News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
RLDRAM

RLDRAM

Low-latency dynamic memory for networking and embedded systems

RLDRAM is a specialty dynamic random-access memory designed for low latency and high bandwidth. Developed by Infineon and later Micron, it serves embedded applications like networking equipment where speed and capacity exceed standard DRAM limits.

Share on WhatsApp

  • First generation RLDRAM appeared in 1999
  • Developed by Infineon with Micron as partner
  • Targets embedded apps like networking equipment
  • Micron demonstrated RLDRAM 3 in 2012
  • Offers SRAM-like interface with DRAM capacity

What it is

Reduced Latency DRAM (RLDRAM) is a type of specialty dynamic random-access memory. It features an interface similar to static RAM (SRAM) but offers the higher storage capacity of DRAM. The technology targets embedded applications that require moderate costs, low latency, and high bandwidth. It performs better than standard commodity DRAM during random accesses or back-to-back read and write operations. Infineon Technologies originally developed the chip, with Micron Technology joining as a partner later.

How it came about

The first generation of RLDRAM devices appeared in 1999. Initially, only Infineon fabricated these chips. Micron Technology later joined as a development partner and second source. In 2003, both companies announced the second-generation specification, known as RLDRAM II. Samples of this newer version appeared that same year. Infineon eventually abandoned further development of the technology. Micron continued the work and introduced RLDRAM II devices. In 2012, Micron demonstrated the first third-generation devices, called RLDRAM 3.

Inside the chip

RLDRAM uses a SRAM-like interface to achieve lower latency than contemporaneous commodity DRAM. This design allows for faster response times in embedded systems. It provides high bandwidth suitable for data-intensive tasks. The memory handles back-to-back read and write accesses more efficiently than standard DRAM. It also excels at completely random access patterns. While it does not match the speed of pure SRAM, it offers greater capacity at a moderate cost. This balance makes it ideal for networking equipment and other embedded applications.

How it was made

Infineon Technologies was the initial manufacturer of RLDRAM devices starting in 1999. Micron Technology later became a second source and development partner. After Infineon exited the development process, Micron took over production of RLDRAM II. The company also led the demonstration of RLDRAM 3 in 2012. Specific manufacturing process nodes and transistor counts are not detailed in the available records. The focus remained on the architectural interface and performance characteristics rather than specific fabrication metrics.

Where it went

RLDRAM is targeted at embedded applications that require a balance of speed and capacity. Computer networking equipment is a primary use case. These systems need memories with low latency and high bandwidth but cannot afford the high cost or low density of SRAM. The chip supports moderate costs while delivering performance superior to commodity DRAM in random access scenarios. It serves roles where back-to-back data transfers are common.

Versions and family

The technology has evolved through three generations. The first generation launched in 1999. RLDRAM II was announced in 2003 by Infineon and Micron, with samples appearing that year. After Infineon left the project, Micron continued with RLDRAM II. The third generation, RLDRAM 3, was demonstrated by Micron in 2012. Each iteration aimed to maintain the low-latency, high-bandwidth profile while improving performance or integration.

Why it matters

RLDRAM filled a niche between high-speed SRAM and high-capacity commodity DRAM. It enabled networking equipment and embedded systems to handle random data accesses more efficiently. By offering a SRAM-like interface with DRAM density, it reduced system costs without sacrificing critical latency performance. Micron's continuation of the line after Infineon's exit ensured the technology remained available for specialized industrial and networking applications.

Questions people ask about RLDRAM

What is RLDRAM used for?

RLDRAM is used in embedded applications such as computer networking equipment. It suits systems needing moderate costs, low latency, and higher capacities than SRAM can provide.

Who developed RLDRAM?

Infineon Technologies originally developed RLDRAM. Micron Technology later joined as a development partner and second source, eventually taking over the product line.

How does RLDRAM differ from standard DRAM?

RLDRAM has a SRAM-like interface and lower latency than commodity DRAM. It performs better during back-to-back read/write operations and random accesses.

Good reading and sources

Where this page comes from

The facts on this page come from the Wikipedia article "RLDRAM", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryChip rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.

It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.