Name: Jeff Hammond
Type: User
Company: @nvidia
Bio: HPC software @NVIDIA in 🇫🇮. Previously @Intel HPC, @argonne-lcf w/ Blue Gene and MPI. PhD in Chemistry from @uchicago for work on @nwchemgit. He/him/hän.
Twitter: science_dot
Location: Helsinki, Finland
Blog: http://jeffhammond.github.io/
Jeff Hammond's Projects
Argonne 1-sided (A1)
A Massively Parallel FFT Library for CPU/GPU
DO NOT WRITE ME WITH HPL SUPPORT QUESTIONS!!! (see the website and the official channels)
AQUARIUS (Advanced QUAntum moleculaR Iterative eqUation Solver) is a parallel quantum chemistry package built on the Cyclops Tensor Framework which provides high-performance structured tensor operations. AQUARIUS is primarily focused on iterative methods such as CC, CI, and EOMCC.
An implementation of ARMCI using MPI one-sided communication (RMA)
Shine some light on whether your suprtcomputer is working
STREAM, for lots of devices written in many programming models
Brilliantly Advanced General Electronic-structure Library
Implementation of MPI that supports large counts
A conda-smithy repository for BigMPI (derived from https://github.com/conda-forge/mpich-feedstock)
A paper about BigMPI
BLAS-like Library Instantiation Software Framework
https://github.com/flame/blis/issues/265
My blog.
Numerical experiments on the Boys function used in atomic integral computations
A mini-app that captures the communication pattern of NWChem---block-sparse matrix multiplication---in flat MPI and hybrid MPI+OpenMP configurations.
The next version of bwa-mem
A parallel runtime library for Fortran 2018 compilers
Process-based Asynchronous Progress Model for MPI Communication
Memory system characterization benchmarks using atomic operations
A simple example of MPI RMA to run on Cori
Collaborating on papers for the ISO C++ committee - public repo
Cyclops Tensor Framework: parallel arithmetic on multidimensional arrays
The Thing That Should Not Be
Thin C++-flavored wrappers for the CUDA Runtime API
Distributed Array Library with Extensible Communication (DALEC)
Intel Data Parallel C++ (and SYCL 2020) Tutorial.
GR-MHD in SYCL for the 2020s and beyond