Open discussion for MAGMA library (Matrix Algebra on GPU and Multicore Architectures)
I have some rather tight memory management needs for my gpu usage. Is there a way that the magma routines could be passed gpu work spaces instead of the magma routines allocating the temp spaces? Specifically, I am looking at zgetrf_gpu.cpp.
- Posts: 58
- Joined: Fri Jan 28, 2011 12:46 pm
Return to User discussion
Who is online
Users browsing this forum: Bing [Bot], Yahoo [Bot] and 2 guests