8 citations · 10 across the 4 of their papers we have counts for
5 papers
CiMBA: Accelerating Genome Sequencing through On-Device Basecalling via Compute-in-Memory
William Andrew Simon, Irem Boybat, Riselda Kodra +8
As genome sequencing is finding utility in a wide variety of domains beyond the confines of traditional medical settings, its computational pipeline faces two significant challenge…
Swordfish: A Framework for Evaluating Deep Neural Network-based Basecalling using Computation-In-Memory with Non-Ideal Memristors
Taha Shahroodi, Gagandeep Singh, Mahdi Zahedi +6
Basecalling, an essential step in many genome analysis studies, relies on large Deep Neural Networks (DNNs) to achieve high accuracy. Unfortunately, these DNNs are computationally…
GateSeeder: Near-memory CPU-FPGA Acceleration of Short and Long Read Mapping
Julien Eudine, Mohammed Alser, Gagandeep Singh +2
Motivation: Read mapping is a computationally expensive process and a major bottleneck in genomics analyses. The performance of read mapping is mainly limited by the performance of…
RUBICON: A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers
Gagandeep Singh, Mohammed Alser, Kristof Denolf +5
Nanopore sequencing generates noisy electrical signals that need to be converted into a standard string of DNA nucleotide bases using a computational step called basecalling. The a…
Machine Learning Training on a Real Processing-in-Memory System
Juan Gómez-Luna, Yuxin Guo, Sylvan Brocard +5
Training machine learning algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, proc…