Energy efficient memory array with optimized burst read and write data access

Prior knowledge of access pattern is leveraged to improve energy dissipation for general matrix operations. This improves memory access energy for a multitude of applications such as image processing, deep neural networks, and scientific computing workloads, for example. In some embodiments, prior k...

Full description

Saved in:
Bibliographic Details
Main Authors Khellah, Muhammad, Augustine, Charles, Koker, Altug, Paul, Somnath, Lines, Andrew, Striramassarma, Lakshminarayanan, Majumder, Turbo, Rajwani, Iqbal
Format Patent
LanguageEnglish
Published 20.02.2024
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Prior knowledge of access pattern is leveraged to improve energy dissipation for general matrix operations. This improves memory access energy for a multitude of applications such as image processing, deep neural networks, and scientific computing workloads, for example. In some embodiments, prior knowledge of access pattern allows for burst read and/or write operations. As such, burst mode solution can provide energy savings in both READ (RD) and WRITE (WR) operations. For machine learning or inference, the weight values are known ahead in time (e.g., inference operation), and so the unused bytes in the cache line are exploited to store a sparsity map that is used for disabling read from either upper or lower half of the cache line, thus saving dynamic capacitance.
Bibliography:Application Number: US201916725747