jrhemstad

two_largest

Adventure in profiling and optimization.

cuda_scalar_result

Answering "What is the faster way to return a single scalar from a kernel to host?"

example_cuda_benchmark

Template repository for CUDA enabled benchmarks using Google Benchmark

cuda_arch_odr

nvtx_wrappers

This repository is deprecated and the code has moved to the official NVIDIA NVTX github repository: https://github.com/NVIDIA/NVTX

creduce-example

Examples on how to use C-Reduce to create minimal compiler bug reproducers

link_test

Testing linkage of function local statics

stdexec

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

.github

accelerated-computing-hub

NVIDIA curated collection of educational resources related to general purpose GPU programming.

cccl

CUDA C++ Core Libraries

compiler-explorer

Run compilers interactively from your web browser and interact with the assembly

cub

Cooperative primitives for CUDA C++.

cuCollections

cuda-api-wrappers

Thin C++-flavored wrappers for the CUDA Runtime API

cuda-quantum

C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows

cudf

Python GPU DataFrame Library

cutlass

CUDA Templates for Linear Algebra Subroutines

devcontainers

gil_preload

Add NVTX ranges to Python GIL

github-markdown

infra

Infrastructure to set up the public Compiler Explorer instances and compilers

jrhemstad

libcudacxx

The NVIDIA C++ Standard Library

llm.c

LLM training in simple, raw C/CUDA

nvbench

CUDA Kernel Benchmarking Library

NVTX

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

rmm

RAPIDS Memory Manager

test_workflow_failure

thrust

Thrust is a C++ parallel programming library which resembles the C++ Standard Library.