Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators · HackerPapers discussions

Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators — mentioned by Someone

Fri, 15 Mar 2024 12:58:43 GMT

> What is the Big O run time on this? The claim is they’re dropping half the multiplications, so it isn’t doing anything for Big O. > If you want to improve the project credibility please consider being honest and open about what is actually going on and giving some clear explanations and illustrations, The math explaining how to halve the number of multiplications in the paper (https://arxiv.org/abs/2311.12224) isn’t hard to understand. You only have to read formulas 2 (traditional matrix multiplication) and 3 to 6. I think it’s clear it does do what’s being advertised, halving the number of…

Paper and discussion history. A mention is not an endorsement.

Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators — HN submission

Sat, 25 Nov 2023 18:37:03 GMT

Double the performance per MAC unit in ML accelerators

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators — HN submission

Fri, 24 Nov 2023 22:16:05 GMT

Fast DNN Accelerator Architectures

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.