AMD explains what High Bandwidth Memory (HBM) is about

Posted on Tuesday, May 19 2015 @ 14:12 CEST by Thomas De Maesschalck

VideoCardz got its hands on a bunch of leaked slides from AMD that detail the advantages that HBM has over GDDR5, you can view the collection over here.

The stacked High Bandwidth Memory (HBM) brings the memory closer to the logic die and enables very wide bus widths. HBM offers much more bandwidth than GDDR5, while promising significant power savings as well as taking up a lot less space on the PCB.

The Radeon R9 390X (Fiji XT) will be the first GPU to use HBM. The chip will use first-gen HBM, next year we'll see the introduction of HBM2 which doubles the bandwidth to 256GB/s per chip. NVIDIA will adopt HBM2 in 2016 with its Pascal GPU.

AMD HBM space savings

About the Author

Thomas De Maesschalck

Thomas has been messing with computer since early childhood and firmly believes the Internet is the best thing since sliced bread. Enjoys playing with new tech, is fascinated by science, and passionate about financial markets. When not behind a computer, he can be found with running shoes on or lifting heavy weights in the weight room.

Loading Comments

Share this story!