i) Using the program sumArraysOnGPU-timer.cu, set the block.x = 1023. Recompile and run it. Compare the result with the execution confi guration of block.x = 1024. Try to explain the difference and the reason.
ii) Refer to sumArraysOnGPU-timer.cu, and let block.x = 256. Make a new kernel to let each thread handle two elements. Compare the results with other execution confi gurations.
Using the program sumArraysOnGPU-timer.cu, set the block.x = 1023. Recompile and run it. Compare the result with the execution confi guration of block.x = 1024. Try to explain the difference and the reason.
Refer to sumArraysOnGPU-timer.cu, and let block.x = 256. Make a new kernel to let each thread handle two elements. Compare the results with other execution confi gurations.
Step 1 : Include the required files and library.
Step 2 : Declare a function sumMatrixOnHost , to perform vector summation on the host side .
Step 3 : Declare a function with __ global __ , which is a CUDA C keyword , to execute the function to perform vector summation on GPU .
Step 4 : Declare Main method/function .
Step 5 : In the Main function Set up device and data size of vector ,Allocate Host Memory and device global memory,Initialize data at host side and then add vector at host side ,transfer data from host to device.
Step 6 : Invoke kernel at host side(1023,1024,256), check for kernel error and copy kernel result back to host side.
Step 7 : Finally Free device global memory,host memory and reset device.
Step 8 : Save and Run the Program. (i) x=1023
#include "common.h" #include <cuda_runtime.h> #include <stdio.h>
/*
- This example demonstrates a simple vector sum on the GPU and on the host.
- sumArraysOnGPU splits the work of the vector sum across CUDA threads on the
- GPU. Only a single thread block is used in this small case, for simplicity.
- sumArraysOnHost sequentially iterates through vector elements on the host.
- This version of sumArrays adds host timers to measure GPU and CPU
- performance. */
void checkResult(float *hostRef, float *gpuRef, const int N) { double epsilon = 1.0E-8; bool match = 1;
for (int i = 0; i < N; i++)
{
if (abs(hostRef[i] - gpuRef[i]) > epsilon)
{
match = 0;
printf("Arrays do not match!\n");
printf("host %5.2f gpu %5.2f at current %d\n", hostRef[i],
gpuRef[i], i);
break;
}
}
if (match) printf("Arrays match.\n\n");
return;
}
void initialData(float *ip, int size) { // generate different seed for random number time_t t; srand((unsigned) time(&t));
for (int i = 0; i < size; i++)
{
ip[i] = (float)( rand() & 0xFF ) / 10.0f;
}
return;
}
void sumArraysOnHost(float *A, float *B, float *C, const int N) { for (int idx = 0; idx < N; idx++) { C[idx] = A[idx] + B[idx]; } } global void sumArraysOnGPU(float *A, float *B, float *C, const int N) { int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < N) C[i] = A[i] + B[i];
}
int main(int argc, char **argv) { printf("%s Starting...\n", argv[0]);
// set up device
int dev = 0;
cudaDeviceProp deviceProp;
CHECK(cudaGetDeviceProperties(&deviceProp, dev));
printf("Using Device %d: %s\n", dev, deviceProp.name);
CHECK(cudaSetDevice(dev));
// set up data size of vectors
int nElem = 1 << 27;
printf("Vector size %d\n", nElem);
// malloc host memory
size_t nBytes = nElem * sizeof(float);
float *h_A, *h_B, *hostRef, *gpuRef;
h_A = (float *)malloc(nBytes);
h_B = (float *)malloc(nBytes);
hostRef = (float *)malloc(nBytes);
gpuRef = (float *)malloc(nBytes);
double iStart, iElaps;
// initialize data at host side
iStart = seconds();
initialData(h_A, nElem);
initialData(h_B, nElem);
iElaps = seconds() - iStart;
printf("initialData Time elapsed %f sec\n", iElaps);
memset(hostRef, 0, nBytes);
memset(gpuRef, 0, nBytes);
// add vector at host side for result checks
iStart = seconds();
sumArraysOnHost(h_A, h_B, hostRef, nElem);
iElaps = seconds() - iStart;
printf("sumArraysOnHost Time elapsed %f sec\n", iElaps);
// malloc device global memory
float *d_A, *d_B, *d_C;
CHECK(cudaMalloc((float**)&d_A, nBytes));
CHECK(cudaMalloc((float**)&d_B, nBytes));
CHECK(cudaMalloc((float**)&d_C, nBytes));
// transfer data from host to device
CHECK(cudaMemcpy(d_A, h_A, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_B, h_B, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_C, gpuRef, nBytes, cudaMemcpyHostToDevice));
// invoke kernel at host side
int iLen = 1023;
dim3 block (iLen);
dim3 grid ((nElem + block.x - 1) / block.x);
iStart = seconds();
sumArraysOnGPU<<<grid, block>>>(d_A, d_B, d_C, nElem);
CHECK(cudaDeviceSynchronize());
iElaps = seconds() - iStart;
printf("sumArraysOnGPU <<< %d, %d >>> Time elapsed %f sec\n", grid.x,
block.x, iElaps);
// check kernel error
CHECK(cudaGetLastError()) ;
// copy kernel result back to host side
CHECK(cudaMemcpy(gpuRef, d_C, nBytes, cudaMemcpyDeviceToHost));
// check device results
checkResult(hostRef, gpuRef, nElem);
// free device global memory
CHECK(cudaFree(d_A));
CHECK(cudaFree(d_B));
CHECK(cudaFree(d_C));
// free host memory
free(h_A);
free(h_B);
free(hostRef);
free(gpuRef);
return(0);
} x=1024
#include "common.h" #include <cuda_runtime.h> #include <stdio.h>
/*
- This example demonstrates a simple vector sum on the GPU and on the host.
- sumArraysOnGPU splits the work of the vector sum across CUDA threads on the
- GPU. Only a single thread block is used in this small case, for simplicity.
- sumArraysOnHost sequentially iterates through vector elements on the host.
- This version of sumArrays adds host timers to measure GPU and CPU
- performance. */
void checkResult(float *hostRef, float *gpuRef, const int N) { double epsilon = 1.0E-8; bool match = 1;
for (int i = 0; i < N; i++)
{
if (abs(hostRef[i] - gpuRef[i]) > epsilon)
{
match = 0;
printf("Arrays do not match!\n");
printf("host %5.2f gpu %5.2f at current %d\n", hostRef[i],
gpuRef[i], i);
break;
}
}
if (match) printf("Arrays match.\n\n");
return;
}
void initialData(float *ip, int size) { // generate different seed for random number time_t t; srand((unsigned) time(&t));
for (int i = 0; i < size; i++)
{
ip[i] = (float)( rand() & 0xFF ) / 10.0f;
}
return;
}
void sumArraysOnHost(float *A, float *B, float *C, const int N) { for (int idx = 0; idx < N; idx++) { C[idx] = A[idx] + B[idx]; } } global void sumArraysOnGPU(float *A, float *B, float *C, const int N) { int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < N) C[i] = A[i] + B[i];
}
int main(int argc, char **argv) { printf("%s Starting...\n", argv[0]);
// set up device
int dev = 0;
cudaDeviceProp deviceProp;
CHECK(cudaGetDeviceProperties(&deviceProp, dev));
printf("Using Device %d: %s\n", dev, deviceProp.name);
CHECK(cudaSetDevice(dev));
// set up data size of vectors
int nElem = 1 << 27;
printf("Vector size %d\n", nElem);
// malloc host memory
size_t nBytes = nElem * sizeof(float);
float *h_A, *h_B, *hostRef, *gpuRef;
h_A = (float *)malloc(nBytes);
h_B = (float *)malloc(nBytes);
hostRef = (float *)malloc(nBytes);
gpuRef = (float *)malloc(nBytes);
double iStart, iElaps;
// initialize data at host side
iStart = seconds();
initialData(h_A, nElem);
initialData(h_B, nElem);
iElaps = seconds() - iStart;
printf("initialData Time elapsed %f sec\n", iElaps);
memset(hostRef, 0, nBytes);
memset(gpuRef, 0, nBytes);
// add vector at host side for result checks
iStart = seconds();
sumArraysOnHost(h_A, h_B, hostRef, nElem);
iElaps = seconds() - iStart;
printf("sumArraysOnHost Time elapsed %f sec\n", iElaps);
// malloc device global memory
float *d_A, *d_B, *d_C;
CHECK(cudaMalloc((float**)&d_A, nBytes));
CHECK(cudaMalloc((float**)&d_B, nBytes));
CHECK(cudaMalloc((float**)&d_C, nBytes));
// transfer data from host to device
CHECK(cudaMemcpy(d_A, h_A, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_B, h_B, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_C, gpuRef, nBytes, cudaMemcpyHostToDevice));
// invoke kernel at host side
int iLen = 1024;
dim3 block (iLen);
dim3 grid ((nElem + block.x - 1) / block.x);
iStart = seconds();
sumArraysOnGPU<<<grid, block>>>(d_A, d_B, d_C, nElem);
CHECK(cudaDeviceSynchronize());
iElaps = seconds() - iStart;
printf("sumArraysOnGPU <<< %d, %d >>> Time elapsed %f sec\n", grid.x,
block.x, iElaps);
// check kernel error
CHECK(cudaGetLastError()) ;
// copy kernel result back to host side
CHECK(cudaMemcpy(gpuRef, d_C, nBytes, cudaMemcpyDeviceToHost));
// check device results
checkResult(hostRef, gpuRef, nElem);
// free device global memory
CHECK(cudaFree(d_A));
CHECK(cudaFree(d_B));
CHECK(cudaFree(d_C));
// free host memory
free(h_A);
free(h_B);
free(hostRef);
free(gpuRef);
return(0);
}
#include "common.h" #include <cuda_runtime.h> #include <stdio.h>
/*
- This example demonstrates a simple vector sum on the GPU and on the host.
- sumArraysOnGPU splits the work of the vector sum across CUDA threads on the
- GPU. Only a single thread block is used in this small case, for simplicity.
- sumArraysOnHost sequentially iterates through vector elements on the host.
- This version of sumArrays adds host timers to measure GPU and CPU
- performance. */
void checkResult(float *hostRef, float *gpuRef, const int N) { double epsilon = 1.0E-8; bool match = 1;
for (int i = 0; i < N; i++)
{
if (abs(hostRef[i] - gpuRef[i]) > epsilon)
{
match = 0;
printf("Arrays do not match!\n");
printf("host %5.2f gpu %5.2f at current %d\n", hostRef[i],
gpuRef[i], i);
break;
}
}
if (match) printf("Arrays match.\n\n");
return;
}
void initialData(float *ip, int size) { // generate different seed for random number time_t t; srand((unsigned) time(&t));
for (int i = 0; i < size; i++)
{
ip[i] = (float)( rand() & 0xFF ) / 10.0f;
}
return;
}
void sumArraysOnHost(float *A, float *B, float *C, const int N) { for (int idx = 0; idx < N; idx++) { C[idx] = A[idx] + B[idx]; } } global void sumArraysOnGPU(float *A, float *B, float *C, const int N) { int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < N) C[i] = A[i] + B[i];
}
int main(int argc, char **argv) { printf("%s Starting...\n", argv[0]);
// set up device
int dev = 0;
cudaDeviceProp deviceProp;
CHECK(cudaGetDeviceProperties(&deviceProp, dev));
printf("Using Device %d: %s\n", dev, deviceProp.name);
CHECK(cudaSetDevice(dev));
// set up data size of vectors
int nElem = 1 << 24;
printf("Vector size %d\n", nElem);
// malloc host memory
size_t nBytes = nElem * sizeof(float);
float *h_A, *h_B, *hostRef, *gpuRef;
h_A = (float *)malloc(nBytes);
h_B = (float *)malloc(nBytes);
hostRef = (float *)malloc(nBytes);
gpuRef = (float *)malloc(nBytes);
double iStart, iElaps;
// initialize data at host side
iStart = seconds();
initialData(h_A, nElem);
initialData(h_B, nElem);
iElaps = seconds() - iStart;
printf("initialData Time elapsed %f sec\n", iElaps);
memset(hostRef, 0, nBytes);
memset(gpuRef, 0, nBytes);
// add vector at host side for result checks
iStart = seconds();
sumArraysOnHost(h_A, h_B, hostRef, nElem);
iElaps = seconds() - iStart;
printf("sumArraysOnHost Time elapsed %f sec\n", iElaps);
// malloc device global memory
float *d_A, *d_B, *d_C;
CHECK(cudaMalloc((float**)&d_A, nBytes));
CHECK(cudaMalloc((float**)&d_B, nBytes));
CHECK(cudaMalloc((float**)&d_C, nBytes));
// transfer data from host to device
CHECK(cudaMemcpy(d_A, h_A, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_B, h_B, nBytes, cudaMemcpyHostToDevice));
CHECK(cudaMemcpy(d_C, gpuRef, nBytes, cudaMemcpyHostToDevice));
// invoke kernel at host side
int iLen = 256;
dim3 block (iLen);
dim3 grid ((nElem + block.x - 1) / block.x);
iStart = seconds();
sumArraysOnGPU<<<grid, block>>>(d_A, d_B, d_C, nElem);
CHECK(cudaDeviceSynchronize());
iElaps = seconds() - iStart;
printf("sumArraysOnGPU <<< %d, %d >>> Time elapsed %f sec\n", grid.x,
block.x, iElaps);
// check kernel error
CHECK(cudaGetLastError()) ;
// copy kernel result back to host side
CHECK(cudaMemcpy(gpuRef, d_C, nBytes, cudaMemcpyDeviceToHost));
// check device results
checkResult(hostRef, gpuRef, nElem);
// free device global memory
CHECK(cudaFree(d_A));
CHECK(cudaFree(d_B));
CHECK(cudaFree(d_C));
// free host memory
free(h_A);
free(h_B);
free(hostRef);
free(gpuRef);
return(0);
}
1023 & 1024 and the elapsed time obtained on Host and GPU is compared.
The number of threads is set as 256 and the elapsed time on Host and GPU is obtained.