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 dossier

M.Sc. research · High-order numerics & parallel kernels

Active modernizationCodebase: IZEM CFD
Target: HPC

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.

L1Physics: Cantera Kinetics
L2Numerics: WENO-5 / TENO
L3Systems: C++17 / HDF5
L4HPC: MPI / OpenMP
Explore solver architecture
  1. 01

    Understand & Audit

    Legacy Fortran Solver

    Baseline verified
  2. 02

    Decouple & Interface

    Architecture Redesign

    Interfaces defined
  3. 03

    Rebuild & Modernize

    Modular C++17 Core

    Active development
  4. 04

    Verify & Validate

    Verification & Validation

    Continuous testing
  5. 05

    Scale & Distribute

    HPC Scale & Distributed Execution

    HPC target
  • Fortran
  • C++17
  • Cantera
  • WENO-5
  • TENO
  • Parallel HDF5
  • MPI
  • OpenMP
Verified against legacy reference

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.

CPU + GPU×MPI / OPENMP / CUDA×OBSERVABILITY
PUBLISHED TECHNICAL REPORT · 2026

Reconstructing Execution States and Message Causality for an MPI Token Ring in Eclipse Trace Compass

HETEROGENEOUS HPC
RESEARCH WORKFLOW
01HARDWARE

CPU + GPU

Multi-core host nodes paired with throughput accelerators via high-speed interconnects

x86_64 HostPCIe / NVLink
02MODELS

MPI / CUDA

Distributed-memory rank orchestration with asynchronous GPU kernel offloading

Kokkos KernelsNon-blocking Ranks
RUNTIME INTERSECTION

HETEROGENEOUS HPC

PERFORMANCE / BEHAVIOR

Decoupling CPU host scheduling from GPU device execution while tracing inter-node communication causality

HOST ⟷ ACCELERATORDISTRIBUTED CAUSALITY
03LOW OVERHEAD

TRACING

Non-intrusive event extraction with minimal runtime skew for MPI communication

LTTng-USTScore-P Traces
04ROCGDB

DEBUGGING

Distributed memory sanitization and asynchronous GPU kernel breakpoint inspection

Kernel TrapsSanitizer
05SCALE

VISUALIZE

Timeline state reconstruction and message causality tracking across clusters

Trace CompassState Systems

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.

01SYSTEMS AT SCALE

High-Performance Computing

Supercomputing Infrastructure

Designing simulation software to effectively exploit massively parallel supercomputing resources, batch schedulers, and high-speed interconnects.

  • MPI
  • SLURM
  • HPC Clusters
  • InfiniBand
02CONCURRENCY

Parallel Computing

Multi-Core & Decomposition

Decomposing spatial computational domains and coordinating multi-threaded execution with minimal synchronization friction.

  • OpenMP
  • Pthreads
  • Domain Decomposition
03RUNTIME DAGS

Task-Based Parallelism

Dynamic Scheduling

Expressing scientific workflows as Directed Acyclic Graphs (DAGs) to enable latency hiding, work-stealing, and asynchronous execution.

  • Task DAGs
  • HPX
  • Dependency Tracking
04ACCELERATORS

Heterogeneous Computing

CPU + GPU Co-Design

Mapping scientific numerical kernels across host CPUs and throughput-oriented GPU accelerators, optimizing data movement across PCIe and NVLink.

  • CUDA
  • ROCm
  • Unified Memory
  • PCIe Transfer
05COMMUNICATION

Distributed Computing

Inter-Node Scalability

Structuring low-overhead ghost-cell halo exchange, non-blocking collective communication, and data locality across distributed cluster nodes.

  • Non-blocking MPI
  • Halo Buffers
  • Scalable Collectives
06ARCHITECTURE

Scientific Software Engineering

Modular Software Design

Applying 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
07MICRO-ARCHITECTURE

Performance Optimization

Cache, SIMD & Roofline

Analyzing cache line utilization, memory bandwidth saturation, and SIMD vectorization to approach theoretical roofline hardware performance limits.

  • Roofline Model
  • SIMD / AVX-512
  • Cache Alignment
08PORTABILITY

Performance Portability

Single-Source Dispatch

Writing portable mathematical kernels that target multi-vendor CPUs and accelerators through modern unified abstraction frameworks.

  • Kokkos
  • C++ Parallel Algorithms
  • Hardware Targets

Methods & runtimes

  • Modern C++
  • MPI / OpenMP
  • Kokkos / CUDA
  • SLURM / CMake
  • Numerical methods
  • Software architecture

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.

01 // GEOMETRY

Blended lifting surfaces with continuous curvature and zero vertical stabilizers.

02 // NUMERICS

Transonic shock wave tracking, pressure discontinuity resolution, and boundary layer interaction.

03 // EXASCALE

GPU-accelerated finite-difference stencil kernels for high-resolution 3D body-fitted meshes.

Click and drag to rotate · 360° orbit available in controls

B-2 SPIRIT
INTERACTIVE 3D STUDY
Three-dimensional flying-wing aircraft with pressure contoursA non-weaponized graphite flying-wing prototype with a blended body, no tail fins, black cockpit and recessed engine inlets. Colored pressure contours follow the wing surface. Animated streamlines and wingtip vortices illustrate airflow. Drag or use arrow keys to rotate. Flow colors are illustrative, not computed results.
TRANSONIC REGIME // MACH 0.85
SIX-VIEW DESIGN SHEETVIEW BLUEPRINT ↗