Ctrl K

ccglib

The Complex Common GEMM Library (ccglib) provides mixed-precision matrix-matrix multiplication kernels for complex data.

5
contributors
130 commitsLast commit ≈ 3 weeks ago6 stars0 forks

Description

The Complex Common GEMM library (ccglib) provides a C++ interface to run complex-valued matrix-matrix multiplication on GPU tensor/matrix cores. The library supports both CUDA and HIP.

Keywords
CUDA
GPU
High performance computing
HIP
Programming languages
  • C++ 81%
  • Cuda 13%
  • CMake 5%
  • C 1%
  • HIP 1%
License
</>Source code

Participating organisations

ASTRON
Netherlands eScience Center

Contributors

Leon Oostrum
Leon Oostrum
Developer
Netherlands eScience Center
BV
Bram Veenboer
Developer
ASTRON
JR
John Romein
Developer
ASTRON
RR
Ronald Rook
Developer
Sioux Technologies
WvB
Wiebe van Breukelen
Developer
ASTRON

Related projects

RECRUIT

Reducing Energy Consumption in Radio-astronomical and Ultrasound Imaging Tools

Updated 6 months ago
In progress

Related software

cudawrappers

CU

The cudawrappers library is a C++ wrapper for the Nvidia C libraries such as the CUDA driver, NVRTC, and cuFFT.

Updated 29 months ago
12

Kernel Tuner

KE

Kernel Tuner greatly simplifies the development of highly-optimized and auto-tuned CUDA, OpenCL, and C code, supporting many advanced use-cases and optimization strategies that speed up the auto-tuning process.

Updated 25 months ago
126 15