AMD has been teasing about its next-gen Radeon (R9 390X we assume) graphics cards and processors back in early May. It is without doubt that at least some of the upcoming graphics cards will be the first to feature high-bandwidth memory (HBM), let's call is the turbo-charged offspring to GDDR5 memory, used in today's graphics cards.

AMD briefed press on HBA last week - High Bandwidth Memory, something they started working on roughly seven years ago. This new type of graphics memory is going to change the para-dime in the graphics industry when we are talking about using less power, smaller form factors but most of all increased & scalable memory bandwidth. In this article we'll dig a little deeper into the new technology.

We've talked about and mentioned HBM many times in the front-page news already. HBM is short for High Bandwidth Memory, basically a new technology that was invented and brainstormed many years ago. With fabrication technology shrinking the time was right for AMD to move forward with their first implementation of HBM. HBM v1 will be introduced soon in products that can not be discussed just yet. There are several advantages to HBM memory, but of course also some concerns. First and foremost, the memory bandwidth that this technology can potentially offer is colossal. But why the move to HBM?