There are deep cnn models for doing joint recognition detection at around 60fps (at 300x300) at reasonable accuracy 75%.
This is arguably the most expensIve part of the pipeline, but we sHould have atleast two more architectures out by NVDA/AMD before any product comes out.
MKL? I don't think so, it takes the worst codepath if the chip isn't GenuineIntel.
OpenBLAS? Doesn't have Ryzen support. Doesn't even recognize some AMD cores.
ACML? Wasn't updated since 2013 or so.
This is a serious question. What are you supposed to do if you need a GEMM kernel for Ryzen? I sure hope AMD puts out updated ACML libraries real soon.
I'd like to see benchmarks with OpenBLAS. Unlike ACML it's under active development, unlike MKL it won't deliberately screw AMD performance, and it offers "pretty good" performance across every environment I've tried it in. Good enough that it's not worth paying for MKL, not worth going through ATLAS's self-tuning routine, not worth changing my build scripts to use vecLib under OS X. If OpenBLAS currently runs poorly on Ryzen I hope Ryzen will get some development love, because I kind of hate using ATLAS and at this point it would take a major advantage to tempt me back away from open source components.
Word!
I think AMD should focus on OpenBLAS and add support for their new CPUs there.
OpenBLAS is part of the foss toolchain for the easybuild easyconfig. So for the HPC field adding support to OpenBLAS would be great.
OpenBLAS performance is atrocious in 32 bit mode because it doesn't properly support AVX with the halved register file. Not the most common configuration, but MKL handles it fine (on Intel chips, obviously).
That said I agree it makes more sense for AMD to contribute to OpenBLAS than anything else.
Interesting -- what are the use cases for single precision BLAS on CPU? All the scientific software I use requires double precision and for tasks that do well with single precision, I would have thought that GPGPU would now be the go-to solution.
It's not so much reduced math performance (it's twice faster than Bulldozer!), it's that Intel chips as of Haswell have dual 256-bit FPUs per core.
If you use them, the Intel chips downclock (sometimes severely) in order not to violate their TDP, but the dual FPUs are still there, and it's still a win for GEMM. I can see why AMD didn't follow along here, but it could be a factor in some small spaces - when you need GEMM but can't use a GPU.
Note that Ryzen can split its 256-bit FPU into two 128-bit units, so on code that's not using AVX, it's completely on par with Intel.
Indeed! I had to struggle with a consumer hp dv65xx for a few years before I finally got my hand on a thinkpad. Opening it up was a nightmare, and I broke random plastic things everytime I opened it up.
Related languages are different due to changes; but they haven't all changed in the same way. Thus it is perfectly sound to describe one language as closest to the common substrate of other related languages.
Looking only at languages L1 through L3 we may infer a common ancestor from what is more shared. Saying that L4 is closest to this hypothetical language is not an empty concept, or artificial based on some ideology.
> > "A deeper realization came further on: there might be limitations in language itself and our ability to represent ideas and think about them that could preclude us from actually understanding the foundations of our situation.
I see this play out every day. As a result of the continued linguistic apartheid in my country, the languages are dead, and the people are stupid as dirt (on average), to be blunt. However, this is mostly Karma, the result of accumulations of centuries past, playing out as the complete decimation of histories; naturally, the education/media system is a propaganda op, with tons of shills at every corner. Those whom you'd wish to see break out of chains, appear to find comfort in them alone. New ideas can't touch them nor move them, because the "programming language" is so outdated, that such sentences will be treated as garbage.
I believe there are deep reasons why India could only think of independence through a class which was more British than Indian. India is but a grave for the civilization it once sustained, and we are but mere flies who wish for a phoenix.
Language does indeed governs our thoughts, and in that respect governs the world we create - it's what makes us human, far more than anything else. Take out the language, and what you get is a mere animal.
I beg your pardon?
Where exactly did I accuse anyone of distributing "Fake News"? I was merely lamenting the slide of a publication, of which I used to respect the views and content, from champion of fact, and keen-eyed investigative journalism to another angry editorialist internet rag. Which, seems to increasingly fail to let the truth get in the way of their click-thru rate. TI's shameful behaviour during the recent incredibly dirty (on both sides) US election wasn't to stand back and give careful considered analysis, but rather pick an enemy and jump into the fray both feet first.
Kinda saddened at the censorship above. I can't help but feel I (and everyone else) have a right to be called names, know the names I'm being called and try and understand why I'm being called them. I'm sure this was in good will, and in the best interests of the discourse on this forum, but damn it's infuriating!
