벅스텔러번트 연구실

Investigating orchestration techniques to mitigate performance bottlenecks of cloud-based streaming frameworks. Big Data streaming applications handle unbounded data sets at millions of events per second with sub-second latency requirements.

Code partitioning method that employs application source-code characteristics to assign code to processing cores on heterogeneous platforms with CPUs and GPUs.

Extending Julia scientific computing language to automatically parallelize matrix computations across a cluster of heterogeneous multicore nodes.

Investigating techniques to cope with state explosion problem in static analysis of multi-threaded programs using Kronecker algebra and lazy evaluation.

Working on high-level language primitives for non-blocking synchronization and investigating weak memory consistency models on ARM and x86 platforms.

Analyzing, validating, and improving VM design for smart contract execution focusing on safety, security, and efficiency from architecture and ISA to runtime implementation.