Task-Based MLIR Compilation for HPC ClustersMS SeminarThis seminar presents a compiler framework for distributed heterogeneous HPC systems built using MLIR. The work explores task-based decomposition of workloads and compilation strategies that map computations efficiently across CPUs and GPUs in cluster environments. It discusses the design of intermediate representations, scheduling strategies, and runtime integration for scalable execution on multi-node systems.
An IR for Distributed Heterogeneous ComputingComputer Systems Workshop 2025This work introduces DHIR, an MLIR-based intermediate representation designed to unify distributed and heterogeneous execution. DHIR enables task parallelism, device placement, and communication within a single abstraction, improving programmability and compiler optimization across CPUs, GPUs, and clusters.
An IR for Distributed Heterogeneous ComputingPLDI SRC 2025This work introduces DHIR, an MLIR-based intermediate representation designed to unify distributed and heterogeneous execution. DHIR enables task parallelism, device placement, and communication within a single abstraction, improving programmability and compiler optimization across CPUs, GPUs, and clusters.