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

201–210 of 722 posts

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

#201

Post by wlesieutre »

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.

I don’t think it’s seen as the end game, it’s that if you want 120 fps (or 144, 165, or 240) without turning down your graphics settings you’re talking $1000+ GPUs plus a huge case and a couple hundreds watts higher on your power supply.

1440p hits a popular balance where it’s more pixels than 1080p but not so absurdly expensive or power hungry.

Eventually 4K might be reasonably affordable, but we’ll settle at 1440p for a while in the meantime like we did at 1080p (which is still plenty popular too).

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

#202

Post by KeplerBoy »

hajile wrote: post #196
layer8 wrote: post #164

Earlier quoted context omitted.

You can’t just throw in more RAM without having the rest of the GPU architected for it. So there’s an R&D cost involved for such a design, and there may even be trade-offs on performance for the mass-market lower-tier models. I’m doubtful that the LLM enthusiast/tinkerer market is large enough for that to be obviously profitable.

That would depend on how they designed the memory controllers. GDDR6 only supporting 1-2gb modules at present (I believe GDDR6W supports 4gb modules). If they were using 12 1gb modules, then increasing to 24gb shouldn't be a very large change. Honestly, Apple seems to be on the right track here. DDR5 is slower than GDDR6, but you can scale the amount of RAM far higher simply by swapping out the density.

It's a 192 bit interface, so 6 16gbit chips.

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

#204

Post by semi-extrinsic »

BenjiWiebe wrote: post #197
kimixa wrote: post #184

Earlier quoted context omitted.

I think there'll be a "financial" winter - or another way a bubble burst - the investment right now is simply unsustainable, how are these products going to be monetized? Nvidia had a revenue of $27billion in 2023 - that's about $160 per person per year [0] for every working age person in the USA. And it's predicted to more than double in 2024. If you reduce that to office workers (you know, the people who might actu…

Well, "AI" is milking cows. Not LLM's though. Our milking robot uses image recognition to find the cow's teats to put the milking cup on.

Yeah, but automated milking robots like that have been in the market for more than a decade now IIRC?

Seems like a lot of CV solutions have seen fairly steady but small incremental advances over the past 10-15 years, quite unrelated to the current AI hype.

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

#205

Post by jvanderbot »

1propionyl wrote: post #129
jvanderbot wrote: post #108

Seems to feature ray tracing (kind of obvious), but also upscaling. My experience on WH40K DT has taught me that upscaling is absolutely vital for a reasonable experience on some games.

> upscaling is absolutely vital for a reasonable experience on some games This strikes me as a bit of a sad state of affairs. We've moved beyond a Parkinson's law of computational resources –usage by games expands to fill the available resources– to resource usage expanding to fill the available resources on the highest end machines unavailable for less than a few thousand dollars... and then using that to train a mo…

Isn't it insane to think that rendering triangles for the visuals in games has gotten so demanding that we need an artificially intelligent system embedded in our graphics cards to paint pixels that look like high definition geometry?

What a time to be alive. Our most advanced technology is used to cheat on homework and play video games.

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

#206

Post by ben_w »

kimixa wrote: post #184
PittleyDunkin wrote: post #156

Earlier quoted context omitted.

> ML is about hit another winter. I agree ML is about to hit (or has likely already hit) some serious constraints compared to breathless predictions of two years ago. I don't think there's anything equivalent to the AI winter on the horizon, though—LLMs even operated by people who have no clue how the underlying mechanism functions are still far more empowered than anything like the primitives of the 80s enabled.

I think there'll be a "financial" winter - or another way a bubble burst - the investment right now is simply unsustainable, how are these products going to be monetized? Nvidia had a revenue of $27billion in 2023 - that's about $160 per person per year [0] for every working age person in the USA. And it's predicted to more than double in 2024. If you reduce that to office workers (you know, the people who might actu…

While I'd agree monetisation seems to be a challenge in the long term (analogy: spreadsheets are used everywhere, but are so easy to make they're not themselves a revenue stream, only as part of a bigger package)…

> Nvidia had a revenue of $27billion in 2023 - that's about $160 per person per year [0] for every working age person in the USA

As a non-American, I'd like to point out we also earn money.

> as no AI is going to milk a cow or serve you starbucks

Cows have been getting the robots for a while now, here's a recent article: https://modernfarmer.com/2023/05/for-years-farmers-milked-co...

Robots serve coffee as well as the office parts of the coffee business: https://www.techopedia.com/ai-coffee-makers-robot-baristas-a...

Some of the malls around here have food courts where robots bring out the meals. I assume they're no more sophisticated than robot vacuum cleaners, but they get the job done.

Transformer models seem to be generally pretty good at high-level robot control, though IIRC a different architecture is needed down at the level of actuators and stepper motors.

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

#207

Post by hulitu »

bryanlarsen wrote: post #138
jmward01 wrote: post #103

12GB max is a non-starter for ML work now. Why not come out with a reasonably priced 24gb card even if it isn't the fastest and target it at the ML dev world? Am I missing something here?

These are $200 low end cards, the B5X0 cards. Presumably they have B7X0 and perhaps even B9X0 cards in the pipeline as well.

> These are $200 low end cards

Hm, i wouldn't consider 200$ low end.

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

#208

Post by treprinum »

elorant wrote: post #142
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...

AMD has a 192GB GPU. I don’t see them eating NVidia’s lunch with it.

They are charging as much as Nvidia for it. Now imagine they offered such a card for $2k. Would that allow them to eat Nvidia's lunch?

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

#209

Post by amelius »

wtallis wrote: post #53
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...

Just how "basic" do you think a GPU can be while having the capability to interface with that much DRAM? Getting there with GDDR6 would require a really wide memory bus even if you could get it to operate with multiple ranks. Getting to 128GB with LPDDR5x would be possible with the 256-bit bus width they used on the top parts of the last generation, but would result in having half the bandwidth of an already mediocre…

What if they put 8 identical GPUs in the package, each with 1/8 the memory? Would that be a useful configuration for a modern LLM?
Post reply on HN