AVX-512, what’s useful for us
1–10 of 50 posts
Re: AVX-512, what’s useful for us
#2 document.querySelector('#k2Container').style.color = 'black';
Other than that, nice intro.
Re: AVX-512, what’s useful for us
#3document.querySelector('#k2Container').style.color = 'black'; and the blog post becomes almost readable. Other than that, nice intro.
Yeah, sorry about that, that site's getting replaced soon.
Re: AVX-512, what’s useful for us
#4It will be a while before AVX-512 becomes practical however. AMD doesn't support it (so any RyZen or Threadripper fans will miss out), and even Intel 8th Gen Coffee-lake doesn't support it.
Only Intel Extreme i9 and Xeon Silver / Gold / Platinum seems to support it. So the market for this instruction set is quite limited.
Re: AVX-512, what’s useful for us
#5It will be a while before AVX-512 becomes practical however. AMD doesn't support it (so any RyZen or Threadripper fans will miss out), and even Intel 8th Gen Coffee-lake doesn't support it. Only Intel Extreme i9 and Xeon Silver / Gold / Platinum seems to support it. So the market for this instruction set is quite limited.
FWIW we're only one generation away from AVX512 on consumer CPUs, Intel's upcoming Cannon Lake architecture will support it.
https://www.anandtech.com/show/11928/intels-document-points-...
Re: AVX-512, what’s useful for us
#6It will be a while before AVX-512 becomes practical however. AMD doesn't support it (so any RyZen or Threadripper fans will miss out), and even Intel 8th Gen Coffee-lake doesn't support it. Only Intel Extreme i9 and Xeon Silver / Gold / Platinum seems to support it. So the market for this instruction set is quite limited.
Skylake-X Core i7 CPUs also support AVX-512
https://ark.intel.com/products/123767/Intel-Core-i7-7820X-X-...
That's still a pretty limited selection of processors though.
Re: AVX-512, what’s useful for us
#7It will be a while before AVX-512 becomes practical however. AMD doesn't support it (so any RyZen or Threadripper fans will miss out), and even Intel 8th Gen Coffee-lake doesn't support it. Only Intel Extreme i9 and Xeon Silver / Gold / Platinum seems to support it. So the market for this instruction set is quite limited.
FWIW we're only one generation away from AVX512 on consumer CPUs, Intel's upcoming Cannon Lake architecture will support it. https://www.anandtech.com/show/11928/intels-document-points-...
Well, one-generation away from consumers being able to buy the chip. And maybe 5-years away before a sizable number of consumers upgrade to that chip (or newer)... since the typical Desktop is at LEAST 5 years old in my experience...
The Users who really need the feature are likely upgrading to AVX-512 computers already. IE: Mac Pro. So adoption is not as bad as my hyperbole above. But its still going to be a while before we can assume AVX512 support on machines.
Hell, with so many people running Sandy Bridge (i7-2xxx series), you can't even assume AVX2 support today.
Re: AVX-512, what’s useful for us
#8document.querySelector('#k2Container').style.color = 'black'; and the blog post becomes almost readable. Other than that, nice intro.
Yeah, sorry about that, that site's getting replaced soon.
Might want to also think about SSL. Certificates are free from Let's Encrypt.
That said, props for the IPv6 support!
Re: AVX-512, what’s useful for us
#9Earlier quoted context omitted.
FWIW we're only one generation away from AVX512 on consumer CPUs, Intel's upcoming Cannon Lake architecture will support it. https://www.anandtech.com/show/11928/intels-document-points-...
Well, one-generation away from consumers being able to buy the chip. And maybe 5-years away before a sizable number of consumers upgrade to that chip (or newer)... since the typical Desktop is at LEAST 5 years old in my experience... The Users who really need the feature are likely upgrading to AVX-512 computers already. IE: Mac Pro. So adoption is not as bad as my hyperbole above. But its still going to be a while b…
Couldn't you use something like GCC function multi-versioning?
Re: AVX-512, what’s useful for us
#10If I'm understanding it correctly, they're not actually using the 512 bit (ZMM) registers, because using them can cause overall system slowdown. It seems to me they're only really useful if you're doing an AVX-512 intensive workload. And do those really exist? For something like bulk matrix multiplications, GPGPU is going to be much better, both in throughput and in operations per joule. I'm remaining to be convinced that the ecological niche occupied by SIMD is significant, let alone expanding.