Fabian Tschopp

@gongzg What's the difference from beignet to the closed source compiler? Can you elaborate why it even exists?

@mattg-sp You can also use more lightweight versions of the benchmark - starting at benchmark1 and if that passes go up in batch size until you found the fastest performing...

Ok. Now it seems the same context is used for LibDNN kernels, right? This begs the question what is contained in the trace of the segfault now.

@mattg-sp Yes, these failures basically mean you can't train correctly (gradients are wrong) with the Caffe convolution engine. You could check if LibDNN verification passes, but Intel spatial convolution uses...

Thanks. Yes I noticed a similar problem actually with windows AMD drivers where the driver would segfault if the `#pragma unroll` at one point did not have an even number...

Hm just removing the pragmas can't cause that, there must have been a case where more was done than just commenting out the pragma, i.e. the stringstream misses a bracket...

It seems that you accidentally uncommented the lines 1050 to 1072? That would be my guess. It's this part: ``` // Store the final results in C /*ss

Ok thanks a lot. I currently have no other suggestion as to what could go wrong.

@psyhtest Thanks this is great to know. No I don't want to hard-code that into the code, but there are actually tuning parameters that change the vectorization data type, so...

@bhack Ok, maybe not directly related (this affects CPUs while your article is about (multiple) Xeon Phi card(s)). But definitely an interesting read, thanks. Sadly, currently don't have such a...