If it was always trivial the compilers would already have solved it and everything would be SIND vectorised by default.
For pure math functions with minimal branches and large data it's certainly possible to vectorise the code relatively easily and gain performance. But once you start...
With a proper AGI possibly, but at the moment "AI" are just probability machines. Outputting the most likely code they've come across based on the prompt and there training set. There is no understanding of the code or it's purpose. Depending on what they're trained on they may produce slower...
AVX512 isn't useless for the standard user. Plenty of basic functions, such as parsing JSON (lots of websites), text processing, sorting, base64 encoding/decoding and similar, can substantially benefit (30-60% faster) when rewritten to use AVX512 operations. The problem is simply the lack of...
Had a quick look at a few tests last night when switching a couple of machines from current release to the windows insider 24H2.
On a 7900 (running at 1080P with a 4070):
Homeworld 3 - +15% (min and average frame rate)
Cinebench 2024 - +8%
Own HPC app - +5%
Cyberpunk 2077 - +5%
Black Myth - 0%...
It's very easy to test this, simply run your fav multi-core benchmarks, reboot, enter bios, disable hyperthreading. Load into windows run your fav multithreaded benchmarks.
Note GB isn't great for multi-core testing so use something more intense that runs for a while.
For potentially radical things they could do with a V-cache die:
1) Double stack them or increase the size, one CPU core with two attached V-cache blocks, how does 128MB of v-cache sound?
2) Use one as a system level cache attached to an IO die, with or without one or two attached to the cores...
So based on the results from JustJosh the models he's testing (for Cinebench 2024) are slightly slower than an M2 Pro at approximately the same power draw.
JJ - 964 points at 55 total system power draw with very little fan noise
On my M2 Pro - 1002 points at ~55W total system draw with...
Malware on either your computer or router? Might be taking a few minutes to start up after a reboot and then eats all your bandwidth? There are no other devices on the network that could be infected and you've changed your wifi password?
If you can buy another Google wifi unit, or Nest Wifi Point setting them up in wifi mesh mode would by far be the easiest solution, it's simply buy a unit plug it in then go to the app and add an extra unit/point.
Note that if you got a Google Wifi point you wouldn't be able to use the ethernet...
Part of the problem is your probably running two different networks with this setup. Your router is most likely running it's DHCP service and assigning IP addresses (probably 192.168.0.x) to anything plugged into to the wired network. Then your google home (unless you set it to bridge mode) is...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.