Research agenda · Scientific computing
Numerical foundations. Modern systems.
Bridging numerical analysis, software architecture, and high-performance computing to build verifiable, scalable simulation software for exascale systems.
01 /Scientific solver modernization
Read full dossierM.Sc. research · High-order numerics & parallel kernels
Track 01 · Scientific Computing & Solver Architecture
Modernization of a Reactive Compressible Multi-Species Solver
Decomposing legacy Fortran into a modular C++17 architecture with Cantera thermodynamics, WENO-5/TENO shock-capturing, and parallel HDF5 scientific I/O.
- 01
Understand & Audit
Legacy Fortran Solver
Baseline verified - 02
Decouple & Interface
Architecture Redesign
Interfaces defined - 03
Rebuild & Modernize
Modular C++17 Core
Active development - 04
Verify & Validate
Verification & Validation
Continuous testing - 05
Scale & Distribute
HPC Scale & Distributed Execution
HPC target
02 /Exascale observability & heterogeneous systems
Exascale tracing · Performance observability · Distributed causality
RESEARCH MAP
Tuning, debugging, and monitoring heterogeneous systems at exascale.
This research focuses on the tools and methods needed to understand heterogeneous HPC systems where CPUs coordinate thousands of nodes and GPUs provide much of the computational power.
Reconstructing Execution States and Message Causality for an MPI Token Ring in Eclipse Trace Compass
CPU + GPU
Multi-core host nodes paired with throughput accelerators via high-speed interconnects
MPI / CUDA
Distributed-memory rank orchestration with asynchronous GPU kernel offloading
HETEROGENEOUS HPC
PERFORMANCE / BEHAVIORDecoupling CPU host scheduling from GPU device execution while tracing inter-node communication causality
TRACING
Non-intrusive event extraction with minimal runtime skew for MPI communication
DEBUGGING
Distributed memory sanitization and asynchronous GPU kernel breakpoint inspection
VISUALIZE
Timeline state reconstruction and message causality tracking across clusters
03 /Research interests
Parallel architectures, memory boundaries & compiler vectorization
Investigating how to structure, coordinate, and accelerate numerical software across modern parallel systems, from cache line vectorization to exascale cluster execution.
High-Performance Computing
Supercomputing InfrastructureDesigning simulation software to effectively exploit massively parallel supercomputing resources, batch schedulers, and high-speed interconnects.
- MPI
- SLURM
- HPC Clusters
- InfiniBand
Parallel Computing
Multi-Core & DecompositionDecomposing spatial computational domains and coordinating multi-threaded execution with minimal synchronization friction.
- OpenMP
- Pthreads
- Domain Decomposition
Task-Based Parallelism
Dynamic SchedulingExpressing scientific workflows as Directed Acyclic Graphs (DAGs) to enable latency hiding, work-stealing, and asynchronous execution.
- Task DAGs
- HPX
- Dependency Tracking
Heterogeneous Computing
CPU + GPU Co-DesignMapping scientific numerical kernels across host CPUs and throughput-oriented GPU accelerators, optimizing data movement across PCIe and NVLink.
- CUDA
- ROCm
- Unified Memory
- PCIe Transfer
Distributed Computing
Inter-Node ScalabilityStructuring low-overhead ghost-cell halo exchange, non-blocking collective communication, and data locality across distributed cluster nodes.
- Non-blocking MPI
- Halo Buffers
- Scalable Collectives
Scientific Software Engineering
Modular Software DesignApplying modern C++ paradigms, zero-cost abstractions, automated regression, and Continuous V&V to sustain long-lived simulation codes.
- Modern C++17
- CMake / CTest
- RAII
- V&V Suites
Performance Optimization
Cache, SIMD & RooflineAnalyzing cache line utilization, memory bandwidth saturation, and SIMD vectorization to approach theoretical roofline hardware performance limits.
- Roofline Model
- SIMD / AVX-512
- Cache Alignment
Performance Portability
Single-Source DispatchWriting portable mathematical kernels that target multi-vendor CPUs and accelerators through modern unified abstraction frameworks.
- Kokkos
- C++ Parallel Algorithms
- Hardware Targets
Methods & runtimes
04 /Aerodynamic simulation & flight shapes
Transonic flow & shock capturing · B-2 Spirit benchmark
AERODYNAMICS / COMPRESSIBLE FLOW
Transonic shock dynamics on complex lifting bodies.
The tailless B-2 flying wing serves as a numerical benchmark for evaluating high-order shock capturing, smooth-surface boundary layers, and GPU kernel efficiency across continuous 3D geometries at Mach 0.85 cruise.
Blended lifting surfaces with continuous curvature and zero vertical stabilizers.
Transonic shock wave tracking, pressure discontinuity resolution, and boundary layer interaction.
GPU-accelerated finite-difference stencil kernels for high-resolution 3D body-fitted meshes.
Click and drag to rotate · 360° orbit available in controls