[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.
  • You may highlight syntax and preserve whitespace by using [code] tags.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


[Advertise on 4chan]


File: file.png (1.31 MB, 1920x1080)
1.31 MB
1.31 MB PNG
will intel save us or will they chase AI like all the other retards
>>
i dont want an intel card because it reportedly has high idle power usage (apparently it gets real bad if you have multi-monitor), and lots of non-gaming GPU-dependent software still only supports CUDA
>>
>>107618153
No because they can't even distrubute their highly sought after high vram GPU properly or in decent volume even though the market demands it and it will sell.
This company is incompetent if the jeet that ruined the RX5700 launch still works there expect it to never end.
>>
>>107618190
>>107618190
lol with the vram prices they will probably just discontinue that model soon, or soft-discontinue it by only selling 5 units per year
>>
>>107618168
>GPU-dependent software still only supports CUDA
what if we asked Nvidias data center AIs to vibe code a solution for it?
>>
>>107618201
And then act like nobody was willing to buy it which brings us back to square one with these fucking clowns.
It's all so tiresome
>>
>>107618168
OneAPI shits on ROCm and they do nothing with it
>>
>>107618153
>Xeon Phi
I have one of these.
I got it working once. Was a pain in the butt to find the right intel compiler for it and get it working, and even then it wasn't really useful to program anything for it. It's been years but IIRC each card runs its own kernel, you push the compiled programs to it, and communicate with it almost like it's another node in a network, just over PCIe. Very odd choice, but I guess in 2014-2015 they were just trying whatever came to mind (or in 2012 when it was designed?) as they saw CUDA taking off in HPC workloads.
Obviously a failed product, but part of me still likes the idea of an chip with SMT4 purpose-built for AVX512.
>>
>>107618153
>Xeon coprocessor
>CPU card
Is Intel going back to the 90s?
>>
>>107618580
the Philippines used to make GPUs? thats the wildest thing about this image
>>
>>107618153
>Retards
>Making more money than God
Pick one
>>
>>107618168
>Muh CUDA
Already losing relavence by the month. Most tools are getting more and more support for Vulkan. Hell even ROCM is gaining.
>>
>>107618168
>i dont want an intel card because it reportedly has high idle power usage
probably because of all the Israeli spyware running in the background
>>
>>107618580
>Is Intel going back to the 90s?
Not anymore, but 15 years ago they sure tried.
Intel only made these AIBs from the early-to-mid-2010's. Here is the first generation:
https://www.intel.com/content/www/us/en/products/sku/80555/intel-xeon-phi-coprocessor-7120a-16gb-1-238-ghz-61-core/specifications.html
It says "61 cores" but they had 4 threads per core, and there were versions with as many as 72 cores. The idea was to take on massively parallel GPU workloads by shipping a "CPU" whose main purpose was to run a gorillion AVX-512 cores instead. Obviously it didn't work.
>>
>>107618665
>Most tools are getting more and more support for Vulkan.

Vulkan Compute? Got any examples?
>>
every game worth playing was released prior to 2004

you don't need a $48,000 dollar gpu to play them
>>
what happened to amd
they used to compete with nvidia years ago, now they are completely irrelevant and forgotten and people who want an alternative to nvidia would rather believe in Intel entering the gpu market or chinks making competitive gpus out of nowhere



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.