File: device-code.ll

package info (click to toggle)
llvm-toolchain-15 1%3A15.0.6-4
  • links: PTS, VCS
  • area: main
  • in suites:
  • 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 (38 lines) | stat: -rw-r--r-- 971 bytes parent folder | download | duplicates (21) 
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
 
; Simple bit of IR to mimic CUDA's libdevice. We want to be
; able to link with it and we need to make sure all __nvvm_reflect
; calls are eliminated by the time PTX has been produced.

target triple = "nvptx-unknown-cuda"

declare i32 @__nvvm_reflect(i8*)

@"$str" = private addrspace(1) constant [8 x i8] c"USE_MUL\00"

define void @unused_subfunc(float %a) {
       ret void
}

define void @used_subfunc(float %a) {
       ret void
}

define float @_Z17device_mul_or_addff(float %a, float %b) {
  %reflect = call i32 @__nvvm_reflect(i8* addrspacecast (i8 addrspace(1)* getelementptr inbounds ([8 x i8], [8 x i8] addrspace(1)* @"$str", i32 0, i32 0) to i8*))
  %cmp = icmp ne i32 %reflect, 0
  br i1 %cmp, label %use_mul, label %use_add

use_mul:
  %ret1 = fmul float %a, %b
  br label %exit

use_add:
  %ret2 = fadd float %a, %b
  br label %exit

exit:
  %ret = phi float [%ret1, %use_mul], [%ret2, %use_add]

  call void @used_subfunc(float %ret)

  ret float %ret
}