Researches

Compiler Support for Hardware Accelerators Bioinformatics and graph dynamic-programming algorithms are slow and difficult to program due to their complex data dependencies. While recent work has introduced unified compilers for hyperdimensional-computing accelerators, there is still no analogous compiler support for dynamic-programming hardware accelerators, leaving developers dependent on manual, hardware-specific tuning.

Graph Analytics on Evolving Data - Common Graph Evolving graphs change over time, requiring queries to run across many snapshots. Computing each snapshot independently wastes work, while traditional streaming approaches suffer from costly deletions and strict sequential updates.

Streaming Graph Accelerator — JetStream Streaming graphs, where nodes and edges change continuously, are central to modern workloads in social networks, bioinformatics, and large-scale data analytics. To accelerate these dynamic workloads, we developed JetStream, a hardware accelerator designed specifically for real-time graph updates.

Research My research bridges compiler optimizations, hardware accelerators, and large-scale graph analytics through hardware/software co-design. I develop MLIR-based compiler infrastructures that automatically map complex bio and graph dynamic-programming workloads onto specialized accelerators, optimizing memory usage and parallelism.