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

91–100 of 722 posts

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

#91

Post by m00x »

yumraj wrote: post #82
m00x wrote: post #73

Earlier quoted context omitted.

This is the most script kiddy comment I've seen in a while. llama.cpp is just inference, not training, and the CUDA backend is still the fastest one by far. No one is even close to matching CUDA on either training or inference. The closest is AMD with ROCm, but there's likely a decade of work to be done to be competitive.

Yes, and inference is a huge market in itself and potentially larger than training (gut feeling haven’t run numbers) Keep NVIDIA for training and Intel/AMD/Cerebras/… for interference.

Inference is still a lot faster on CUDA than on CPU. It's fine if you run it at home or on your laptop for privacy, but if you're serving those models at any scale, you're going to be using GPUs with CUDA.

Inference is also a much smaller market right now, but will likely be overtaken later as we have more people using the models than competing to train the best one.

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

#93

Post by adventured »

FuriouslyAdrift wrote: post #78
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...

HBM3E memory is at least 3x the price of DDR5 (it requires 3x the wafer as DDR5) and capacity is sold out for all of 2025 already... that's the price and production bottleneck. High speed, low latency server grade DDR5 is around $800-$1600 for 128GB. Triple that for $2400 - $4800 just for the memory. Still need the GPUs/APUs, card, VRMs, etc. Even the nVidia H100 with "only" 94GB starts at $30k...

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 brand + transaction network. So the fact that a hardware manufacturer is hitting those levels is truly remarkable.

It's very clear that either AMD or Intel could accept far lower margins to go after them. And indeed that's exactly what will be required for any serious attempt to cut into their monopoly position.

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

#94

Post by icegreentea2 »

declan_roberts wrote: post #86

I think a graphics card tailored for 2k gaming is actually great. 2k really is the goldilocks zone between 4k and 1080p graphics before you start creeping into diminishing returns.

2k usually refers to 1080p no? The k is the approximate horizontal resolution, so 1920x1080 is definitely 2k enough.

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

#95

Post by kevingadd »

treprinum wrote: post #62
wtallis wrote: post #53

Earlier quoted context omitted.

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…

M3/M4 Max MacBooks with 128GB RAM are already way better than an A6000 for very large local LLMs. So even if the GPU is as slow as the one in M3/M4 Max (<3070), and using some basic RAM like LPDDR5x it would still be way faster than anything from NVidia.

Are you suggesting that Intel 'just' release a GPU at the same price point as an M4 Max SOC? And that there would be a large market for it if they did so? Seems like an extremely niche product that would be demanding to manufacture. The M4 Max makes sense because it's a complete system they can sell to Apple's price-insensitive audience, Intel doesn't have a captive market like that to sell bespoke LLM accelerator cards to yet.

If this hypothetical 128GB LLM accelerator was also a capable GPU that would be more interesting but Intel hasn't proven an ability to execute on that level yet.

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

#96

Post by babypuncher »

CoastalCoder wrote: post #21

Given Intel's recent troubles, I'm trying to decide how risky it is to invest in their platform. Especially discrete GPUs for Linux gaming Fortunately, having their Linux drivers be (mostly?) open source makes a purchase seem less risky.

I can't speak from experience with their GPUs on Linux, but I know on Windows most of their problems stem from supporting pre-DX12 Direct3D titles. Nvidia and AMD have spent many years polishing up their Direct3D support and putting in driver-side hacks that paper over badly programmed Direct3D games.

These are obviously Windows-specific issues that don't come up at all in Linux, where all that Direct3D headache is taken care of by DXVK. Amusingly a big part of Intel's efforts to improve D3D performance on Windows has been to use DXVK for many titles.

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

#97

Post by giobox »

declan_roberts wrote: post #86

I think a graphics card tailored for 2k gaming is actually great. 2k really is the goldilocks zone between 4k and 1080p graphics before you start creeping into diminishing returns.

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 prices Intel are suggesting in the press releases, you maybe here save 40-50 bucks over an ~equivalent NVidia 4060.

I would also argue like others here that with tech like frame gen, DLSS etc, even the cheapest discrete NVidia 40xx parts are arguably 1440p optimized now, it doesn't even need to be said in their marketing materials. Im not as familiar with AMD's range right now, but I suspect virtually every discrete graphics card they sell is "2k optmized" by the standard Intel used here, and also doesn't really warrant explicit mention.

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

#99

Post by antisthenes »

icegreentea2 wrote: post #94
declan_roberts wrote: post #86

I think a graphics card tailored for 2k gaming is actually great. 2k really is the goldilocks zone between 4k and 1080p graphics before you start creeping into diminishing returns.

2k usually refers to 1080p no? The k is the approximate horizontal resolution, so 1920x1080 is definitely 2k enough.

2k Usually refers to 2560x1440.

1920x1080 is 1080p.

It doesn't make a whole lot of sense, but that's how it is.

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

#100

Post by jsheard »

treprinum wrote: post #62
wtallis wrote: post #53

Earlier quoted context omitted.

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…

M3/M4 Max MacBooks with 128GB RAM are already way better than an A6000 for very large local LLMs. So even if the GPU is as slow as the one in M3/M4 Max (<3070), and using some basic RAM like LPDDR5x it would still be way faster than anything from NVidia.

The M4 Max needs an enormous 512bit memory bus to extract enough bandwidth out of those LPDDR5x chips, while the GPUs that Intel just launched are 192/160bit and even flagships rarely exceed 384bit. They can't just slap more memory on the board, they would need to dedicate significantly more silicon area to memory IO and drive up the cost of the part, assuming their architecture would even scale that wide without hitting weird bottlenecks.
Post reply on HN