Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17541 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929516139511808 |
|---|---|
| author | Ugur, Muhammed Pothukuchi, Raghavendra Pradyumna Bhattacharjee, Abhishek |
| author_facet | Ugur, Muhammed Pothukuchi, Raghavendra Pradyumna Bhattacharjee, Abhishek |
| contents | Neural interfaces read the activity of biological neurons to help advance the neurosciences and offer treatment options for severe neurological diseases. The total number of neurons that are now being recorded using multi-electrode interfaces is doubling roughly every 4-6 years \cite{Stevenson2011}. However, processing this exponentially-growing data in real-time under strict power-constraints puts an exorbitant amount of pressure on both compute and storage within traditional neural recording systems. Existing systems deploy various accelerators for better performance-per-watt while also integrating NVMs for data querying and better treatment decisions. These accelerators have direct access to a limited amount of fast SRAM-based memory that is unable to manage the growing data rates. Swapping to the NVM becomes inevitable; however, naive approaches are unable to complete during the refractory period of a neuron -- i.e., a few milliseconds -- which disrupts timely disease treatment. We propose co-designing accelerators and storage, with swapping as a primary design goal, using theoretical and practical models of compute and storage respectively to overcome these limitations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17541 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Swapping-Centric Neural Recording Systems Ugur, Muhammed Pothukuchi, Raghavendra Pradyumna Bhattacharjee, Abhishek Hardware Architecture Neural interfaces read the activity of biological neurons to help advance the neurosciences and offer treatment options for severe neurological diseases. The total number of neurons that are now being recorded using multi-electrode interfaces is doubling roughly every 4-6 years \cite{Stevenson2011}. However, processing this exponentially-growing data in real-time under strict power-constraints puts an exorbitant amount of pressure on both compute and storage within traditional neural recording systems. Existing systems deploy various accelerators for better performance-per-watt while also integrating NVMs for data querying and better treatment decisions. These accelerators have direct access to a limited amount of fast SRAM-based memory that is unable to manage the growing data rates. Swapping to the NVM becomes inevitable; however, naive approaches are unable to complete during the refractory period of a neuron -- i.e., a few milliseconds -- which disrupts timely disease treatment. We propose co-designing accelerators and storage, with swapping as a primary design goal, using theoretical and practical models of compute and storage respectively to overcome these limitations. |
| title | Swapping-Centric Neural Recording Systems |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2409.17541 |