Page 1 of 1

double precision routines on compute capability <1.3 devices

Posted: Thu Jul 21, 2011 5:01 am
by ffox80
Hi,
MAGMA really seems great. However, I noticed that on devices with compute capability <1.3 (no double precision, afaik) the behavior is as misleading as supplied tests are.
A lot of tests, including the zgemm and dgemm tests pass without any warning, as they compare only MAGMA against CudaBLAS results. Comparing them against the CPU-Lapack results instantly reveals that the results are just wrong.
I'd also suggest to supply a warning if the double-prec routines are issued on such a device.

Thank you for your outstanding work!
Best,
Frank

Re: double precision routines on compute capability <1.3 dev

Posted: Mon Jul 25, 2011 11:33 am
by Stan Tomov
Hi,
Thank you for pointing this out. We will put this on our to-do-list, or at least to think about it. I am not sure how CUBLAS handles it. We can handle the MAGMA BLAS similarly to CUBLAS for unsupported hardware. The MAGMA (high-level) algorithms are based on BLAS so for those algorithms we can leave it up to the BLAS implementation to decide how to handle unsupported hardware.
Stan