double precision routines on compute capability <1.3 devices

Open discussion for MAGMA library (Matrix Algebra on GPU and Multicore Architectures)

double precision routines on compute capability <1.3 devices

Postby ffox80 » Thu Jul 21, 2011 5:01 am

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!
Posts: 7
Joined: Thu Jul 21, 2011 4:26 am

Re: double precision routines on compute capability <1.3 dev

Postby Stan Tomov » Mon Jul 25, 2011 11:33 am

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 Tomov
Posts: 258
Joined: Fri Aug 21, 2009 10:39 pm

Return to User discussion

Who is online

Users browsing this forum: No registered users and 1 guest