From Wikipedia, the free encyclopedia
Jump to: navigation, search
This article is about DDR4 SDRAM. For graphics DDR4, see GDDR4. For the video game, see Dance Dance Revolution 4thMix.
Samsung displays first DDR4 module.jpg
The first DDR4 memory module was manufactured by Samsung and announced in January 2011.
Type synchronous dynamic random-access memory
Release date September 2012[1]
Predecessor DDR3 SDRAM
Website JEDEC

In computing, DDR4 SDRAM, an abbreviation for double data rate fourth generation synchronous dynamic random-access memory, is a type of synchronous dynamic random-access memory (SDRAM) with a high bandwidth ("double data rate") interface. Released to the market in 2014,[2][3][4] it is one of the latest variants of dynamic random access memory (DRAM), some of which have been in use since the early 1970s,[5] and a higher-speed successor to the DDR2 and DDR3 technologies. It is not compatible with any earlier type of random access memory (RAM) due to different signaling voltages, physical interface and other factors.

DDR4 SDRAM was released to the public market in Q2 2014 with a focus on ECC memory,[6] and an anticipated launch for non-ECC modules in Q3 2014.[7]


Two 8 GiB DDR4-2133 ECC 1.2 V RDIMMs

The primary advantages of DDR4 as opposed to its predecessor, DDR3, include higher module density and lower voltage requirements, coupled with higher data rate transfer speeds. The DDR4 standard allows for DIMMs of up to 128 GiB in capacity, compared to the DDR3's maximum of 16 GiB per DIMM.[8]

DDR4 operates at a voltage of 1.2 V with a frequency between 1600 and 3200 MHz, compared to frequencies between 800 and 2400 MHz and voltage requirements of 1.5 or 1.65 V of DDR3. Although a low-voltage standard has yet to be finalized, it is anticipated that low-voltage DDR4 will run at a voltage of 1.05 V, compared to DDR3's low-voltage standard (DDR3L) which requires 1.35 V to operate.[9]


Standards body JEDEC began working on a successor to DDR3 around 2005,[10] about 2 years before the launch of DDR3 in 2007.[11][12] The high-level architecture of DDR4 was planned for completion in 2008.[13]

Some advance information was published in 2007,[14] and a guest speaker from Qimonda provided further public details in a presentation at the August 2008 San Francisco Intel Developer Forum (IDF).[14][15][16][17] DDR4 was described as involving a 30 nm process at 1.2 volts, with bus frequencies of 2133 MT/s "regular" speed and 3200 MT/s "enthusiast" speed, and reaching market in 2012, before transitioning to 1 volt in 2013.[15][17]

Subsequently, further details were revealed at MemCon 2010, Tokyo (a computer memory industry event), at which a presentation by a JEDEC director titled "Time to rethink DDR4" [18] with a slide titled "New roadmap: More realistic roadmap is 2015" led some websites to report that the introduction of DDR4 was probably[19] or definitely[20][21] delayed until 2015. However, DDR4 test samples were announced in line with the original schedule in early 2011 at which time manufacturers began to advise that large scale commercial production and release to market was scheduled for 2012.[2]

DDR4 was expected to represent 5% of the DRAM market in 2013,[2] and to reach mass market adoption and 50% market penetration around 2015;[2] as of 2013, however, adoption of DDR4 has been delayed and it is no longer expected to reach a majority of the market until 2016 or later.[22] The transition from DDR3 to DDR4 is thus taking longer than the approximately five years taken for DDR3 to achieve mass market transition over DDR2.[23] In part, this is because changes required to other components would affect all other parts of computer systems, which would need to be updated to work with DDR4.[24]

In February 2009, Samsung validated 40 nm DRAM chips, considered a "significant step" towards DDR4 development[25] since in 2009, DRAM chips were only beginning to migrate to a 50 nm process.[26] In January 2011, Samsung announced the completion and release for testing of a 2 GiB DDR4 DRAM module based on a process between 30 and 39 nm.[27] It has a maximum data transfer rate of 2133 MT/s at 1.2 V, uses pseudo open drain technology (adapted from graphics DDR memory[28]) and draws 40% less power than an equivalent DDR3 module.[27][29][30]

Three months later in April 2011, Hynix announced the production of 2 GiB DDR4 modules at 2400 MT/s, also running at 1.2 V on a process between 30 and 39 nm (exact process unspecified),[2] adding that it anticipated commencing high volume production in the second half of 2012.[2] Semiconductor processes for DDR4 are expected to transition to sub-30 nm at some point between late 2012 and 2014.[23][31]

In May 2012, Micron announced[3] it is aiming at starting production in late 2012 of 30 nm modules.

In July 2012, Samsung Electronics Co., Ltd., announced that it has begun sampling the industry's first 16 GiB registered dual inline memory modules (RDIMMs) using DDR4 SDRAM for enterprise server systems.[32][33]

In September 2012, JEDEC released the final specification of DDR4.[1]

In April 2014, Hynix announced that it has developed the world’s first highest density of 128 GiB module based on 8 Gib DDR4 using 20 nm class technology. The module works at 2133 Mbit/s, with a 64-bit I/O it processes up to 17 GB of data per second. Hynix expects DDR4 SDRAM to be commercialized by 2015, and make it a standard by 2016.[34]

Market perception and adoption[edit]

In April 2013, a news writer at International Data Group (IDG)—​an American technology research business originally part of IDC—​produced an analysis of their perceptions related to DDR4 SDRAM.[35] The conclusions were that the increasing popularity of mobile computing and other devices using slower but low powered memory, the slowing of growth in the traditional desktop computing sector, and the consolidation of the memory manufacturing marketplace, meant that margins on RAM were tight.

As a result, the looked-for premium pricing used for initial profitability when introducing new technology to the marketplace, was harder to achieve, and capacity had shifted to other sectors; SDRAM manufacturers and chipset creators were, to an extent, "stuck between a rock and a hard place" where, according to iSupply, "Nobody wants to pay a premium for DDR4 products, and manufacturers don't want to make the memory if they are not going to get a premium".[35] A switch in market sentiment towards desktop computing and release of chipsets having DDR4 support by Intel and AMD could therefore potentially lead to "aggressive" growth.[35]

Intel's 2014 Haswell-E roadmap revealed the company's first use of DDR4 SDRAM in Haswell-E CPU.[36]


The new chips will use a 1.2 V supply[37]:16[38][39] with a 2.5 V auxiliary supply for wordline boost called VPP,[37]:16, versus the standard 1.5 V of DDR3 chips, with lower voltage variants at 1.05 V appearing in 2013. DDR4 is expected to be introduced at transfer rates of 2133 MT/s,[37]:18 estimated to rise to a potential 4266 MT/s[24] by 2013. The minimum transfer rate of 2133 MT/s was said to be due to progress made in DDR3 speeds which, being likely to reach 2133 MT/s, left little commercial benefit to specifying DDR4 below this speed.[24][23] Techgage interpreted Samsung's January 2011 engineering sample as having CAS latency of 13 clock cycles, described as being comparable to the move from DDR2 to DDR3.[28]

Internal banks are increased to 16 (4 bank select bits), with up to 8 ranks per DIMM.[37]:16

Protocol changes include:[37]:20

  • Parity on the command/address bus
  • Data bus inversion (like GDDR4)
  • CRC on the data bus
  • Independent programming of individual DRAMs on a DIMM, to allow better control of on-die termination.

Increased memory density is anticipated, possibly using TSV ("through-silicon via") or other 3D stacking processes.[24][23][40][41] The DDR4 specification will include standardized 3D stacking "from the start" according to JEDEC,[41] with provision for up to 8 stacked dies.[37]:12 X-bit Labs predicted that "as a result DDR4 memory chips with very high density will become relatively inexpensive".[24] Prefetch remains at 8n[37]:16 with bank groups, including the use of two or four selectable bank groups.[42]

Switched memory banks are also an anticipated option for servers.[23][40]

In 2008, concerns were raised in the book Wafer Level 3-D ICs Process Technology that non-scaling analog elements such as charge pumps and voltage regulators, and additional circuitry "have allowed significant increases in bandwidth but they consume much more die area". Examples include CRC error-detection, on-die termination, burst hardware, programmable pipelines, low impedance, and increasing need for sense amps (attributed to a decline in bits per bitline due to low voltage). The authors noted that as a result, the amount of die used for the memory array itself has declined over time from 70–78% with SDRAM and DDR1, to 47% for DDR2, to 38% for DDR3 and potentially to less than 30% for DDR4.[43]

The specification defined standards for x4, x8, x16 memory devices with capacities of 2, 4, 8, 16Gib.[44]

Command encoding[edit]

Although it still operates in fundamentally the same way, DDR4 makes one major change to the command formats used by previous SDRAM generations. A new command signal /ACT is low to indicate the activate (open row) command.

The activate command requires more address bits than any other (18 row address bits in an 8 Gib part), so the standard /RAS, /CAS and /WE signals are shared with high-order address bits that are not used when /ACT is high. The combination of /RAS=L, /CAS=H and /WE=H that previously encoded an activate command is unused.

As in previous SDRAM encodings, A10 is used to select command variants: auto-precharge on read and write commands, and one bank vs all banks for the precharge command. It also selects two variants of the ZQ calibration command.

In addition, A12 is used to request burst chop: truncation of an 8-transfer burst after 4 transfers. Although the bank is still busy and unavailable for other commands until 8 transfer times have elapsed, a different bank can be accessed.

Also, the number of bank addresses has been increased greatly. There are 4 bank select bits to select up to 16 banks within each DRAM: 2 bank address bits (BA0, BA1), and 2 bank group bits (BG0, BG1). There are additional timing restrictions when accessing banks within the same bank group; it is faster to access a bank in a different bank group.

In addition, there are 3 chip select signals (C0, C1, C2), allowing up to 8 stacked chips to be placed inside a single DRAM package. These effectively act as three more bank select bits, bringing the total to 7 (128 possible banks).

DDR4 command encoding[45]
/CS BGn, BAn /ACT A17 A16
A13 A12 A11 A10 A9–0 Command
H — x — Deselect (No operation)
L bank L Row address Active (activate): open a row
L x H x H H H — x — No operation
L x H x H H L x long x ZQ Calibration
L bank H x H L H x BC x AP Column Read (BC=burst chop)
L bank H x H L L x BC x AP Column Write (AP=auto-precharge)
L x H x L H H — x — (Unassigned, reserved)
L x H x L H L x H x Precharge all banks
L bank H x L H L x L x Precharge one bank
L x H x L L H — x — Refresh
L register H 0 L L L 0 data Mode register set (MR0–MR6)

Note: x bits are "don't care", but must be at a valid voltage level, either 0 or 1.

Standard transfer rates are 1600, 1866, 2133 and 2400 MT/s.[45] (12/15, 14/15, 16/15 and 18/15 GHz clock speeds, double data rate.) 2666 and 3200 MT/s (20/15 and 24/15 GHz clock speeds) are provided for, but the specifications are not yet complete.

Design considerations[edit]

Some key points for IC and PCB design were identified by the DDR4 team at Micron Technology:[46]

IC design:[46]

  • VrefDQ calibration (DDR4 "requires that VrefDQ calibration be performed by the controller");
  • New addressing schemes ("bank grouping", ACT_n to replace RAS#, CAS#, and WE# commands, PAR and Alert_n for error checking and DBI_n for data bus inversion);
  • New power saving features (Low Power Auto Self Refresh, Temperature Controlled Refresh, Fine Granularity Refresh, Data Bus Inversion, and CMD/ADDT latency).

Circuit board design:[46]

  • New power supplies (VDD/VDDQ at 1.2V and wordline boost, known as VPP, at 2.5V);
  • VrefDQ must be supplied internal to the DRAM while VrefCA is supplied externally from the board;
  • DQ pins terminate high using pseudo-open-drain I/O (this differs from the CA pins in DDR3 which are center-tapped to VTT).[46]

Module packaging[edit]

DDR4 memory comes in 288-pin DIMM modules, similar in size to 240-pin DDR3 DIMMs. The pins are spaced more closely (0.85 mm instead of 1.0) to fit the increased amount within the same 5¼ inch (133.35 mm) standard DIMM length but, the height is increased slightly (31.25 mm/1.23 in instead of 30.35 mm/1.2 in) to make signal routing easier, and the thickness is also increased (to 1.2 mm from 1.0) to accommodate more signal layers.[47]

DDR4 SO-DIMMs have 260 pins (rather than DDR3's 204 pins), which are also spaced closer (0.5 rather than 0.6 mm), and are 2.0 mm wider (69.6 versus 67.6 mm), but remain the same 30 mm in height.[48]

For the Skylake microarchitecture, Intel also designed a SO-DIMM package named UniDIMM, which can be populated with either DDR3 or DDR4 chips. At the same time, integrated memory controller (IMC) of Skylake CPUs is announced to be capable of working with either type of memory. The purpose of UniDIMMs is to help in the market transition from DDR3 to DDR4, where pricing and availability may make it undesirable to switch the RAM type. UniDIMMs have the same dimensions and number of pins as regular DDR4 SO-DIMMs, but the edge connector's notch is placed differerently to avoid accidental use in incompatible DDR4 SO-DIMM sockets.[49]


As of 2014, no direct successor technology (which would presumably be named "DDR5 SDRAM") is currently planned. Some sources speculate that any future memory standards will use a serial interface, as opposed to DDR4's 288/260-pin parallel interface, and mention Micron Technology's Hybrid Memory Cube (HMC) stacked memory as an example. The technical progression of other computer buses converged toward replacing parallel buses with serial buses; for example, Parallel ATA was replaced with Serial ATA, and PCI evolved into PCI Express. In general, serial buses are easier to scale up and have fewer wires/traces, making circuit boards using them easier to design.[50][51][52]

In 2011, JEDEC also published the Wide I/O 2 standard; like the Hybrid Memory Cube, it stacks multiple memory dies, but does that directly on top of the CPU and in the same package. This memory layout provides higher bandwidth and better power performance than DDR4 SDRAM, and allows a wide interface with short signal lengths. It primarily aims to replace various mobile DDRX SDRAM standards used in high-performance embedded and mobile devices, such as smartphones.[53][54] Hynix proposed similar High Bandwidth Memory (HBM), which was published as JEDEC JESD235. Both Wide I/O 2 and HBM use a very wide parallel memory interface, up to 512 bits wide for Wide I/O 2 (compared to 64 bits for DDR4), running at a lower frequency than DDR4.[55]

Wide I/O 2 is targeted at high-performance compact devices such as smartphones, where it will be integrated into the processor or system on a chip (SoC) packages. HBM is targeted at graphics memory and general computing, while HMC targets high-end servers and enterprise applications.[55]

GDDR5 SGRAM, which was introduced before DDR4, is a type of DDR3 synchronous graphics RAM and not a successor to DDR4.

See also[edit]


  1. ^ a b JEDEC Announces Publication of DDR4 Standard | JEDEC
  2. ^ a b c d e f Marc (2011-04-05). "Hynix produces its first DDR4 modules". behardware.com. Retrieved 2012-04-14. 
  3. ^ a b Micron teases working DDR4 RAM, engadget.com, 2012-05-08, retrieved 2012-05-08 
  4. ^ "Samsung mass-produces DDR4". Retrieved 2013-08-31. 
  5. ^ The DRAM Story, www.ieee.org, 2008, p. 10, retrieved 2012-01-23 
  6. ^ "Crucial DDR4 Server Memory Now Available". globenewswire.com. 2 June 2014. Retrieved 12 December 2014. 
  7. ^ Vättö, Kristian (2014-06-04). "Computex 2014: Crucial shows Ballistix Elite DDR4". AnandTech (AnandTech). Retrieved 2014-06-04. Availability is slated for August but pricing has yet to be announced. 
  8. ^ "Why migrate to DDR4?". EETimes. 
  9. ^ "DDR4 – Advantages of Migrating from DDR3", accessed 8-20-2014.
  10. ^ Sobolev, Vyacheslav (2005-05-31). "JEDEC: Memory standards on the way". digitimes.com. Retrieved 2011-04-28. Initial investigations have already started on memory technology beyond DDR3. JEDEC always has about three generations of memory in various stages of the standardization process: current generation, next generation, and future. 
  11. ^ "DDR3: Frequently asked questions". Kingston Technology. Retrieved 2011-04-28. "DDR3 memory launched in June 2007" 
  12. ^ Valich, Theo (2007-05-02). "DDR3 launch set for May 9th". The Inquirer. Retrieved 2011-04-28. 
  13. ^ Hammerschmidt, Christoph (2007-08-29). "Non-volatile memory is the secret star at JEDEC meeting". eetimes.com. Retrieved 2011-04-28. 
  14. ^ a b "DDR4 – the successor to DDR3 memory". The "H" (h-online.com). 2008-08-21. Archived from the original on 26 May 2011. Retrieved 2011-04-28. The JEDEC standardisation committee cited similar figures around one year ago 
  15. ^ a b Graham-Smith, Darien (2008-08-19). "IDF: DDR3 won't catch up with DDR2 during 2009". PC Pro. Retrieved 2011-04-28. 
  16. ^ Volker Risska (Volker Rißka) (2008-08-21). "IDF: DDR4 als Hauptspeicher ab 2012 ["Intel Developer Forum: DDR4 as the main memory from 2012"]". computerbase.de. Retrieved 2011-04-28.  (English)
  17. ^ a b Novakovic, Nebojsa (2008-08-19). "Qimonda: ddr3 moving forward". The Inquirer. Retrieved 2011-04-28. 
  18. ^ Gervasi, Bill. "Time to rethink DDR4". July 2010. Discobolus Designs. Retrieved 2011-04-29. 
  19. ^ "DDR4-Speicher kommt wohl später als bisher geplant ("DDR4 memory is probably later than previously planned")". heise.de. 2010-08-17. Retrieved 2011-04-29.  (English)
  20. ^ Nilsson, Lars-Göran (2010-08-16). "DDR4 not expected until 2015". semiaccurate.com. Retrieved 2011-04-29. 
  21. ^ By 'annihilator' (2010-08-18). "DDR4 memory in Works, Will reach 4.266GHz". wccftech.com. Retrieved 2011-04-29. 
  22. ^ Shah, Agam. "Adoption of DDR4 memory faces delays", TechHive (IDG), April 12, 2013. Retrieved on June 30, 2013.
  23. ^ a b c d e 後藤 弘茂 ("Gotou Shigehiro"). "メモリ4Gbps時代へと向かう次世代メモリDDR4 ("Towards Next-Generation 4Gbps DDR4 Memory")". 2010-08-16. PC Watch (Japan). Retrieved 2011-04-25.  (English translation)
  24. ^ a b c d e Shilov, Anton (2010-08-16), Next-Generation DDR4 Memory to Reach 4.266 GHz, Xbitlabs.com, retrieved 2011-01-03 
  25. ^ Gruener, Wolfgang (February 4, 2009). "Samsung hints to DDR4 with first validated 40 nm DRAM". tgdaily.com. Retrieved 2009-06-16. 
  26. ^ Jansen, Ng (January 20, 2009). "DDR3 Will be Cheaper, Faster in 2009". dailytech.com. Retrieved 2009-06-17. 
  27. ^ a b "Samsung Develops Industry's First DDR4 DRAM, Using 30nm Class Technology". Samsung. 2011-04-11. Retrieved 26 April 2011. 
  28. ^ a b Perry, Ryan (2011-01-06). "Samsung Develops the First 30nm DDR4 DRAM". techgage.com. Retrieved 2011-04-29. 
  29. ^ "Samsung Develops Industry's First DDR4 DRAM, Using 30nm Class Technology". Samsung. 2011-01-04. Retrieved 2011-03-13. 
  30. ^ Protalinski, Emil (2011-01-04), Samsung develops DDR4 memory, up to 40% more efficient, Techspot.com, retrieved 2012-01-23 
  31. ^ "Diagram: Anticipated DDR4 timeline". 2010-08-146. PC Watch (Japan). Retrieved 2011-04-25.  (Linked from cited PC Watch article dated August 16, 2010)
  32. ^ "Samsung Samples Industry’s First DDR4 Memory Modules for Servers.". 
  33. ^ "Samsung Samples Industry’s First 16-Gigabyte Server Modules Based on DDR4 Memory technology". 
  34. ^ "SK Hynix Developed the World’s First Highest Density 128GB DDR4 Module". 
  35. ^ a b c Shah, Agam (2013-04-12). "Adoption of DDR4 memory faces delays". IDG News. Retrieved 22 April 2013. 
  36. ^ "Haswell-E - Intel's First 8 Core Desktop Processor Exposed". TechPowerUp. 
  37. ^ a b c d e f g Jung, J.Y. (2012-09-11), "How DRAM Advancements are Impacting Server Infrastructure", Intel Developer Forum 2012, Samsung, retrieved 2012-09-15 
  38. ^ Looking forward to DDR4, Pcpro.co.uk, 2008-08-19, retrieved 2012-01-23 
  39. ^ IDF: DDR4 - the successor to DDR3 memory, Heise-online.co.uk, 2008-08-21, retrieved 2012-01-23 
  40. ^ a b Swinburne, Richard (2010-08-26). "DDR4: What we can Expect". bit-tech.net. Retrieved 2011-04-28. Page 1Page 2Page 3
  41. ^ a b "JEDEC Announces Broad Spectrum of 3D-IC Standards Development". JEDEC. 2011-03-17. Retrieved 26 April 2011. 
  42. ^ "Main Memory: DDR3 & DDR4 SDRAM". jedec.org. Retrieved 2012-04-14. 
  43. ^ Tan, Gutmann and Reif (2008). Wafer Level 3-D ICs Process Technology. Springer. pp. 278 (sections 12.3.4–12.3.5). ISBN 9780387765341. 
  45. ^ a b JEDEC Standard JESD79-4: DDR4 SDRAM, JEDEC Solid State Technology Association, September 2012, retrieved 2012-10-11.  Username "cypherpunks" and password "cypherpunks" will allow download.
  46. ^ a b c d "Want the latest scoop on DDR4 DRAM? Here are some technical answers from the Micron team of interest to IC, system, and pcb designers". Denali Memory Report, a memory market reporting site. 2012-07-26. Archived from the original on 2013-12-02. Retrieved 22 April 2013. 
  47. ^ JEDEC MO-309E Whitepaper., accessed Aug. 20, 2014.
  48. ^ "DDR4 SDRAM SO-DIMM (MTA18ASF1G72HZ, 8GB) Datasheet" (PDF). Micron Technology. 2014-09-10. Retrieved 2014-11-20. 
  49. ^ "How Intel Plans to Transition Between DDR3 and DDR4 for the Mainstream". TechPowerUp. 
  50. ^ "Xilinx Ltd - Goodbye DDR, hello serial memory". epdtonthenet.net. 
  51. ^ Schmitz, Tamara (October 27, 2014). "The Rise of Serial Memory and the Future of DDR". Retrieved March 1, 2015. 
  52. ^ "SemiWiki - Bye-Bye DDRn Protocol?". semiwiki.com. 
  53. ^ Brian Bailey. "Is Wide I/O a game changer?". EDN. 
  54. ^ "JEDEC Publishes Breakthrough Standard for Wide I/O Mobile DRAM". jedec.org. 
  55. ^ a b "Beyond DDR4: The differences between Wide I/O, HBM, and Hybrid Memory Cube - ExtremeTech". ExtremeTech. Retrieved 25 January 2015. 

External links[edit]