File: llvm.amdgcn.init.exec.ll

package info (click to toggle)
llvm-toolchain-6.0 1%3A6.0.1-10
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 598,080 kB
  • sloc: cpp: 3,046,253; ansic: 595,057; asm: 271,965; python: 128,926; objc: 106,554; sh: 21,906; lisp: 10,191; pascal: 6,094; ml: 5,544; perl: 5,265; makefile: 2,227; cs: 2,027; xml: 686; php: 212; csh: 117
file content (80 lines) | stat: -rw-r--r-- 2,280 bytes parent folder | download
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
;RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck %s --check-prefix=GCN

; GCN-LABEL: {{^}}full_mask:
; GCN: s_mov_b64 exec, -1
; GCN: v_add_f32_e32 v0,
define amdgpu_ps float @full_mask(float %a, float %b) {
main_body:
  %s = fadd float %a, %b
  call void @llvm.amdgcn.init.exec(i64 -1)
  ret float %s
}

; GCN-LABEL: {{^}}partial_mask:
; GCN: s_mov_b64 exec, 0x1e240
; GCN: v_add_f32_e32 v0,
define amdgpu_ps float @partial_mask(float %a, float %b) {
main_body:
  %s = fadd float %a, %b
  call void @llvm.amdgcn.init.exec(i64 123456)
  ret float %s
}

; GCN-LABEL: {{^}}input_s3off8:
; GCN: s_bfe_u32 s0, s3, 0x70008
; GCN: s_bfm_b64 exec, s0, 0
; GCN: s_cmp_eq_u32 s0, 64
; GCN: s_cmov_b64 exec, -1
; GCN: v_add_f32_e32 v0,
define amdgpu_ps float @input_s3off8(i32 inreg, i32 inreg, i32 inreg, i32 inreg %count, float %a, float %b) {
main_body:
  %s = fadd float %a, %b
  call void @llvm.amdgcn.init.exec.from.input(i32 %count, i32 8)
  ret float %s
}

; GCN-LABEL: {{^}}input_s0off19:
; GCN: s_bfe_u32 s0, s0, 0x70013
; GCN: s_bfm_b64 exec, s0, 0
; GCN: s_cmp_eq_u32 s0, 64
; GCN: s_cmov_b64 exec, -1
; GCN: v_add_f32_e32 v0,
define amdgpu_ps float @input_s0off19(i32 inreg %count, float %a, float %b) {
main_body:
  %s = fadd float %a, %b
  call void @llvm.amdgcn.init.exec.from.input(i32 %count, i32 19)
  ret float %s
}

; GCN-LABEL: {{^}}reuse_input:
; GCN: s_bfe_u32 s1, s0, 0x70013
; GCN: s_bfm_b64 exec, s1, 0
; GCN: s_cmp_eq_u32 s1, 64
; GCN: s_cmov_b64 exec, -1
; GCN: v_add_u32_e32 v0, s0, v0
define amdgpu_ps float @reuse_input(i32 inreg %count, i32 %a) {
main_body:
  call void @llvm.amdgcn.init.exec.from.input(i32 %count, i32 19)
  %s = add i32 %a, %count
  %f = sitofp i32 %s to float
  ret float %f
}

; GCN-LABEL: {{^}}reuse_input2:
; GCN: s_bfe_u32 s1, s0, 0x70013
; GCN: s_bfm_b64 exec, s1, 0
; GCN: s_cmp_eq_u32 s1, 64
; GCN: s_cmov_b64 exec, -1
; GCN: v_add_u32_e32 v0, s0, v0
define amdgpu_ps float @reuse_input2(i32 inreg %count, i32 %a) {
main_body:
  %s = add i32 %a, %count
  %f = sitofp i32 %s to float
  call void @llvm.amdgcn.init.exec.from.input(i32 %count, i32 19)
  ret float %f
}

declare void @llvm.amdgcn.init.exec(i64) #1
declare void @llvm.amdgcn.init.exec.from.input(i32, i32) #1

attributes #1 = { convergent }