Life is a series of firsts. First step, first word, first job.
   Fran Allen, an IBM Fellow Emeritus and a maverick in the field of computer science for nearly half a century—since before it even existed—gives this idea new meaning.
   In 1989, she became the first female IBM Fellow. In 2000, the first recipient of the IBM Technology Mentoring Award named in her honor (she’s well known as a mentor and advocate for women in computing). She was the first Anita Borg Award winner for Technical Leadership in 2004 and, last February, the first woman ever to receive the A.M. Turing Award from the Association for Computing Machinery, her field’s version of the Nobel Prize.
   “Now I get invitations from around the world to come talk to women computer scientists and that’s what I’ve been doing,” Allen says. This month, EECS hosts Allen for a series of appearances, including a Regents’ Lecture, “The Challenge of the Multi Cores: Think Sequential, Run Parallel,” at 4 p.m. January 31 in Sibley Auditorium.
   Allen, a specialist in high-performance computing, grew up on a farm in upstate New York. She taught math at her local high school; she knew most of her students. While working toward her master’s at the University of Michigan, IBM came knocking. They were in the midst of a recruiting effort and hired Allen as a programmer. She says she figured she’d pay off her debts, then get back to teaching.
   That was 50 years ago. Her first task was to instruct research scientists in IBM’s new computer language, FORTRAN. “The goals of that project were to make computers accessible and useful to users, to make the users more productive and to make the results just as good on every program they worked on nearly every time,” Allen says. “Those are still my goals today.”
   Her Regents’ lecture is intended to encourage new approaches to this very philosophy. Multi-core computers, she explains, allow for increasing parallelism, the ability to perform multiple tasks at once. While it may be possible to get 20 cores on a chip, according to Allen, the software side isn’t up to par with the hardware side.
   “All of nature is parallel. We think in parallel. But the machine is based on a paradigm that is sequential: a followed by b, followed by c. What I’m trying to do is to get people to go back and think about the way we’re expressing our applications.”
   During Allen’s Berkeley visit she’ll also sip tea with undergraduates, visit classrooms and departments, meet with faculty and lead a panel discussion at 5 p.m. Wednesday, January 30 titled “Shattering the Glass Ceiling: Career Advancement for Women Engineers.”
   She should know all about that.

By Megan Mansell Williams