Re:We ported CAFFE from CUDA to HIP – and here’s what happened…
by jbmorgado on Wednesday July 12, 2017 @05:03PM
(#14756661)
Well, I was hoping for some quantitative benchmarks, the only conclusion from this posts is that HIP conversion tool is supposed to work 99.6% of times according to AMD.
Re:We ported CAFFE from CUDA to HIP – and here’s what happened…
by cwyers on Wednesday July 12, 2017 @05:29PM
(#14756869)
Yeah.
> When running on CUDA, the ported HIP application uses a compilation, runtime, and library flow that is very similar to the original CUDA application. Thus, we would expect the HIP/CUDA application to deliver very similar performance as the original CUDA/CUDA app.
You'd expect? I don't know if I'd trust benchmarks AMD put out on this subject, but I'd trust them more than not even bothering to benchmark.
Re:We ported CAFFE from CUDA to HIP – and here’s what happened…
by pmalynin on Wednesday July 12, 2017 @05:04PM
(#14756669)
Clickbait happened;
But it seems like they were able to increase portability at no loss of performance (and even it looks like a performance increase in some cases if I read correctly), among other things -- which is always commendable.
> When running on CUDA, the ported HIP application uses a compilation, runtime, and library flow that is very similar to the original CUDA application. Thus, we would expect the HIP/CUDA application to deliver very similar performance as the original CUDA/CUDA app.
You'd expect? I don't know if I'd trust benchmarks AMD put out on this subject, but I'd trust them more than not even bothering to benchmark.
But it seems like they were able to increase portability at no loss of performance (and even it looks like a performance increase in some cases if I read correctly), among other things -- which is always commendable.