Updated: Intel Cans Xe-HP Server GPU Products, Shifts Focus To Xe-HPC and Xe-HPG
by Ryan Smith on November 1, 2021 10:30 PM ESTUpdate 11/01:
In an additional tweet posted over the weekend by Raja Koduri, the Intel GPU frontman confirmed that Intel will be bringing products based on their Xe-HPG architecture to the server market.
We leveraged Xe HP to build developer ecosystem for HPC, AI and Visual cloud. It’s being used on-site at Argonne and other customers.
— Raja Koduri (@Rajaontheedge) October 30, 2021
We’ll have Xe HPG based data center products for visual cloud/AI Inference and Xe HPC based products for HPC/AI Training @intelgraphics pic.twitter.com/iHZa2dMLqd
Painting very broad strokes here from a 280 character announcement, it sounds like Intel will take a very similar tack as NVIDIA for their initial generation of products. That means offering Ponte Vecchio (Xe-HPC) for HPC and high performance AI training, while using the Alchemist (Xe-HPG) products for less intense/more scalable tasks such as AI inference and server-based graphics. All of which leaves me even more curious if Intel has retained Xe-HP’s tile capabilities for Xe-HPG.
With his tweet, Koduri also included a slightly updated version of one of Intel's Xe-HPG slides, which now includes the server graphics role.
Original Story (10/29):
In a tweet published yesterday afternoon by Raja Koduri, Intel’s SVP and GM of the Accelerated Computing Systems and Graphics (AXG) Group, the GPU frontman revealed that Intel has dropped their plans to bring their Xe-HP series of server GPUs to the commercial market. Citing that Xe-HP has evolved into the Xe-HPC (Ponte Vecchio) and Xe-HPG (Intel Arc) families within Intel’s GPU group, the company seemingly no longer sees a need to release a second set of server GPUs – at least, not something based on Xe-HP as we know it.
We deployed Xe HP in our oneAPI devcloud and leveraged it as a SW development vehicle for oneAPI and Aurora. We currently don’t intend to productize Xe HP commercially, it evolved into HPG and HPC that are on general market production path
— Raja Koduri (@Rajaontheedge) October 28, 2021
Also known by the codename Arctic Sound, Intel’s initial family of server GPUs has been the most visible product under development from Intel’s reborn GPU group. Koduri frequently showed off chips housing the silicon as it was brought-up in Intel’s labs. And, Xe-LP/DG1 excepted, this was the first high-performance Xe silicon that Intel developed. Notably, it was also the only high-performance Xe silicon slated to be manufactured by Intel; Xe-HPC’s compute tiles and Xe-HPG dies are both being built by TSMC.
We haven’t heard much of Xe-HP this year, and in retrospect that was a sign that something was amiss. Still, as of year Intel had been showing off Xe-HP demos with performance as high as 42 TFLOPS of FP32 throughput. And in November the company announced that Xe-HP was sampling to select customers.
But, as it would seem, Xe-HP just isn’t meant to be. For 2021 Intel has been focused on getting Ponte Vecchio assembled for the Aurora supercomputer (and eventually other customers), as well as bringing up the Xe-HPG Alchemist GPU family for Q1 of 2022. According to Koduri, Xe-HP has been leveraged as a development vehicle for Aurora and Intel’s oneAPI – so it hasn’t gone unused – but that’s as far as Xe-HP has made it.
For now, the cancellation of Xe-HP raises some big questions about Intel’s server GPU plans. Xe-HP was intended to be the backbone of their server efforts, utilizing a scalable design that could range from one to four cores to serve datacenter needs ranging from compute to media processing. Between Xe-HP and Ponte Vecchio covering the very high end of the market (e.g. HPC), Intel was slated to develop a potent slate of parallel processors to compete with market-leader NVIDIA, and offer traditional Intel customers a GPU option that let them stay in Intel’s ecosystem.
At this point it’s not clear what will fill the void left by Xe-HP in Intel’s product stack. Ponte Vecchio is in production now, and judging from Intel’s revised Aurora figures, is performing better than expected. But the massive chip is expensive to build – at least in its current configuration. And while Xe-HPG could be called up for server use next year, unless Intel is able to tile it like Xe-HP, they won’t be able to offer the kind of performance that Xe-HP was slated to deliver.
Equally nebulous is a full understanding of why Intel opted to cancel Xe-HP. With the silicon already up and running, canceling it certainly sets back their server GPU plans. But as AMD has already begun rolling out their new CDNA2 architecture-based server GPU products, and NVIDIA is likely aiming for some kind of refresh of their own in 2022, there’s certainly the question of whether Xe-HP was simply too late and/or too slow to compete in the server market. Coupled with that, it’s the only lineup of high-performance Xe parts that Intel was fabbing themselves, using the 10nm Enhanced Superfin process (now referred to as Intel 7).
In any case, Intel is clearly not giving up on their plans to break into the server GPU market, even if pieces of that plan now need to be rewritten. We’ve reached out to Intel for additional details, and we’ll update this story further if Intel releases a more detailed statement on their server GPU plans.
Source: Raja Koduri (Twitter)
47 Comments
View All Comments
mode_13h - Monday, November 1, 2021 - link
For the most part, I mean. Obviously, Xe-HPC is targeted at the high-end of Xeon Phi's market. There were a few supercomputers that used it.kwohlt - Tuesday, November 2, 2021 - link
23 and 13 year ago business decisions are irrelevant to current market conditions. GPU is quickly becoming more important than CPU in many critical workflows. The role of the CPU is shrinking, and if Intel wants to be around, they need to diversify their compute products away from strictly CPU.1998 was an entire generation ago.
hansmuff - Tuesday, November 2, 2021 - link
Hah, I had one. It was fairly awful overall, but I could play Q3 Arena with it, which is really all that mattered ;)bananaforscale - Friday, November 5, 2021 - link
"I think I heard somewhere" means exactly nothing. BTW, discrete, not discreet.YB1064 - Saturday, October 30, 2021 - link
I have yet to see a single discrete consumer GPU from INTEL on Newegg/Amazon? Is this dead?whatthe123 - Sunday, October 31, 2021 - link
they're coming out for retail next year using tsmc chipsmode_13h - Sunday, October 31, 2021 - link
They've been selling DG1 to OEMs for over a year, IIRC. That's a PCIe card with the same 96 EU GPU as in Tiger Lake. Also, like Tiger Lake, it uses regular DDR4!Silver5urfer - Friday, October 29, 2021 - link
Raja hype boys. As usual.Now for that new Xe mainstream, I will see how will Intel screw up. I have my huge doubts on the driver side of things than anything else. Because there are a TON of games we have and lot of workloads we have and it has to support everything out of gate. Which is a super mighty task.
Plus thanks to Windows 10 DCH BS the drivers will be a nasty mess, just like how Nvidia's latest 493 branch has been. Sadly no more Win32 drivers from any company because M$ wants their draconian standard no matter what. NVCP was not bundled with first 493 branch and forced people to get it from Store now they added. Also reading some reports on Mining Nerf lol.
Intel also eats up TSMC 6nm overall TSMC so expect high price and low availability if ETH mining is good, add even more worse outcome.
At this point nobody can fix the GPU market.
iranterres - Friday, October 29, 2021 - link
LOL Intel are burying theirselves again.TheJian - Saturday, October 30, 2021 - link
Yeah, 6.8B NET INCOME just sucks this Q...It's so terrible to be Intel.Then again, AMD made less then 1B NET so... What world do you live in? I live in one where ~7 is FAR larger than ~1. But hey, what do I know, these are just numbers...who cares....ROFL. ;)
3nm TSMC INTEL server/mobile incoming in 1Q. :) AMD 3nm server coming in....2024 or 2025?
People can't be this stupid. AMD is winning...AMD is winning...pfft. Ok. But at least they bought some shares back (been diluting them for 15yrs now, about time they bought a few back...LOL). AMD's Mkap is 3/4 of Intel's and Intel is making 6.8B NET in a Q while AMD is winning (making less than 1 BTW)...ROFLMAO. I take it back, people are stupid.