What’s next from AMD? Advanced Micro Devices divulge information about its latest High Bandwidth Memory (HBM) interface for GPUs recently. The company is set to release next-gen Radeon 300-series product line and finally, APUs combining central processing and graphics processing.
It takes a lot of time for AMD to finalized this particular technology. As what the AMD chief technology officer Joe Macri said the technology was seven years in the making and he is further quoted that the big bonus for the chip maker—rival Nvidia is “at least a year behind” on HBM.
To provide notable performance three times of the currently arranged GDDR5 memory used by GPUs the technology associate heap of RAM. Aside from that AMD can also squeeze a lot more HBM into the space taken up by conventional GDDR5 memory—to wit, 1GB of HBM fits onto a 5mm-by-7mm cell, while you’d need a 24mm-by-28mm footprint for 1GB of GDDR5.
AMD‘s new memory technology should prove to be an almost immediate advantage for the company in the consumer market. That is what the principal analyst for Moor Insights & Strategy, Patrick Moorhead said.
“AMD has worked for years to make HBM a reality, and I believe they will have a time-to-market advantage on end products with the technology,” Moorhead added. “HBM helps solve what will become a big issue in graphics—scaling memory performance and power.
“I see applicability in graphics cards, PC APUs, and even some enterprise server workloads. The software is here today for the consumer workloads, but AMD or its partners will need to work hard to make a dent in the HPC market.”