1
我在寫一個簡單的CUDA程序進行性能測試。
這與矢量計算無關,但僅用於簡單(並行)字符串轉換。CUDA性能測試
#include <stdio.h>
#include <string.h>
#include <cuda_runtime.h>
#define UCHAR unsigned char
#define UINT32 unsigned long int
#define CTX_SIZE sizeof(aes_context)
#define DOCU_SIZE 4096
#define TOTAL 100000
#define BBLOCK_SIZE 500
UCHAR pH_TXT[DOCU_SIZE * TOTAL];
UCHAR pH_ENC[DOCU_SIZE * TOTAL];
UCHAR* pD_TXT;
UCHAR* pD_ENC;
__global__
void TEST_Encode(UCHAR *a_input, UCHAR *a_output)
{
UCHAR *input;
UCHAR *output;
input = &(a_input[threadIdx.x * DOCU_SIZE]);
output = &(a_output[threadIdx.x * DOCU_SIZE]);
for (int i = 0 ; i < 30 ; i++) {
if ((input[i] >= 'a') && (input[i] <= 'z')) {
output[i] = input[i] - 'a' + 'A';
}
else {
output[i] = input[i];
}
}
}
int main(int argc, char** argv)
{
struct cudaDeviceProp xCUDEV;
cudaGetDeviceProperties(&xCUDEV, 0);
// Prepare Source
memset(pH_TXT, 0x00, DOCU_SIZE * TOTAL);
for (int i = 0 ; i < TOTAL ; i++) {
strcpy((char*)pH_TXT + (i * DOCU_SIZE), "hello world, i need an apple.");
}
// Allocate vectors in device memory
cudaMalloc((void**)&pD_TXT, DOCU_SIZE * TOTAL);
cudaMalloc((void**)&pD_ENC, DOCU_SIZE * TOTAL);
// Copy vectors from host memory to device memory
cudaMemcpy(pD_TXT, pH_TXT, DOCU_SIZE * TOTAL, cudaMemcpyHostToDevice);
// Invoke kernel
int threadsPerBlock = BLOCK_SIZE;
int blocksPerGrid = (TOTAL + threadsPerBlock - 1)/threadsPerBlock;
printf("Total Task is %d\n", TOTAL);
printf("block size is %d\n", threadsPerBlock);
printf("repeat cnt is %d\n", blocksPerGrid);
TEST_Encode<<<blocksPerGrid, threadsPerBlock>>>(pD_TXT, pD_ENC);
cudaMemcpy(pH_ENC, pD_ENC, DOCU_SIZE * TOTAL, cudaMemcpyDeviceToHost);
// Free device memory
if (pD_TXT) cudaFree(pD_TXT);
if (pD_ENC) cudaFree(pD_ENC);
cudaDeviceReset();
}
當我BLOCK_SIZE值更改爲2至1000,我得到了下面的持續時間(從NVIDIA視覺分析器)
TOTAL BLOCKS BLOCK_SIZE Duration(ms)
100000 50000 2 28.22
100000 10000 10 22.223
100000 2000 50 12.3
100000 1000 100 9.624
100000 500 200 10.755
100000 250 400 29.824
100000 200 500 39.67
100000 100 1000 81.268
我的GPU是的GeForce GT520,最大threadsPerBlock值是1024,所以我預測當BLOCK爲1000時我會獲得最佳性能,但上表顯示不同的結果。
我不明白爲什麼持續時間不是線性的,我該如何解決這個問題。 (或者我怎麼能找到優化的花紋塊值(mimimum持續時間)