Bio-Specific Hardware Accelerators: From Emerging Devices to Bio-informatics Applications

Farzane Zokaee, Ph.D. candidate in the Intelligent System Engineering department at the Indiana University-Bloomington

1400 Wegmans Hall

Genomics is rapidly becoming a leading field in medicine. It makes significant progress in more targeted, personalized, and proactive health care; identifies treatment options; screens newborns for genetic disorders; and tracks outbreaks of diseases, such as Ebola, Zika, and COVID-19.
With modern high-throughput genome sequencing technologies such as Illumina, PacBio SMRT, and Oxford Nanopore, the rate of genomic data growth over the last decade has been truly astounding. The total amount of data generated per day doubles every seven months and is expected to exceed YouTube and Twitter by 2025. The massive amount of data presents a significant challenge for genome analysis. On the other hand, classic Moore’s Law is slowing down. On high-end servers, an analysis of a single genome can take hundreds of CPU hours. In order to overcome the challenge of analyzing massive genomic data, it is essential to design bio-specific hardware accelerators. A recent trend in hardware accelerator design has focused on taking advantage of emerging technologies such as, resistive random-access memory (ReRAM), superconductor single-flux quantum (SFQ), and photonics in order to bypass the limitations of Moor's law. These emerging devices feature near-zero leakage current, low power consumption, as well as fast operating frequency capabilities. Therefore, accelerators based on emerging devices are the hope for future computing with dramatically improve throughput and energy efficiency.

 Bio: Farzane Zokaee is a Ph.D. candidate in the Intelligent System Engineering department at the Indiana University Bloomington.  The focus of her research is on designing bio-specific hardware accelerators using emerging technologies such as, resistive random-access memory (ReRAM), superconductors, and photonics. The results of her research have been published in top conferences such as MICRO, HPCA, PACT, DAC, DATE, and CAL. Additionally, she interned at Western Digital Corp., where she contributed to the development of transformer models for DNA language in the genome. 

 Refreshments will be provided.