AMD has hit Intel hard in all CPU segments but its the server segment where the blue team has seen the full might of Zen-based EPYC processors. Intel's iconic Xeon lineup has been disrupted since the arrival of the first generation EPYC CPUs codenamed Naples and the lead was extended with the second generation EPYC lineup, codenamed Rome. However, Intel's first 10nm family is shipping out later this year and as per the latest rumors, it's next-generation 10nm family will be making its way to the server segment by 2021.
Intel 10nm Sapphire Rapids Xeon Scalable Family To Go Against AMD's 4th Gen EPYC Genoa Server CPUs By Late 2021
Intel has so far confirmed that it's Ice Lake family hits the streets around Q4 2020 which would be around the same time AMD introduces its 3rd Generation EPYC Milan CPUs based on the new Zen 3 core architecture. The Ice Lake CPUs, in general, will be Intel's first 10nm server processor lineup, featuring the Sunny Cove core architecture, PCIe Gen 4 support, and a range of new features. But AMD, on the other hand, would make use of a refined 7nm process node along with an upgraded CPU architecture 'Zen 3', which is expected to deliver some big IPC gains.
But its neither Intel's 10nm Ice Lake or AMD's 7nm EPYC Milan that is the topic of today's discussion but its rather the parts succeeding them in 2021. In a leaked roadmap from Intel Russia which was spotted by Momomo_US a few days ago, we get to see some more information on where the Intel Xeon Scalable Family is headed with its next-generation Eagle Stream Platform which will support 2 major Xeon families, Sapphire Rapids & Granite Rapids.
In a previous article, we reported that Sapphire Rapids will utilize an enhanced 10nm process node whereas Granite Rapids will be Intel's first 7nm process-based server lineup. The Intel Eagle Stream platform is suggested to continue till 2023 with Sapphire Rapids coming in late 2021 while Granite Rapids could deploy around late 2022 or early 2023. In its roadmap, Intel also shows that Sapphire Rapids will bring a new architecture which is hinted by the dark blue color that refers to a Tock while Granite Rapids would bring forth a smaller process node, also referred to as a Tick and hinted by light blue color.
Intel Xeon CPU Families (Preliminary):
| Family Branding | Diamond Rapids | Clearwater Forest | Granite Rapids | Sierra Forest | Emerald Rapids | Sapphire Rapids | Ice Lake-SP | Cooper Lake-SP | Cascade Lake-SP/AP | Skylake-SP |
|---|---|---|---|---|---|---|---|---|---|---|
| Process Node | TBD | Intel 18A | Intel 3 | Intel 3 | Intel 7 | Intel 7 | 10nm+ | 14nm++ | 14nm++ | 14nm+ |
| Platform Name | Intel Oak Stream | Intel Birch Stream | Intel Birch Stream | Intel Mountain Stream Intel Birch Stream | Intel Eagle Stream | Intel Eagle Stream | Intel Whitley | Intel Cedar Island | Intel Purley | Intel Purley |
| Core Architecture | Panther Cove-X | Darkmont | Redwood Cove | Sierra Glen | Raptor Cove | Golden Cove | Sunny Cove | Cascade Lake | Cascade Lake | Skylake |
| MCP (Multi-Chip Package) SKUs | Yes | TBD | Yes | Yes | Yes | Yes | No | No | Yes | No |
| Socket | LGA XXXX / 9324 | LGA 4710 / 7529 | LGA 4710 / 7529 | LGA 4710 / 7529 | LGA 4677 | LGA 4677 | LGA 4189 | LGA 4189 | LGA 3647 | LGA 3647 |
| Max Core Count | TBD | Up To 288 | Up To 128 | Up To 288 | Up To 64? | Up To 56 | Up To 40 | Up To 28 | Up To 28 | Up To 28 |
| Max Thread Count | TBD | Up To 288 | Up To 256 | Up To 288 | Up To 128 | Up To 112 | Up To 80 | Up To 56 | Up To 56 | Up To 56 |
| Max L3 Cache | TBD | TBD | 480 MB L3 | 108 MB L3 | 320 MB L3 | 105 MB L3 | 60 MB L3 | 38.5 MB L3 | 38.5 MB L3 | 38.5 MB L3 |
| Memory Support | Up To 16-Channel DDR5? | TBD | Up To 12-Channel DDR5-6400 MCR-8800 | Up To 12-Channel DDR5-6400 | Up To 8-Channel DDR5-5600 | Up To 8-Channel DDR5-4800 | Up To 8-Channel DDR4-3200 | Up To 6-Channel DDR4-3200 | DDR4-2933 6-Channel | DDR4-2666 6-Channel |
| PCIe Gen Support | PCIe 6.0? | TBD | 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) | TBD | TBD | Up To 500W | Up To 350W | Up To 350W | Up To 350W | 105-270W | 150W-250W | 165W-205W | 140W-205W |
| 3D Xpoint Optane DIMM | TBD | TBD | Donahue Pass | TBD | Crow Pass | Crow Pass | Barlow Pass | Barlow Pass | Apache Pass | N/A |
| Competition | AMD EPYC Venice | AMD EPYC Zen 5C | AMD EPYC Turin | AMD EPYC Bergamo | AMD EPYC Genoa ~5nm | AMD EPYC Genoa ~5nm | AMD EPYC Milan 7nm+ | AMD EPYC Rome 7nm | AMD EPYC Rome 7nm | AMD EPYC Naples 14nm |
| Launch | 2025-2026 | 2025 | 2024 | 2024 | 2023 | 2022 | 2021 | 2020 | 2018 | 2017 |
Intel Sapphire Rapids Xeon CPUs - What We Know So Far
The 10nm++ based Sapphire Rapids is expected to make use of the updated Willow Cove core architecture which replaces Sunny Cove in 2020. The Sapphire Rapids lineup will make use of 8 channel DDR5 memory 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 Whitley platform which would house Cooper Lake-SP and Ice Lake-SP processors.
The Sapphire Rapids core counts are expected to reach up to 48 cores (<200W) in single and dual-socket platforms while the 4S/8S platforms are expected to make use of 32 core parts with over 200W TDPs. We can see higher core counts and the higher TDPs could represent higher clocks on the 10nm process node but that's mere speculation at this point in time.
Russian🍻
CPX : 24C , 165-200W , 4S
ICX : 24C , >200W , 2S
ICX : 32C , 150-200W , 2S
SPR : 48C , <200W , 1-2S
SPR : 32C , >200W , 2S/4-8S
*not Max cores.— 188号 (@momomo_us) June 3, 2020
While this will allow Intel to match up or even outpace AMD's EPYC offerings if Milan will end up reusing DDR4 and PCIe Gen 4 from the upcoming EPYC Rome platform. That remains to be seen. Intel's Sapphire Rapids family will be launching the same year that Intel introduces their first datacenter Xe GPUs based on the 7nm process node which is to be the first lead product on the 7nm process node so we can see that Intel has prioritized its server GPU roadmap far more aggressively compared to its server CPU roadmap. The main reason for this is to power the ARNL Aurora Supercomputer which becomes operational in 2021.
The platform would be competing against AMD's Zen 4 based EPYC Genoa lineup which would also be moving to a newer platform known as SP5. AMD has promised new memory along with new capabilities for the Genoa lineup which would include support for DDR5, PCIe 5.0, and more. We don't know what other features would the new lineup include but Intel is doing the same with 8-channel DDR5 support & a new interconnect such as CXL for the Eagle Stream platform. Intel plans to tackle AMD in two key departments with Sapphire Rapids, one being increased per core output (performance) and decreased TCO$ per core.
Currently, AMD's EPYC CPUs demolish Intel in terms of performance per watt, a number of cores/threads, feature set, and total cost of operation with major players in the server segment switching their cloud datacenters to AMD's EPYC CPUs. It remains to be seen if Intel can make a complete or even a partial recovery of its Xeon segment with Sapphire Rapids. For now, Intel is indeed launching its Sapphire Rapids Xeon Scalable family in 2021 but chances here we could see a limited production for the Aurora supercomputer with volume shipments happening around the first half of 2022.
