Pinned Repositories
apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
argobots
Copy of Argobots Repository
bolt
Official BOLT Repository
daos
DAOS Storage Engine
daos-copy
ECP-ST-CAR-PUBLIC
The Exascale Computing Project Software Technologies Capability Assessment Report - Public Version
FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
llvm-releases
sollve
SOLLVE release
triton
Development repository for the Triton language and compiler
shintaro-iwasaki's Repositories
shintaro-iwasaki/llvm-releases
shintaro-iwasaki/triton
Development repository for the Triton language and compiler
shintaro-iwasaki/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
shintaro-iwasaki/argobots
Copy of Argobots Repository
shintaro-iwasaki/bolt
Official BOLT Repository
shintaro-iwasaki/daos
DAOS Storage Engine
shintaro-iwasaki/daos-copy
shintaro-iwasaki/FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
shintaro-iwasaki/fbgemm_rocm
shintaro-iwasaki/FBTT-Embedding
This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.
shintaro-iwasaki/folly
An open-source C++ library developed and used at Facebook.
shintaro-iwasaki/jekyll-action
A GitHub Action to publish Jekyll based content as a GitHub Pages site
shintaro-iwasaki/kineto
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
shintaro-iwasaki/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
shintaro-iwasaki/llvm-releases-dev
shintaro-iwasaki/minighost
shintaro-iwasaki/mpich
Official MPICH Repository
shintaro-iwasaki/ompi
Open MPI main development repository
shintaro-iwasaki/ompi-2
shintaro-iwasaki/optimizers
For optimization algorithm research and development.
shintaro-iwasaki/osu-abt
OSU Micro-Benchmarks 5.7 + Argobots
shintaro-iwasaki/p2s2-www
International Workshop on Parallel Programming Models and Systems Software for High-End Computing Website
shintaro-iwasaki/ppopp21-preemption-artifact
Artifact of the paper "Lightweight Preemptive User-Level Threads" in PPoPP'21
shintaro-iwasaki/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
shintaro-iwasaki/qthreads
Lightweight locality-aware user-level threading runtime.
shintaro-iwasaki/rccl-tests
RCCL Performance Benchmark Tests
shintaro-iwasaki/shintaro-iwasaki.github.io
shintaro-iwasaki/spack
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.
shintaro-iwasaki/triton-shared
Shared Middle-Layer for Triton Compilation
shintaro-iwasaki/yaksa-www
Yaksa: High-performance Noncontiguous Data Management