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
|
; Copyright (c) 1993-2023, NVIDIA CORPORATION. All rights reserved.
;
; Redistribution and use in source and binary forms, with or without
; modification, are permitted provided that the following conditions
; are met:
; * Redistributions of source code must retain the above copyright
; notice, this list of conditions and the following disclaimer.
; * Redistributions in binary form must reproduce the above copyright
; notice, this list of conditions and the following disclaimer in the
; documentation and/or other materials provided with the distribution.
; * Neither the name of NVIDIA CORPORATION nor the names of its
; contributors may be used to endorse or promote products derived
; from this software without specific prior written permission.
;
; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
; EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
; IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
; PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
; CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
; EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
; PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
; PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
; OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
; (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
; OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-i128:128:128-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
target triple = "nvptx64-nvidia-cuda"
define i32 @ave(i32 %a, i32 %b) {
entry:
%add = add nsw i32 %a, %b
%div = sdiv i32 %add, 2
ret i32 %div
}
define void @simple(i32* %data) {
entry:
%0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
%1 = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
%mul = mul i32 %0, %1
%2 = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
%add = add i32 %mul, %2
%call = call i32 @ave(i32 %add, i32 %add)
%idxprom = sext i32 %add to i64
%arrayidx = getelementptr inbounds i32, i32* %data, i64 %idxprom
store i32 %call, i32* %arrayidx, align 4
ret void
}
declare i32 @llvm.nvvm.read.ptx.sreg.ctaid.x() nounwind readnone
declare i32 @llvm.nvvm.read.ptx.sreg.ntid.x() nounwind readnone
declare i32 @llvm.nvvm.read.ptx.sreg.tid.x() nounwind readnone
!nvvm.annotations = !{!1}
!1 = !{void (i32*)* @simple, !"kernel", i32 1}
!nvvmir.version = !{!2}
!2 = !{i32 2, i32 0, i32 3, i32 1}
|
