File: llvm.amdgcn.buffer.load.dwordx3.ll

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (94 lines) | stat: -rw-r--r-- 4,654 bytes parent folder | download | duplicates (2)
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
;RUN: llc < %s -march=amdgcn -mcpu=gfx600 -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,SI
;RUN: llc < %s -march=amdgcn -mcpu=gfx700 -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,GCNX3

;CHECK-LABEL: {{^}}buffer_load_format_immoffs_x3:
;SI: buffer_load_format_xyzw v[0:3], off, s[0:3], 0 offset:42
;GCNX3: buffer_load_format_xyz v[0:2], off, s[0:3], 0 offset:42
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_load_format_immoffs_x3(<4 x i32> inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.buffer.load.format.v3f32(<4 x i32> %0, i32 0, i32 42, i1 0, i1 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}buffer_load_immoffs_x3:
;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40
;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_load_immoffs_x3(<4 x i32> inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.buffer.load.v3f32(<4 x i32> %0, i32 0, i32 40, i1 0, i1 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}buffer_raw_load_immoffs_x3:
;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40
;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_raw_load_immoffs_x3(<4 x i32> inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32> %0, i32 40, i32 0, i32 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}buffer_struct_load_format_immoffs_x3:
;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_struct_load_format_immoffs_x3(<4 x i32> inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32> %0, i32 0, i32 42, i32 0, i32 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}struct_buffer_load_immoffs_x3:
;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @struct_buffer_load_immoffs_x3(<4 x i32> inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32> %0, i32 0, i32 40, i32 0, i32 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}buffer_raw_ptr_load_immoffs_x3:
;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40
;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_raw_ptr_load_immoffs_x3(ptr addrspace(8) inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 40, i32 0, i32 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}buffer_struct_ptr_load_format_immoffs_x3:
;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @buffer_struct_ptr_load_format_immoffs_x3(ptr addrspace(8) inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8) %0, i32 0, i32 42, i32 0, i32 0)
  ret <3 x float> %data
}

;CHECK-LABEL: {{^}}struct_ptr_buffer_load_immoffs_x3:
;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
;CHECK: s_waitcnt
define amdgpu_ps <3 x float> @struct_ptr_buffer_load_immoffs_x3(ptr addrspace(8) inreg) {
main_body:
  %data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 0, i32 40, i32 0, i32 0)
  ret <3 x float> %data
}

declare <3 x float> @llvm.amdgcn.buffer.load.format.v3f32(<4 x i32>, i32, i32, i1, i1) #0
declare <3 x float> @llvm.amdgcn.buffer.load.v3f32(<4 x i32>, i32, i32, i1, i1) #0
declare <3 x float> @llvm.amdgcn.raw.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32>, i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32>, i32, i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0
declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0