22h ago
This week’s Expander progress focused on GPU & FPGA Acceleration for Expander. Let's dive into the updates.
1/
FPGA Linear GKR Implementation:
Completed the full hardware implementation of the dual-phase prepare operator in the LinearGKR algorithm, including atomic indirect operations on FPGA. This marks a major step toward a fully pipelined LinearGKR acceleration flow. RTL simulation completes.
2/
Resolve GPU's inefficiency via FPGA:
Resolved the efficiency bottleneck in the random accumulation writes of the GPU prepare phase, increasing the effective bandwidth from 1 TB/s to 6 TB/s by using FPGA.
3/
BN254 Pipeline Optimization: Currently addressing the issue of excessive pipeline depth in BN254 arithmetic logic on FPGA, targeting better timing closure and resource balancing.
Stay tuned for more updates.
3.09K
19
The content on this page is provided by third parties. Unless otherwise stated, OKX is not the author of the cited article(s) and does not claim any copyright in the materials. The content is provided for informational purposes only and does not represent the views of OKX. It is not intended to be an endorsement of any kind and should not be considered investment advice or a solicitation to buy or sell digital assets. To the extent generative AI is utilized to provide summaries or other information, such AI generated content may be inaccurate or inconsistent. Please read the linked article for more details and information. OKX is not responsible for content hosted on third party sites. Digital asset holdings, including stablecoins and NFTs, involve a high degree of risk and can fluctuate greatly. You should carefully consider whether trading or holding digital assets is suitable for you in light of your financial condition.