cuda 内存拷贝速率

cuda 内存拷贝速率问题

`` CPU与GPU之间内存拷贝速率，一个9M的图片，CPU->GPU耗时9ms，GPU->CPU耗时11ms，项目要求处理的是大图，对每一个像素点做处理，以400M的图片为例子，cpu与gpu之间拷贝均耗时200多ms。显卡带宽为192GB/s，(我认为的)正常情况应该传输速率很快，请问一下有什么需要修改的地方吗（刚刚接触GPU的萌新）。下图为GPU型号：

void Binaryzation_GPU(CppColorRange* range_host,byte* src_host, byte* dst_host, int width, int height)
{
	int length = width * height;
	int memSize = length * sizeof(uchar4);
	CppColorRange range_devive = *range_host;
	uchar4* src_device;
	uchar4* dst_device;
	cudaMalloc((void**)&src_device, memSize);
	cudaMallocHost((void**)&dst_device, memSize);
	//copy
	cudaMemcpy((void**)src_device, src_host, memSize, cudaMemcpyHostToDevice);
	cudaMemcpy((void**)dst_device, dst_host, memSize, cudaMemcpyHostToDevice);
	dim3 threadsPerBlock(32, 32);
	dim3 blocksPerGrid((width + threadsPerBlock.x - 1) / threadsPerBlock.x, (height + threadsPerBlock.y - 1) / threadsPerBlock.y);
	cudaDeviceSynchronize();
	kernel_Binaryzation << <blocksPerGrid, threadsPerBlock >> >(range_devive, src_device, dst_device, width, height);
	cudaMemcpy((void**)dst_host, dst_device, memSize, cudaMemcpyDeviceToHost);
	cudaFree(src_device);
	cudaFree(dst_device);
}