cublas padding zeros

[BlahCuda]

I’ve noticed that cublas dgemm is noticeably faster when the dimensions of the input matrices are multiples of 32 (it might be some other number e.g. 16, 64, etc. but I haven’t tried narrowing it down yet). Given this is the case, is it a good idea to extend the matrix size by padding the entries with zeroes? Are there routines that automatically take care of this process on the GPU?

EDIT: I’ve noticed that the MAGMA library optimizes well with square matrices but same can’t be said for rectangular matrices.

[avidday]

Just use cudaMemset() to zero the padded device array first, then copy the “valid” data on top of the zeroed array.

[LSChien]

I’ve noticed that cublas dgemm is noticeably faster when the dimensions of the input matrices are multiples of 32 (it might be some other number e.g. 16, 64, etc. but I haven’t tried narrowing it down yet). Given this is the case, is it a good idea to extend the matrix size by padding the entries with zeroes? Are there routines that automatically take care of this process on the GPU?

EDIT: I’ve noticed that the MAGMA library optimizes well with square matrices but same can’t be said for rectangular matrices.

suppose you do C = A * B

do you try to set lda (leading dimension of matrix A), and ldc to be multiple of 32 even

dimension of A, C is not multiple of 32?

DGEMM of CUBLAS has large variation when you sweep dimension N.

you can use Volkov’s code, it is more uniform on performance.