Toggle navigation
Toggle navigation
Home
DCUM Forums
Nanny Forums
Events
About DCUM
Advertising
Search
Recent Topics
Hottest Topics
FAQs and Guidelines
Privacy Policy
Your current identity is: Anonymous
Login
Preview
Subject:
Forum Index
»
Advanced Academic Programs (AAP)
Reply to "Fairfax Co. students create light-powered super chip, impacting data center industry"
Subject:
Emoticons
More smilies
Text Color:
Default
Dark Red
Red
Orange
Brown
Yellow
Green
Olive
Cyan
Blue
Dark Blue
Violet
White
Black
Font:
Very Small
Small
Normal
Big
Giant
Close Marks
[quote=Anonymous][quote=Anonymous][quote=Anonymous]https://arxiv.org/abs/2208.06749 Tensor algebra lies at the core of computational science and machine learning. Due to its high usage, entire libraries exist dedicated to improving its performance. Conventional tensor algebra performance boosts focus on algorithmic optimizations, which in turn lead to incremental improvements. In this paper, we describe a method to accelerate tensor algebra a different way: by outsourcing operations to an optical microchip. We outline a numerical programming language developed to perform tensor algebra computations that is designed to leverage our optical hardware's full potential. We introduce the language's current grammar and go over the compiler design. We then show a new way to store sparse rank-n tensors in RAM that outperforms conventional array storage (used by C++, Java, etc.). This method is more memory-efficient than Compressed Sparse Fiber (CSF) format and is specifically tuned for our optical hardware. Finally, we show how the scalar-tensor product, rank-$n$ Kronecker product, tensor dot product, Khatri-Rao product, face-splitting product, and vector cross product can be compiled into operations native to our optical microchip through various tensor decompositions. Impressive that FCPS kids are showing "a new way to store sparse rank-n tensors in RAM that outperforms conventional array storage". [/quote] That is cool, but how is this related to the light-powered super chip?[/quote] It's an algorithm that would turn fundamental deep learning operations currently run on GPUs into operations that could run on a hypothetical optical microchip[/quote]
Options
Disable HTML in this message
Disable BB Code in this message
Disable smilies in this message
Review message
Search
Recent Topics
Hottest Topics