Par Lab Seminar: Extracting Parallelism from Quantitative Finance Algorithms in Multicore Environment
Shuo Li of Intel will speak on Thursday, October 15 at 11am in 430 Soda Hall (the Woz).
This talk summarizes author’s experience in working with key algorithms in quantitative finance. It starts with a discussion of floating point arithmetic of contemporary microprocessors and presents two ways parallelism can be expressed, threading and SIMD. Then it examines how to achieve high performance computing with 3 popular financial algorithms. Finally it enumerates a few development tools and library useful for building high performance numerical software.
Shuo Li is a senior financial software engineer at software and services group at Intel Corporation. For the past 6 years, Shuo has been closely working with quantitative software developers in financial service industry to parallelize and optimize the key financial algorithms for multicore and manycore execution environment. Shuo has more than 20 years of software engineering experience with Intel. His main interest has been software development tools and environment, high performance software engineering and throughput computing.
Shuo holds a master’s degree in Computer Science from University of Oregon, a master’s degree in computational finance and an MBA degree from Duke University.