Skip to content
View dssgabriel's full-sized avatar
🧐
Accelerating science
🧐
Accelerating science
  • CEA
  • France
  • 01:29 (UTC +02:00)

Block or report dssgabriel

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dssgabriel/README.md

Hello there!

I am a PhD candidate at CEA — the French Atomic Energy and Alternative Energies Commission. My research focuses on managing data structure representations within heterogeneous architectures for exascale-class HPC workloads.

I hold an MSc in High Performance Computing & Simulation from Paris-Saclay University, and I also have a BSc in Computer Science from University of Versailles.

Currently working on

  • Tiled layouts for C++23 std::mdspan
  • Kokkos + MPI/NCCL interoperability within the kokkos-comm project

Centers of interest

  • CPU & GPU microarchitecture design
  • Performance optimization & micro-benchmarking for heterogeneous systems
  • High-performance data structures & algorithms
  • Memory layout & management
  • Software engineering best practices

Programming languages

  • C and C++
  • Rust
  • Python
  • AArch64, x86-64 and a bit of RV64 (especially SIMD ISA extensions)

Frameworks

  • Kokkos
  • MPI
  • NCCL
  • CUDA/HIP
  • OpenMP

Pinned Loading

  1. kokkos/kokkos-comm kokkos/kokkos-comm Public

    Experimental MPI Wrapper for Kokkos

    C++ 20 11

  2. Rust-CUDA Rust-CUDA Public

    Forked from Rust-GPU/Rust-CUDA

    Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust. This fork adds initial CUDA 12 support.

    Rust 17 1

  3. master-thesis master-thesis Public

    Master's thesis on Rust and GPU programming at CEA/Paris-Saclay University

    Typst 2

  4. interpol interpol Public

    Forked from async-mpi-benchmarks/interpol

    Interposition library to trace and profile non-blocking MPI calls.

    Rust

  5. arm-sve-benchmarks arm-sve-benchmarks Public

    Performance comparison between small hand-written SVE kernels and compiler-generated ones.

    C 10 3

  6. sve-string-routines-benchmarks sve-string-routines-benchmarks Public

    Comparative performance benchmarks for hand-optimized Arm SVE implementations of C standard library string routines.

    C