Intel has listed down several next-generation CPU & GPU products on its official webpage which include the likes of Raptor Lake, Meteor Lake, Xe-HPG DG2 graphics cards, and several HPC class designs such as Emerald Lake & Ponte Vecchio. While we have all heard about these products at some point, the official listings also provide some additional details and all credit goes to Komachi and Momomo_US in finding these out.
Intel's Unreleased & Next-Generation CPU / GPU Families Confirmed - Raptor Lake, Meteor Lake, Xe-HPG DG2 For Consumers & Emerald Lake, Ponte Vecchio For HPC
There are several lineups to go through so we will divide the article into two segments, one for the CPUs and the other for the GPUs. The Intel CPU families that have been confirmed include the 13th Generation Raptor Lake & 14th Generation Meteor Lake. Well, Intel already confirmed Meteor Lake a few days back but we get a few more tidbits.
These two families are aimed at the consumer end & for servers, Intel has listed down its Emerald Lake and Diamond Lake families that will succeed the Sapphire Rapids and Granite Rapids Xeon CPUs. On the GPU front, Intel has listed down several of its Xe-HPG DG2 GPU-based graphics card configurations and also pointed out a specific variant of its flagship Ponte Vecchio GPU. So let's start off with the CPUs.
Intel 13th Generation Raptor Lake Desktop (Consumer) CPUs
The listing itself doesn't reveal any new specifications but does confirm that the Raptor Lake CPUs do exist and will now be part of the 13th Gen Intel Core CPU family. The Raptor Lake CPUs are also listed alongside Alder Lake CPUs (S-Series) which more or less confirms that they will be compatible with the LGA 1700 socket.
To start off with what we know so far, Intel Raptor Lake CPUs will be replacing Alder Lake but it won't be a huge change as we will get to see moving from Rocket Lake to Alder Lake. Alder Lake 12th Gen' CPUs will be the first Intel CPUs to utilize a hybrid core design approach while being based on the 10nm Enhanced SuperFin process. It will also get a brand new platform that will support DDR5 and PCIe 5.0. Raptor Lake will essentially carry most of these features over while offering slight upgrades to the platform and core changes.
For the desktop Intel Raptor Lake parts, it is stated that the lineup will get new hybrid CPU core changes for improved core performance. We know that Alder Lake maxes out at 16 cores and 24 threads. These include 8 cores based on the Golden Cove architecture and 8 cores based on the Gracemont core architecture. It is expected that Raptor Lake would reuse these cores but we can expect some changes to the way cache and clocks are handled for both desktop and mobility CPU parts.
There's also a mention of CPU cache for gaming which could be Intel's answer to AMD's own game cache. We don't know yet if this will be some embedded DRAM cache featured on Raptor Lake or a beefed-up L2/L3 design but we can definitely see some big performance upgrades in games that will help Intel compete with the absolute massive caches that AMD's Ryzen CPUs have to offer. The Intel vPro technology will also be expanded upon in terms of feature set. While Raptor Lake CPUs for the desktop will utilize DDR5-4800 and feature up to 48 PCIe Gen 5 lanes, mobility variants will get support for new LPDDR5X memory and also get a new DLVR power delivery system.
Intel 14th Generation Meteor Lake Desktop (Consumer) CPUs
Intel also confirms Meteor Lake, its 14th Generation Desktop CPU family, on its official webpage. We already got some details from Intel such as the fact that Intel's Meteor Lake line of desktop and mobility CPUs are expected to be based on a new line of Cove core architecture. This is rumored to be known as the 'Redwood Cove' as was reported by MLID (Moore's Law is Dead) and will be based on a 7nm EUV process node. It is stated that the Redwood Cove is designed from the ground up to be an agnostic node which means that it can be fabricated at different fabs. There are references mentioned that point out to TSMC to be a backup or even a partial supplier for the Redwood Cove-based chips. This might tell us why Intel is stating multiple manufacturing processes for the CPU family.
Intel Meteor Lake 14th Gen Desktop/Mobility CPUs For Consumers (Image Via)
The Meteor Lake CPUs may possibly be the first CPU generation from Intel to say farewell to the ring bus interconnect architecture. There are also rumors that Meteor Lake could be a fully 3D-Stacked design and could utilize an I/O die sourced from an external fab (TSMC sighted again). It is highlighted that Intel will be officially utilizing its Foveros Packaging Technology on the CPU to inter-connect the various dies on the chip (XPU).
The Meteor Lake Desktop CPU family is expected to retain support on the LGA 1700 socket which is the same socket used by Alder Lake & Raptor Lake processors. We can expect DDR5 memory and PCIe Gen 5.0 support. The platform will support both DDR5 & DDR4 memory with the mainstream and budget tier options going for DDR4 memory DIMMs while the premium & high-end offerings going for DDR5 DIMMs. The site also lists down both Meteor Lake P and Meteor Lake M CPUs that will be aimed at mobility platforms.
Intel Mainstream Desktop CPU Generations Comparison:
|Intel CPU Family||Processor Process||Processor Architecture||Processors Cores/Threads (Max)||TDPs||Platform Chipset||Platform||Memory Support||PCIe Support||Launch|
|Sandy Bridge (2nd Gen)||32nm||Sandy Bridge||4/8||35-95W||6-Series||LGA 1155||DDR3||PCIe Gen 2.0||2011|
|Ivy Bridge (3rd Gen)||22nm||Ivy Bridge||4/8||35-77W||7-Series||LGA 1155||DDR3||PCIe Gen 3.0||2012|
|Haswell (4th Gen)||22nm||Haswell||4/8||35-84W||8-Series||LGA 1150||DDR3||PCIe Gen 3.0||2013-2014|
|Broadwell (5th Gen)||14nm||Broadwell||4/8||65-65W||9-Series||LGA 1150||DDR3||PCIe Gen 3.0||2015|
|Skylake (6th Gen)||14nm||Skylake||4/8||35-91W||100-Series||LGA 1151||DDR4||PCIe Gen 3.0||2015|
|Kaby Lake (7th Gen)||14nm||Skylake||4/8||35-91W||200-Series||LGA 1151||DDR4||PCIe Gen 3.0||2017|
|Coffee Lake (8th Gen)||14nm||Skylake||6/12||35-95W||300-Series||LGA 1151||DDR4||PCIe Gen 3.0||2017|
|Coffee Lake (9th Gen)||14nm||Skylake||8/16||35-95W||300-Series||LGA 1151||DDR4||PCIe Gen 3.0||2018|
|Comet Lake (10th Gen)||14nm||Skylake||10/20||35-125W||400-Series||LGA 1200||DDR4||PCIe Gen 3.0||2020|
|Rocket Lake (11th Gen)||14nm||Cypress Cove||8/16||35-125W||500-Series||LGA 1200||DDR4||PCIe Gen 4.0||2021|
|Alder Lake (12th Gen)||Intel 7||Golden Cove (P-Core)|
|16/24||35-125W||600 Series||LGA 1700/1800||DDR5 / DDR4||PCIe Gen 5.0||2021|
|Raptor Lake (13th Gen)||Intel 7||Raptor Cove (P-Core)|
|24/32||35-125W||700-Series||LGA 1700/1800||DDR5 / DDR4||PCIe Gen 5.0||2022|
|Meteor Lake (14th Gen)||Intel 4||Redwood Cove (P-Core)|
|TBA||35-125W||800 Series?||LGA 1851||DDR5||PCIe Gen 5.0||2023|
|Arrow Lake (15th Gen)||Intel 20A||Lion Cove (P-Core)|
|40/48||TBA||900-Series?||LGA 1851||DDR5||PCIe Gen 5.0||2024|
|Lunar Lake (16th Gen)||Intel 18A||TBD||TBA||TBA||1000-Series?||TBA||DDR5||PCIe Gen 5.0?||2025|
|Nova Lake (17th Gen)||Intel 18A||TBD||TBA||TBA||2000-Series?||TBA||DDR5?||PCIe Gen 6.0?||2026|
Intel Granite Rapids, Emerald Rapids, Diamond Rapids Future Xeon / HEDT CPU Families
Aside from the consumer-oriented lineups, we also have confirmation on the existence of the Intel Emerald Rapids and Diamond Rapid processors. According to the listings, it looks like the Sapphire Rapids family of 4th Gen Xeon Scalable Processors will be replaced by Emerald Rapids on the same Eagle Stream platform.
Moving forward, Intel is expected to update its Xeon platform with Mountain Stream and Birch Stream. Now interestingly, both Granite and Diamond Rapids are listed for Mountain Stream but only Diamond Rapids is listed for the Birch Stream platform. The Diamond Stream platform will replace Granite Rapids as its successor but we don't know the exact details regarding the Mountain and Birch Stream platforms yet.
Previous reports have stated that Granite Rapids will arrive on the Birch Stream platform and will be compatible with the Birch Stream platform too. So it is likely that the Birch Stream platform will support both Granite Rapids-SP and Diamond Rapids-SP chips while Mountain Stream will support Granite Rapids-AP and Diamond Rapids-AP chips. Granite Rapids is currently pitted to launch in 2023 on the 7nm process node while Diamond Rapids will launch around 2024 and feature either an advanced version of the 7nm process node or a 5nm process from Intel.
Intel Xeon SP Families (Preliminary):
|Family Branding||Skylake-SP||Cascade Lake-SP/AP||Cooper Lake-SP||Ice Lake-SP||Sapphire Rapids||Emerald Rapids||Granite Rapids||Diamond Rapids|
|Process Node||14nm+||14nm++||14nm++||10nm+||Intel 7||Intel 7||Intel 3||Intel 3?|
|Platform Name||Intel Purley||Intel Purley||Intel Cedar Island||Intel Whitley||Intel Eagle Stream||Intel Eagle Stream||Intel Mountain Stream|
Intel Birch Stream
|Intel Mountain Stream
Intel Birch Stream
|Core Architecture||Skylake||Cascade Lake||Cascade Lake||Sunny Cove||Golden Cove||Raptor Cove||Redwood Cove?||Lion Cove?|
|IPC Improvement (Vs Prev Gen)||10%||0%||0%||20%||19%||8%?||35%?||39%?|
|MCP (Multi-Chip Package) SKUs||No||Yes||No||No||Yes||Yes||TBD (Possibly Yes)||TBD (Possibly Yes)|
|Socket||LGA 3647||LGA 3647||LGA 4189||LGA 4189||LGA 4677||LGA 4677||TBD||TBD|
|Max Core Count||Up To 28||Up To 28||Up To 28||Up To 40||Up To 56||Up To 64?||Up To 120?||Up To 144?|
|Max Thread Count||Up To 56||Up To 56||Up To 56||Up To 80||Up To 112||Up To 128?||Up To 240?||Up To 288?|
|Max L3 Cache||38.5 MB L3||38.5 MB L3||38.5 MB L3||60 MB L3||105 MB L3||120 MB L3?||240 MB L3?||288 MB L3?|
|Memory Support||DDR4-2666 6-Channel||DDR4-2933 6-Channel||Up To 6-Channel DDR4-3200||Up To 8-Channel DDR4-3200||Up To 8-Channel DDR5-4800||Up To 8-Channel DDR5-5600?||Up To 12-Channel DDR5-6400?||Up To 12-Channel DDR6-7200?|
|PCIe Gen Support||PCIe 3.0 (48 Lanes)||PCIe 3.0 (48 Lanes)||PCIe 3.0 (48 Lanes)||PCIe 4.0 (64 Lanes)||PCIe 5.0 (80 lanes)||PCIe 5.0 (80 Lanes)||PCIe 6.0 (128 Lanes)?||PCIe 6.0 (128 Lanes)?|
|TDP Range (PL1)||140W-205W||165W-205W||150W-250W||105-270W||Up To 350W||Up To 375W?||Up To 400W?||Up To 425W?|
|3D Xpoint Optane DIMM||N/A||Apache Pass||Barlow Pass||Barlow Pass||Crow Pass||Crow Pass?||Donahue Pass?||Donahue Pass?|
|Competition||AMD EPYC Naples 14nm||AMD EPYC Rome 7nm||AMD EPYC Rome 7nm||AMD EPYC Milan 7nm+||AMD EPYC Genoa ~5nm||AMD EPYC Bergamo||AMD EPYC Turin||AMD EPYC Venice|
There's also a mention of the Fishhawk Falls platform for Emerald Rapids CPUs which may confirm that Intel plans to get back in the HEDT segment which is currently dominated by the Threadripper CPU family from AMD. Fishhawk Falls platform will be succeeding the Galcier Falls platform which supported Intel's 10th Gen Cascade Lake-X HEDT CPUs. Intel has since seemed to have abandoned its HEDT lineup entirely. We can hope for Intel to return to the enthusiast CPU segment once again with Emerald Rapids chips.
Intel Xe-HPG DG2 Desktop & Mobility Discrete GPUs For Gaming Graphics Cards
Moving over to the graphics side of things, we have details regarding several SKUs & configurations of the Xe-HPG DG2 GPU. Videocardz has done an absolutely terrific job in gathering all of the data available which confirms that at least three primarily DG2 SKUs exist which include the 512 EU, 384 EU, and 128 EU chips. Each SKU will feature multiple variants with different configurations.
We don't know the final naming convention that Intel would use for its various DG2 GPU configurations but they can keep it simple by going with DG2-512, DG2-384 & DG2-128. These will be similar to how NVIDIA and AMD name their various GPU configurations such as Ampere GA102, GA104, GA106, and AMD's Navi 21, Navi 22 & Navi 23 GPUs.
Intel Xe-HPG DG2 GPU Specs & Details (via Videocardz):
Intel Xe-HPG DG2 512 EU Discrete Gaming Graphics Cards
Each Xe-HPG based DG2 GPU SKU will come in various configurations which will range from the full-fat chip to several cut-down variants. This is similar to NVIDIA's Ampere GA102-400, GA102-200 naming schemes, or AMD's Navi 21 XTX, Navi 21 XT, Navi 21 XL naming conventions. The top DG2 512 EU variant has just one configuration listed so far and that utilizes the full die with 4096 cores, 256-bit bus interface, and up to 16 GB GDDR6 memory (8 GB GDDR6 listed too). Based on demand and yields, Intel could produce more variants of this flagship chip but we can't say for sure right now.
Intel Xe-HPG DG2 384 EU Discrete Gaming Graphics Cards
Moving on, we have the Intel Xe-HPG DG2 384 GPU SKU which is expected to comprise at least three variants. The full fat chip will feature 3072 cores, up to 12 GB GDDR6 memory (6 GB GDDR6 listed too), and a 192-bit bus interface. Then we have two variants, a 256 EU and a 192 EU variant which are comprised of 2048 and 1536 cores. While both variants feature a 128-bit bus interface, the 256 EU SKU will come with up to 8 GB GDDR6 memory (4 GB GDDR6 listed too) while the 192 EU variant will stick with just 4 GB GDDR6 memory. Based on the specifications, these GPUs will be positioned as mainstream parts.
Videocardz had earlier leaked out the die configuration of the Intel Xe-HPG DG2 384 GPU variant which should measure 190mm2. The PCB blueprint shows 6 memory module locations which do confirm a 192-bit bus interface and either 6 or 12 GB GDDR6 memory capacity.
Intel Xe-HPG DG2 128 EU Discrete Gaming Graphics Cards
Then lastly, we have the Intel Xe-HPG DG2 128 EU parts. The top config is once again a full-fat SKU with 1024 cores, a 64-bit bus interface, and 4 GB GDDR6 memory. The cut-down variant will come with 96 EUs or 768 cores and a 4 GB GDDR6 memory featured across a 64-bit bus interface. This GPU will be very similar to the DG1 GPU-based discrete SDV board however DG2 will have a more improved architecture design and definitely more performance uplift over the first-gen Xe GPU architecture. This lineup is definitely going to be aimed at the entry-level desktop discrete market based on the specifications.
Being the biggest GPU in the Xe-HPG stack, the DG2-512EU will be based on the BGA 2660 socket whereas the smallest SKU, the DG2-128EU, will be based on the BGA 1379 socket. The list also says that the GPU SKUs will feature varying GDDR6 memory speeds starting with 14 Gbps on the entry-level designs and going all the way up to 18 Gbps on the flagship designs. While discrete desktop graphics cards will be available, Intel will also unleash its DG2 discrete GPU lineup on the mobility Tiger Lake-H and Alder Lake-P notebooks.
Intel Xe-HPG Based Discrete Alchemist GPU Configurations:
|GPU Variant||Graphics Card Variant||GPU Die||Execution Units||Shading Units (Cores)||Memory Capacity||Memory Speed||Memory Bus||TGP|
|Xe-HPG 512EU||ARC A780?||Arc ACM-G10||512 EUs||4096||Up To 32/16 GB GDDR6||18 / 16 / 14 Gbps||256-bit||~225W (Desktops)
|Xe-HPG 384EU||ARC A580?||Arc ACM-G10||384 EUs||3072||Up To 12 GB GDDR6||16 / 14 Gbps||192-bit||150-200W (Desktops)
|Xe-HPG 256EU||ARC A550?||Arc ACM-G10||256 EUs||2048||Up To 8 GB GDDR6||16 / 14 Gbps||128-bit||60-80W (Laptops)|
|Xe-HPG 128EU||ARC A380?||Arc ACM-G11||128 EUs||1024||Up To 6 GB GDDR6||16 / 14 Gbps||96-bit||~75W (Desktops)|
|Xe-HPG 128EU||ARC A350?||Arc ACM-G11||128 EUs||1024||Up To 4 GB GDDR6||16 / 14 Gbps||64-bit||35-50W (Laptops)|
|Xe-HPG 96EU||ARC A330?||Arc ACM-G11||86 EUs||768||Up To 4 GB GDDR6||16 / 14 Gbps||64-bit||~35W (Laptops)|
Intel Ponte Vecchio Xe-HPC GPU With 600W Liquid Cooling Module
Lastly, we have a new thermal configuration listed for Intel's flagship Xe-HPC GPU, Ponte Vecchio. We already detailed the Ponte Vecchio GPU which is expected to feature over 100 billion transistors a few days back but it looks like the chip will require some serious amounts of cooling performance as listed by Intel.
The company has listed down a 600W OCM-OAM liquid cooling module for Ponte Vecchio which may give us a hint at its extremely high TDP. The GPU is going to feature several PetaFlops of HPC horsepower so a cooling design of this tier is expected. We can expect to see this module in action on the Aurora supercomputer which Intel has stated will become operational by end of this year.