263
Upcoming Hardware Launches 2022 (Updated Apr 2022)
(263 Comments) »Introduction
In this article, which our team will regularly update, we will maintain a growing list of information pertaining to upcoming hardware releases based on leaks and official announcements as we spot them. There will obviously be a ton of rumors on unreleased hardware, and it is our goal to—based on our years of industry experience—exclude the crazy ones. In addition to these upcoming hardware release news, we will regularly adjust the structure of this article to better organize information. Each time an important change is made to this article, it will re-appear on our front page with a "new" banner, and the additions will be documented in the forum comments thread. This article will not leak information we signed an NDA for.Feel free to share your opinions and tips in the forum comments thread and subscribe to the same thread for updates.
Last Update (Apr 22nd):
- Updated AMD Zen 4 / Ryzen 7000
- Updated Intel Sapphire Rapids
- Added Intel Alder Lake-X
- Updated Intel DG2
- Updated AMD Radeon RX 6550 XT / 6650 XT / 6750 XT / 6850 XT / 6950 XT
- Updated NVIDIA Ada
- Added NVIDIA Blackwell
- Updated AMD Navi 31 / 32 / 33
- Added AMD B650 Chipset
- Updated Intel Z790 / H770 / B760 Chipsets
- Updated HBM3 Memory
- Updated TSMC 3 nanometer and 2 nanometer
- Removed launched products: Ryzen 7 5800X3D, Ryzen Zen 3 Threadripper, EPYC Milan-X, Intel Core i9-12900KS, NVIDIA Hopper, GeForce RTX 3090 Ti,
Processors
AMD Zen 4 / Ryzen 7000 Series [updated]
- Release Date: H2 2022
- Launched around same time as RDNA3 GPU architecture
- "In Design" as of Nov 2018
- "On Track" for 2021 launch as of Dec 9, 2019, possibly not true anymore
- 5 nm TSMC process, possibly EUV
- Desktop codename: "Raphael"
- DDR5 memory support, 5200 MT/s
- AMD will wait for better DDR5 availability before launch of AM5 platform
- Server: up to 12 TB on server, RDDR5 and LRDDR5, 12-channel
- Improves IPC by up to 29%
- Server platform codenamed "Genoa", up to 96 cores, 320 W TDP, up to 400 W
- Server socket: SP5, 6096-pin LGA
- Up to 64 cores for EPYC
- Up to 16 cores for notebook (Raphael-H)
- Desktop platform goes up to 170 W, with 16 cores
- 100-000000666-21_N is an 8c/16t design, so basically Ryzen 7 7800X
- 100-000000665-21_N is 16c/32t, probably Ryzen 9 7950X
- Desktop changes socket to AM5
- Socket AM5 is LGA1718, like Intel, no more pins
- Socket AM4 coolers will be compatible with AM5
- Support for PCI-Express 5.0
- Genoa (EPYC Server) will also have CXL
- Bergamo uses Zen 4c on 5 nm with up to 128 cores
- More cores per chiplet
- Increased L2 cache of 1 MB per core
- ES seen running at 1.5 V
- All Zen 4 CPUs will have RDNA2 integrated graphics
- Possible that some cores are running at lower clock/voltage to emulate an "efficient core" concept
- Support for AVX512 instructions, also BFloat16 and "other ISA extensions."
- "Enhanced Security Features"
- Improved thermal sensors and power management
- DDR5 memory overclocking is a core focus
- RAMP (Ryzen Accelerated Memory Profile) as competitor to Intel XMP
- Uses 3rd generation Infinity Fabric, which adds cache-coherent unified memory
- Nov 2020 statement from AMD: "Zen 4 is going to have a similar long list of things, where you look at everything from the caches, to the branch prediction, [to] the number of gates in the execution pipeline. Everything is scrutinized to squeeze more performance out."
- Adds support for USB 4.0 (via separate chip)
AMD Zen 5 / Ryzen 8000 Series
- Release Date: 2022
- 5 nm or 3 nm TSMC process
- DDR5 memory support
- PCI-Express Gen 5
- Codename "Strix Point" could feature big.LITTLE core design, similar to Alder Lake
- Another codename: "Granite Ridge"
- Uses Socket SP5 for server, desktop uses Socket AM5
- Possibly all APUs (with integrated graphics)
Intel Alder Lake-N
- Release Date: Unknown
- Gracemont cores only, no Golden Cove cores
- Possibly for embedded designs or Chromebooks
- No PCIe lanes from the CPU
- Gen 12.2 iGPU GT1 with 32 EUs
Intel Alder Lake-X [added]
- Release Date: Unknown
- Could be a desktop version of Sapphire Rapids
Intel Raptor Lake
- Release Date: Q4 2022, possibly advanced to Q3 2022. Mobile in Q4
- Successor to Alder Lake
- Uses "enhanced" Golden Cove cores, known as "RPC" / "Raptor Cove"
- Better IPC, frequency, perf/W than Alder Lake
- More E-Cores
- L2 cache increased
- Up to 5.5 GHz
- big.LITTLE design
- Core i9-13900K: 24C (8+16) 32T, 36M L3, 32 EU, 125 W
- Core i9-13900: 24C (8+16) 32T, 36M L3, 32 EU, 65 W
- Core i7-13700K: 16C (8+8) 24T, 30M L3, 32 EU, 125 W
- Core i7-13700: 16C (8+8) 24T, 30M L3, 32 EU, 65 W
- Core i5-13500K: 14C (6+8) 20T, 24M, 32 EU, 125 W
- Core i5-13500: 14C (6+8) 20T, 24M, 32 EU, 65 W
- Core i5-13400: 10C (6+4) 16T, 21M, 24 EU, 65 W
- Core i3-13300: 4C (4+0) 8T, 12M, 32 EU, 65 W
- Pentium: 2C (2+0) 4T, 6M, 16 EU, 65 W
- Little cores are Gracemont, same as Alder Lake
- DDR5-5600 and faster
- Might also support DDR4
- Increased cache size
- Competitor to AMD's Zen 4
- Uses same Socket LGA1700 as Alder Lake
Intel Sapphire Rapids [updated]
- Release Date: 2022
- Ramp up: Q2 2022
- Successor to Cooper Lake
- For enterprise / data center
- 10 nm+ SuperFin production process, now called "Intel 7"
- Uses chiplet architecture
- All chiplets are connected through a mesh fabric to minimize latencies
- EMIB to connect the dies using an active interposer
- Yet another leak talks about 60 cores with 4x 15-core chiplets
- Xeon 8476 & 8480: 56c/112t, 1.9 GHz base, 3.3 GHz Boost, 1-core up to 3.7 GHz, PL1=350 W, PL2=420 W
- Engineering Sample: 20 Cores, 40 MB L2 cache, 75 MB L3 cache, 1.5 GHz
- 2 MB L2 cache per core
- 1.875 MB L3 cache, for a max total of 112.5 MB
- Uses Socket LGA4677 or LGA4189
- Supports 1, 2, 4 and 8 Socket configurations
- 8-channel DDR5 memory, DDR5-4800
- HBM memory supported, 1 TB/s, 64 GB HBM2E per socket
- HBM can operate as DRAM cache or as additional DRAM memory, or HBM-only, without system DRAM
- Golden Cove CPU cores (same as Alder Lake)
- 350 W max TDP
- ES clocked at 2 GHz
- PCIe 5.0, 128 lanes
- CXL 1.1 support, 4x x16 devices
- DLBoost, Enhanced SGX, improved Cryptographic Instructions, FP16
- UPI bus improved: "UPI 2.0 is wider and faster", up to 4x 24 UPI links @ 16 GT/s
- Platform name: Eagle Stream
- Chipset name: Emmitsburg
- Specific Sapphire Rapids variants will come with on-package HBM, also called "PMEM" (package memory)
- Includes CLDEMOTE instruction to invalidate cache lines
- Might support firmware updates without reboot
Intel Sapphire Rapids HEDT
- Release Date: Q3 2022
- High-end Desktop (HEDT) version of Sapphire Rapids Xeon
- Same underlying tech as Sapphire Rapids: 10 nm SuperFin, PCIe 5.0, DDR5
- Designed to combat AMD Threadripper
- Uses Intel W790 chipset
Intel Grand Ridge
- Release Date: 2022 or later
- Produced on 7 nm HLL+ process
- Successor to Atom "Snow Ridge"
- 24 cores across 6 clusters with 4 cores each
- 4 MB L2 per cluster, plus L3 cache
- Uses Gracemont CPU core
- Dual-channel DDR5
- PCI-Express Gen 4 with 16 lanes
Intel Elkhart Lake
- Release Date: unknown
- Produced on 10 nm process
- Designed for next-gen Pentium Silver and Celeron processors
- CPU cores use Tremont architecture
- GPU uses Gen 11
- Dual-core and quad-core configurations
- Single-channel memory controller with DDR4 and LPDDR4/x support
- Engineering sample: 1.9 GHz, 5/9/12 W TDP
Intel Meteor Lake
- Release Date: 2023
- Taped in as of May 2021
- First test production: Nov 2021
- "Powering on" in Q2 2022
- Succeeds "Alder Lake"
- New microarchitecture for P-Cores, "Redwood Cove", two generations ahead of "Golden Cove"
- E-Cores are Crestmont
- Hybrid processor—big.LITTLE architecture
- Multi-chip-module using Foveros packaging technology
- Produced on various processes, at different fabs, even non-Intel
- Four distinct tiles
- Compute tile on Intel 4 (7 nm)
- Graphics tile on TSMC N3, Intel Gen 12.7 architecture, 352 EUs
- SOC tile on TSMC
- Fourth tile is for IO
- PCI-Express 5.0
- DDR5 + LPDDR5X
- As of late 2020, Intel is adding support for Meteor Lake to the Linux Kernel
Intel Arrow Lake
- Release Date: 2023 or 2024
- Succeeds "Meteor Lake"
Intel Lunar Lake
- Release Date: 2023 or 2024
- Succeeds "Arrow Lake"
- Uses Intel 18A process paired with external foundry services
Intel Granite Rapids
- Release Date: 2022
- Successor to Sapphire Rapids
- 8-channel DDR5
- For enterprise / data center
- PCIe 5.0
- Probably 7 nm+ process
- Platform name: Eagle Stream
VIA CenTaur / Zhaoxin KaiXian
- Release Date: H2 2020
- Eight-core 64-bit CPU, 2.5 GHz
- AVX-512 supported
- 16 nm FinFET TSMC
- 195 mm² die size
- Use LGA socket
- Codename: "CHA", pronounced "C-H-A"
- Separate AI co-processor "NCORE"
- All cores + NCORE connected using a ring bus
- Integrated VIA S3 graphics with DirectX 11.1
- 16 MB shared L3 cache
- Four-channel DDR4-3200 memory support
- 44 PCI-Express 3.0 lanes
- Sold as Zhaoxin KaiXian KX-6780A in China (end of Jan 2020): 8 core, 8 threads, 2.7 GHz, 8 MB cache, dual-channel DDR4-3200
- Southbridge integrated
- Multi-socket capable
Graphics / GPUs
NVIDIA RTX 3060 Ultra
- Release Date: 2021 or 2022
- Same GA104 GPU as RTX 3060 Ti and RTX 3070
- 12 GB GDDR6
- 192-bit or 256-bit memory bus
- $449
NVIDIA RTX 3060 Super, RTX 3070 Super / RTX 3080 Super / RTX 3090 Super
- Release Date: 2022
- RTX 3060 Super: 5632 cores, 12 GB GDDR6
- RTX 3070 Super: 5888 cores, 8 GB GDDR6X
- RTX 3080 Super: 8960 cores, 12 GB GDDR6X
- RTX 3090 Super: 10752 cores, 24 GB GDDR6X 21 Gbps, 400 W+
NVIDIA Ampere Refresh
- Release Date: unknown
- NVIDIA is moving their existing designs from Samsung 8 nm to TSMC 7 nm
NVIDIA Ada Lovelace / GeForce RTX 4080 / RTX 4090 [updated]
- Release Date: not before 2022
- Successor to "Ampere" architecture, possibly gaming-only focused
- AD102: 18,432 shaders, 144 SMs
- 5 nanometer process at TSMC
- Up to 70 FLOP/s, more than 2 GHz
- 21 Gbps memory
- Up to 24 GB
- AD102 GPU seems to be pin-compatible with GA102, up to 600 W board power draw
- Uses new 12+4 power connector
- Larger caches (to catch up with AMD)
- AD102: 144 SM, 384-bit, 96 MB cache
- AD103: 84 SM, 256-bit, 64 MB cache
- AD104: 60 SM, 192-bit, 64 MB cache
- AD106: 36 SM, 128-bit, 3 MB cache
- AD107: 24 SM, 128-bit, 2 MB cache
NVIDIA Blackwell [added]
- Release Date: 2022 or 2023
- Focused on compute (not gaming)
- GPUs: GB100 and GB102
AMD Navi 31 / 32 / 33 [updated]
- Release date: unknown, probably 2022
- Dual-chiplet design
- Uses RDNA3 architecture
- Each chiplet has 80 CU / 5120 cores
- Total 10240 cores
- Possibly RT improvements
- Navi 31: 7680 cores, 256 MB cache
- Navi 32: 5120 cores, 192 MB cache
- Navi 33: 2048 cores, 64 MB cache
- Faster GDDR6
AMD Radeon RX 6550 XT / 6650 XT / 6750 XT / 6850 XT / 6950 XT [updated]
- Release date: May 10, 2022
- Uses faster 18 Gbps GDDR6 memory
- 6 nm or 7 nm process
- Possibly only RX 6950 XT, RX 6750 XT and RX 6650 XT, other variants might be cancelled
- PowerColor Radeon RX 6650 XT Hellhound: 17.5 Gbps memory and higher clocks, other specs unchanged
- Sapphire Radeon RX 6950 XT Toxic: 360 mm watercooling, 3x 8-pin
AMD Radeon RX 7600 XT
- Release date: unknown
- Uses Navi 23 GPU (RDNA2)
- Optical shrink to 6 nm for better heat/efficiency
- Rest of specs identical to RX 6600 XT: 32 CU, 2048 cores, 128-bit GDDR6
AMD Radeon RX 7700 XT
- Release date: unknown
- Uses Navi 22 GPU (RDNA2)
- Optical shrink to 6 nm for better heat/efficiency
- Rest of specs identical to RX 6700 XT: 40 CU, 2560 cores, 192-bit GDDR6
AMD RDNA 3
- Release Date: 2022
- Tapeout: End of 2021
- "Advanced Node", probably TSMC 6 nm or 5 nm, possibly EUV
- Launches at around the same time as Zen 4
- Big focus is power efficiency
- RX 7900 XT: 40% faster than RX 6900 XT, in some cases up to 60-80%
- RX 7900 XT: 15,360 GPU cores (4x that of RX 6800)
- Chiplet design with discrete IO and compute dies similar to Ryzen
- Target is +50% perf/W
- Support for DisplayPort 2.0 (higher bitrate, 10K @ 60 or 2x 4K 144)
Intel DG2 discrete GPU / Arch Alchemist [updated]
- Release Date: 2022. Q1 Mobile, Q2 Desktop, Q3 Workstation
- Desktop cards delayed to late-June/July
- Successor to DG1 Intel Xe discrete GPU
- Released under the "Arc" brand name
- GPU codename "Alchemist"
- Comes to Alder Lake-P laptops first
- Product names: Arc 380, Arc 350, Arc A370M and, Arc A350M
- A310: 64 or 96 EUs, 4 GB GDDR6, 64-bit memory
- A350M: DG2-128, 96 EU, 768 shaders, 1150 MHz, 4 GB GDDR6, 64-bit, 25-35 W
- A370M: DG2-128, 128 EU, 1024 shaders, 1550 MHz, 4 GB GDDR6, 64-bit, 35-50 W
- A550M: DG2-512, 256 EU, 2048 shaders, 900 MHz, 8 GB GDDR6, 128-bit, 60-80 W
- A730M: DG2-512, 384 EU, 3072 shaders, 1100 MHz, 12 GB GDDR6, 192-bit, 80-120 W
- A770M: DG2-512, 512 EU, 4096 shaders, 1650 MHz, 16 GB GDDR6, 256-bit, 120-150 W
- Arc A780: 2.25 GHz, 1093 MHz memory (17.5 Gbps)
- Arc A380 performance is comparable to GTX 1660 Ti
- Arctic Sound-M is for the data center, 512 EU, with AV1 hardware encode
- Package: BGA2660
- Three GPU chip die designs exist: DG2-128 (ACM-G11), DG2-256 (ACM-G12) and DG2-512 (ACM-G10)
- DG2-512 is 406 mm², 21.7B transistors
- DG2-128 die size: 190 mm²
- Produced on TSMC 6 nanometer process
- Arc Desktop card prototype uses 3x 8-pin power
- On Alder Lake-P it uses a PCIe Gen 4 x12 link between Tiger Lake H and DG2
- Intel's DLSS competitor to be called "XeSS"
- No mining lock
- Supports ray tracing, with hardware units
- First price estimates: $825 and $650 for slightly weaker model
- At Intel Architecture Day 2021, Intel mentioned that they'll stop using "EU" as unit count. Instead the words used are "Vector Engines"
- "Matrix Engines" are hardware acceleration units for matrix math, similar to NVIDIA's Tensor Cores
- One Xe core is 128 shader cores, four such cores per slice, multiple slices per GPU
- Overclocking supported at launch, within driver control panel
- "now sampling to partners" as of July 2021
- Discrete card board partners (AICs) so far are: ASUS, MSI, Gigabyte
Intel Battlemage Architecture
- Release Date: Not before 2023
- Discrete GPU architecture
- Successor to "Alchemist" architecture
- Also called "Xe2 HPG"
Intel Celestial Architecture
- Release Date: 2024
- Discrete GPU architecture
- Successor to "Battlemage" architecture
- Also called "Xe3 HPG"
- Targets "Ultra Enthusiast" segment
Intel Druid Architecture
- Release Date: Not before 2025
- Discrete GPU architecture
- Successor to "Celestial" architecture
- Also called "Xe Next HPG"
Intel Ponte Vecchio
- Release Date: 2022
- Discrete GPU
- Mix of various manufacturing technologies: Intel 10 nm SuperFin, TSMC 7 nm and TSMC 5 nm
- Multiple GPU dies will be combined into a single accelerator
- Architected "for HPC modeling and simulation workloads and AI training"
- Workloads can be processed by GPU and CPU at the same time, using Intel oneAPI
- Foveros packaging technology
- Supports DirectX 12 mesh shaders
- "petaflops in your palm"
- Will be installed in Leibniz Supercomputing Centre in 2022
- Up to 600 W, liquid-cooled in OAM Form Factor
- Xe link to combine multiple GPUs (CXL interconnect)
- 63 silicon tiles: 16 for compute, 8 for Rambo cache, 2 Foveros base, 2 Xe Link, 8 HBM2E, 11 EMIB connection, 16 thermal tiles
- Eight GPU tiles with 32,768 shader cores each, for a total of 262,144 cores
- Rambo cache is SRAM with four banks of 3.75 MB = 15 MB per tile at 1.3 TB/s
- Base tile is 646 mm² on Intel 7 (10 nm)
- Compute tiles on TSMC N5
- Xe Link on TSMC N7
- Rambo and Foveros on Intel 7
- FIVR on-die
- Supports ray tracing
- PCI-Express 5.0 interface, 16 lanes
- Hardware acceleration for matrix operations
Zhaoxin Discrete GPU
- Release Date: unknown
- Discrete GPU
- Produced on 28 nanometer production process
- 70 W TDP
- Based on VIA S3 graphics IP
Chipsets
Intel W790
- Release Date: Q2 2022
- Chipset for HEDT platform based on Sapphire Rapids
Intel Z790 / H770 / B760 [updated]
- Release Date: Late 2022
- Chipsets for Raptor Lake 13th Gen
- Z790: 20 PCIe 4.0 lanes (instead of 12), 8x PCIe 3.0 (from 16), one additional USB 3.2 Gen 2x2
- H770: 16 PCIe 4.0 lanes (instead of 12), 8x PCIe 3.0 (from 12)
- B760: 10 PCIe 4.0 lanes (instead of 6), 4x PCIe 3.0 (from 8)
AMD B650 [added]
- Release Date: 2022
- Upcoming chipset for Zen 4
AMD X670
- Release Date: 2022
- Upcoming chipset for Zen 4
- Could be a multi-chip-module of two B650 chips
Memory
DDR6 System Memory
- Release Date: Unknown
- Four channels per module (2x that of DDR5, 4x that of DDR4)
- 64 banks
- Speeds starting at 12800 MT/s, up to 17,000 MT/s with OC
GDDR6+ Graphics Memory
- Release Date: Unknown
- Production: 2021
- Up to 24,000 MT/s
- Production process: 1z nm
GDDR7 Graphics Memory
- Release Date: Unknown
- Speeds: 32,000 MT/s
- "Real-time error protection feature", maybe some kind of ECC?
HBM3 Graphics Memory [updated]
- Specification released: Jan 2022
- Products: some time in 2022
- Double the memory bandwidth per stack
- Twice the number of channels: 16 vs 8 on HBM2
- 8 Gb to 32 Gb capacity per layer
- On-die ECC
- Expected to be produced using 7 nm technologies
- NVIDIA working on GPUs with HBM3 support
- Hynix in Oct 2021: 6.4 Gbps per pin, stack bandwidth 819 GB/s, 24 GB and 16 GB stacks
- Hynix in March 2022: up to 12-Hi-stack, 24 GB, 16 channels, 6.4 Gbps
- Rambus announced in August 2021 that their memory controller is ready, up to 8.4 Gbps
- 1024-bit bus width
HBMNext Memory
- Release Date: late 2022 or 2023
- JEDEC work in progress
- Micron involved
Silicon Fabrication Tech
TSMC 5 nanometer
- Release Date: March 2020 to tape-out customer designs
- Risk production as of Q2 2019
- High volume production: Q2 2020
- Uses TSMC's second implementation of EUV (Extreme Ultra Violet)
- Up to 1.8x the density of 7 nm
- Up to 14 layers
- +15% higher clocks
- 30% better bower than N7
- Intel might be a customer of this node
- N5P "Plus" node: improvement to N5 while staying on 5 nm, 84%–87% increase in transistor densities over N7
TSMC 5 nanometer+
- Release Date: 2021
- High-volume production in Q4 2020
- Uses EUV (Extreme Ultra Violet)
TSMC 4 nanometer
- Volume production: Q3 2021
- Mass production: 2022 or 2023
- Codename "N4"
- Uses EUV lithography
TSMC 4 nanometer+
- First tape outs: H2 2022
- Codename "N4P"
- 11% performance boost over N5, 6% over N4
- 22% better power vs N5
- 6% higher density than N5
TSMC 3 nanometer [updated]
- April 2020: on track
- Risk production: H2 2021
- Volume production: H2 2022 (confirmed as of Apr 2022)
- FinFET technology
- Uses TSMC's third implementation of EUV (Extreme Ultra Violet)
- 10%–15% speed improvement at iso-power or 25%–30% power reduction at iso-speed, compared to N5
- 30,000 wafers per month at the start, 105,000 by 2023
- 12-inch wafer size
- Intel has announced they have placed two orders for processors based on this process
- AMD will use this process for Zen 4
- TSMC N3E making good progress, now in 2023
TSMC 3 nanometer+
- Release date: 2023
- First client will be Apple
TSMC 2 nanometer [updated]
- Release Date: 2023 (risk production)
- Volume production: 2025
- June 2020: TSMC is accelerating R&D
- Sep 2020: fab construction has begun
- Will use Gate-All-Around (GAA) technology
- Multi-bridge channel field effect transistor (MBCFET) architecture
TSMC 1 nanometer
- Release Date: Unknown
- Uses Semi-metal bismuth for contact electrodes
Samsung 6 nanometer
- Release Date: unknown
- First product taped out as of Q2 2019
- Uses EUV (Extreme Ultra Violet)
- Special variant for customers
Samsung 5 nanometer
- Release Date: 2021
- Ready for customer sample production as of Q2 2019
- In production as of Q4 2020
- Yields are challenging as of Q2 2020
- Yields below 50% as of Q3 2021
- Plans to build fab in Austin TX, for $18B
- Uses EUV (Extreme Ultra Violet)
- Up to 25% the density of 7 nm
- 20% lower power consumption
- 10% higher performance
Samsung 3 nanometer
- Mass Production: H12022
- Uses Gate All Around FET transistors (GAA), Multi-Bridge-Channel FET (MBCFETTM)
- 50% less power while delivering 30% more performance
- 35% less silicon space taken per transistor (vs. 7 nm)
- 2nd generation 3 nm expected in 2025
Samsung 2 nanometer
- In early development as of Oct 2021, mass production in 2025
- Uses Multi-Bridge-Channel FET (MBCFETTM)
Intel 7 nanometer / "Intel 4"
- Release Date: 2022
- Uses EUV (Extreme Ultra Violet)
- 4x reduction in design rules
- Planned to be used on multiple products: CPU, GPU, AI, FPGA, 5G networking
- 20% perf/watt over 10 nm SuperFin ("Intel 7")
- Jan 2021: Intel reports "issues fixed"
- Jul 2021: Intel renames this process to "Intel 4"
Intel 3
- Release Date: 2023
- Uses EUV (Extreme Ultra Violet)
- Possibly still a 7 nanometer node, with improvements
- 18% perf/watt vs Intel 4
- Denser HP library
- more EUV
- Improve drive-current and via resistance
Intel 20A
- Release Date: H1 2024
- 20 Angstrom = 2 nanometer
- New transistors called RibbonFET
- PowerVia to connect silicon dies
Intel 18A
- Release Date: H2 2024
- 18 Angstrom = 1.8 nanometer
Other
PCI-Express 5.0 SSDs
- Release Date: Phison H2-2022, Kioxia Q4-2021
- Mainstream PCIe 5.0 SSDs only in 2024
- Uses new PCIe 5.0 interface to double transfer rates per lane, up to 16 GB/s
- Kioxia: U.2 and M.2 support, up to 14 GB/s
- Phison: PS5026-E26 controller, PCIe dual port, SR-IOV, ONFI 5.x, NVMe 2.0, ARM R5 CPU TSMC 12 nm, 12 GB/s read, 11 GB/s write, 1.5M IOPS read, 2M IOPS write, support for TLC and QLC
- Probably targeted more at enterprise (Intel Sapphire Rapids) than consumer (Intel Alder Lake)
Toshiba/WD 5-Bit-per-Cell NAND Flash (PLC)
- Release Date: Delayed to 2025
- Stores an additional bit of information per cell (compared to QLC)
- 32 states per cell
- Will enable even cheaper SSDs, probably at a performance cost
Toshiba XL-Flash
- Developed by Toshiba
- Uses existing SLC flash technology to improve latencies
- 1/10th the read latency of TLC
- Good for random IOPS and better QoS at shallow queue depth
- Can combine SLC and TLC/QLC for tiered, cost-optimized storage
- Intel Optane memory competitor
- 128 gigabit (Gb) die (in a 2-die, 4-die, 8-die package)
- 4 KB page size for more efficient operating system reads and writes
- 16-plane architecture for more efficient parallelism
- Fast page read and program times
Toshiba 162-layer 3D NAND Flash
- Release Date: 2021
- Developed by Toshiba and partner Western Digital
- Called "6th generation"
- 10% better lateral cell array density
- 40% reduction in die size compared to 112-layer technology
- 10% improvement to read latency
- Uses Circuit Under Array CMOS placement and 4-plane operation
- Reduces cost per bit by 70%
Samsung 176-layer 3D NAND Flash
- Release Date: 2021
- 7th generation V-NAND
- Originally known as "160"-layer 3D NAND, now 176-layer
- Will be used on PCIe 4.0 and 5.0 SSDs
Intel CXL Interconnect
- New interconnect for high-bandwidth devices like GPUs
- Targeted at enterprise and servers
- Competitor to NVLink, Infinity Fabric, and PCI-Express
- Uses PCIe physical layer
- Link layer designed for low latency
- 32 Gbps per lane, per direction (like PCIe Gen 5.0)
- Samsung has announced open-source Scalable Memory Development Kit (SMDK) in Oct 2021
PCI-Express 6.0
- Release Date: 2022
- Spec version 1.0 published as of Jan 2022
- Spec version 0.9 published as of Oct 2021
- Spec version 0.5 published as of Feb 2020
- Spec version 0.7 published as of Nov 2020
- 64 GT/s raw bit rate, up to 256 GB/s with x16
- Rambus has controller IP reasy as of Jan 2022
- Includes low-latency Forward Error Correction (FEC) with additional mechanisms to improve bandwidth efficiency
- Maintains backwards compatibility with all previous generations of PCIe technology
- New physical layer with PAM4 (pulse amplitude modulation) signaling replacing NRZ (non-return to zero)
USB 4.0
- Release Date: end of 2020
- Specification Released: September 2019
- Conceptually similar to Thunderbolt 3
- Up to 40 Gbps speeds using two-lane operation
- Multiple data and display protocols can share bandwidth
- Uses USB Type-C connector
- Backwards compatible with USB 2.0, 3.0, 3.1, 3.2, and Thunderbolt 3
- Resulting connection scales to the best mutual capability of the devices being connected
Thunderbolt 5
- Release Date: unknown
- Speeds up to 80 Gbps
- Uses PAM-3 technology for higher transfer rates
- Test chip manufactured on 6 nm at TSMC
May 16th, 2022 02:31 EDT
change timezone
Latest GPU Drivers
New Forum Posts
-
by zx128kBest value for money out of these four AUD? Upgrade from a 2060 (7)
-
by Sithaer1600X to 5600(X) (79)
-
by EntropyZWhat are you playing? (15222)
-
by HyderzWhat's the primary resolution/refresh rate you're gaming at on your PC (2022)? (71)
-
by frigiderDell Workstation Owners Club (2378)
-
by R-T-BWhat's your latest tech purchase? (11975)
-
by tabascosauzLife and times of Austere Box & Ol' Beastie (213)
-
by MachineLearningTPU's Nostalgic Hardware Club (14039)
-
by FreedomEclipseThermaltake Armor Revo: external PSU mounting idea (25)
-
by zx128kDell RTX 3080 vbios (20)
Popular Reviews
- AMD FSR 2.0 Quality & Performance Review - The DLSS Killer
- NVIDIA GeForce RTX 3090 Ti Founders Edition Review
- Cooler Master HAF 700 EVO Review
- AMD Radeon RX 6400 Review
- Sapphire Radeon RX 6950 XT Nitro+ Pure Review
- Gigabyte UD1000GM PG5 1000 W Review - The First PCIe 5.0 PSU
- USB Sound Cards Explained: Tech, Benefits, Do I Need One?
- Upcoming Hardware Launches 2022 (Updated Apr 2022)
- DeepCool AS500 Plus White Review
- AMD Ryzen 7 5800X3D Review - The Magic of 3D V-Cache
Controversial News Posts
- Bitcoin Bloodbath Brings Cheer to Gamers as Graphics Card Prices Plummet (112)
- NVIDIA Allegedly Testing a 900 Watt TGP Ada Lovelace AD102 GPU (102)
- AMD Ryzen 7 5800X3D Starts Selling at 30% Mark-up (96)
- Elon Musk to Acquire Twitter (86)
- EKWB Lays Off 25% of Workforce, Blames Lower Watercooling Sales (84)
- Radeon RX 6x50 XT Pricing Leaks Ahead of Next Week's Launch (82)
- AMD Radeon RX 6400 Launched at $159 (81)
- Tesla to Patch 130,000 Cars with AMD Ryzen APUs Due to Overheating (79)