News Intel cancels Falcon Shores GPU for AI workloads — Jaguar Shores to be successor

[Admin]

Intel's next-generation AI and HPC GPU will only be used internally, Jaguar shores will be the real successor for Gaudi 3 in the AI space.

Intel cancels Falcon Shores GPU for AI workloads — Jaguar Shores to be successor : Read more

 

[bit_user]

In a move almost as unsurprising as it is sad...

 

[Gururu]

They timed this one correctly after barely beating earnings.

 

[thestryker]

I can't help but wonder if the enterprise compute strategy was derailed by shareholders wanting maximum return and the rapid rise of AI volume. HPC should have rather reliable returns and margins though certainly not high volume. AMD's APU strategy seems like an extremely good one for the classic HPC space, but Intel punted on theirs around a year after announcing it. That's when the split strategy of seemingly going all in on Gaudi while developing next generation enterprise GPU compute happened.

Of course with Aurora just now being announced with full availability perhaps underlying issues were discovered. Given the problems they had with the Alchemist design this is also rather believable.

 

[Root Canal]

In a move almost as unsurprising as it is sad...

Rialto Bridge gone, Falcon Shores gone.. Intel should start somewhere, but they keep kicking the can.

 

[bit_user]

I can't help but wonder if the enterprise compute strategy was derailed by shareholders wanting maximum return and the rapid rise of AI volume.

Intel wasted a critical decade by messing around with Xeon Phi when they should've been following a more classical dGPU approach. Then, with Ponte Vecchio, they decided to try to catch up in a single generation. The result was a wildly overambitious project. That backlogged a bunch of stuff behind it, and now they're left with a train wreck on their hands.

And what happens when one product line looks like it's in trouble? Others try to cover for it, such as with features like AMX. I'm pretty sure that's how we ended up with delays in Sapphire Rapids, not to mention why it wasn't very competitive on core counts or cost. If Intel had a credible datacenter GPU, instead of Xeon Phi, maybe they wouldn't have bothered with AMX.

I honestly haven't followed Gaudi enough to know whether it fell into some of the same pitfalls as Ponte Vecchio. I do think Intel should've had a clearer vision for how their datacenter GPUs would coexists with Gaudi, because there was an awful lot of overlap that maybe someone thought was just being cautious, but I'm sure it didn't help the schedule or costs, any.

 

[jkflipflop98]

Really, they need to just put me in charge of the company.