GPU621/Intel oneMKL - Math Kernel Library
Intel® oneAPI Math Kernel Library
Group Members
- Menglin Wu
- Syed Muhammad Saad Bukhari
- Lin Xu
Introduction
Intel Math Kernel Library, or now known as oneMKL (as part of Intel’s oneAPI), is a library of highly optimized and extensively parallelized routines, that was built to provide maximum performance across a variety of CPUs and accelerators.
There are many functions included in domains such as sparse and dense linear algebra, sparse solvers, fast Fourier transforms, random number generation, basic statistics etc., and there are many routines supported by the DPC++ Interface on CPU and GPU.
Progress Report
progress 100%
Setting up MKL
First, you need to download the mkl library from the intel official website through the URL: https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html
Then you need to set additional include directories and additional library directories on visual studio, don’t forget to change the configuration and platform.
Finally, modify the additional dependencies with the help of the URL https://www.intel.com/content/www/us/en/developer/tools/oneapi/onemkl-link-line-advisor.html
MKL Testing
In this project I want to compare the running time of the serial version and the optimized version of MKL under multithreading.
serial version
clock_t startTime = clock();
for (i = 0; i < m; i++) {
for (j = 0; j < n; j++) {
sum = 0.0;
for (k = 0; k < p; k++)
sum += A[p * i + k] * B[n * k + j];
C[n * i + j] = sum;
}
}
clock_t endTime = clock();
MKL version
Used to set the number of threads that MKL runs, mkl_set_num_threads().
max_threads = mkl_get_max_threads();
printf(" Finding max number %d of threads Intel(R) MKL can use for parallel runs \n\n", max_threads);
printf(" Running Intel(R) MKL from 1 to %i threads \n\n", max_threads * 2);
for (i = 1; i <= max_threads * 2; i++) {
for (j = 0; j < (m * n); j++)
C[j] = 0.0;
mkl_set_num_threads(i);
cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
m, n, p, alpha, A, p, B, n, beta, C, n);
s_initial = dsecnd();
for (r = 0; r < LOOP_COUNT; r++) {
cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
m, n, p, alpha, A, p, B, n, beta, C, n);
}
s_elapsed = (dsecnd() - s_initial) / LOOP_COUNT;
https://raw.githubusercontent.com/MenglinWu9527/m3u/main/Snipaste_2021-12-01_00-20-37.jpeg
| serial | 1 | 2 | 3 | 4 | 5 | 6 |
|---|---|---|---|---|---|---|
| 9000 | 15.7 | 7.7 | 6.4 | 8.1 | 7.4 | 7.5 |
Here is my computer's number of logical processors.
wmic:root\cli>cpu get numberoflogicalprocessors
NumberOfLogicalProcessors
6
When mkl_get_max_threads is equal to the number of physical cores, the performance is the best, not the number of threads, which is the following 3 instead of 6.
Source Code
Serial
- include <stdio.h>
- include <stdlib.h>
- include <time.h>
/* Consider adjusting LOOP_COUNT based on the performance of your computer */ /* to make sure that total run time is at least 1 second */
- define LOOP_COUNT 220 //220 for more accurate statistics
int main() {
double* A, * B, * C; int m, n, p, i, j, k, r; double alpha, beta; double sum; double s_initial, s_elapsed;
printf("\n This example demonstrates threading impact on computing real matrix product \n"
" C=alpha*A*B+beta*C using Intel(R) MKL function dgemm, where A, B, and C are \n"
" matrices and alpha and beta are double precision scalars \n\n");
m = 2000, p = 200, n = 1000;
printf(" Initializing data for matrix multiplication C=A*B for matrix \n"
" A(%ix%i) and matrix B(%ix%i)\n\n", m, p, p, n);
alpha = 1.0; beta = 0.0;
printf(" Allocating memory for matrices aligned on 64-byte boundary for better \n"
" performance \n\n");
A = (double*)malloc(m * p * sizeof(double), 64);
B = (double*)malloc(p * n * sizeof(double), 64);
C = (double*)malloc(m * n * sizeof(double), 64);
if (A == NULL || B == NULL || C == NULL) {
printf("\n ERROR: Can't allocate memory for matrices. Aborting... \n\n");
free(A);
free(B);
free(C);
return 1;
}
printf(" Intializing matrix data \n\n");
for (i = 0; i < (m * p); i++) {
A[i] = (double)(i + 1);
}
for (i = 0; i < (p * n); i++) {
B[i] = (double)(-i - 1);
}
for (i = 0; i < (m * n); i++) {
C[i] = 0.0;
}
clock_t startTime = clock();
for (i = 0; i < m; i++) {
for (j = 0; j < n; j++) {
sum = 0.0;
for (k = 0; k < p; k++)
sum += A[p * i + k] * B[n * k + j];
C[n * i + j] = sum;
}
}
clock_t endTime = clock();
s_elapsed = (endTime - startTime) / LOOP_COUNT;
printf(" == Matrix multiplication using triple nested loop completed == \n"
" == at %.5f milliseconds == \n\n", (s_elapsed * 1000));
printf(" Deallocating memory \n\n");
free(A);
free(B);
free(C);
if (s_elapsed < 0.9 / LOOP_COUNT) {
s_elapsed = 1.0 / LOOP_COUNT / s_elapsed;
i = (int)(s_elapsed * LOOP_COUNT) + 1;
printf(" It is highly recommended to define LOOP_COUNT for this example on your \n"
" computer as %i to have total execution time about 1 second for reliability \n"
" of measurements\n\n", i);
}
printf(" Example completed. \n\n");
return 0;
}
MKL version
- include <stdio.h>
- include <stdlib.h>
- include "mkl.h"
/* Consider adjusting LOOP_COUNT based on the performance of your computer */ /* to make sure that total run time is at least 1 second */
- define LOOP_COUNT 220 // 220 for more accurate statistics
int main() {
double* A, * B, * C;
int m, n, p, i, j, r, max_threads;
double alpha, beta;
double s_initial, s_elapsed;
printf("\n This example demonstrates threading impact on computing real matrix product \n"
" C=alpha*A*B+beta*C using Intel(R) MKL function dgemm, where A, B, and C are \n"
" matrices and alpha and beta are double precision scalars \n\n");
m = 2000, p = 200, n = 1000;
printf(" Initializing data for matrix multiplication C=A*B for matrix \n"
" A(%ix%i) and matrix B(%ix%i)\n\n", m, p, p, n);
alpha = 1.0; beta = 0.0;
printf(" Allocating memory for matrices aligned on 64-byte boundary for better \n"
" performance \n\n");
A = (double*)mkl_malloc(m * p * sizeof(double), 64);
B = (double*)mkl_malloc(p * n * sizeof(double), 64);
C = (double*)mkl_malloc(m * n * sizeof(double), 64);
if (A == NULL || B == NULL || C == NULL) {
printf("\n ERROR: Can't allocate memory for matrices. Aborting... \n\n");
mkl_free(A);
mkl_free(B);
mkl_free(C);
return 1;
}
printf(" Intializing matrix data \n\n");
for (i = 0; i < (m * p); i++) {
A[i] = (double)(i + 1);
}
for (i = 0; i < (p * n); i++) {
B[i] = (double)(-i - 1);
}
for (i = 0; i < (m * n); i++) {
C[i] = 0.0;
}
max_threads = mkl_get_max_threads();
printf(" Finding max number %d of threads Intel(R) MKL can use for parallel runs \n\n", max_threads);
printf(" Running Intel(R) MKL from 1 to %i threads \n\n", max_threads * 2);
for (i = 1; i <= max_threads * 2; i++) {
for (j = 0; j < (m * n); j++)
C[j] = 0.0;
mkl_set_num_threads(i);
cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
m, n, p, alpha, A, p, B, n, beta, C, n);
s_initial = dsecnd();
for (r = 0; r < LOOP_COUNT; r++) {
cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
m, n, p, alpha, A, p, B, n, beta, C, n);
}
s_elapsed = (dsecnd() - s_initial) / LOOP_COUNT;
printf(" == Matrix multiplication using Intel(R) MKL dgemm completed ==\n"
" == at %.5f milliseconds using %d thread(s) ==\n\n", (s_elapsed * 1000), i);
}
printf(" Deallocating memory \n\n");
mkl_free(A);
mkl_free(B);
mkl_free(C);
if (s_elapsed < 0.9 / LOOP_COUNT) {
s_elapsed = 1.0 / LOOP_COUNT / s_elapsed;
i = (int)(s_elapsed * LOOP_COUNT) + 1;
printf(" It is highly recommended to define LOOP_COUNT for this example on your \n"
" computer as %i to have total execution time about 1 second for reliability \n"
" of measurements\n\n", i);
}
printf(" Example completed. \n\n");
return 0;
}