dgesv.c

#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 */

Makefile

build: dgesv_accelerate dgesv_openblas

dgesv_accelerate: dgesv.c
	clang -o $@ -DDGESV=dgesv $< -framework Accelerate

lib:
	mkdir -p $@
lib/libgfortran.dylib: | lib
	curl -L https://github.com/JuliaBinaryWrappers/CompilerSupportLibraries_jll.jl/releases/download/CompilerSupportLibraries-v0.4.3%2B0/CompilerSupportLibraries.v0.4.3.aarch64-apple-darwin-libgfortran5.tar.gz | tar -zxv lib/libg*.dylib
lib/libopenblas.dylib: lib/libgfortran.dylib | lib
	curl -L https://github.com/JuliaBinaryWrappers/OpenBLAS32_jll.jl/releases/download/OpenBLAS32-v0.3.13%2B3/OpenBLAS32.v0.3.13.aarch64-apple-darwin-libgfortran5.tar.gz | tar -zxv lib/libopenblas*.dylib

dgesv_openblas: dgesv.c lib/libopenblas.dylib
	clang -o $@ -DDGESV=dgesv_ $< -lopenblas -L./lib -Wl,-rpath,@loader_path/lib

timing_solo: build
	@echo " -> First, Accelerate on its own:"
	time ./dgesv_accelerate
	@echo " -> Second, OpenBLAS on its own: (using 4 threads, so we only get scheduled on performance cores)"
	OPENBLAS_NUM_THREADS=4 time ./dgesv_openblas

timing_oversubscribed: build
	@echo " -> Next, two Accelerates: (should be 2x the time of Accelerate)"
	./dgesv_accelerate & ./dgesv_accelerate & time wait
	@echo " -> Next, one Accelerate in the background with 4-core OpenBLAS running in the foreground:"
	./dgesv_accelerate & OPENBLAS_NUM_THREADS=4 time ./dgesv_openblas

timing_optimal: build
	@echo " -> OpenBLAS on its own: (using 3 threads, sowe leave one performance core open)"
	OPENBLAS_NUM_THREADS=3 time ./dgesv_openblas
	@echo " -> Finally, one Accelerate in the background with 3-core OpenBLAS running in the foreground:"
	./dgesv_accelerate & OPENBLAS_NUM_THREADS=3 time ./dgesv_openblas