Intel 20 Core & 40 Thread Sapphire Rapids Xeon CPU Spotted & Tested, Dual Socket Config With Up To 75 MB Cache & Up To 4.7 GHz Clocks

Hassan Mujtaba
Intel Xeon Platinum 8380 "Ice Lake" CPU Shows Great Improvement In Linux 6.0 1

An Intel Sapphire Rapids Xeon CPU has been spotted and tested within the Geekbench database. The chip was spotted by Benchleaks and from the looks of things, it seems to be an early sample that is evident by its lower base clock and the fact that was tested on an internal Intel platform & not a third-party Server vendor.

Intel Sapphire Rapids 20 Core & 40 Thread Xeon CPUs Tested In Dual Socket Configuration, Rock Up To 75 MB Cache & 4.7 GHz Clocks

Dissecting the Geekbench listing, it looks like the test platform was part of a 2S configuration that was running dual Intel Sapphire Rapids Xeon CPUs. The engineering sample is listed as Family 6 Model 143 Stepping 2 which confirms that it is part of the Sapphire Rapids lineup & based on the Intel 10nm ESF (Enhanced SuperFin) architecture with Golden Cove cores.

Related Story Intel’s Project Firefly Takes The Best of Phones To Build Laptops In A Slim 12.9mm Metal Chassis With No Vents

Each CPU features 20 cores and 40 threads & makes up a total of 40 cores and 80 threads for the server itself. Each chip features 75.0 MB of L3 (37.5 MB per chip) and 20.0 MB of L2 cache per chip. Both of these caches have seen a significant boost over the Ice Lake Xeon CPUs.

As for clock speeds, since the Intel Sapphire Rapids Xeon CPU is still an early engineering sample, it has a base clock of 1.50 GHz but can boost up to 4.7 GHz as reported by Geekbench. We cannot say how accurate these clock speeds are but they do look pretty high for a server platform so it could likely be a high-clock optimized chip. The other possibility is like I said, a faulty clock speed which is a very common scenario within the Geekbench database.

The Intel 20 Core & 40 Thread Sapphire Rapids Xeon CPU was tested within the older Geekbench 4 benchmark with 32 GB of memory (presumably DDR5 since that is what the next-generation Xeon chips support) and well, performance was quite lackluster with a single-core score of 1340 points & a multi-core score of 31,666 points. Again, these are results from a very early sample and an older & outdated benchmark so we can see performance improvements in later benchmarks. Sapphire Rapids is pitted for a launch next year so it will take time for better samples to appear in databases.

Here's Everything We Know About Intel's 4th Gen Sapphire Rapids Xeon CPUs

The Sapphire Rapids-SP family will be replacing the Ice Lake-SP family and will go all on board with the 10nm Enhanced SuperFin process node that will be making its formal debut later this year in the Alder Lake consumer family. From what we know so far, Intel's Sapphire Rapids-SP lineup is expected to utilize the Golden Cove architecture & will be based on the 10nm Enhanced SuperFin process node.

The Sapphire Rapids lineup will make use of 8 channel DDR5 memory with speeds of up to 4800 MT/s and support PCIe Gen 5.0 on the Eagle Stream platform. The Eagle Stream platform will also introduce the LGA 4677 socket which will be replacing the LGA 4189 socket for Intel's upcoming Cedar Island & Whitley platform which would house Cooper Lake-SP and Ice Lake-SP processors, respectively. The Intel Sapphire Rapids-SP Xeon CPUs will also come with CXL 1.1 interconnect that will mark a huge milestone for the blue team in the server segment.

Intel Sapphire Rapids-SP Xeon Server CPU Specifications. (Image Credits: Videocardz)

Coming to the configurations, the top part is started to feature 56 cores with a TDP of 350W. What is interesting about this configuration is that it is listed as a low-bin split variant which means that it will be using a tile or MCM design. The Sapphire Rapids-SP Xeon CPU will be composed of a 4-tile layout with each tile featuring 14 cores each.

It looks like AMD will still hold the upper hand in the number of cores & threads offered per CPU with their Genoa chips pushing for up to 96 cores whereas Intel Xeon chips would max out at 56 cores if they don't plan on making SKUs with a higher number of tiles. Intel will have a wider and more expandable platform that can support up to 8 CPUs at once so unless Genoa offers more than 2P (dual-socket) configurations, Intel will have the lead in the most number of cores per rack with an 8S rack packing up to 448 cores and 896 threads.

The Intel Saphhire Rapids CPUs will contain 4 HBM2 stacks with a maximum memory of 64 GB (16GB each). The total bandwidth from these stacks will be 1 TB/s. According to leaked details from AdoredTV, HBM2 and GDDR5 will be able to work together in flat, caching/2LM, and hybrid modes. The presence of memory so near to the die would do absolute wonders for certain workloads that require huge data sets and will basically act as an L4 cache.

AMD has been taking away quite a few wins from Intel as seen in the recent Top500 charts from ISC '21. Intel would really have to up their game in the next couple of years to fight back the AMD EPYC threat.

Which server lineup do you think will offer the best feature set for enterprise markets?

Intel Xeon CPU Families (Preliminary):

Family BrandingCoral RapidsDiamond RapidsClearwater ForestGranite RapidsSierra ForestEmerald RapidsSapphire RapidsIce Lake-SPCooper Lake-SPCascade Lake-SP/APSkylake-SP
Process NodeIntel 14A?Intel 18A-PIntel 18AIntel 3Intel 3Intel 7Intel 710nm+14nm++14nm++14nm+
Platform NameTBDIntel Oak StreamIntel Birch StreamIntel Birch StreamIntel Mountain Stream
Intel Birch Stream
Intel Eagle StreamIntel Eagle StreamIntel WhitleyIntel Cedar IslandIntel PurleyIntel Purley
Core ArchitectureTBDPanther Cove-XDarkmontRedwood CoveSierra GlenRaptor CoveGolden CoveSunny CoveCascade LakeCascade LakeSkylake
MCP (Multi-Chip Package) SKUsYesYesYesYesYesYesYesNoNoYesNo
SocketTBDLGA XXXX / 9324LGA 4710 / 7529LGA 4710 / 7529LGA 4710 / 7529LGA 4677LGA 4677LGA 4189LGA 4189LGA 3647LGA 3647
Max Core CountTBDUp To 192 P-CoresUp To 288Up To 128Up To 288Up To 64?Up To 56Up To 40Up To 28Up To 28Up To 28
Max Thread CountTBDUp To 192Up To 288Up To 256Up To 288Up To 128Up To 112Up To 80Up To 56Up To 56Up To 56
Max L3 CacheTBDTBDTBD480 MB L3108 MB L3320 MB L3105 MB L360 MB L338.5 MB L338.5 MB L338.5 MB L3
Memory SupportTBDUp To 16-Channel DDR5-9000+Up To 12-Channel DDR5-8000Up To 12-Channel DDR5-6400
MCR-8800
Up To 12-Channel DDR5-6400Up To 8-Channel DDR5-5600Up To 8-Channel DDR5-4800Up To 8-Channel DDR4-3200Up To 6-Channel DDR4-3200DDR4-2933 6-ChannelDDR4-2666 6-Channel
PCIe Gen SupportPCIe 6.0PCIe 6.0PCIe 5.0 (96 Lanes)PCIe 5.0 (136 Lanes)PCIe 5.0 (88Lanes)PCIe 5.0 (80 Lanes)PCIe 5.0 (80 lanes)PCIe 4.0 (64 Lanes)PCIe 3.0 (48 Lanes)PCIe 3.0 (48 Lanes)PCIe 3.0 (48 Lanes)
TDP Range (PL1)TBDTBDUp To 500WUp To 500WUp To 350WUp To 350WUp To 350W105-270W150W-250W165W-205W140W-205W
3D Xpoint Optane DIMMTBDTBDN/ADonahue PassN/ACrow PassCrow PassBarlow PassBarlow PassApache PassN/A
CompetitionTBDAMD EPYC VeniceAMD EPYC TurinAMD EPYC TurinAMD EPYC BergamoAMD EPYC Genoa ~5nmAMD EPYC Genoa ~5nmAMD EPYC Milan 7nm+AMD EPYC Rome 7nmAMD EPYC Rome 7nmAMD EPYC Naples 14nm
Launch2028-20292027202620242024202320222021202020182017
Hassan Mujtaba Photo

About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.

Follow Wccftech on Google to get more of our news coverage in your feeds.

Button