2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2016,2017,2018,2019,2020, by the GROMACS development team, led by
5 * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
6 * and including many others, as listed in the AUTHORS file in the
7 * top-level source directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
36 /*! \libinternal \file
37 * \brief Implements the GPU region timer for CUDA.
39 * \author Aleksei Iupinov <a.yupinov@gmail.com>
44 #ifndef GMX_GPU_UTILS_GPUREGIONTIMER_CUH
45 #define GMX_GPU_UTILS_GPUREGIONTIMER_CUH
47 #include "gromacs/gpu_utils/cudautils.cuh"
48 #include "gromacs/gpu_utils/gputraits.cuh"
50 #include "gpuregiontimer.h"
52 /*! \libinternal \brief
53 * This is a GPU region timing implementation for CUDA.
54 * It provides methods for measuring the last timespan.
55 * Copying/assignment is disabled since the underlying timing events are owned by this.
57 class GpuRegionTimerImpl
59 //! The underlying timing event pair - the beginning and the end of the timespan
60 cudaEvent_t eventStart_, eventStop_;
65 const int eventFlags = cudaEventDefault;
66 CU_RET_ERR(cudaEventCreate(&eventStart_, eventFlags), "GPU timing creation failure");
67 CU_RET_ERR(cudaEventCreate(&eventStop_, eventFlags), "GPU timing creation failure");
71 CU_RET_ERR(cudaEventDestroy(eventStart_), "GPU timing destruction failure");
72 CU_RET_ERR(cudaEventDestroy(eventStop_), "GPU timing destruction failure");
75 GpuRegionTimerImpl(const GpuRegionTimerImpl&) = delete;
77 GpuRegionTimerImpl& operator=(GpuRegionTimerImpl&&) = delete;
78 //! Moving is disabled but can be considered in the future if needed
79 GpuRegionTimerImpl(GpuRegionTimerImpl&&) = delete;
81 /*! \brief Will be called before the region start. */
82 inline void openTimingRegion(const DeviceStream& deviceStream)
84 CU_RET_ERR(cudaEventRecord(eventStart_, deviceStream.stream()),
85 "GPU timing recording failure");
88 /*! \brief Will be called after the region end. */
89 inline void closeTimingRegion(const DeviceStream& deviceStream)
91 CU_RET_ERR(cudaEventRecord(eventStop_, deviceStream.stream()),
92 "GPU timing recording failure");
95 /*! \brief Returns the last measured region timespan (in milliseconds) and calls reset() */
96 inline double getLastRangeTime()
98 float milliseconds = 0.0;
99 CU_RET_ERR(cudaEventElapsedTime(&milliseconds, eventStart_, eventStop_),
100 "GPU timing update failure");
105 /*! \brief Resets internal state */
106 inline void reset() {}
108 /*! \brief Returns a new raw timing event
109 * for passing into individual GPU API calls.
110 * This is just a dummy in CUDA.
112 inline CommandEvent* fetchNextEvent() { return nullptr; }
115 //! Short-hand for external use
116 using GpuRegionTimer = GpuRegionTimerWrapper<GpuRegionTimerImpl>;