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

Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

phoronix.com

Post reply on HN
Print view View original

41–50 of 131 posts

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#41

Post by Tepix »

schmorptron wrote: post #18
mft_ wrote: post #16

I have no idea of the likely price, but (IMO) this is the sort of disruption that Intel needs to aim at if it's going to make some sort of dent in this market. If they could release this for around the price of a 5090, it would be very interesting.

Maybe not that low, but given it's using LPDDR5 instead of GDDR7, at least the ram should be a lot cheaper.

It‘s LPDDR5X

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#43

Post by 0xfedcafe »

RoyTyrell wrote: post #2

Will this have any support for open source libraries like PyTorch or will it be all Intel proprietary software that you need a license for?

OpenVino is entirely open-source and can run PyTorch and ONNX models, so this is definitely not a topic of concern. PyTorch also has native Intel GPU support https://docs.pytorch.org/docs/stable/notes/get_start_xpu.htm...

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#44

Post by yjftsjthsd-h »

halJordan wrote: post #34
makapuf wrote: post #29

Funny they still call them graphics cards when they're really... I dont know, matmul cards ? Tensor cards ? TPU ? Well that sums it up maybe, what those are are really CUDA cards.

Dude, this is asinine. Graphics cards have been doing matrix and vector operations since they were invented. No one had a problem with calling matrix multiplers graphics cards until it became cool to hate AI.

GPUs may well have done the same-ish operations for a long time, but they were doing those operations for graphics. GPGPU didn't take off until relatively recently.

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#45

Post by wmf »

baq wrote: post #23
mft_ wrote: post #16

I have no idea of the likely price, but (IMO) this is the sort of disruption that Intel needs to aim at if it's going to make some sort of dent in this market. If they could release this for around the price of a 5090, it would be very interesting.

With this much ram don’t expect anything remotely affordable by civilians.

160 GB LPDDR5 is ~$1,200 retail so the card could be sold for $2,000. The price will depend on how desperate Intel is. Intel probably can't copy Nvidia's pricing.

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#46

Post by wmf »

makapuf wrote: post #29

Funny they still call them graphics cards when they're really... I dont know, matmul cards ? Tensor cards ? TPU ? Well that sums it up maybe, what those are are really CUDA cards.

This sounds like a gaming card with extra RAM so it's kind of appropriate to call it a graphics card.

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#47

Post by wtallis »

Tepix wrote: post #41
schmorptron wrote: post #18

Earlier quoted context omitted.

Maybe not that low, but given it's using LPDDR5 instead of GDDR7, at least the ram should be a lot cheaper.

It‘s LPDDR5X

LPDDR5x really just means LPDDR5 running at higher than the original speed of 6400MT/s. Absent any information about which faster speed they'll be using, this correction doesn't add anything to the discussion. Nobody would expect even Intel to use 6400MT/s for a product that far in the future. Where they'll land on the spectrum from 8533 MT/s to 10700 MT/s is just a matter for speculation at the moment.

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#49

Post by dragonwriter »

baq wrote: post #23
mft_ wrote: post #16

I have no idea of the likely price, but (IMO) this is the sort of disruption that Intel needs to aim at if it's going to make some sort of dent in this market. If they could release this for around the price of a 5090, it would be very interesting.

With this much ram don’t expect anything remotely affordable by civilians.

I mean, even without that, the phrase “enterprise GPU”, does not tend to convey “priced for typical consumers”.

Re: Intel Announces Inference-Optimized Xe3P Graphics Card with 160GB VRAM

#50

Post by shwaj »

adastra22 wrote: post #37
halJordan wrote: post #34

Earlier quoted context omitted.

Dude, this is asinine. Graphics cards have been doing matrix and vector operations since they were invented. No one had a problem with calling matrix multiplers graphics cards until it became cool to hate AI.

It was many generations before vector operations were moved onto graphics chips.

I think they’re using “vector” in the linear algebra sense, e.g. multiplying a matrix and a vector produces a different vector.

Not, as I assume you mean, vector graphics like SVG, and renderers like Skia.

Post reply on HN