On Friday afternoon, Intel printed a letter by Jeff McVeigh, the corporate’s interim GM of their Accelerated Computing Programs and Graphics group (AXG). In it, McVeigh supplied a short replace on the state of Intel’s server GPU product lineups and buyer adoption. However, extra importantly, his letter supplied an replace to Intel’s server GPU roadmap – and it’s a little bit of a bombshell. Briefly, Intel is canceling a number of server GPU merchandise that had been deliberate to be launched over the subsequent yr and a half – together with their HPC-class Rialto Bridge GPU – and going all-in on Falcon Shores, whose trajectory has additionally been altered, delaying it till 2025. There’s rather a lot to digest right here, so let’s dive proper in.
Intel’s most up-to-date public server GPU product roadmap, launched again throughout SC22 in Might of 2022, outlined that Intel supposed to launch server GPU merchandise at a reasonably speedy clip. This was (partially) to make up for misplaced time from the a number of delays involving Ponte Vecchio, Intel’s first HPC-class GPU that’s now bought underneath the Knowledge Middle GPU Max household. At that occasion, Intel introduced Ponte Vecchio’s successor, Rialto Bridge, which was to be an evolution of Ponte and was set to pattern in mid-2023. Following up on Rialto can be Falcon Shores in 2024, which together with using a good newer model of Intel’s Xe GPU structure, can be Intel’s first mixed CPU+GPU product (XPU) and was slated to be the last word evolution of each Intel’s HPC CPU and GPU traces.
However, citing “a objective of maximizing return on funding for purchasers”, Intel has considerably refactored their server GPU roadmap, cancelling their beforehand deliberate 2023/2024 merchandise. Rialto Bridge, introduced lower than a yr in the past, has been scrapped. As an alternative, Intel will probably be shifting straight on to Falcon Shores for his or her HPC GPU wants.
These cancellations additionally impression Intel’s Flex line of server GPUs for cloud gaming and media encoding, with Intel axing Lancaster Sound (aka “Subsequent Sound”) in favor of shifting on to its successor, Melville Sound. Melville Sound’s improvement will probably be accelerated, in flip, although Intel hasn’t hooked up a tough date to it. Beforehand, it was anticipated at across the identical time as Falcon Shores.
Intel didn’t present any new visuals for the brand new roadmap, however I’ve gone forward and kitbashed one thing collectively based mostly on their SC22 slide with a purpose to present the place issues stand, and what merchandise have been cancelled
In accordance with Intel, these product modifications are designed to permit the corporate to align itself to a two-year product launch cadence for server GPUs. Rivals NVIDIA and AMD have been working at the same cadence for the previous a number of years, so this may convey Intel’s product cycles roughly according to the competitors. Which, as Intel places it “matches buyer expectations on new product introductions and permits time to develop their ecosystems.”
Studying between the traces, the implication is that Intel wasn’t assured on their capability to promote Rialto and Lancaster to their core buyer base. Whether or not that’s solely due to the speedy product launch cycles, or if there was one thing extra to it, is a element that can stay contained in the halls of Intel for now. However regardless, the corporate is basically scrubbing their plans to launch new server GPU merchandise this yr with a purpose to concentrate on their successors afterward.
And in case there’s any doubt about whether or not this can be a good or unhealthy improvement for Intel, I’ll observe that this data was launched after 5pm Japanese on a Friday. So Intel may be very clearly attempting to bury unhealthy information right here by releasing it on the finish of the week.
Falcon Shores Goes from an XPU in 2024 to a GPU in 2025
In addition to cancelling Rialto Bridge and Lancaster Sound, the opposite main replace to come back from Intel’s letter is the revelation that Intel has considerably refactored their plans for Falcon Shore. What was (and should but nonetheless be) Intel’s first mixed CPU+GPU product for HPC has now been retasked to function Intel’s next-generation HPC GPU. Which in flip has vital repercussions for Intel’s product lineup, and their aggressive positioning.
Falcon Shores was one other 2022 Intel announcement, which was revealed again on the firm’s 2022 Investor Assembly in February. At a excessive degree, Falcon Shores was designed to be Intel’s first XPU product – a chip utilizing a wide range of compute architectures with a purpose to finest meet the execution wants of a single workload. This is able to be achieved through the use of separate processor tiles, and whereas in observe this primarily meant placing Xe GPU tiles and x86 CPU tiles collectively on a single chip, the tiled strategy left the door open to including different varieties of accelerators as properly. Intel is already doing tiled server chips with merchandise like Ponte Vecchio and the just lately launched Sapphire Rapids XCC, so Falcon Shores was slated to be the subsequent step by inserting greater than only one kind of accelerator on a chip.
On the time, Falcon Shores was slated for launch in 2024, to be constructed on an “angstrom period course of”. As deliberate, Falcon Shores would have been Intel’s energy play for the HPC business, permitting them to ship a mixed GPU+CPU product based mostly on their newest architectures and constructed on their cutting-edge 20A/18A course of node, givng them an edge within the HPC market and placing them forward of conventional GPU-based accelerators. And whereas Falcon Shores might but stay as much as these objectives, it received’t be doing so in 2024. And even 2025, for that matter.
As an alternative, Falcon Shores has been retasked to function an HPC GPU half. Intel’s transient letter doesn’t go into the technical modifications, however the implications are that slightly than mixing CPU and GPU tiles on a single chip, Intel goes to dedicate itself to constructing a product out of simply GPU tiles, lowering what was to be intel’s XPU right into a extra easy GPU.
With the cancellation of Rialto Bridge, it goes with out saying that Intel wants a brand new HPC-class GPU product in the event that they wish to stay out there. And whereas there’s presently no cause to suppose that Falcon Shores received’t be an excellent product, the truth that Intel has delayed it till 2025 shouldn’t be a promising signal. Ponte Vecchio is already an older design than its age lets on – it was initially supposed to launch in 2021 and compete with the HPC GPUs of that period – so by not having something newer to supply till 2025, Intel is basically ceding the HPC GPU marketplace for the subsequent two years, exterior of their supercomputer wins. Intel’s long-term plans nonetheless name for the corporate to take a large chunk of the extremely worthwhile server GPU market – to swipe a chunk of what’s largely been NVIDIA’s pie – so these developments primarily put these plans on maintain for an additional two years.
And what might show worse, this places Intel even farther behind its rivals in delivery an XPU/APU-like product. As confirmed by Serve The House, whereas Intel hasn’t given up on delivery a Falcon Shores XPU, the prioritization of GPUs implies that such a product wouldn’t launch in 2025. Meaning an Intel server-class XPU is now a 2026 product at finest – and longer nonetheless at worst.
In the meantime AMD will probably be delivery the same server APU later this yr with the Intuition MI300. That half will make use of a number of chiplets/tiles on a single chip with a purpose to provide HPC-class CPU and GPU efficiency on a single chip, undertaking a long-awaited objective for AMD. And whereas NVIDIA is a bit farther behind in integration with their Grace Hopper superchip – it’s primarily two tightly-coupled chips on a single board, slightly than being chiplets on a single chip – it’s nonetheless forward of the place Intel is at this time. And, worryingly for Intel, the next-gen successor to that half is nearly sure to launch earlier than any potential Falcon Shores XPU hits the market.
In different phrases, by pushing again their server GPU schedule, all of Intel’s merchandise that relied on it at the moment are equally delayed. That leaves Intel’s server CPUs to carry the road on their very own for the subsequent few years.
A Historical past of Server GPU Cancellations as Intel Retains Making an attempt
Finally, the cancellation of Rialto Bridge makes it the most recent in what has turn into a surprisingly lengthy line of cancelled GPUs and GPU-like accelerators over at Intel. The corporate has, in a single type or one other, been making an attempt to interrupt into the accelerator market because the late ‘00s, with initiatives reminiscent of Larrabee. And now, 15 years later, Intel nonetheless isn’t as far alongside because it needs to be, and continues to be cancelling chips to get there.
As the most recent in Intel server GPU casualties, Rialto Bridge is becoming a member of not solely Larrabee, however Intel’s ill-fated Xeon Phi lineup as properly. And even then, Rialto Bridge can’t declare to be the primary Xe structure half to get canned – that honor goes to Xe-HP, which was cancelled in favor of utilizing Intel’s combined compute and graphics Xe-HPG silicon.
The silver lining to this case, a minimum of, is that Intel isn’t cancelling a complete structure right here. The Xe structure has firmly established itself as Intel’s in-house GPU structure, and the truth that it’s delivery in every part from SoCs to video playing cards to HPC accelerators underscores its viability and significance at Intel. The cancellation of Rialto Bridge coupled with the delay of Falcon Shores continues to be a big setback for Intel, however on the finish of the day it’s simply shelving one iteration of the broader Xe structure for an additional.
Within the meantime, Intel will maintain working to develop their GPU choices, and to interrupt into the HPC GPU market in a much bigger means. It’s a market that is just too huge and too worthwhile for Intel to disregard – least it eats much more into their server CPU gross sales – so that they must maintain at it till they discover the success they search.