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
|
; Copyright (c) 2014-2023, 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.
; This NVVM IR program shows how to use shared memory.
; What it does is similar to the following CUDA C code.
;
;
; __shared__ int a;
; __shared__ int b[10];
;
; __global__ void foo()
; {
; a = 1;
; b[5] = 2;
; }
;
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"
@a = internal addrspace(3) global i32 undef, align 4
@b = internal addrspace(3) global [10 x i32] undef, align 4
define void @foo() {
entry:
store i32 1, i32 addrspace(3)* @a, align 4
store i32 2, i32 addrspace(3)* getelementptr inbounds ([10 x i32], [10 x i32] addrspace(3)* @b, i64 0, i64 5), align 4
ret void
}
!nvvm.annotations = !{!0}
!0 = !{void ()* @foo, !"kernel", i32 1}
!nvvmir.version = !{!1}
!1 = !{i32 2, i32 0}
|
