Source code that accompanies The CUDA Handbook.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 

52 lines
2.0 KiB

/*
*
* atomicFloat.cu
*
* Microdemo for atomic floating point addition in global memory.
*
* NOT INTENDED AS A SAMPLE FOR ANYTHING OTHER THAN CODE GENERATION.
*
* Build with:
* nvcc --gpu-architecture sm_20 --cubin atomicFloat.cu
* cuobjdump --dump-sass atomicFloat.cubin
*
* Copyright (c) 2011-2012, Archaea Software, LLC.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "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.
*
*/
__global__ void
AddToFloat( float *sum, float *out, const float *pIn )
{
(void) atomicAdd( &out[threadIdx.x], pIn[threadIdx.x] );
}
__global__ void
ReturnFloat( float *sum, float *out, const float *pIn )
{
out[threadIdx.x] = atomicAdd( &out[threadIdx.x], pIn[threadIdx.x] );
}