Today, MLCommons published results of its industry AI performance benchmark in which both the 4th Generation Intel Xeon Scalable processor (code-named Sapphire Rapids) and Habana Gaudi 2 dedicated deep learning accelerator logged impressive training results.


"I'm proud of our team's continued progress since we last submitted leadership results on MLPerf in June. Intel's 4th gen Xeon Scalable processor and Gaudi 2 AI accelerator support a wide array of AI functions and deliver leadership performance for customers who require deep learning training and large-scale workloads." Sandra Rivera, Intel executive vice president and general manager of the Datacenter and AI Group

In advance of Supercomputing '22 in Dallas, Intel Corporation has introduced the Intel Max Series product family with two leading-edge products for high performance computing (HPC) and artificial intelligence (AI): Intel Xeon CPU Max Series (code-named Sapphire Rapids HBM) and Intel Data Center GPU Max Series (code-named Ponte Vecchio). The new products will power the upcoming Aurora supercomputer at Argonne National Laboratory, with updates on its deployment shared today.

The Xeon Max CPU is the first and only x86-based processor with high bandwidth memory, accelerating many HPC workloads without the need for code changes. The Max Series GPU is Intel's highest density processor, packing over 100 billion transistors into a 47-tile package with up to 128 gigabytes (GB) of high bandwidth memory. The oneAPI open software ecosystem provides a single programming environment for both new processors. Intel's 2023 oneAPI and AI tools will deliver capabilities to enable the Intel Max Series products' advanced features.

Intel just finalized the launch date of its 4th Gen Xeon Scalable "Sapphire Rapids" server processors. The company plans to launch them on January 10, 2023. The new processors will be launched at a special event dedicated to the company's various new Data Center (group) innovations, which cover server processors, new networking innovations, possible launches from Intel's ecosystem partners, and more.

A lot is riding on the success of "Sapphire Rapids," as they see the introduction of Intel's new high-performance CPU core on in the enterprise segment at core-counts of up to 60-core/120-thread per socket; along with cutting-edge new I/O that includes DDR5 memory, PCI-Express Gen 5, next-gen CXL, and on-package HBM memory on certain variants.

Intel's upcoming Sapphire Rapids processors have faced multiple delays over the past few years. Built on Intel 7 manufacturing process, the CPU is supposed to bring new advances for Intel's clients and significant performance uplifts. However, TrendForce reports that the mass production of Sapphire Rapids processors will be delayed from Q4 of 2022 to the first half of 2023. The reason for this (yet another) delay is that the Sapphire Rapids MCC die is facing a meager yield on Intel 7 manufacturing technology, estimated to be at only 50-60% at the time of writing. Economically, this die-yielding percentage is not profitable for Intel since many dies are turning out to be defective.

This move will stop many OEMs and cloud service providers (CSPs) from rolling out products based on the Sapphire Rapids design and will have to delay it until next year's mass production. On the contrary, AMD is likely to reap the benefits of Intel's delay, and AMD's x86 server market share will jump from 15% in 2022 to 23% in 2023. Given that AMD ships processors with the highest core counts, many companies will opt for AMD's solutions in their data centers. With more companies being concerned by their TCO measures with rising energy costs, favors fall in the hand of single-socket servers.

According to the latest TrendForce research, pandemic-induced materials shortages abated in the second half of this year and the supply and delivery of short-term materials has recovered significantly. However, assuming materials supply is secure and demand can be met, the annual growth rate of server shipments in 2023 is estimated to be only 3.7%, which is lower than 5.1% in 2022.

TrendForce indicates that this growth slowdown is due to three factors. First, once material mismatch issues had eased, buyers began adjusting previously placed purchase order overruns. Thus, ODM orders also decreased but this will not affect the 2022 shipment volume of whole servers for the time being. Second, due to the impact of rising inflation and weakness in the overall economy, corporate capital investment may trend more conservative and IT-related investment will emphasize flexibility, such as the replacement of certain server terminals with cloud services. Third, geopolitical changes will drive the continuing emergence of demand for small-scale data centers and previous construction of hyperscale data centers will slow. The recent ban on military/HPC servers issued by the U.S. Department of Commerce on October 7 has a very low market share in terms of its application category, so the impact on the overall server market is limited at present. However, if the scope of the ban is expanded further in the future, it will herald a more significant slowdown risk for China's server shipment momentum in 2023.

SK Hynix at the 2022 Intel InnovatiON event, showed off some unconventional server memory capacities. The company presented DDR5 RDIMMs in 48 GB and 96 GB densities, besides the usual 32 GB, 64 GB, and 128 GB ones. These are being offered in data-rates of DDR5-5600 and DDR5-6400, which indicates that DDR5-5600 (JEDEC-standard) could be the standard memory speed supported by Xeon Scalable "Sapphire Rapids" processors, with some (or all) models also supporting DDR5-6400. These are not XMP or overclocking SPDs, but JEDEC-standard ones that the processors can automatically train to. The flagship product among SK Hynix's booth would have to be a mammoth 256 GB DDR5-5600 RDIMM, which should enable servers with up to 4 TB of memory per socket (@2 RDIMMs per channel).

Intel in the second day of its InnovatiON event, turned attention to its next-generation Xeon Scalable "Sapphire Rapids" server processors, and demonstrated on-package accelerators. These are fixed-function hardware components that accelerate specific kinds of popular server workloads (i.e. run them faster than a CPU core can). With these, Intel hopes to close the CPU core-count gap it has with AMD EPYC, with the upcoming "Zen 4" EPYC chips expected to launch with up to 96 cores per socket in its conventional variant, and up to 128 cores per socket in its cloud-optimized variant.

Intel's on-package accelerators include AMX (advanced matrix extensions), which accelerate recommendation-engines, natural language processing (NLP), image-recognition, etc; DLB (dynamic load-balancing), which accelerates security-gateway and load-balancing; DSA (data-streaming accelerator), which speeds up the network stack, guest OS, and migration; IAA (in-memory analysis accelerator), which speeds up big-data (Apache Hadoop), IMDB, and warehousing applications; a feature-rich implementation of the AVX-512 instruction-set for a plethora of content-creation and scientific applications; and lastly, the QAT (QuickAssist Technology), with speed-ups for data compression, OpenSSL, nginx, IPsec, etc. Unlike "Ice Lake-SP," QAT is now implemented on the processor package instead of the PCH.

OneRaichu, who has access to engineering samples of both the AMD "Raphael" Ryzen 7000-series, and Intel 13th Gen Core "Raptor Lake," performed IPC comparisons between the two, by disabling E-cores on the "Raptor Lake," fixing the clock speeds of both chips to 3.60 GHz, and testing them across a variety of DDR5 memory configurations. The IPC testing was done with SPEC, a mostly enterprise-relevant benchmark, but one that could prove useful in tracing where the moderately-clocked enterprise processors such as EPYC "Genoa" and Xeon Scalable "Sapphire Rapids" land in the performance charts. OneRaichu also threw in scores obtained from a 12th Gen Core "Alder Lake" processor for this reason, as its "Golden Cove" P-core powers "Sapphire Rapids" (albeit with more L2 cache).

With DDR5-4800 memory, and testing on SPECCPU2017 Rate 1, at 3.60 GHz, the AMD "Zen 4" core ends up with the highest scores in SPECint, topping even the "Raptor Cove" P-core. It scores 6.66, compared to 6.63 total of the "Raptor Cove," and 6.52 of the "Golden Cove." In the SPECfp tests, however, the "Zen 4" core falls beind "Raptor Cove." Here, scores a 9.99 total compared to 9.91 of the "Golden Cove," and 10.21 of the "Raptor Cove." Things get interesting at DDR5-6000, a frequency AMD considers its "sweetspot," The 13th Gen "Raptor Cove" P-core tops SPECint at 6.81, compared to 6.77 of the "Zen 4," and 6.71 of "Golden Cove." SPECfp sees the "Zen 4" fall behind even the "Golden Cove" at 10.04, compared to 10.20 of the "Golden Cove," and 10.46 of "Raptor Cove."

Intel's Xeon Scalable "Sapphire Rapids" processor may have a tough time getting to market, as leaked benchmarks suggest that even its premium HPC models with on-package HBM2E memory are outperformed by AMD's older-generation "Zen 3" EPYC processors. The 64-core/128-thread EPYC "Milan-X" processor based on older "Zen 3" microarchitecture with 3D Vertical Cache (3DV cache) chiplets, allegedly outperforms 52-core/104-thread Xeon Platinum 8472C and 60-core/120-thread Xeon Platinum 8490H "Sapphire Rapids" engineering samples in CPU-Z Bench and V-ray tests that scale across cores. These benchmark scores were compared with those of the EPYC "Milan-X" by Tom's Hardware, in which they well woefully short of the AMD chips.

During Evercore ISI TMT conference, Intel announced that the company would continue to lose market share, with a possible bounce back in the coming years. According to the latest report, Intel's CEO Pat Gelsinger announced that he expects the company to continue to lose its market share to AMD as the competition has "too much momentum" going for it. AMD's Ryzen and EPYC processors continue to deliver power and efficiency performance figures, which drives customers towards the company. On the other hand, Intel expects a competing product, especially in the data center business with Sapphire Rapids Xeon processors, set to arrive in 2023. Pat Gelsinger noted, "Competition just has too much momentum, and we haven't executed well enough. So we expect that bottoming. The business will be growing, but we do expect that there continues to be some share losses. We're not keeping up with the overall TAM growth until we get later into '25 and '26 when we start regaining share, material share gains."

The only down years that are supposed to show a toll of solid competition are 2022 and 2023. As far as creating a bounceback, Intel targets 2025 and 2026. "Now, obviously, in 2024, we think we're competitive. 2025, we think we're back to unquestioned leadership with our transistors and process technology," noted CEO Gelsinger. Additionally, he had a say about the emerging Arm CPUs competing for the same server market share as Intel and AMD do so, stating that "Well, when we deliver the Forest product line, we deliver power performance leadership versus all Arm alternatives, as well. So now you go to a cloud service provider, and you say, 'Well, why would I go through that butt ugly, heavy software lift to an ARM architecture versus continuing on the x86 family?"

An AMD Ryzen Threadripper PRO 5995WX 64-core/128-thread workstation processor was overclocked to 5.15 GHz all-core by Taiwanese overclocker TSAIK, under extreme cooling, and it [predictably] crushed the Cinebench R23 world-record. The chip scored a godlike 116142 points in the multi-threaded benchmark, ahead of the previous record-holder—105170 points scored on a Threadripper 3990X, by Splave.

The 5995WX, as we mentioned, was subjected to extreme cooling, using liquid-nitrogen. using a Bitspower-made evaporator. The chip was supported by 128 GB of octal-channel DDR4-3200 memory, and an MSI PRO WS WRX80 motherboard. Windows 10 21H2 was the OS of choice. Threadrippers will continue to dominate multi-threaded CPU benchmark leaderboards until Intel can put up a fight with an HEDT variant of its upcoming "Sapphire Rapids" processor.

AMD in its Q2-2022 financial results call with analysts, confirmed that the company's next-generation Ryzen 7000 desktop processors based on the "Zen 4" microarchitecture will debut this quarter (i.e. Q3-2022, or before October 2022). CEO Dr Lisa Su stated "Looking ahead, we're on track to launch our all-new 5 nm Ryzen 7000 desktop processors and AM5 platforms later this quarter with leadership performance in gaming and content creation."

The company also stated that its next-generation Radeon 7000 series GPUs based on the RDNA3 graphics architecture are on-track for launch "later this year," without specifying whether it meant this quarter, which could mean launch any time before January 2023. AMD is also on course to beating Intel to the next-generation of server processors with DDR5 and PCIe Gen 5 support, with its EPYC "Genoa" 96-core processor slated for later this year, as Intel struggles with a Q1-2023 general availability timeline for its Xeon Scalable "Sapphire Rapids" processor.

Intel is reportedly moving the general availability of its 4th Gen Xeon Scalable processor, codenamed "Sapphire Rapids," in the region of early-February to early-March, 2023. The enterprise processors were expected to debut toward the end of 2022, and some of the oldest company roadmaps referencing the processor put its launch back in Q1-2021. Igor's Lab reports that there are as many as 12 steppings of the processor, with the latest discovered being the E5 (the others being A0, A1, B0, C0, C1, C2, D0, E0, E2, E3 and E4; although these could be validation samples handed out to various large customers of Intel to try these chips with their various applications. Built on the Intel 7 node, the processor features up to 60 "Golden Cove" CPU cores, a DDR5 memory interface, PCI-Express Gen 5, and various on-die accelerators. Certain variants even feature up to 32 GB of on-package HBM.

Intel's upcoming Sapphire Rapids processors will not only be present in the server sector but will also span the high-end desktop (HEDT) platform. Today, according to the findings of a Twitter user, @InstLatX64, we have an appearance of Intel's upcoming Sapphire Rapids HEDT SKU in Kernel.org boot logs. Named Intel Xeon W9-3495, this model features 56 cores and 112 threads. While there is no specific information about base and boost frequencies, we know that the SKU supports AVX-512 and AMX instructions. This is a welcome addition, as we have seen Intel disable AVX-512 on consumer chips altogether.

With a high core count and additional instructions for Deep Learning, this CPU will power workstations sometimes in the future. With the late arrival of Sapphire Rapids for servers, a HEDT variant should follow.

Last week, AMD announced that its Ryzen Threadripper Pro 5900WX-series of processors were going to be available from more OEMs, with an eventual retail version of the three models going to be available. Now the company has shared the retail pricing for the new workstation processors and it would appear that AMD's HEDT platform has become unobtanium for most consumers, after having been one of the cheapest platforms out there only a couple of generations ago. According to Tom's Hardware, whom AMD shared the pricing with, the Ryzen Threadripper Pro 5965WX, the 24 core, 48 thread entry level model, will start at US$2,399, which is more than a 32 core, 64 thread Threadripper 3970X, which has a retail price of US$1,999.

A step up is the 32 core, 64 thread Threadripper Pro 5975WX for US$3,299 and at the top of the stacks, sits the 64 core, 128 thread Threadripper Pro 5995WX for the hefty price of US$6,499. All three models have 128 PCIe lanes and a 280 W TDP. AMD seems to have decided to cash in on its core and thread advantage over Intel, as Intel's highest-end workstation chip is the Xeon W-3375, with 38 cores and 76 threads, which comes in at US$4,499, but only has half the PCIe lane count and a much smaller cache. That said, Intel is expected to launch its 4th generation of Xeon W processors, codenamed Sapphire Rapids later this year, which is expected to feature a 56 core, 112 thread SKU, which should bring some competition to AMD in this market segment.

Intel's high-end desktop (HEDT), usually reserved for workstation and enterprise applications, is due for an update, and the company is readying an entire family of updated products. Today, we found a leak of what appears to be an Intel Sapphire Rapids design made for desktops. Called Xeon W5-3433, the CPU appears in the SiSoftware Sandra benchmark database. It carries a configuration of 16 cores and 32 threads and is equipped with 32 MB of L2 cache and 45 MB of L3 cache. Having 2 MB of L2 cache per core suggests that the design is not an Alder Lake variation. This specific SKU is clocked at 1.99 GHz, meaning an early engineering sample.

The Sapphire Rapids HEDT platform is codenamed FishHawk Falls. Intel is supposed to offer Alder Lake-X processors with higher core counts and the FishHawk Falls. Both will be running on the same W790 chipset; however, the Sapphire Rapids implementation will carry more cores in a Xeon package designed for professionals. There was an Ice Lake-X Xeon processor called Xeon W-3335 with 16 cores and 32 threads, meaning that the leaked Xeon W5-3433 is its direct successor.

Intel's ambitious next-generation server processor, Xeon "Sapphire Rapids," hit its second shipping delay this year, according to the company. Speaking at the Bank of America Securities Global Technology Conference, Intel's Sandra Rivera stated that the volume ramp for "Sapphire Rapids," is not going as planned, indicating that its general availability could be delayed for the second time after original plans to do so in the first quarter of 2022.

Riviera was quick to defend the Intel 7 silicon fabrication node (10 nm Enhanced SuperFin) that the "Sapphire Rapids" chip is based on. "One thing I didn't mention on Sapphire, it sits on - it's on our 7-nanometer node and so the process is quite healthy. In fact Alder Lake, which is our client product ramped 15 million units. I think we announced at Q1 earnings, which makes that the fastest ramping, you know one of the fastest ramping client products in almost a decade."

Intel has allowed the media to get a closer look at the next generation of silicon that will power millions of systems in years to come during its private Vision event. PC Watch, a Japanese tech media, managed to get some shots of the upcoming Meteor Lake, Sapphire Rapids, and Ponte Vecchio processors. Starting with Meteor Lake, Intel has displayed two packages for this processor family. The first one is the ultra-compact, high-density UP9 package used for highly compact mobile systems, and it is made out of silicon with minimal packaging to save space. The second one is a traditional design with more oversized packaging, designed for typical laptop/notebook configurations.

Intel is slowly transitioning its data center customers to a new processor generation called Sapphire Rapids. Today, thanks to the hardware leaker Yuuki_ans we have more profound insights into the top-end 56-core Sapphire Rapids processor and its power settings. According to the leak, we have information on either Xeon Platinum 8476 or Platinum 8480 designs that are equipped with 56 cores and 112 threads. This model was running at the base frequency of 1.9 GHz and a boost frequency of 3.3 GHz. Single-core can boost to 3.7 GHz if the report is giving a correct reading. Remember that this is only an engineering sample, so the final target speeds could differ. It carries 112 MB of L2 and 105 MB of L3 cache, and this sample was running with 1 TB of DDR5 memory with CL40-39-38-76 timings.

Perhaps the most exciting finding is the power configuration of this SKU. Intel has enabled this CPU to consume 350 Watts in PL1 rating, with up to 420 Watts in PL2 performance mode. The enforced BIOS power limit rating is set at an astonishing 764 Watts, which could happen with AVX-512 enabled. Final TDP ratings are yet to be disclosed; however, these Sapphire Rapids processors are shaping to be relatively power-hungry chips.

Enthused with its IPC leadership, Intel is possibly planning a return to the high-end desktop (HEDT) market segment, with the "Alder Lake-X" line of processors, according to a Tom's Hardware report citing a curious-looking addition to an AIDA64 beta change-log. The exact nature of "Alder Lake-X" (ADL-X) still remains a mystery—one theory holds that ADL-X could be a consumer variant of the "Sapphire Rapids" microarchitecture, much like how the 10th Gen Core "Cascade Lake-X" was to "Cascade Lake," a server processor microarchitecture. Given that Intel is calling it "Alder Lake-X" and not "Sapphire Rapids-X," it could even be a whole new client-specific silicon. What's the difference between the two? It's all in the cores.

While both "Alder Lake" and "Sapphire Rapids" come with "Golden Cove" performance cores (P-cores), they use variants of it. Alder Lake has the client-specific variant with 1.25 MB L2 cache, a lighter client-relevant ISA, and other optimizations that enable it to run at higher clock speeds. Sapphire Rapids, on the other hand, will use a server-specific variant of "Golden Cove" that's optimized for the Mesh interconnect, has 2 MB of L2 cache, a server/HPC-relevant ISA, and a propensity to run at lower clock speeds, to support the silicon's overall TDP and high CPU core-count.

Intel Xeon Scalable "Sapphire Rapids" is an upcoming enterprise processor with a CPU core count of up to 60. This core-count is achieved using four dies inter-connected using EMIB. Locuza, who leads social media with logic die annotation, posted one for "Sapphire Rapids," based on a high-resolution die-shot revealed by Intel in its ISSCC 2022 presentation.

Each of the four dies in "Sapphire Rapids" is a fully-fledged multi-core processor in its own right, complete with CPU cores, integrated northbridge, memory and PCIe interfaces, and other platform I/O. What brings four of these together is the use of five EMIB bridges per die. This allows CPU cores of a die to transparantly access the I/O and memory controlled any of the other dies transparently. Logically, "Sapphire Rapids" isn't unlike AMD "Naples," which uses IFOP (Infinity Fabric over package) to inter-connect four 8-core "Zeppelin" dies, but the effort here appears to be to minimize the latency arising from an on-package interconnect, toward a high-bandwidth, low-latency one that uses silicon bridges with high-density microscopic wiring between them (akin to an interposer).

At Intel's 2022 Investor Meeting, Chief Executive Officer Pat Gelsinger and Intel's business leaders outlined key elements of the company's strategy and path for long-term growth. Intel's long-term plans will capitalize on transformative growth during an era of unprecedented demand for semiconductors. Among the presentations, Intel announced product roadmaps across its major business units and key execution milestones, including: Accelerated Computing Systems and Graphics, Intel Foundry Services, Software and Advanced Technology, Network and Edge, Technology Development, More: For more from Intel's Investor Meeting 2022, including the presentations and news, please visit the Intel Newsroom and Intel.com's Investor Meeting site.

Intel's next-generation Xeon processors code-named Sapphire Rapids are on track to hit the market this year. These new processors are supposed to bring a wide array of new and improved features and a chance for Intel to show off its 10 nm SuperFin manufacturing process in the server market. Thanks to the Twitter user YuuKi_AnS, we have some of the first tests run in AIDA64 and Cinebench R15 benchmark suites. Yuuki managed to get ahold of DDR5-enabled Sapphire Rapids Xeon with 48 cores and 96 threads, equipped with a base frequency of 2.3 GHz and boost speeds of 3.3 GHz. The processor tested was an engineering sample with a Q-SPEC designation of "QYFQ" and made for Intel Socket E (LGA-4677). This CPU sample was locked at 270 Watt TDP.

Below, you can see the performance results of this processor, tested in the AIDA64 cache and memory benchmark and Cinebench R15 bench test. There is a comparison between AMD's Milan-X and Xeon Platinum 8380, so the numbers are more in check of what you can expect from the final product.

Server processors tend to be one of the most profitable businesses for AMD and Intel. Thus, investment groups and analysts closely monitor happenings in the server and data center world. A report from Mizuho Securities (investment bank) Managing Director Jordan Klein states that many upcoming changes on the server processor front are coming this year. Mr. Klein cites sources over at Insupur Systems, one of the most prominent server vendors. More precisely, Dolly Wu is the VP and GM of Datacenter/Cloud at Inspur. According to the report, AMD and Intel will change their strategy in the server market going forward in 2022.

As far as AMD is concerned, the company plans to increase the pricing of its EPYC processors by 10-30%. This increase should be a bit easier on the strategic cloud customers. The report also indicates that as the demand far exceeds the supply of EPYC processors, AMD increases prices and makes a "take it or leave it" offer, resulting in most customers accepting the increased costs. Another interesting tidbit from the report was the talk about Intel. The blue team laid out its strategy to launch highly-anticipated Sapphire Rapids Xeons in Q2 of 2022. However, it will maybe get delayed to Q3 of 2022. Intel doesn't plan to increase prices to remain competitive with AMD, so the server space will see Intel fighting to regain the lost market share.

Intel is reportedly disabling the rudimentary AVX-512 instruction-set support on its 12th Gen Core "Alder Lake" processors using a firmware/ME update, reports Igor's Lab. Intel does not advertise AVX-512 for Alder Lake, even though the instruction-set was much publicized for a couple of its past-generation client-segment chips, namely 11th Gen Rocket Lake, and 10th Gen Cascade Lake-X HEDT processors. The company will likely make AVX-512 a feature that sets apart its next-gen HEDT processors derived from Sapphire Rapids, its upcoming enterprise microarchitecture.

AVX-512 is technically not advertised for Alder Lake, but software that calls for these instructions can utilize them on certain 12th Gen Core processors, when paired with older versions of the Intel ME firmware. The ME version Intel releases to OEMs and motherboard vendors alongside its upcoming 65 W Core desktop processors, and the Alder Lake-P mobile processors, will prevent AVX-512 from being exposed to the software. Intel's reason to deprecate what little client-relevant AVX-512 instructions it had for Core processors, could have do with energy efficiency, as much as lukewarm reception from client software developers. The instruction is more relevant to the HPC and cloud-computing markets.Many Thanks to TheoneandonlyMrK for the tip.