AMD's just taken the wraps off its shiny new high bandwidth memory (HBM) technology, and as rumoured, the company is limited to a total of 4GB for its first-generation HBM product. While AMD has yet to reveal specifics of what that product might be, it did tell us that it'll be a GPU, it'll be priced towards the higher end of the spectrum, and that you'll be able to walk into a store and buy one within "the next couple of months." The rumour mill strongly suggests that this first HBM part will be the R9 390X.
The reason for the 4GB restriction for the company's upcoming GPU is due to the first-generation HBM design. HBM uses stacked memory chips along with a silicon interposer and through-silicon-vias (an interconnect that runs through the chip from top to bottom) in order to move the DRAM closer to the GPU. This shortens the traces, allowing for increased bandwidth and lower power consumption. Currently, those chips can only be stacked four dies high. With each die limited to 2Gbit, each stack is one gigabyte. AMD's current design only allows for four stacks around the GPU, limiting the system to four gigabytes.
It's not entirely clear why the company has been limited to four stacks of memory for its first-generation product. If AMD is sticking with its GCN 1.1 architecture for the launch of HBM, the physical die size of the GPU may have had something to do with it. It could also simply be down to cost. HBM, while cheaper than rival stacked memory technology Hybrid Memory Cube (HMC), is still likely to be pricier than the equivalent DRAM, making eight stacks impractical. Regardless, a leaked set of slides from HBM manufacturer Hynix alleges that second-generation HBM will double capacity to 2GB per stack, allowing for graphics cards with 8GB of RAM in the future.
Read 1 remaining paragraphs | Comments
No comments:
Post a Comment