MAGMA Forum

Austin, I see. This sounds good. We have been asked by users to provide this type of stream interface, so any experimental results on performance would be very useful for us to know. I can check with NVIDIA developers if routine arguments are always sent asynchronously or if there are cases that the...

The current code uses stream 0 for the GPU BLAS. This would not allow concurrent BLAS execution on the GPU from the different threads. Related to the communications, I think magmablas_dpermute_long2s does not use synchronous communications. The routine does not have any explicit communication, only ...

We have

Ubuntu 12.04.2 LTS
OpenCL 1.2
AMD-APP 1124.2
Driver version 12.10.5 (module loaded - fglrx 12.10.5 [Mar 20 2013] with 1 minors)
clAmdBlas 1.11.314 (also 1.8.286 and 1.8.291)

Hi, These undefined routines are supposed to be in lapack. Maybe check to see if they are indeed there, e.g., nm liblapack.a | grep ssyevd If it is not there, probably you have some incomplete version of LAPACK, e.g., something that comes with ATLAS. If it is there, probably just adding -llapack onc...

Actually we have similar problem on a new system that we just setup. We rely on the clAmdBlas so this is one of the first things that we check when there are problems. On dgemm we also get somehow similar results ./testing_dgemm Initializing clMAGMA runtime ... Usage: testing_dgemm [-NN|NT|TN|TT] [-...

We are also running on Ubuntu 12.04 (.2 LTS).

uname -a

gives
Linux genesis 3.2.0-23-generic #36-Ubuntu SMP Tue Apr 10 20:39:51 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux.
Are the clMAGMA testing routines working, e.g., testing_sgemm?
Stan

Hello,
These functions are from the LAPACK library. LAPACK is a MAGMA dependency and has to be installed or your system and linked.I see you have but don't have -llapack. Do you have a liblapack.a somewhere in /home/ronald/lapack-3.4.1/?

Hello,
The cmake building capabilities are not up to date. Please use the Makefiles as described in README. Please post your make.inc file if you still have problems compiling (and the errors that you get). Thanks.
Stan

Hello,
I looked at your code and was wondering if the problem comes from Maybe you should have

Hi Luis, I just ran the test and reproduced your result on a K20c. I added a check for the factorization though and for the orthogonality and everything looks fine: test> ./benchmark_cpu -N 2000 Reading input file Read succesful Calculating eigenvalues with MKL Quering space... Solving eigenvalues.....