Search found 279 matches

by Stan Tomov
Wed Apr 14, 2010 12:39 pm
Forum: User discussion
Topic: MAGMA for NVIDIA FERMI
Replies: 1
Views: 9458

Re: MAGMA for NVIDIA FERMI

Hi Allan,
Sorry for the delay.
We are getting a Fermi and see if something has to be changed.
We tested on pre-reliese card and as functionality everything worked,
it just may need some Fermi-specific tuning.
Stan
by Stan Tomov
Sat Mar 20, 2010 9:03 pm
Forum: User discussion
Topic: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!
Replies: 6
Views: 12643

Re: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!

Argument hwork in magma_sgetrs_gpu is work space on the CPU memory. If you want to solve 1 RHS, hwork should point to at least N single precision floating point numbers. Can you try sgetrs_gpu on problems of sizes divisible by 32 - in magma 0.2 we were going to cublas strsm if N is not divisible by ...
by Stan Tomov
Thu Mar 18, 2010 4:56 pm
Forum: User discussion
Topic: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!
Replies: 6
Views: 12643

Re: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!

The example is in testing_sgesv_gpu.cpp. I see you gave the performance of testing_sgesv_gpu and it seems good as it goes up to 39.91 GFlop/s for magma_sgetrf_gpu followed by magma_sgetrs_gpu (with 1 RHS) vs 40.17 GFlop/s for just the factorization. Do you mean it gets slow when you do 1000 solves? ...
by Stan Tomov
Thu Mar 18, 2010 12:45 pm
Forum: User discussion
Topic: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!
Replies: 6
Views: 12643

Re: MAGMA_SGETRS_GPU less powerful than SGETRS (ACML) !!!

Hello, Your benchmark must be similar to testing_sgesv_gpu from the magma distribution. Do you get lower than expected performance with testing_sgesv_gpu as well? If yes, the reason may be that the matrix that you factor does not start at address divisible by 16*sizeof(float). If no, probably you lo...
by Stan Tomov
Thu Mar 04, 2010 1:45 pm
Forum: User discussion
Topic: magmablas_stranspose
Replies: 1
Views: 4840

Re: magmablas_stranspose

There isn't because for now the function is used internally. The function definition is extern "C" void magmablas_stranspose(float *odata, int ldo, float *idata, int ldi, int m, int n ) It takes an input m x n matrix in idata with leading dimension ldi (>=m) and transposes it, writing the output in ...
by Stan Tomov
Sat Jan 16, 2010 12:04 pm
Forum: User discussion
Topic: Matlab/nvmex - failure to compile
Replies: 10
Views: 27492

Re: Matlab/nvmex - failure to compile

Hi,
These are defined in testing/get_nb.cpp
Regards,
Stan
by Stan Tomov
Fri Jan 08, 2010 3:58 pm
Forum: User discussion
Topic: Magma and GPU Memory Limitation
Replies: 1
Views: 5559

Re: Magma and GPU Memory Limitation

The answer to all three questions is "yes". There are different ways to do it, but we haven't included in MAGMA any implementations yet (targeting these cases). Our first goal/priority in MAGMA is to provide a version with basic functionality (as currently available) and later use it as a building b...
by Stan Tomov
Fri Jan 08, 2010 3:06 pm
Forum: User discussion
Topic: sgetrf matlab mex file - crashing...
Replies: 13
Views: 29111

Re: sgetrf matlab mex file - crashing...

Jpeinado, We leave it up to the user to allocate memory, e.g., working spaces, etc.; the magma and magmablas libraries do not need and do not allocate additional memory space. The examples in the testing directory use pinned memory for performance, but non-pinned would work as well. We are still wor...
by Stan Tomov
Mon Dec 14, 2009 1:01 pm
Forum: User discussion
Topic: segmentation faults and non-MKL build
Replies: 2
Views: 7301

Re: segmentation faults and non-MKL build

Hello, The testing drivers assume memory on the card of size ~1GB and try to allocate memory for matrix of size 10,000 x 10,000. I see you have 511MB. We will change this in the future - to read the card specification and run tests that are according to the card,s memory size. For now you can try sm...
by Stan Tomov
Fri Dec 11, 2009 2:03 am
Forum: User discussion
Topic: sgetrf matlab mex file - crashing...
Replies: 13
Views: 29111

Re: sgetrf matlab mex file - crashing...

Jpeinado,
I only commented out getting the matrix A using mxGetData. I directly allocated A and used the rest of the Boxed Cyclon code as a simple cpp code (not as a mex file), linking it with the shared libraries posted in the other thread ("Matlab/nvmex - failure to compile").
Stan