CS Compiler Seminar: Please join us on April 10th, from 4 pm - 5 pm in Siebel 3102 where Abdul Rafae Noor will give a talk, “MISAAL: Synthesis-Based Automatic Generation of Efficient and Retargetable Semantics-Driven Optimizations”. Please see the abstract and biography below:
Title: MISAAL: Synthesis-Based Automatic Generation of Efficient and Retargetable Semantics-Driven Optimizations
To Appear in ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2025)
Abstract: Using program synthesis to select instructions for and optimize input programs is receiving increasing attention. However, existing synthesis-based compilers are faced by two major challenges that prohibit the deployment of program synthesis in production compilers: exorbitantly long synthesis times spanning several minutes and hours; and scalability issues that prevent synthesis of complex modern compute and data swizzle instructions, which have been found to maximize performance of modern tensor and stencil workloads. This paper proposes MISAAL, a synthesis-based compiler that employs a novel strategy to use formal semantics of hardware instructions to automatically prune a large search space of rewrite rules for modern complex instructions in an offline stage. MISAAL also proposes a novel methodology to make term-rewriting process in the online stage (at compile-time) extremely lightweight so as to enable programs to compile in seconds. Our results show that MISAAL reduces compilation times by up to a geomean of 16x compared to the state-of-the-art synthesis-based compiler, Hydride. MISAAL also delivers competitive runtime performance against the production compiler for image processing and deep learning workloads, Halide, as well as Hydride across x86, Hexagon and ARM.
Speaker Bio.: Rafae is a 5th year Ph.D. student at UIUC, advised by Professor Vikram Adve. His research interests include automated compiler construction for heterogeneous architectures using formal methods and compiler techniques.