Compare the differences in the MAGMA library

[Selena]

Hello all member!
In the before magma linear algebra library. I Used version 1.6.1.
http://icl.cs.utk.edu/magma/software/

In the testing code exercising dgemm functionality (source code: testing_dgemm.cpp), there was a call to functions magma_dgemm and magmablas_dgemm. Can someone clarify the difference between the two? Which one is more general (not tied to just GPU)?
Thank's a lot!

[mgates3]

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 implementation to study or modify.

They are both GPU-only implementations.

-mark

[Selena]

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 implementation to study or modify.

They are both GPU-only implementations.

-mark

Thanks for your information for sharing.
Through An inspection of the source code reveals that magmablas_Xgemm is actually a C function that launches an appropriate gemm kernel on the GPU. Thus magmablas_Xgemm is a GPU-specific routine. On the other hand, magma_Xgemm is intended to be accelerator-agnostic routine that (currently) can be used for either GPU (NVIDIA/AMD, ...) or MIC.

Ref files, relative to MAGMA source directory (the CUDA edition):

Code: Select all

./magmablas/dgemm_fermi.cu
./interface_cuda/blas_d.cpp