Register Allocation by Graph Coloring       


Programming Languages Accomplishment | 1982

IBM researcher: Gregory Chaitin

Where the work was done: IBM T.J. Watson Research Center

What we accomplished: To make programs run as fast as possible, it is important that as much data as possible be in registers, which can be accessed immediately by the processor, as opposed to being in memory, which can take many cycles, even hundreds of cycles, for the processor to access. Chaitin (pictured) introduced an efficient and widely used global register allocator to keep data in registers and minimize "spilling" of values from registers to memory.

Related links: 1982 paper: Register Allocation & Spilling via Graph Coloring

Image credit: Alchetron

BACK TO PROGRAMMING LANGUAGES
BACK TO IBM RESEARCH ACCOMPLISHMENTS