You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
75 lines
2.3 KiB
Plaintext
75 lines
2.3 KiB
Plaintext
// Copyright NVIDIA Corporation 2007 -- Ignacio Castano <icastano@nvidia.com>
|
|
//
|
|
// Permission is hereby granted, free of charge, to any person
|
|
// obtaining a copy of this software and associated documentation
|
|
// files (the "Software"), to deal in the Software without
|
|
// restriction, including without limitation the rights to use,
|
|
// copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
// copies of the Software, and to permit persons to whom the
|
|
// Software is furnished to do so, subject to the following
|
|
// conditions:
|
|
//
|
|
// The above copyright notice and this permission notice shall be
|
|
// included in all copies or substantial portions of the Software.
|
|
//
|
|
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
// EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
|
|
// OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
// NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
|
|
// HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
|
|
// WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
// FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
|
|
// OTHER DEALINGS IN THE SOFTWARE.
|
|
|
|
#include <stdlib.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <math.h>
|
|
|
|
#include "CudaMath.h"
|
|
|
|
#define THREAD_COUNT 256
|
|
#define MAX_KERNEL_WIDTH 32
|
|
|
|
|
|
#if __DEVICE_EMULATION__
|
|
#define __debugsync() __syncthreads()
|
|
#else
|
|
#define __debugsync()
|
|
#endif
|
|
|
|
|
|
__constant__ float kernel[MAX_KERNEL_WIDTH];
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
// Monophase X convolution filter
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
// Monophase Y convolution filter
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
// Setup kernel
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
extern "C" void setupConvolveKernel(const float * k, int w)
|
|
{
|
|
w = min(w, MAX_KERNEL_WIDTH);
|
|
cudaMemcpyToSymbol(kernel, k, sizeof(float) * w, 0);
|
|
}
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
// Launch kernel
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
|
|
|
|
|
|
|