colin
/
CuPBoP
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

adding microbench frame

This commit is contained in:
Hyesoon Kim 2022-05-19 18:42:30 -04:00
parent 4ff2041677
commit 5cc096e9a3
4 changed files with 166 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
examples/microbench/cudamemcpy_test.cc Normal file
View File

@ -0,0 +1,42 @@
#include <stdio.h>
__global__
void saxpy(int n, float a, float *x, float *y)
{
int i = blockIdx.x*blockDim.x + threadIdx.x;
if (i < n) y[i] = a*x[i] + y[i];
}
int main(void)
{
int N = 1<<20;
float *x, *y, *d_x, *d_y;
x = (float*)malloc(N*sizeof(float));
y = (float*)malloc(N*sizeof(float));
cudaMalloc(&d_x, N*sizeof(float));
cudaMalloc(&d_y, N*sizeof(float));
for (int i = 0; i < N; i++) {
x[i] = 1.0f;
y[i] = 2.0f;
}
cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);
// Perform SAXPY on 1M elements
// saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);
cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);
float maxError = 0.0f;
for (int i = 0; i < N; i++)
maxError = max(maxError, abs(y[i]-4.0f));
printf("Max error: %f\n", maxError);
cudaFree(d_x);
cudaFree(d_y);
free(x);
free(y);
}

42
examples/microbench/dummy_kernel.cc Normal file
View File

@ -0,0 +1,42 @@
#include <stdio.h>
__global__
void saxpy(void)
{
int i = blockIdx.x*blockDim.x + threadIdx.x;
printf("block_id:%d thread_id:%d \n", i)
}
int main(void)
{
int N = 1<<20;
float *x, *y, *d_x, *d_y;
x = (float*)malloc(N*sizeof(float));
y = (float*)malloc(N*sizeof(float));
cudaMalloc(&d_x, N*sizeof(float));
cudaMalloc(&d_y, N*sizeof(float));
for (int i = 0; i < N; i++) {
x[i] = 1.0f;
y[i] = 2.0f;
}
cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);
// Perform SAXPY on 1M elements
saxpy<<<(1,1)>>>;
cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);
float maxError = 0.0f;
for (int i = 0; i < N; i++)
maxError = max(maxError, abs(y[i]-4.0f));
printf("Max error: %f\n", maxError);
cudaFree(d_x);
cudaFree(d_y);
free(x);
free(y);
}

41
examples/microbench/kerne_arg.cc Normal file
View File

@ -0,0 +1,41 @@
#include <stdio.h>
__global__
void saxpy(int N)
{
printf("hello!: %d\n", N);
}
int main(void)
{
int N = 1<<20;
float *x, *y, *d_x, *d_y;
x = (float*)malloc(N*sizeof(float));
y = (float*)malloc(N*sizeof(float));
cudaMalloc(&d_x, N*sizeof(float));
cudaMalloc(&d_y, N*sizeof(float));
for (int i = 0; i < N; i++) {
x[i] = 1.0f;
y[i] = 2.0f;
}
cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);
// Perform SAXPY on 1M elements
saxpy<<<(1,1)>>>(N);
cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);
float maxError = 0.0f;
for (int i = 0; i < N; i++)
maxError = max(maxError, abs(y[i]-4.0f));
printf("Max error: %f\n", maxError);
cudaFree(d_x);
cudaFree(d_y);
free(x);
free(y);
}

41
examples/microbench/one_thread_kernel.cc Normal file
View File

@ -0,0 +1,41 @@
#include <stdio.h>
__global__
void saxpy(void)
{
printf("hello!\n");
}
int main(void)
{
int N = 1<<20;
float *x, *y, *d_x, *d_y;
x = (float*)malloc(N*sizeof(float));
y = (float*)malloc(N*sizeof(float));
cudaMalloc(&d_x, N*sizeof(float));
cudaMalloc(&d_y, N*sizeof(float));
for (int i = 0; i < N; i++) {
x[i] = 1.0f;
y[i] = 2.0f;
}
cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);
// Perform SAXPY on 1M elements
saxpy<<<(1,1)>>>;
cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);
float maxError = 0.0f;
for (int i = 0; i < N; i++)
maxError = max(maxError, abs(y[i]-4.0f));
printf("Max error: %f\n", maxError);
cudaFree(d_x);
cudaFree(d_y);
free(x);
free(y);
}