Accelerate framework uses only one core on Mac M1

Question

mottelet OP

Created May ’21

Replies 2

Boosts 1

Views 2.3k

Participants 2

The following C program (dgesv_ex.c)

Code Block #include <stdlib.h>
#include <stdio.h>
/* DGESV prototype */
extern void dgesv( int* n, int* nrhs, double* a, int* lda, int* ipiv,
                double* b, int* ldb, int* info );
/* Main program */
int main() {
        /* Locals */
        int n = 10000, info;
        /* Local arrays */
        /* Initialization */
        double *a = malloc(n*n*sizeof(double));
        double *b = malloc(n*n*sizeof(double));
        int *ipiv = malloc(n*sizeof(int));
        for (int i = 0; i < n*n; i++ )
        {
                a[i] = ((double) rand()) / ((double) RAND_MAX) - 0.5;
        }
        for(int i=0;i<n*n;i++)
        {
            b[i] = ((double) rand()) / ((double) RAND_MAX) - 0.5;
        }
        /* Solve the equations A*X = B */
        dgesv( &n, &n, a, &n, ipiv, b, &n, &info );
        free(a);
        free(b);
        free(ipiv);
        exit( 0 );
} /* End of DGESV Example */

compiled on a Mac mini M1 with the command

Code Block clang -o dgesv_ex dgesv_ex.c -framework accelerate

uses only one core of the processor (as also shown by the activity monitor)

Code Block me@macmini-M1 ~ % time ./dgesv_ex 
./dgesv_ex  35,54s user 0,27s system 100% cpu 35,758 total

I checked that the binary is of the right type:

Code Block me@macmini-M1 ~  % lipo -info dgesv
Non-fat file: dgesv is architecture: arm64

As a comparaison, on my Intel MacBook Pro I get the following output :

Code Block me@macbook-intel ˜ % time ./dgesv_ex
./dgesv_ex  142.69s user 0,51s system 718% cpu 19.925 total

Is it a known problem ? Maybe a compilation flag or else ?

Boost

Answer 1

Engineer OP

Apple

Jun ’21

This is expected (and not a problem!). For sufficiently large matrices on Apple Silicon, linear algebra is performed using the AMX engine, which can be driven by a single core, allowing the other cores to do other work.

2

Answer 2

mottelet OP

Jul ’21

Ok, then, prove it with some piece of code...

S.

0