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

121–130 of 131 posts

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

#121

Post by matt-p »

vardump wrote: post #104
Aurornis wrote: post #100

Earlier quoted context omitted.

> Examples like self hosted LLM finetuning and RAG on an old dell or HP server with these type of cards on them. This won’t be in the price range of an old Dell server or a fun impulse buy for a hobbyist. 160GB of raw LPDDR5X chips alone is not cheap. This is a server/workstation grade card and the price is going where the market will allow. Consider that an nVidia card with almost half the RAM is going to cost $8K o…

That nVidia card is going to have 5x the memory bandwidth. LPDDR5X is going to be rather low bandwidth. (My guess is Intel's card is only going to have about 400 GB/s bandwidth.)

Last year's M4 max MacBook is 520GB/s and (I expect) that should be closer to 1TB/s in a year or two by the time they are using ddr5. It would be deeply embarrassing if they had worse performance than apples cheaper laptop.

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

#122

Post by jychang »

kingstnap wrote: post #112
jychang wrote: post #86

Earlier quoted context omitted.

It’s LPDDR5x It’s gonna be slowwww It’s gonna be what, 273GB/sec vram bandwidth at most? Might as well as buy an AND 395+ 128GB right now for the same inference performance and slightly less VRAM.

Bandwidth depends very much on on bus width. If its fast LPDDR5x (9600 MT/s) with 512 bit bus width (8 64bit channels (actually multiples of quad 16 bit subchannel nonsense)) it could be upwards of 600 GB/s. Lots of bandwidth like the beefy macs have.

1. 600GB/sec is still slow as hell. You might as well as use regular DDR5 RAM then if you're so slow, you can spec regular system DDR5 RAM faster than 600GB/sec. The half decade old consumer 3090 is 1.5x that speed. The current 5090 is 1,792 GB/s. The current nvidia datacenter cards are 8 TB/s. What's the point of having lots of VRAM if your system RAM is faster?

For context: if you have a 160GB dense ML model in VRAM and you're just running 600GB/sec, you can do... roughly 4 tokens per second AT BEST. That massive amount of VRAM is unusable if it's slow.

2. 512 bit LPDDR5x is most likely just 512GB/sec with typical LPDDR5x that's not overly expensive. I would be HIGHLY surprised if they gave it the more expensive RAM that'd break 600GB/sec. The Intel B60 is at 456 GB/s and that's using GDDR6.

Honestly, you're better off waiting for regular DDR6 to come out in a year and just build a system using that.

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

#123

Post by jychang »

maeln wrote: post #91
jychang wrote: post #86

Earlier quoted context omitted.

It’s LPDDR5x It’s gonna be slowwww It’s gonna be what, 273GB/sec vram bandwidth at most? Might as well as buy an AND 395+ 128GB right now for the same inference performance and slightly less VRAM.

Slow is better than nothing. A card with this much VRAM in a "prosumer" price range would be really interesting right now for workstation, to work with big models.

Slow is worse than nothing.

What's the point of this card that's going to be released around the same time as DDR6, and DDR6 will be faster? Might as well as use cheaper system RAM if you system RAM is slower than VRAM.

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

#124

Post by baq »

matt-p wrote: post #119
baq wrote: post #69

Earlier quoted context omitted.

It’d be a disaster for Intel if it sold for less than 3k, personally I think they’re aiming for break even at 5k a pop at least, and I wouldn’t be surprised to advertise 2x memory at half nvidia price, which would put it at ~15-20k? and a healthy margin which they need like oxygen now. Of course it’s all for naught if it doesn’t perform compute-wise.

4x 5090s gets you way faster inference than I suspect this will, or the 6000 pro if you needed datacentre format at expense of raw speed. Given either of those setups is ~8k this will have to come in for less than that.

but it's easier to fit 8x Crescent Island than 40x 5090 into a single chassis

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

#125

Post by Sweepi »

Aurornis wrote: post #101
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.

> If they could release this for around the price of a 5090 This is not targeted at consumers. It’s competing with nVidia’s high RAM workstation cards. Think $10K price range, not $1-2K. The 160GB of LPDDR5X chips alone is expensive enough that they couldn’t release this at the $2K price point unless they felt like giving it away (which they don’t)

In the back of my head floats $200 - $300 for the 64 GiB GDDR7 that you get for spending 7k-10k on an ADA 6000 96 GiB instead of 2k for a 5090 32 GiB. Am I off? Is LPDDR5X more expensive?

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

#127

Post by nullsmack »

Aurornis wrote: post #101
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.

> If they could release this for around the price of a 5090 This is not targeted at consumers. It’s competing with nVidia’s high RAM workstation cards. Think $10K price range, not $1-2K. The 160GB of LPDDR5X chips alone is expensive enough that they couldn’t release this at the $2K price point unless they felt like giving it away (which they don’t)

They better watch the price because you can get a 128GB AMD Strix Halo mini pc for ~1700-2000 today, and those will be even cheaper a year from now. If they're trying to be competitive then it really needs to be more in that ballpark than the massively overpriced Nvidia range.

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

#128

Post by conradev »

Aurornis wrote: post #101
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.

> If they could release this for around the price of a 5090 This is not targeted at consumers. It’s competing with nVidia’s high RAM workstation cards. Think $10K price range, not $1-2K. The 160GB of LPDDR5X chips alone is expensive enough that they couldn’t release this at the $2K price point unless they felt like giving it away (which they don’t)

The GDDR7 found next to most Blackwell chips is more expensive than the LPDDR5X next to this or an M-series/Strix Halo chip.

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

#129

Post by killingtime74 »

musicale wrote: post #64
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.

Intel made a dent in the consumer gaming market with Battlemage. They made a dent in the HPC market / Top500 with intel MAX. It will be interesting to see if they can make a dent in the AI inference market (presumably datacenter/enterprise).

Not sure where you're getting that from, battlemage has been considered a failure. https://finance.yahoo.com/news/report-indicates-intels-lates...
Post reply on HN