A new start in dGPU is no easy task, but I honestly thought Arc’s relative RTRT and compute perf were quite good?
My main complaint would be their Linux support situation for Arc. I’m hoping it will improve over time.
Buffalox@lemmy.world 6 months ago
Intel has always been able to come back when the competition surpassed them.
But honestly, this time I was very skeptical they would make it. More than 5 years fumbling the ball in several ways, after Itanium they failed in their production process, and they failed on core design against AMD. Resulting in the first period where Intel was pressed and actually had deficits.
They’d also failed on GPU and their Ray-tracing design, that was to compete on AI too. None of that worked at all against way better competing products. And when their products began to fall behind against AMD on servers, it seemed like the ship had sailed.
But it seems Intel is clawing their way back again, as they’ve managed so many times before.
And I’ve never cheered it as much as I do now. TSMC was on the way to monopolize high end chip manufacturing, and in the long run, that is very unhealthy for everybody involved.
vikingtons@lemmy.world 6 months ago
Buffalox@lemmy.world 6 months ago
I do not count Arc as a failure, allegedly the cards are pretty good with the new drivers. It was previous attempts of making cards that ran pure raytracing, that were supposed to compete with Nvidia in datacenters. But to be fair, 5 years of fumbling is some years ago, I was talking more 5 to 10 years back, where it appeared Intel failed with just about everything.
But Itanium their new server 64 bit CPU is way longer ago, and so is the GPU I think it was Knights Ferry, complete failure with twice the energy consumption and half the performance of Nvidia. Only later production began to fail too, and Intel Core2 was shortly beat by Ryzen on all parameters, and of course Optane failed too.
hips_and_nips@lemmy.world 6 months ago
Itanium
Now there’s a name I haven’t heard in a long time.
And the Xeon Phi (Knight’s Ferry/Landing) was in the GPU space, but only in GPGPU. The idea was that the Xeon Phi, with an x86-compatible core, could, with less modification, run software that was originally targeted to a standard x86 CPU. Something like 68-70 x86-64 cores.
I had a couple of them when I was taking parallel programming back in the day. Nifty little devices, but largely outshined by distributed multiprocessing for x86-64 and paled in comparison to the power of CUDA. That might be my own bias talking though.
Buffalox@lemmy.world 6 months ago
paled in comparison to the power of CUDA. That might be my own bias talking though.
I don’t have personal experience, but AFAIK that’s what everybody says.
vikingtons@lemmy.world 6 months ago
Oh right, my mistake. I do vaguely recall their prior endeavour
Brkdncr@lemmy.world 6 months ago
Intel fell behind on servers? Source?
vikingtons@lemmy.world 6 months ago
In terms of technology & product offerings (perf/watt, compute density, TCO) relative to AMD, then Intel have absolutely fallen behind.
Though, this story has taken time to reflect in server market share, and Intel are still the major player.
ColeSloth@discuss.tchncs.de 6 months ago
More like quickly losing ground. AMD has been taking server side from Intel over the past like 8 years. Intel still has more out there, but every year AMD has been gaining share.
In 2016 amd server share was like 1%. Now it’s at 17% and climbing every year.
the_q@lemmy.world 6 months ago
They haven’t made a comeback yet. This article is just pr to make sure investors don’t leave just yet.
Buffalox@lemmy.world 6 months ago
Yes, I suppose you are right, this is a year into the future, and we’ve seen promises before, where it didn’t go quite as planned.
Still it looks like they at least are catching up.