Abstract

Fixes #1846 Assumes joblib/threadpoolctl#257 will get merged; if not, or if API changes, this will need to change too. It is compatible with older threadpoolctl though. PR in changelog Figure ou...

Python helpers to limit the number of threads used in native libraries that handle their own internal threadpool (BLAS and OpenMP implementations) - joblib/threadpoolctl

Large Language Models (LLMs) have shown strong capabilities in code generation and reasoning, motivating extensive benchmarks for evaluating functional correctness. However, performance optimizatio…

NASA is bringing its latest high-performance computing (HPC) technologies, scientific research, and artificial intelligence innovations to Supercomputing 2026, with a series of technical demonstrations scheduled at Booth 4038 in the event's Exhibit Hall. The presentations will feature NASA experts discussing advances in Fortran programming, OpenMP GPU acceleration, high-resolution hydrology simulations, modular supercomputing infrastructure, and HPC resource management. NASA's Supercomputing 2026 Technical Demonstration Schedule…

LightGBM Python bindings with CPU/OpenMP support, without GPU or CUDA

XGBoost Python bindings built from source for CPU/OpenMP, without CUDA or NCCL

DistPCA is a distributed out-of-core C++ framework for tera-scale genomic Principal Component Analysis (PCA), designed to scale efficiently across both single- and multi-node computing systems. Built on top of Message Passing Interface (MPI), it employs a hybrid multi-level parallelism scheme combining multiprocessing, OpenMP multithreading, SIMD vectorization, and double buffering across all three stages of the PCA pipeline (I/O, data preprocessing, numerical method). Evaluated on datasets reaching up to 11 TB, DistPCA achieves speedups of up to 58.2× and over 98% reduction in wall-clock time, while maintaining parallel efficiency above 82% and preserving the accuracy of the recovered principal components (PCs). For a detailed description of the framework and experimental evaluation, please refer to our preprint. Detailed instructions on how to set up and use the framework, as well as how to reproduce our experiments, are provided in the README.md file.

Coding agents are increasingly used to optimize code, but existing benchmarks fix one accelerator, programming model or harness, so they cannot isolate what each component contributes or show wheth…