MAGMA Forum

Hi, what is exactly your problem ? Do you have a segfault ? do you have a problem of precision in the result ? What is the size ? What is your configuration ? The only thing I see, is that you need to have ldda and lddb multiple of 32 for LU and at one point your are using ldda instead of lddb but i...

John,

thanks for this, we were searching how to handle that too. And we were thinking about providing a function to the user to compute the correct pointer on the device, but it will probably work for MAGMA and not for cublas.

Mathieu

Hi, Now I see. This routines are part of the functions we still need to port on four precisions, everything has been done in src directory (LAPACK functions), but there is still a lot of work in magmablas directory and most of it will be probably included by NVIDIA. We will add define to the correct...

Hi,

it just means that you don't have enough memory to run the default configuration.
You should try to specify M and N:
./testing_zgetrf_gpu -M 1024 -N 1024

Mathieu

Hi,

I note that and I will try to get it fixed.

Mathieu

Hi, I won't enter into details, but quark should have not appear into the previous release. The new directory control contains all the workaround of MAGMA and will contains the future functions for initialisation of MAGMA library in a context for using different cards for example or multi-threaded c...

Hi, I will check, because I haven't work on this paper, but I think that the difference of performance you get on these routines is due to the cublasAlloc that we added to the function to make it user friendly. When the workspace is allocated once out of the function, it can change a lot the perform...

Hi,

you probably have to replace f2c by gftortran. f2c was the library used by f77 and has been changed with the gfortran compiler.

Mathieu

Hi,

it's part of our plan. In a first shot we will provide the possibility to compile two different libraries with different symbols, and we will think how to merge them in only one library. But it will be probably for next month, not before.

Mathieu

Hi,

thank you to be interrested in contributing to MAGMA, you can send the patch directly to me and Stan at [mfaverge, tomov] AT eecs.utk.edu
I will try to integrate it as fast as possible.

Thanks,
Mathieu