Re:Composable multi-threaded parallelism in Julia
by steev on Wednesday July 24, 2019 @06:42AM
(#20513835)
GPU parallelism is highly specialized and requires very specific workloads (e.g., many linear algebra workloads). GPUs are a bad choice for general parallelized tasks.
[ Parent
| on HN ]
Re:Composable multi-threaded parallelism in Julia
by seanmcdirmid on Wednesday July 24, 2019 @02:00PM
(#20517835)
Yes, but for heavy numeric problems, GPUs are your best bet if you can make them work. The question is what is Julia being used for, I guess.
Re:Composable multi-threaded parallelism in Julia
by scott_s on Wednesday July 24, 2019 @04:34PM
(#20519363)
A quibble: it's not necessarily "heavy numeric" problems, but problems where the calculations involve extensive data-reuse. (Of which matrix operations are the most obvious.) The GPU is massively parallel, but the up-front cost of transferring data to the GPU is quite high.
Hence, in order for that up-front cost to be worth it, the algorithms run on the GPU need to re-use that data many times. If the algorithms running on the GPU don't make extensive reuse of the data sent to it, it would be faster to just do the calculation on the host CPU.