About

Dibyendu Das is a highly experienced Sr Principal Engineer at Intel Corporation with over 27 years of experience in the field of compilers, computer architecture, and program performance understanding. He is currently exploring future technologies related to the enablement of AI in compiler algorithms and utilizing ML/DL algorithms for molecular drug design. In his previous role at AMD, Dibyendu worked on compiler optimizations for CPU using LLVM and was the lead of the team that developed AOCC, AMD's premium optimizing compiler that achieved world record SPEC benchmark scores. He was also involved with GPGPU optimizations. Prior to that, he spent several years at HP and IBM working on various aspects of programming language performance, better code generation and optimization, as well as assist tools for programmers. Dibyendu's current research and work include DL4Code: Deep Learning for Programming, Compilers & Code Generation, Hybrid Graph Coloring Algorithm for Register Allocation, and Implementing Cross-Device Atomics in Heterogeneous Processors, among others. He has also presented his research at various conferences and workshops, such as PAKDD, Supercomputing, Euro-LLVM, and IPDPS. Dibyendu's specialties include compilers, parallel processing, computer architecture, GPGPU computing, multicores, GPUs, APUs, programming languages, and standard template libraries. He has a degree in Computer Science from Jadavpur University and has also studied at St. Xavier's College in Kolkata. Overall, Dibyendu Das is a highly skilled and experienced engineer with a passion for exploring new technologies and pushing the boundaries of what is possible in the field of compilers and computer architecture.