conv17, i8* %fname, i8* %arraydecay)
ret void
}
; Function Attrs: nounwind readnone
declare i8 @llvm.x86.avx512.cvtw2mask.128(<8 x i16>)
; Function Attrs: nounwind readnone
declare i8 @llvm.x86.avx512.cvtd2mask.128(<4 x i32>)
|
