Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

phoronix.com

Post reply on HN
Print view View original

601–610 of 722 posts

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#601

Post by theshrike79 »

philistine wrote: post #158
giobox wrote: post #97

Earlier quoted context omitted.

For sure its been a sweet spot for a very long time for budget conscious gamers looking for best balance of price and frame rates, but 1440p optimized parts are nothing new. Both NVidia and AMD make parts that target 1440p display users too, and have done for years. Even previous Intel parts you can argue were tailored for 1080p/1440p use, given their comparative performance deficit at 4k etc. Assuming they retail at…

I'm baffled that PC gamers have decided that 1440p is the endgame for graphics. When I look at a 27-inch 1440p display, I see pixel edges everywhere. It's right at the edge of losing the visibility of individual pixels, since I can't perceive them at 27-inch 2160p, but not quite there yet for desktop distances. Time marches on, and I become ever more separated from gaming PC enthusiasts.

4k gaming (2160p) is like watching 8k video on your TV.

It's doable, the tech is there. But the cost is WAY too high compared to what you get from it in the end.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#602

Post by theshrike79 »

rmm wrote: post #9

I put an a360 Card into an old machine I turned into a plex server. It turned it into a transcoding powerhouse. I can do multiple indepdent streams now without it skipping a beat. Price-performance ratio was off the chart

Good to know. I'm still waiting for UNRaid 7.0 for proper Arc support to pull the trigger on one.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#603

Post by theshrike79 »

tokioyoyo wrote: post #144
elorant wrote: post #131

Earlier quoted context omitted.

Would it though? How many people are running inference at home? Outside of enthusiasts I don't know anyone. Even companies don't self-host models and prefer to use APIs. Not that I wouldn't like a consumer GPU with tons of VRAM, but I think that the market for it is quite small for companies to invest building it. If you bother to look at Steam's hardware stats you'll notice that only a small percentage is using high…

This is the weird part, I saw the same comments in other threads. People keep saying how everyone yearns for local LLMs… but other than hardcore enthusiasts it just sounds like a bad investment? Like it’s a smaller market than gaming GPUs. And by the time anyone runs them locally, you’ll have bigger/better models and GPUs coming out, so you won’t even be able to make use of them. Maybe the whole “indoctrinate users t…

The future of local LLMs is not people running it on their PCs.

It's going to be a HomePod/AppleTV/Echo/Google Home -style box you set up in a corner and forget about it.

Then your devices in the ecosystem can offload some LLM tasks to that local system for inference, without having to do everything on-device.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#604

Post by weatherlite »

bayindirh wrote: post #264
treprinum wrote: post #26

Why don't they just release a basic GPU with 128GB RAM and eat NVidia's local generative AI lunch? The networking effect of all devs porting their LLMs etc. to that card would instantly put them as a major CUDA threat. But beancounters running the company would never get such an idea...

Disclosure: HPC admin who works with NIVIDA cards here. Because, no. It's not as simple as that. NVIDIA has a complete ecosystem now. They have cards. They have cards of cards (platforms), which they produce, validate and sell. They have NVLink crossbars and switches which connects these cards on their card of cards with very high speeds and low latency. For inter-server communication they have libraries which coordi…

> NVIDIA has a complete ecosystem now. They have cards. They have cards of cards

Nvidia is starting to sound like a house of cards to me.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#605

Post by FeepingCreature »

ryao wrote: post #515
wtallis wrote: post #146

Earlier quoted context omitted.

You're asking for a GPU die at least as large as NVIDIA's TU102 that was $1k in 2018 when paired with only 11GB of RAM (because $1k couldn't get you a fully-enabled die to use 12GB of RAM). I think you're off by at least a factor of two in your cost estimates.

If Intel came out with an ARC GPU with 128GB VRAM at a $2000 price point, I and many others would likely buy it immediately.

Though Intel should also identify say the top-100 finetuners and just send it to them for free, on the down low. That would create some market pressure.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#606

Post by FeepingCreature »

ac29 wrote: post #448
treprinum wrote: post #195

Earlier quoted context omitted.

That's why I said "basic GPU". It doesn't have to be too fast but it should still be way faster than a regular CPU. Intel already has Xeon Phi so a lot of things were developed already (like memory controller, heavy parallel dies etc.)

I wonder at that point you'd just be better served by CPU with 4 channels of RAM. If my math is right 4 channels of DDR5-8000 would get you 256GB/s. Not as much bandwidth as a typical discrete GPU, but it would be trivial to get many hundreds of GB of RAM and would be expandable. Unfortunately I don't think either Intel or AMD makes a CPU that supports quad channel RAM at a decent price.

I think all the people saying "just use a CPU" massively underestimate the speed difference between current CPUs and current GPUs. There's like four orders of magnitude. It's not even in the same zip code. Say you have a 64-core CPU at 2Ghz with 512-bit 1-cycle FP16 instructions. That gives you 32 ops per cycle, 2048 across the entire package, so 4TFlops.

My 7900 XTX does 120TFlops.

To match that, you would need to scale that CPU up to either 2048 cores, 2KB per register (still one-cycle!) or 64Ghz.

I guess if you had 1024-bit registers and 8Ghz, you could get away with only 240 cores. Good luck thermal dissipating that btw. To reverse an opinion I'm seeing in this thread, at that point your CPU starts looking more like a GPU by necessity.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#607

Post by ryao »

timschmidt wrote: post #303
pixelpoet wrote: post #265

Earlier quoted context omitted.

You are absolutely correct, and even my non-prophetic ass echoed exactly the first sentence of the top comment in this HN thread ("Why don't they just release a basic GPU with 128GB RAM and eat NVidia's local generative AI lunch?"). Yes, yes, it's not trivial to have a GPU with 128gb of memory with cache tags and so on, but is that really in the same universe of complexity of taking on Nvidia and their CUDA / AI moat…

Both Intel and AMD produce server chips with 12 channel memory these days (that's 12x64bit for 768bit) which combined with DDR5 can push effective socket bandwidth beyond 800GB/s, which is well into the area occupied by single GPUs these days. You can even find some attractive deals on motherboard/ram/cpu bundles built around grey market engineering sample CPUs on aliexpress with good reports about usability under Li…

12 channel DDR5 is actually 12x32-bit. JEDEC in its wisdom decided to split the 64-bit channels of earlier versions of DDR into 2x 32-bit channels per DIMM. Reaching 768-bit memory buses with DDR5 requires 24 channels.

Whenever I see DDR5 memory channels discussed, I am never sure if the speaker is accounting for the 2x 32-bit channels per DIMM or not.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#608

Post by FeepingCreature »

talldayo wrote: post #166
adventured wrote: post #93

Earlier quoted context omitted.

Nvidia's $30,000 is a 90% margin product at scale. They could charge 1/3 that and still be very profitable. There has rarely been such a profitable large corporation in terms of the combo of profit & margin. Their last quarter was $35b in sales and $26b in gross profit ($21.8b op income; 62% op income margin vs sales). Visa is notorious for their extreme margin (66% op income margin vs sales) due to being basically a…

> And indeed that's exactly what will be required for any serious attempt to cut into their monopoly position. You misunderstand why and how Nvidia is a monopoly. Many companies make GPUs, and all those GPUs can be used for computation if you develop compute shaders for them. This part is not the problem, you can already go buy cheaper hardware that outperforms Nvidia if price is your only concern. Software is the is…

CUDA is not the issue. AMD have already reimplemented like 80% of it, and honestly that part of it mostly works fine. Pytorch supports it, (almost) all the big frameworks support it, if you're not doing really arcane things it just works. It's the drivers! They took like two years after the release of their flagship card to stop randomly crashing. Everything geohot has ever said about AMD drivers is 100% true. They just cannot stop shooting themselves in the foot.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#609

Post by FeepingCreature »

jjmarr wrote: post #485
treprinum wrote: post #385

Earlier quoted context omitted.

AMD GPUs aren't very attractive to ML folks because they don't outshine Nvidia in any single aspect. Blasting lots of RAM onto a GPU would make it attractive immediately with lots of attention from devs occupied with more interesting things.

MI300X already leads in VRAM as it has 192 GB. For local inference, 7900 XTX has 24 GB of VRAM for less than $1000. At what threshold of VRAM would you start being interested in MI?

I have a 7900 XTX. Honestly I regret it. It took two years for the driver to stop randomly crashing with very pedestrian ROCm loads. And there's no future in AMD support now they're getting out of the high-end dual-use GPU game anyways. I should have gone with NVidia.

Re: Intel announces Arc B-series "Battlemage" discrete graphics with Linux support

#610

Post by adriancr »

hentrep wrote: post #194
adriancr wrote: post #181

Earlier quoted context omitted.

Not OP but for me a big thing is privacy, I can feed it personal documents and expect those to not leak. It has zero cost, hardware is already there. I'm not captive to some remote company. I can fiddle and integrate with other home sensors / automation as I want.

Curious as I’m of the same mind - what’s your local AI setup? I’m looking to implement a local system that would ideally accommodate voice chat. I know the answer depends on my use case - mostly searching and analysis of personal documents - but would love to hear how you’ve implemented.

If you are just starting up, you can try out 'open-webui' as inspiration. After that you can just use llama.cpp to build out your own things.

Hardware side, I just have a beefy server that acts as a router (mellanox card to provider fiber optic and local fiber network), firewall, wifi access point, zigbee coordinator, host to various services, camera video feed ingestion and processing, and so on...

Post reply on HN