Join us for our upcoming SAFARI Live Seminar: 

Speaker: Harisankar (Hari) Sadasivan, AMD AI Group & University of Washington

Date: Wednesday, Nov 27, 17:00 Zurich time (CET)
Where: Livestream on YouTube (Link)

Title: Accelerated systems for long-read DNA alignment 

Abstract:
ONT nanopore long-read DNA sequence alignment is an important step in enabling promising healthcare applications in Precision Medicine and metagenomics. The irregularity of the workload in terms of noise and size presents certain computational challenges in accelerating it. In this talk, we will discuss some of the HW-SW optimizations we did in SquiggleFilter ASIC to enable alignment in the raw signal space for targeted pathogen detection and how we then optimized the SquiggleFilter algorithm for GPUs. Following this, we will discuss how we optimized Minimap2, a SOTA long-read aligner, on GPUs. We will then discuss some of the performance considerations we had to make with respect to various form factors and different GPU vendors.

Speaker Bio:
Dr. Harisankar (Hari) Sadasivan is a Member of Technical Staff in the AMD AI Group, a faculty member (part-time) at the University of Washington, Seattle, and a Senior Member of IEEE. Hari’s research focuses on 3 Critical and Emergent Technologies (CET) that are identified as significant for US’s national security- ‘advanced computing’ for ‘artificial intelligence’ and ‘biotechnologies’. At AMD, Hari leads the AMD Center of Excellence in AI at UW Seattle and co-founded the AMD lifesciences group. Hari received his PhD and Masters in CSE from the University of Michigan Ann Arbor. Hari is a Technical reviewer with several IEEE/ACM venues including the longest, oldest and the most prestigious formats. Hari has previously worked with NVIDIA and Samsung R&D.