https://www.techpowerup.com/230224/...bm2-stack-availability-paves-the-way-for-vegareleased an updated HBM2 specifications document that pins availability of 4 gigabyte (32 Gbit) HBM2 stacks to the first quarter of 2017. This paves the way for mass-production and market availability of AMD's upcoming Radeon "Vega" graphics chip, which feature two such 4 GB HBM2 stacks, making up 8 GB of total memory.
SK Hynix H5VR32ESM4H-H1K memory stack, which will be integrated by AMD onto its Vega10 multi-chip module (MCM), ticks at 1.60 Gbps (per pin), with a cumulative bandwidth of 204.8 GB/s per stack. With two such stacks, Vega10 could feature 409.6 GB/s of memory bandwidth, assuming AMD uses the reference clock speeds for these stacks.
Q&A session with AMD Senior Fellow Jeffrey Cheng on his area of expertise – the AMD Vega memory architecture. Check it out!
http://www.techarp.com/articles/amd-vega-memory-architecture-qa/
- AMD Vega was specifically architected to handle big datasets, with a heterogenous memory architecture, a wide and flat address space, and a High Bandwidth Cache Controller.
- AMD chose to design a heterogenous memory architecture to support various memory technologies like HBM2 and even non-volatile memory (e.g. Radeon Solid State Graphics).
- At any given moment, the amount of data processed by the GPU is limited, so it doesn’t make sense to store a large dataset in DRAM. It would be better to cache the data required by the GPU on very fast memory (e.g. HBM2), and intelligently move them according to the GPU’s requirements.
- The AMD Vega’s heterogenous memory architecture allows for easy integration of future memory technologies like storage-class memory (flash memory that can be accessed in bytes, instead of blocks).
AMD has announced that they will be holding a Capsaicin Event at GDC 2017 on February 28th, where AMD will be showcasing some of their newest graphics hardware.
(...)
"... The Capsaicin livestream kicks off at 10:30 AM from Ruby Skye, a feature-packed show highlighting the hottest new graphics and VR technologies propelling the games industry forward. The Cream Developer Sessions will start shortly after at 2:30 PM, with a special talk featuring Unity and Epic."
AMD will reportedly be releasing Vega as part of the RX 500 series, with both Vega 10 and 11 based GPUs as part of their new graphics.
As far back as CES 2017 we have seen leaks regarding AMD's RX 500 series of GPUs, which have hinted that Vega will not be a simple extension of AMD's Polaris-based 400 series.
Right now it is rumoured that AMD has created both a high-performing Vega 10 GPU and a lower performing Vega 11 GPU, both of which are expected to make up the high-end of the RX 500 series. On the low-end, AMD is expected to launch refreshed versions of their new Polaris designs, using an optimised 14nm design and offering increased efficiency over the RX 400 series.