English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

From classical HPC to deep learning, MatMul is at the heart of today'scomputing. The recent Maddness method approximates MatMul without the need formultiplication by using a hash-based version of product quantization (PQ)indexing into a look-up table (LUT). Stella Nera is the first Maddnessaccelerator and it achieves 15x higher area efficiency (GMAC/s/mm^2) and morethan 25x higher energy efficiency (TMAC/s/W) than direct MatMul acceleratorsimplemented in the same technology. The hash function is a decision tree, whichallows for an efficient hardware implementation as the multiply-accumulateoperations are replaced by decision tree passes and LUT lookups. The entireMaddness MatMul can be broken down into parts that allow an effectiveimplementation with small computing units and memories, allowing it to reachextreme efficiency while remaining generically applicable for MatMul tasks. Ina commercial 14nm technology and scaled to 3nm, we achieve an energy efficiencyof 161 TOp/s/W@0.55V with a Top-1 accuracy on CIFAR-10 of more than 92.5% usingResNet9.

Stella Nera: Achieving 161 TOp/s/W with Multiplier-free DNN Acceleration based on Approximate Matrix Multiplication