cs_cuda_contrib.h

Go to the documentation of this file.

#ifndef __CS_CUDA_CONTRIB_H__
#define __CS_CUDA_CONTRIB_H__
 
/*============================================================================
 * CUDA utility functions, from CUDA libraries or examples itself.
 *============================================================================*/
 
/* Copyright (c) 2021, 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.
 */
 
/*----------------------------------------------------------------------------*/
 
template <class T>
__device__ __forceinline__ T warpReduceSum(unsigned int mask, T mySum) {
  for (int offset = warpSize / 2; offset > 0; offset /= 2) {
    mySum += __shfl_down_sync(mask, mySum, offset);
  }
  return mySum;
}
 
#if __CUDA_ARCH__ >= 800
// Specialize warpReduceFunc for int inputs to use __reduce_add_sync intrinsic
// when on SM 8.0 or higher
template <>
__device__ __forceinline__ int warpReduceSum<int>(unsigned int mask,
                                                  int mySum) {
  mySum = __reduce_add_sync(mask, mySum);
  return mySum;
}
#endif
 
#if (__CUDA_ARCH__ < 600)
// Atomic double add for older GPUs.
 
__device__  unsigned long long int atomicCAS(unsigned long long int *address,
                                             unsigned long long int  compare,
                                             unsigned long long int  val);
 
__device__ double atomicAddDouble(double *address, double val) {
  unsigned long long int *address_as_ull = (unsigned long long int *)address;
  unsigned long long int old = *address_as_ull, assumed;
  do {
    assumed = old;
    old = atomicCAS(address_as_ull, assumed,
                    __double_as_longlong(val + __longlong_as_double(assumed)));
  } while (assumed != old);
  return __longlong_as_double(old);
}
 
#endif
 
/*----------------------------------------------------------------------------*/
 
#endif /* __CS_CUDA_CONTRIB_H__ */