GDDR6 SDRAM (original) (raw)

From Wikipedia, the free encyclopedia

Type of synchronous graphics random-access memory

This article is about DDR graphics RAM (SGRAM). For non-graphics (dynamic) DDR memory, see SDRAM.

GDDR6 SDRAMGraphics Double Data Rate 6 Synchronous Dynamic Random-Access Memory

Graphics Double Data Rate 6 Synchronous Dynamic Random-Access Memory (GDDR6 SDRAM) is a type of synchronous graphics random-access memory (SGRAM) with a high bandwidth, "double data rate" interface, designed for use in graphics cards, game consoles, and high-performance computing. It is a type of GDDR SDRAM (graphics DDR SDRAM), and is the successor to GDDR5. Just like GDDR5X it uses QDR (quad data rate) in reference to the write command clock (WCK) and ODR (Octal Data Rate) in reference to the command clock (CK).[1]

The finalized specification was published by JEDEC in July 2017.[2] GDDR6 offers increased per-pin bandwidth (up to 16 Gbit/s[3]) and lower operating voltages (1.35 V[4]), increasing performance and decreasing power consumption relative to GDDR5X.[5][6]

Commercial implementation

[edit]

At Hot Chips 2016, Samsung announced GDDR6 as the successor of GDDR5X.[5][6] Samsung later announced that the first products would be 16 Gbit/s, 1.35 V chips.[7][8] In January 2018, Samsung began mass production of 16 Gb (2 GB) GDDR6 chips, fabricated on a 10 nm class process and with a data rate of up to 18 Gbit/s per pin.[9][8][10]

In February 2017, Micron Technology announced it would release its own GDDR6 products by early 2018.[11] Micron began mass production of 8 Gb chips in June 2018.[12]

SK Hynix announced its GDDR6 products would be released in early 2018.[13][3] SK Hynix announced in April 2017 that its GDDR6 chips would be produced on a 21 nm process and be 10% lower voltage than GDDR5.[3] The SK Hynix chips were expected to have a transfer rate of 14–16 Gbit/s.[4] The first graphics cards to use SK Hynix's GDDR6 RAM were expected to use 12 GB of RAM with a 384-bit memory bus, yielding a bandwidth of 768 GB/s.[3] SK Hynix began mass production in February 2018, with 8 Gbit chips and a data rate of 14 Gbit/s per pin.[14]

Nvidia officially announced the first consumer graphics cards using GDDR6, the Turing-based GeForce RTX 2080 Ti, RTX 2080 & RTX 2070 on August 20, 2018,[15] RTX 2060 on January 6, 2019[16] and GTX 1660 Ti on February 22, 2019.[17] GDDR6 memory from Samsung Electronics is also used for the Turing-based Quadro RTX series.[18] The RTX 20 series initially launched with Micron memory chips, before switching to Samsung chips by November 2018.[19]

AMD officially announced the Radeon RX 5700, 5700 XT, and 5700 XT 50th Anniversary Edition on June 10, 2019. These Navi 10[20] GPUs utilize 8 GB of GDDR6 memory.[21]

A GeForce RTX 3090 Custom Edition with GDDR6X RAM

Micron developed GDDR6X in close collaboration with Nvidia. GDDR6X SGRAM had not been standardized by JEDEC yet. Nvidia is Micron's only GDDR6X launch partner.[22] GDDR6X offers increased per-pin bandwidth between 19–21 Gbit/s with PAM4 signaling, allowing two bits per symbol to be transmitted and replacing earlier NRZ (non return to zero, PAM2) coding that provided only one bit per symbol, thereby limiting the per-pin bandwidth of GDDR6 to 16 Gbit/s.[23] The first graphics cards to use GDDR6X are the Nvidia GeForce RTX 3080 and 3090 graphics cards. PAM4 signalling is not new but it costs more to implement, partly because it requires more space in chips and is more prone to signal-to-noise ratio (SNR) issues,[24] which mostly limited its use to high speed networking (like 200G Ethernet). GDDR6X consumes 15% less power per transferred bit than GDDR6, but overall power consumption is higher since GDDR6X is faster than GDDR6. On average, PAM4 consumes less power and uses fewer pins than differential signalling while still being faster than NRZ. GDDR6X is thought to be cheaper than High Bandwidth Memory.[25]

Samsung announced the development of GDDR6W on November 29, 2022.[26]
Its improvements over GDDR6 are:

• Higher per pin transmission rate of 22 Gb/s
• Doubling per package capacity from 16 Gb to 32 Gb
• Double the I/O pins from 32 to 64
• 36% lower thickness (0.7 mm down from 1.1 mm by using Fan-Out Wafer-Level Packaging (FOWLP)
• List of interface bit rates

1. ^ Smith, Ryan. "Micron Spills on GDDR6X: PAM4 Signaling For Higher Rates, Coming to NVIDIA's RTX 3090". www.anandtech.com.
2. ^ "GRAPHICS DOUBLE DATA RATE 6 (GDDR6) SGRAM STANDARD | JEDEC". www.jedec.org.
3. ^ a b c d Shilov, Anton (30 April 2017). "SK Hynix to Ship GDDR6 for Graphics Cards by Early 2018". Anandtech. Retrieved 2 May 2017.
4. ^ a b Born, Eric (16 May 2017). "SK Hynix's first GDDR6 RAM will initially top out at 14 Gbps". Tech Report. Retrieved 16 May 2017.
5. ^ a b Walton, Mark (23 August 2016). "HBM3: Cheaper, up to 64GB on-package, and terabytes-per-second bandwidth". Ars Technica. Retrieved 3 February 2017.
6. ^ a b Ferriera, Bruno (23 August 2016). "HBM3 and GDDR6 emerge fresh from the oven of Hot Chips". Tech Report. Retrieved 3 February 2017.
7. ^ Shilov, Anton (14 November 2017). "Samsung Preannounces 16 Gbps GDDR6 Chips for Next-Gen Graphics Cards". Anandtech. Retrieved 14 November 2017.
8. ^ a b Killian, Zak (18 January 2018). "Samsung fires up its foundries for mass production of GDDR6 memory". Tech Report. Retrieved 18 January 2018.
9. ^ "Samsung Electronics Starts Producing Industry's First 16-Gigabit GDDR6 for Advanced Graphics Systems". Samsung. January 18, 2018. Retrieved 15 July 2019.
10. ^ "Samsung Begins Producing The Fastest GDDR6 Memory In The World". Wccftech. 18 January 2018. Retrieved 16 July 2019.
11. ^ Tallis, Billy (3 February 2017). "Micron 2017 Roadmap Detailed: 64-Layer 3D NAND, GDDR6 Getting Closer, & CEO Retiring". Anandtech. Retrieved 7 February 2017.
12. ^ "Micron Begins Volume Production of GDDR6 High Performance Memory". Micron Technology. June 25, 2018. Retrieved 14 July 2019.
13. ^ "Press Release < PR < SK hynix". Archived from the original on 2017-04-24. Retrieved 2017-05-11.
14. ^ Shilov, Anton (February 6, 2018). "SK Hynix Lists GDDR6 Memory as 'Available Now', Publishes Final Specs". AnandTech. Retrieved 14 July 2019.
15. ^ "10 Years in the Making: NVIDIA Brings Real-Time Ray Tracing to Gamers with GeForce RTX".
16. ^ "NVIDIA GeForce RTX 2060 is Here: Next-Gen Gaming Takes off".
17. ^ "New GeForce GTX 1660 Ti Delivers Great Performance Leap for Every Gamer, Starting at $279".
18. ^ Mujtaba, Hassan (14 August 2018). "Samsung GDDR6 Memory Powers NVIDIA's Turing GPU Based Quadro RTX Cards". wccftech.com. Retrieved 19 June 2019.
19. ^ Maislinger, Florian (21 November 2018). "Faulty RTX 2080 Ti: Nvidia switches from Micron to Samsung for GDDR6 memory". PC Builder's Club. Retrieved 15 July 2019.
20. ^ AMD RX Vega series
21. ^ June 2019, Zhiye Liu 11 (11 June 2019). "AMD Radeon RX 5700 XT 50th Anniversary Edition Actually Looks Promising". Tom's Hardware.{{[cite web](/wiki/Template:Cite%5Fweb "Template:Cite web")}}: CS1 maint: numeric names: authors list (link)
22. ^ September 2020, Anton Shilov 06 (6 September 2020). "Micron Reveals GDDR6X Details: The Future of Memory, or a Proprietary DRAM?". Tom's Hardware. Retrieved 2020-09-07.{{[cite web](/wiki/Template:Cite%5Fweb "Template:Cite web")}}: CS1 maint: numeric names: authors list (link)
23. ^ "Doubling I/O Performance with PAM4 - Micron Innovates GDDR6X to Accelerate Graphics Memory". Micron. Archived from the original on 19 September 2020. Retrieved 11 September 2020.
24. ^ Maliniak, David (January 14, 2016). "EDN - The fundamentals of PAM4".
25. ^ Smith, Ryan. "Micron Spills on GDDR6X: PAM4 Signaling For Higher Rates, Coming to NVIDIA's RTX 3090". www.anandtech.com.
26. ^ "A Bridge Between Worlds: How Samsung's GDDR6W Creates Immersive Metaverse Experiences with Powerful Graphics Memory". Retrieved 2022-11-29.