File: vector-alloca-limits.ll

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-6~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 1,418,812 kB
  • sloc: cpp: 5,290,827; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,900; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,892; xml: 953; cs: 573; fortran: 539
file content (136 lines) | stat: -rw-r--r-- 4,946 bytes parent folder | download | duplicates (5)
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-promote-alloca -sroa -instcombine < %s | FileCheck -check-prefix=OPT %s
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-promote-alloca -sroa -instcombine -amdgpu-promote-alloca-to-vector-limit=32 < %s | FileCheck -check-prefix=LIMIT32 %s

target datalayout = "A5"

; OPT-LABEL: @alloca_8xi64_max1024(
; OPT-NOT: alloca
; OPT: <8 x i64>
; LIMIT32: alloca
; LIMIT32-NOT: <8 x i64>
define amdgpu_kernel void @alloca_8xi64_max1024(i64 addrspace(1)* %out, i32 %index) #0 {
entry:
  %tmp = alloca [8 x i64], addrspace(5)
  %x = getelementptr [8 x i64], [8 x i64] addrspace(5)* %tmp, i32 0, i32 0
  store i64 0, i64 addrspace(5)* %x
  %tmp1 = getelementptr [8 x i64], [8 x i64] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i64, i64 addrspace(5)* %tmp1
  store i64 %tmp2, i64 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_9xi64_max1024(
; OPT: alloca [9 x i64]
; OPT-NOT: <9 x i64>
; LIMIT32: alloca
; LIMIT32-NOT: <9 x i64>
define amdgpu_kernel void @alloca_9xi64_max1024(i64 addrspace(1)* %out, i32 %index) #0 {
entry:
  %tmp = alloca [9 x i64], addrspace(5)
  %x = getelementptr [9 x i64], [9 x i64] addrspace(5)* %tmp, i32 0, i32 0
  store i64 0, i64 addrspace(5)* %x
  %tmp1 = getelementptr [9 x i64], [9 x i64] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i64, i64 addrspace(5)* %tmp1
  store i64 %tmp2, i64 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_16xi64_max512(
; OPT-NOT: alloca
; OPT: <16 x i64>
; LIMIT32: alloca
; LIMIT32-NOT: <16 x i64>
define amdgpu_kernel void @alloca_16xi64_max512(i64 addrspace(1)* %out, i32 %index) #1 {
entry:
  %tmp = alloca [16 x i64], addrspace(5)
  %x = getelementptr [16 x i64], [16 x i64] addrspace(5)* %tmp, i32 0, i32 0
  store i64 0, i64 addrspace(5)* %x
  %tmp1 = getelementptr [16 x i64], [16 x i64] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i64, i64 addrspace(5)* %tmp1
  store i64 %tmp2, i64 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_17xi64_max512(
; OPT: alloca [17 x i64]
; OPT-NOT: <17 x i64>
; LIMIT32: alloca
; LIMIT32-NOT: <17 x i64>
define amdgpu_kernel void @alloca_17xi64_max512(i64 addrspace(1)* %out, i32 %index) #1 {
entry:
  %tmp = alloca [17 x i64], addrspace(5)
  %x = getelementptr [17 x i64], [17 x i64] addrspace(5)* %tmp, i32 0, i32 0
  store i64 0, i64 addrspace(5)* %x
  %tmp1 = getelementptr [17 x i64], [17 x i64] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i64, i64 addrspace(5)* %tmp1
  store i64 %tmp2, i64 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_9xi128_max512(
; OPT: alloca [9 x i128]
; OPT-NOT: <9 x i128>
; LIMIT32: alloca
; LIMIT32-NOT: <9 x i128>
define amdgpu_kernel void @alloca_9xi128_max512(i128 addrspace(1)* %out, i32 %index) #1 {
entry:
  %tmp = alloca [9 x i128], addrspace(5)
  %x = getelementptr [9 x i128], [9 x i128] addrspace(5)* %tmp, i32 0, i32 0
  store i128 0, i128 addrspace(5)* %x
  %tmp1 = getelementptr [9 x i128], [9 x i128] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i128, i128 addrspace(5)* %tmp1
  store i128 %tmp2, i128 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_9xi128_max256(
; OPT-NOT: alloca
; OPT: <9 x i128>
; LIMIT32: alloca
; LIMIT32-NOT: <9 x i128>
define amdgpu_kernel void @alloca_9xi128_max256(i128 addrspace(1)* %out, i32 %index) #2 {
entry:
  %tmp = alloca [9 x i128], addrspace(5)
  %x = getelementptr [9 x i128], [9 x i128] addrspace(5)* %tmp, i32 0, i32 0
  store i128 0, i128 addrspace(5)* %x
  %tmp1 = getelementptr [9 x i128], [9 x i128] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i128, i128 addrspace(5)* %tmp1
  store i128 %tmp2, i128 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_16xi128_max256(
; OPT-NOT: alloca
; OPT: <16 x i128>
; LIMIT32: alloca
; LIMIT32-NOT: <16 x i128>
define amdgpu_kernel void @alloca_16xi128_max256(i128 addrspace(1)* %out, i32 %index) #2 {
entry:
  %tmp = alloca [16 x i128], addrspace(5)
  %x = getelementptr [16 x i128], [16 x i128] addrspace(5)* %tmp, i32 0, i32 0
  store i128 0, i128 addrspace(5)* %x
  %tmp1 = getelementptr [16 x i128], [16 x i128] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i128, i128 addrspace(5)* %tmp1
  store i128 %tmp2, i128 addrspace(1)* %out
  ret void
}

; OPT-LABEL: @alloca_9xi256_max256(
; OPT: alloca [9 x i256]
; OPT-NOT: <9 x i256>
; LIMIT32: alloca
; LIMIT32-NOT: <9 x i256>
define amdgpu_kernel void @alloca_9xi256_max256(i256 addrspace(1)* %out, i32 %index) #2 {
entry:
  %tmp = alloca [9 x i256], addrspace(5)
  %x = getelementptr [9 x i256], [9 x i256] addrspace(5)* %tmp, i32 0, i32 0
  store i256 0, i256 addrspace(5)* %x
  %tmp1 = getelementptr [9 x i256], [9 x i256] addrspace(5)* %tmp, i32 0, i32 %index
  %tmp2 = load i256, i256 addrspace(5)* %tmp1
  store i256 %tmp2, i256 addrspace(1)* %out
  ret void
}

attributes #0 = { "amdgpu-flat-work-group-size"="1,1024" }
attributes #1 = { "amdgpu-flat-work-group-size"="1,512" }
attributes #2 = { "amdgpu-flat-work-group-size"="1,256" }