File: divergence-driven-abs.ll

package info (click to toggle)
llvm-toolchain-15 1%3A15.0.6-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,554,644 kB
  • sloc: cpp: 5,922,452; ansic: 1,012,136; asm: 674,362; python: 191,568; objc: 73,855; f90: 42,327; lisp: 31,913; pascal: 11,973; javascript: 10,144; sh: 9,421; perl: 7,447; ml: 5,527; awk: 3,523; makefile: 2,520; xml: 885; cs: 573; fortran: 567
file content (71 lines) | stat: -rw-r--r-- 2,734 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
; RUN:  llc -march=amdgcn -stop-after=amdgpu-isel < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI %s
; RUN:  llc -march=amdgcn -mcpu=gfx900 -stop-after=amdgpu-isel < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX900 %s

; FUNC-LABEL: {{^}}v_abs_i32:
; GCN: S_ABS_I32
define amdgpu_kernel void @s_abs_i32(i32 addrspace(1)* %out, i32 %val) nounwind {
  %neg = sub i32 0, %val
  %cond = icmp sgt i32 %val, %neg
  %res = select i1 %cond, i32 %val, i32 %neg
  %res2 = add i32 %res, 2
  store i32 %res2, i32 addrspace(1)* %out, align 4
  ret void
}

; FUNC-LABEL: {{^}}v_abs_i32:
; SI:  V_SUB_CO_U32_e64
; GFX900: V_SUB_U32_e64
; GCN: V_MAX_I32_e64
define amdgpu_kernel void @v_abs_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %src) nounwind {
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %gep.in = getelementptr inbounds i32, i32 addrspace(1)* %src, i32 %tid
  %val = load i32, i32 addrspace(1)* %gep.in, align 4
  %neg = sub i32 0, %val
  %cond = icmp sgt i32 %val, %neg
  %res = select i1 %cond, i32 %val, i32 %neg
  %res2 = add i32 %res, 2
  store i32 %res2, i32 addrspace(1)* %out, align 4
  ret void
}

; FUNC-LABEL: {{^}}s_abs_v2i32:
; GCN: S_ABS_I32
; GCN: S_ABS_I32
define amdgpu_kernel void @s_abs_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %val) nounwind {
  %z0 = insertelement <2 x i32> undef, i32 0, i32 0
  %z1 = insertelement <2 x i32> %z0, i32 0, i32 1
  %t0 = insertelement <2 x i32> undef, i32 2, i32 0
  %t1 = insertelement <2 x i32> %t0, i32 2, i32 1
  %neg = sub <2 x i32> %z1, %val
  %cond = icmp sgt <2 x i32> %val, %neg
  %res = select <2 x i1> %cond, <2 x i32> %val, <2 x i32> %neg
  %res2 = add <2 x i32> %res, %t1
  store <2 x i32> %res2, <2 x i32> addrspace(1)* %out, align 4
  ret void
}

; FUNC-LABEL: {{^}}v_abs_v2i32:
; SI:  V_SUB_CO_U32_e64
; GFX900: V_SUB_U32_e64
; GCN: V_MAX_I32_e64
; GCN: V_MAX_I32_e64
define amdgpu_kernel void @v_abs_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %src) nounwind {
  %z0 = insertelement <2 x i32> undef, i32 0, i32 0
  %z1 = insertelement <2 x i32> %z0, i32 0, i32 1
  %t0 = insertelement <2 x i32> undef, i32 2, i32 0
  %t1 = insertelement <2 x i32> %t0, i32 2, i32 1
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %gep.in = getelementptr inbounds <2 x i32>, <2 x i32> addrspace(1)* %src, i32 %tid
  %val = load <2 x i32>, <2 x i32> addrspace(1)* %gep.in, align 4
  %neg = sub <2 x i32> %z1, %val
  %cond = icmp sgt <2 x i32> %val, %neg
  %res = select <2 x i1> %cond, <2 x i32> %val, <2 x i32> %neg
  %res2 = add <2 x i32> %res, %t1
  store <2 x i32> %res2, <2 x i32> addrspace(1)* %out, align 4
  ret void
}

declare i32 @llvm.amdgcn.workitem.id.x() #0

attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }