Apple ships a tuned ATLAS with every MacOS X 10.2. It is
multi-processor aware for selected routines (e.g. dgemm).
It is part of the vecLib framework;
#include <vecLib/vecLib.h>
cc myMath.c -framework vecLib
In many cases the BLAS can be directed to treat a given matirx in its
natural *or* its transposed form.
The costly storage accesses needed to perform an explicit transpose can
then be avoided completely.
See, for example,the parameters Order,TransA, and TransB passed to
cblas_dgemm:
void cblas_dgemm(const enum CBLAS_ORDER Order, const enum
CBLAS_TRANSPOSE TransA,
const enum CBLAS_TRANSPOSE TransB, const int M, const
int N,
const int K, const double alpha, const double *A,
const int lda, const double *B, const int ldb,
const double beta, double *C, const int ldc);
"vecLib -- one-stop shopping for your performance math needs."
Steve Peters
Numerics and Vectorization
Apple Computer, Inc.
_______________________________________________
scitech mailing list | email@hidden
Help/Unsubscribe/Archives: http://www.lists.apple.com/mailman/listinfo/scitech
Do not post admin requests to the list. They will be ignored.
