QUDA  v1.1.0
A library for QCD on GPUs
block.h
Go to the documentation of this file.
1 /*
2 Copyright (c) 2013, NVIDIA Corporation
3 All rights reserved.
4 
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions are met:
7  * Redistributions of source code must retain the above copyright
8  notice, this list of conditions and the following disclaimer.
9  * Redistributions in binary form must reproduce the above copyright
10  notice, this list of conditions and the following disclaimer in the
11  documentation and/or other materials provided with the distribution.
12  * Neither the name of the <organization> nor the
13  names of its contributors may be used to endorse or promote products
14  derived from this software without specific prior written permission.
15 
16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
17 ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
20 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27 
28 #pragma once
29 #include <trove/aos.h>
30 #include <trove/warp.h>
31 
32 namespace trove {
33 
34 
35 template<int s, typename T, typename I>
36 __device__
37 trove::array<T, s> load_array_warp_contiguous(const T* src, const I& idx) {
38  typedef trove::array<T, s> array_type;
39  const array_type* src_ptr = (const array_type*)(src) + idx;
40  return load_warp_contiguous(src_ptr);
41 }
42 
43 template<int s, typename T, typename I>
44 __device__
45 trove::array<T, s> load_array(const T* src, const I& idx) {
46  typedef trove::array<T, s> array_type;
47  const array_type* src_ptr = (const array_type*)(src) + idx;
48  return *src_ptr;
49 }
50 
51 template<int s, typename T, typename I>
52 __device__
53 void store_array_warp_contiguous(T* dest, const I& idx, const trove::array<T, s>& src) {
54  typedef trove::array<T, s> array_type;
55  array_type* dest_ptr = (array_type*)(dest) + idx;
56  store_warp_contiguous(src, dest_ptr);
57 }
58 
59 template<int s, typename T, typename I>
60 __device__
61 void store_array(T* dest, const I& idx, const trove::array<T, s>& src) {
62  typedef trove::array<T, s> array_type;
63  array_type* dest_ptr = (array_type*)(dest) + idx;
64  *dest_ptr = src;
65 }
66 
67 }
Definition: aos.h:38
__device__ void store_array(T *dest, const I &idx, const trove::array< T, s > &src)
Definition: block.h:61
__device__ trove::array< T, s > load_array(const T *src, const I &idx)
Definition: block.h:45
__device__ trove::array< T, s > load_array_warp_contiguous(const T *src, const I &idx)
Definition: block.h:37
__device__ enable_if< detail::use_shfl< T >::value, T >::type load_warp_contiguous(const T *src)
Definition: aos.h:69
__device__ enable_if< detail::use_shfl< T >::value >::type store_warp_contiguous(const T &data, T *dest)
Definition: aos.h:89
__device__ void store_array_warp_contiguous(T *dest, const I &idx, const trove::array< T, s > &src)
Definition: block.h:53