Search found 918 matches
- Thu Dec 19, 2019 4:26 pm
- Forum: User discussion
- Topic: Multiple hybrid gpu linear solver
- Replies: 1
- Views: 784
Re: Multiple hybrid gpu linear solver
magma_cgesv works on multiple GPUs; it calls magma_cgetrf, which calls magma_cgetrf_m. However, as you observe, the forward and back solves (getrs) are on the CPU. It's unclear if multi-GPU pivoting (laswp) and triangular solves (trsm) in getrs would benefit from the GPU, since there would be signif...
- Thu Nov 07, 2019 2:47 pm
- Forum: User discussion
- Topic: MAGAMA routines and CUDA kernels
- Replies: 4
- Views: 2486
Re: MAGAMA routines and CUDA kernels
Yes, magma_dmalloc is just a wrapper around cudaMalloc. It is type-safe (you don't need to use sizeof(double) as you do with cudaMalloc), but otherwise nothing special going on. If you call asynchronous MAGMA routines that take a magma_queue, use the stream from the magma_queue to call CUDA function...
- Wed Nov 06, 2019 4:31 pm
- Forum: User discussion
- Topic: MAGAMA routines and CUDA kernels
- Replies: 4
- Views: 2486
Re: MAGAMA routines and CUDA kernels
I'm not sure what you mean by "the arrays created by MAGMA routines". Do you mean arrays allocated by, say, magma_dmalloc? Yes, that's just a chunk of memory on the GPU, so you can process it equally well with MAGMA, cuBLAS, and your own custom CUDA kernels. It sounds like checking the coefficients ...
- Tue Oct 29, 2019 8:11 pm
- Forum: User discussion
- Topic: Bug: getrf_batched kernel produces NaNs on singular square inputs of size <=32
- Replies: 1
- Views: 880
Re: Bug: getrf_batched kernel produces NaNs on singular square inputs of size <=32
You need to have a Bitbucket account to post bug reports. I posted this there for tracking:
https://bitbucket.org/icl/magma/issues/ ... es-nans-on
-mark
https://bitbucket.org/icl/magma/issues/ ... es-nans-on
-mark
- Sun Oct 27, 2019 11:19 pm
- Forum: User discussion
- Topic: Compare the differences in the MAGMA library
- Replies: 2
- Views: 1045
Re: Compare the differences in the MAGMA library
Use magma_dgemm. It is simply a wrapper around cublasDgemm. magmablas_dgemm is MAGMA's own implementation, which dates back to the Fermi architecture. NVIDIA adapted this implementation for the cublasDgemm, and further optimized it. We keep the code around in case someone wants an open-source implem...
- Thu Oct 17, 2019 9:41 am
- Forum: User discussion
- Topic: Sqrt(r) is not rational, where r is a perfect square
- Replies: 2
- Views: 977
Re: Sqrt(r) is not rational, where r is a perfect square
I think you are on the wrong forum. This forum is for MAGMA, the GPU library for linear algebra (http://icl.utk.edu/magma/). It sounds like you want MAGMA, the computational algebra system (http://magma.maths.usyd.edu.au/magma/).
-mark
-mark
- Mon Oct 07, 2019 4:01 pm
- Forum: User discussion
- Topic: Best solution for solving hundreds of small linear systems
- Replies: 3
- Views: 1276
Re: Best solution for solving hundreds of small linear systems
Yes, unfortunately here the time gets rounded down. But the performance is reflected in the Gflop/s rate. You can compute the approximate time using the formula:
2/3 n^3 * batch_count / (gflop/s)
For instance
2/3 * 100^3 * 500 / 158.36e9 = 0.0021 sec.
-mark
2/3 n^3 * batch_count / (gflop/s)
For instance
2/3 * 100^3 * 500 / 158.36e9 = 0.0021 sec.
-mark
- Mon Oct 07, 2019 2:01 pm
- Forum: User discussion
- Topic: How to detect different MAGMA flavors at compile time?
- Replies: 2
- Views: 1386
Re: How to detect different MAGMA flavors at compile time?
MAGMA 1.0 is quite old, so I personally wouldn't bother. If you insist, there are MAGMA_VERSION_MAJOR, _MINOR, and _MICRO macros. See include/magma_types.h. clMAGMA is not actively maintained — even AMD's clBLAS is a couple years old at this point. clMAGMA uses HAVE_clAmdBlas or HAVE_clBLAS macros, ...
- Thu Oct 03, 2019 11:06 am
- Forum: User discussion
- Topic: How to solve polynomial equations?
- Replies: 3
- Views: 1834
Re: How to solve polynomial equations?
This forum is for the MAGMA linear algebra library for GPUs (http://icl.utk.edu/magma/). It doesn't solve polynomial equations. Perhaps you are intending the Magma Computational Algebra System (http://magma.maths.usyd.edu.au/magma/).
-mark
-mark
- Fri Sep 27, 2019 2:09 pm
- Forum: User discussion
- Topic: Problem of xlf+xlc for magma has been resolved.
- Replies: 3
- Views: 1342
Re: Problem of xlf+xlc for magma has been resolved.
When using xlf, use -DNOCHANGE instead of -DADD_ in the make.inc file when compiling MAGMA. Then it will use the correct Fortran naming convention for IBM's Fortran. Ideally, the whole software stack — e.g., BLAS, LAPACK, MAGMA, your application — are compiled using the same set of compilers (e.g., ...