1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
|
/* Copyright (c) 2022, 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.
*/
// Utilities and system includes
#include <helper_cuda.h>
// clamp x to range [a, b]
__device__ float clamp(float x, float a, float b) { return max(a, min(b, x)); }
__device__ int clamp(int x, int a, int b) { return max(a, min(b, x)); }
// convert floating point rgb color to 8-bit integer
__device__ int rgbToInt(float r, float g, float b) {
r = clamp(r, 0.0f, 255.0f);
g = clamp(g, 0.0f, 255.0f);
b = clamp(b, 0.0f, 255.0f);
return (int(b) << 16) | (int(g) << 8) | int(r);
}
__global__ void cudaProcess(unsigned int *g_odata, int imgw) {
extern __shared__ uchar4 sdata[];
int tx = threadIdx.x;
int ty = threadIdx.y;
int bw = blockDim.x;
int bh = blockDim.y;
int x = blockIdx.x * bw + tx;
int y = blockIdx.y * bh + ty;
uchar4 c4 = make_uchar4((x & 0x20) ? 100 : 0, 0, (y & 0x20) ? 100 : 0, 0);
g_odata[y * imgw + x] = rgbToInt(c4.z, c4.y, c4.x);
}
extern "C" void launch_cudaProcess(dim3 grid, dim3 block, int sbytes,
unsigned int *g_odata, int imgw) {
cudaProcess<<<grid, block, sbytes>>>(g_odata, imgw);
}
|
