3 papers
cs.AR2024
High-Performance Data Mapping for BNNs on PCM-based Integrated Photonics
Taha Shahroodi, Raphael Cardoso, Stephan Wong +3
State-of-the-Art (SotA) hardware implementations of Deep Neural Networks (DNNs) incur high latencies and costs. Binary Neural Networks (BNNs) are potential alternative solutions to…
cs.AR2024
Rethinking the Producer-Consumer Relationship in Modern DRAM-Based Systems
Minesh Patel, Taha Shahroodi, Aditya Manglik +4
Generational improvements to commodity DRAM throughout half a century have long solidified its prevalence as main memory across the computing industry. However, overcoming today's…
cs.AR2023
An In-Memory Architecture for High-Performance Long-Read Pre-Alignment Filtering
Taha Shahroodi, Michael Miao, Joel Lindegger +3
With the recent move towards sequencing of accurate long reads, finding solutions that support efficient analysis of these reads becomes more necessary. The long execution time req…