Overview

Featured Videos

Your Innovation, Our Memory

Your Innovation, Our Memory

Emerging technologies require innovation on a whole new scale. See how we partner closely with our customers to gain unique insights about how we can optimize our memory solutions to enable your innovations—and help you change the world.

View video
Memory for Automotive

Memory for Automotive

Technology is reshaping the concept of driving. Automakers are developing countless new driver-assistance features and systems. See how Micron’s memory solutions are helping to enable these new supercomputing capabilities.

View video

About Micron

Where there's memory, there's Micron

Engineered for Innovation

For more than 30 years Micron has redefined innovation by designing, developing, and manufacturing some of the world’s most advanced technologies.

Learn more
Elpida is Now Micron

Elpida Is Now Micron

With the combined strength of our products, technology, and team members—our customers now have access to the broadest portfolio of best-in-class technology.

About the acquisition

Welcome to My Workspace!

Create an account to access these benefits:

  • Save part pages
  • Save Data Sheets and other files
  • Create folders to organize your projects
  • Share folders with colleagues
  • Organize secure documents for easy access
  • "Follow" parts to see alerts and updates

Learn more about Workspace features

Don't have an account yet? Sign up

Already have an account?   Login

My Folders

Your workspace is your area to organize and save part pages, data sheets, and links for easy access in the future. You can even start by saving some of the pages you've recently accessed below:

HMC Is Here Part 2 Standard Page Save
My Workspace

HMC Arrives Just in Time to Be Your New Standard for Memory Performance: Part 2

Tom Kinsley   |   November 14, 2013   |   All Products

In my last post, I touched on some obstacles of traditional memory for system designers and hinted at the reasons why so many companies have selected Hybrid Memory Cube (HMC) as their new standard for memory performance. Here, let’s start to break down some of the key features—including abstracted memory,  unique interface, and superior performance—that make HMC such a breakthrough solution.

Abstracted Memory Management and Communication

The standard DDR4 data sheet exceeds 200 pages with complex timing and signaling variations defined for multiple speed grades. On the other hand, the HMC data sheet has no memory timing requirements; no RAS, CAS, WE, and CS signals; no refresh requirements; no tFAW, tRP, tWR, and tRC restrictions; and no slew rate adjustments for voltage or bus loading variations. HMC is agnostic to memory; it can support any memory type without changes to the protocol. The standardized communication protocol defined by the Hybrid Memory Cube Consortium (HMCC) supports multiple READ, WRITE, and ATOMIC commands within a reliable packet with a header and tail that provide data routing between the host and all cubes within the channel. The protocol is simple and adaptive to future HMC devices.

High-level HMC block diagram

Simple and Scalable Interface

Traditional memory channels have wide interfaces that run multiple devices in lockstep, are extremely sensitive to signal loading, and require coordinated accesses to prevent bus contention. HMC uses high-speed serial/deserializer (SERDES) channels to interface to the outside world. These channels run directly between devices and can operate independently of each other, yet can talk to any memory location within the cube. Each HMC lane runs at 10 Gb/s, 12.5 Gb/s, or 15 Gb/s with multiple channel configurations to support almost any bandwidth requirement up to 160 GB/s per cube. Not only does the cube provide bandwidth scalability, it also supports cube-to-cube chaining to increase memory density without increasing the pin count of the host.

Superior and Sustainable Performance

Before HMC, it was impossible to sustain 160 GB/s (that’s 1.28Tb!) of memory bandwidth—all day long. It took the efforts of many accomplished engineers, working for several years, to resolve the well-documented “memory wall” problem with HMC. The HMC stack consists of four or eight memory layers and one logic layer. The memory is based on our high-volume process node but designed just for HMC. Each memory layer has millions of memory cells in defined groups (vaults) with complex support logic (vault controller) that controls all aspects of the memory cells and provides an interface to the internal crossbar switch. The logic die is manufactured at a world-class logic foundry so we can maximize the density of the memory layers and take advantage of the predictability of the logic process to ensure robust vault controllers. HMC has 16 vaults that operate independently of each other and are designed to sustain 10 GB/s (80 Gb/s) of true memory bandwidth from each vault. The logic layer also supports the external interfaces, cross-bar switch, memory schedulers, built-in self-test (BIST), sideband channels, and numerous reliability, availability, and serviceability (RAS) features.

There’s more! Keep an eye out for my next post where I’ll discuss these additional HMC features:

  • Uncomplicated board layout and dense package
  • Exceptional RAS features
  • Low total cost of ownership (TCO)
  • Stable technology and long-term support

If you have any questions or thoughts about today’s post, please leave a comment below.

Login or Sign-up for an account to leave a comment.