59 lines
2.4 KiB
Plaintext
59 lines
2.4 KiB
Plaintext
/*
|
|
Copyright (c) 2014, Evghenii Gaburov
|
|
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 Intel 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 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.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#define programCount 32
|
|
#define programIndex (threadIdx.x & 31)
|
|
#define taskIndex0 (blockIdx.x*4 + (threadIdx.x >> 5))
|
|
#define taskCount0 (gridDim.x*4)
|
|
#define taskIndex1 (blockIdx.y)
|
|
#define taskCount1 (gridDim.y)
|
|
#define taskIndex2 (blockIdx.z)
|
|
#define taskCount2 (gridDim.z)
|
|
#define taskIndex (taskIndex0 + taskCount0*(taskIndex1 + taskCount1*taskIndex2))
|
|
#define taskCount (taskCount0*taskCount1*taskCount2)
|
|
#define warpIdx (threadIdx.x >> 5)
|
|
#define launch(ntx,nty,ntz,func) if (programIndex==0) func<<<dim3(((ntx)+4-1)/4,nty,ntz),128>>>
|
|
#define sync cudaDeviceSynchronize()
|
|
#define cif if
|
|
__device__ __forceinline__ static double __shfl(double x, int lane)
|
|
{
|
|
return __hiloint2double(
|
|
__shfl_xor(__double2hiint(x), lane),
|
|
__shfl_xor(__double2loint(x), lane));
|
|
|
|
}
|
|
#define shuffle(x,y) __shfl(x,y)
|
|
#define broadcast(x,y) __shfl(x,y)
|