总之,我编写了一个非常简单的 OpenCL 内核,它使用简单的平均将 RGB 图像转换为灰度。
一些背景:
- 图像存储在映射内存中,作为 24 位非填充内存块
- 输出数组存储在固定内存中(映射为
clEnqueueMapBuffer
),大小为 8 bpp - 设备上分配了两个缓冲区(
clCreateBuffer
),一个是专门读取的(我们clWriteBuffer
在内核启动之前进入),另一个是专门写入(我们clReadBuffer
在内核完成之后)
我在 1280x960 图像上运行它。该算法的串行版本平均为 60 毫秒,OpenCL 内核平均为 200 毫秒!!!我做错了什么,但我不知道如何进行,优化什么。(在没有内核调用的情况下计时我的读/写,算法在 15 毫秒内运行)
我正在附加内核设置(大小和参数)以及内核
编辑:所以我写了一个更笨的内核,它内部没有全局内存访问,它只有 150 毫秒......这仍然非常慢。我想也许我搞砸了全局内存读取,它们必须是 4 字节对齐的还是什么?没有...
编辑2:从我的内核中删除所有参数给了我显着的加速......我很困惑我认为既然我是clEnqueueWriteBuffer
内核应该不从主机->设备和设备->主机进行内存传输... .
编辑3:想通了,但我仍然不明白为什么。如果有人能解释一下,我很乐意为他们提供正确的答案。问题是按值传递自定义结构。看起来我需要为他们分配一个全局内存位置并传递他们cl_mem
的 s
内核调用:
//Copy input to device
result = clEnqueueWriteBuffer(handles->queue, d_input_data, CL_TRUE, 0, h_input.widthStep*h_input.height, (void *)input->imageData, 0, 0, 0);
if(check_result(result, "opencl_rgb_to_gray", "Failed to write to input buffer on device!")) return 0;
//Set kernel arguments
result = clSetKernelArg(handles->current_kernel, 0, sizeof(OpenCLImage), (void *)&h_input);
if(check_result(result, "opencl_rgb_to_gray", "Failed to set input struct.")) return 0;
result = clSetKernelArg(handles->current_kernel, 1, sizeof(cl_mem), (void *)&d_input_data);
if(check_result(result, "opencl_rgb_to_gray", "Failed to set input data.")) return 0;
result = clSetKernelArg(handles->current_kernel, 2, sizeof(OpenCLImage), (void *)&h_output);
if(check_result(result, "opencl_rgb_to_gray", "Failed to set output struct.")) return 0;
result = clSetKernelArg(handles->current_kernel, 3, sizeof(cl_mem), (void *)&d_output_data);
if(check_result(result, "opencl_rgb_to_gray", "Failed to set output data.")) return 0;
//Determine run parameters
global_work_size[0] = input->width;//(unsigned int)((input->width / (float)local_work_size[0]) + 0.5);
global_work_size[1] = input->height;//(unsigned int)((input->height/ (float)local_work_size[1]) + 0.5);
printf("Global Work Group Size: %d %d\n", global_work_size[0], global_work_size[1]);
//Call kernel
result = clEnqueueNDRangeKernel(handles->queue, handles->current_kernel, 2, 0, global_work_size, local_work_size, 0, 0, 0);
if(check_result(result, "opencl_rgb_to_gray", "Failed to run kernel!")) return 0;
result = clFinish(handles->queue);
if(check_result(result, "opencl_rgb_to_gray", "Failed to finish!")) return 0;
//Copy output
result = clEnqueueReadBuffer(handles->queue, d_output_data, CL_TRUE, 0, h_output.widthStep*h_output.height, (void *)output->imageData, 0, 0, 0);
if(check_result(result, "opencl_rgb_to_gray", "Failed to write to output buffer on device!")) return 0;
核心:
typedef struct OpenCLImage_t
{
int width;
int widthStep;
int height;
int channels;
} OpenCLImage;
__kernel void opencl_rgb_kernel(OpenCLImage input, __global unsigned char* input_data, OpenCLImage output, __global unsigned char * output_data)
{
int pixel_x = get_global_id(0);
int pixel_y = get_global_id(1);
unsigned char * cur_in_pixel, *cur_out_pixel;
float avg = 0;
cur_in_pixel = (unsigned char *)(input_data + pixel_y*input.widthStep + pixel_x * input.channels);
cur_out_pixel = (unsigned char *)(output_data + pixel_y*output.widthStep + pixel_x * output.channels);
avg += cur_in_pixel[0];
avg += cur_in_pixel[1];
avg+= cur_in_pixel[2];
avg /=3.0f;
if(avg > 255.0)
avg = 255.0;
else if(avg < 0)
avg = 0;
*cur_out_pixel = avg;
}