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
|
/*
* Copyright (c) 2016 University of Cordoba and University of Illinois
* All rights reserved.
*
* Developed by: IMPACT Research Group
* University of Cordoba and University of Illinois
* http://impact.crhc.illinois.edu/
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* with the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* > Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimers.
* > Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimers in the
* documentation and/or other materials provided with the distribution.
* > Neither the names of IMPACT Research Group, University of Cordoba,
* University of Illinois nor the names of its contributors may be used
* to endorse or promote products derived from this Software without
* specific prior written permission.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS WITH
* THE SOFTWARE.
*
*/
#include "cuda_runtime.h"
#include <stdlib.h>
#include <atomic>
#include "support/common.h"
cudaError_t call_PTTWAC_soa_asta(int blocks, int threads, int A, int B, int b, T *input,
int *finished, int *head, int l_mem_size);
cudaError_t call_BS_marshal(int blocks, int threads, int m, int n, T *input, int l_mem_size);
|
