57
edits
Changes
→Kernel Version 2
{| class="wikitable mw-collapsible mw-collapsed"
! Flat profileCall Graph
|-
|
{| class="wikitable mw-collapsible mw-collapsed"
! Flat profileCall Graph
|-
|
=== Assignment 2 ===
# include <iostream> # include <iomanip> # include <ctime> # include <chrono> # include <cstdlib> # include <cmath> #include <cuda_runtime.h> using namespace std; using namespace std::chrono; const double pi =3.141592653589793; const int ntpb ===CUDA enabled functions====1024;The main function was changed to perform the copying of data from host to device, launch the kernel, copy back results from the device to host and release all memory, on host and device. void cosine_transform_test01 ( int size );
}
}
}
void cosine_transform_test01 ( int size){ int n =size; int seed; double *r; double *hs; double *s =new double[n]; double *d_a; double *d_b; //allocate memory on the device for the randomly generated array and for the array in which transform values will be stored cudaMalloc((void**)&d_a,sizeof(double) * n); cudaMalloc((void**)&d_b,sizeof(double) * n); seed =123456789; r =Profiling resultsr8vec_uniform_01_new ( n, seed ); //copy randomly generated values from host to device cudaMemcpy(d_a,r,sizeof(double)*n,cudaMemcpyHostToDevice); int nblks =(n + ntpb - 1) / ntpb; steady_clock::time_point ts, te; ts =steady_clock::now(); cosTransformKernel<<<nblks,ntpb>>>(d_a,d_b,size); cudaDeviceSynchronize(); te =steady_clock::now(); reportTime("Cosine Transform on device",te-ts); cudaMemcpy(s,d_b,sizeof(double)*n,cudaMemcpyDeviceToHost); ts =steady_clock::now(); hs = cosine_transform_data ( n, r ); te = steady_clock::now(); reportTime("Cosine Transform on host",te-ts); cudaFree(d_a); cudaFree(d_b); delete [] r; delete [] s; delete [] hs;} |} The graph for the execution time difference between the device and the host looks like: [[File:kernel1.png]] Even though the kernel includes a for-loop the execution time has decreased drastically. Thats because each thread is now responsible for one calculating one element of the final Cos transformed matrix(unit vector).
=== Assignment 3 ===
For optimizing the code better, we thought of removing the iterative loop from the kernel by using threadIdx.y to control calculation of each element's cosine for that position in the supposed matrix. The problem in this was that each thread was in a racing condition to write to the same memory location, to sum up the cosine transformations for all elements of that row. We solved this by using the atomic function. Its prototype is as follows.
double atomicAdd(double* address, double value)
=====Kernel Version 2=====
{| class="wikitable mw-collapsible mw-collapsed"
! Kernel 2
|-
|
# include <cmath>
# include <cstdlib>
# include <iostream>
# include <iomanip>
# include <ctime>
# include <chrono>
# include <cstdlib>
# include <cmath>
#include <limits>
#include <cuda_runtime.h>
#include <cuda.h>
using namespace std;
using namespace std::chrono;
const double pi = 3.141592653589793;
const unsigned ntpb = 32;
void cosine_transform_test01 ( int size );
double *r8vec_uniform_01_new ( int n, int &seed ){
int i;
const int i4_huge = 2147483647;
int k;
double *r;
if ( seed == 0 ){
cerr << "\n";
cerr << "R8VEC_UNIFORM_01_NEW - Fatal error!\n";
cerr << " Input value of SEED = 0.\n";
exit ( 1 );
}
r = new double[n];
for ( i = 0; i < n; i++ ){
k = seed / 127773;
seed = 16807 * ( seed - k * 127773 ) - k * 2836;
if ( seed < 0 ){
seed = seed + i4_huge;
}
r[i] = ( double ) ( seed ) * 4.656612875E-10;
}
return r;
}
double *cosine_transform_data ( int n, double d[] ){
double angle;
double *c;
int i;
int j;
c = new double[n];
for ( i = 0; i < n; i++ ){
c[i] = 0.0;
for ( j = 0; j < n; j++ ){
angle = pi * ( double ) ( i * ( 2 * j + 1 ) ) / ( double ) ( 2 * n );
c[i] = c[i] + cos ( angle ) * d[j];
}
c[i] = c[i] * sqrt ( 2.0 / ( double ) ( n ) );
}
return c;
}
void reportTime(const char* msg, steady_clock::duration span) {
auto ms = duration_cast<milliseconds>(span);
std::cout << msg << " - took - " <<
ms.count() << " millisecs" << std::endl;
}
__global__ void cosTransformKernel(double *a, double *b, const int n){
double angle;
const double pi = 3.141592653589793;
int j = blockIdx.x * blockDim.x + threadIdx.x;
int i = blockIdx.y * blockDim.y + threadIdx.y;
if(i<n && j<n){
angle = pi * ( double ) ( i * ( 2 * j + 1 ) ) / ( double ) ( 2 * n );
double value = cos ( angle ) * a[j];
b[i] = atomicAdd(&b[i], value);
}
//square root of the whole cos transformed row term
if(j==n-1 && i<n){
b[i] *= sqrt ( 2.0 / ( double ) ( n ) );
}
}
int main (int argc, char* argv[] ){
if (argc != 2) {
std::cerr << argv[0] << ": invalid number of arguments\n";
std::cerr << "Usage: " << argv[0] << " size_of_vector\n";
return 1;
}
int n = std::atoi(argv[1]);
cosine_transform_test01 (n);
return 0;
}
void cosine_transform_test01 ( int size){
int n = size;
int seed;
double *r;
double *hs; //host side pointer to store the array returned from host side cosine_transform_data, for comparison purposes
double *s = new double[n];
//double *t;
double *d_a;
double *d_b;
//allocate memory on the device for the randomly generated array and for the array in which transform values will be stored
cudaMalloc((void**)&d_a,sizeof(double) * n);
cudaMalloc((void**)&d_b,sizeof(double) * n);
seed = 123456789;
r = r8vec_uniform_01_new ( n, seed );
//copy randomly generated values from host to device
for(int i=0; i<n; i++)
s[i]=0.0;
cudaMemcpy(d_a,r,sizeof(double)*n,cudaMemcpyHostToDevice);
cudaMemcpy(d_b,s,sizeof(double)*n,cudaMemcpyHostToDevice);
int nblks = (n + ntpb - 1) / ntpb;
dim3 grid(nblks,nblks,1);
dim3 block(ntpb,ntpb,1);
steady_clock::time_point ts, te;
ts = steady_clock::now();
cosTransformKernel<<<grid,block>>>(d_a,d_b,size);
cudaDeviceSynchronize();
te = steady_clock::now();
reportTime("Cosine Transform on device",te-ts);
cudaMemcpy(s,d_b,sizeof(double)*n,cudaMemcpyDeviceToHost);
ts = steady_clock::now();
hs = cosine_transform_data ( n, r );
te = steady_clock::now();
reportTime("Cosine Transform on host",te-ts);
cudaFree(d_a);
cudaFree(d_b);
delete [] r;
delete [] s;
delete [] hs;
//delete [] t;
return;
}
|}
Here is a comparison between the naive and optimized kernel
[[File:kernel2.jpg]]
Evidently, there is some performance boost for the new version. However, each call to atomicAdd by a thread locks the global memory until the old value is read and added to the passed value. This deters faster execution as might be expected.