CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
kernel_launch.h
Go to the documentation of this file.
1 /***************************************************************************************************
2  * Copyright (c) 2017-2019, NVIDIA CORPORATION. All rights reserved.
3  *
4  * Redistribution and use in source and binary forms, with or without modification, are permitted
5  * provided that the following conditions are met:
6  * * Redistributions of source code must retain the above copyright notice, this list of
7  * conditions and the following disclaimer.
8  * * Redistributions in binary form must reproduce the above copyright notice, this list of
9  * conditions and the following disclaimer in the documentation and/or other materials
10  * provided with the distribution.
11  * * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used
12  * to endorse or promote products derived from this software without specific prior written
13  * permission.
14  *
15  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
16  * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
17  * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE
18  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
19  * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
20  * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
21  * STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
22  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
23  *
24  **************************************************************************************************/
29 #pragma once
30 
31 #include "cutlass/cutlass.h"
32 
33 namespace cutlass {
34 
36 
39 
41  dim3 grid;
42 
44  dim3 block;
45 
47  size_t dynamic_smem;
48 
49  //
50  // Methods
51  //
52 
56  dim3 _grid = dim3(1,1,1),
57  dim3 _block = dim3(1,1,1),
58  size_t _dynamic_smem = 0
59  ):
60  grid(_grid),
61  block(_block),
62  dynamic_smem(_dynamic_smem) { }
63 };
64 
66 
67 } // namespace cutlass
CUTLASS_HOST_DEVICE KernelLaunchConfiguration(dim3 _grid=dim3(1, 1, 1), dim3 _block=dim3(1, 1, 1), size_t _dynamic_smem=0)
Constructs a KernellaunchConfiguration object.
Definition: kernel_launch.h:55
Definition: aligned_buffer.h:35
Structure containing the basic launch configuration of a CUDA kernel.
Definition: kernel_launch.h:38
#define CUTLASS_HOST_DEVICE
Definition: cutlass.h:89
size_t dynamic_smem
Bytes of dynamically allocated SMEM in addition to static SMEM.
Definition: kernel_launch.h:47
dim3 block
CUDA threablock dimensions.
Definition: kernel_launch.h:44
dim3 grid
CUDA grid dimensions.
Definition: kernel_launch.h:41
Basic include for CUTLASS.