4021877
doi
10.5281/zenodo.4021877
oai:zenodo.org:4021877
Axel Huebl
Helmholtz-Zentrum Dresden-Rossendorf, Lawrence Berkeley National Laboratory
Axel Naumann
CERN
Vassil Vassilev
CERN
Adding CUDA® Support to Cling: JIT Compile to GPUs
Simeon Ehrig
Helmholtz-Zentrum Dresden-Rossendorf
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Programming Languages
Compilers & Tools
GPU
Interactive Computing
JIT
CUDA
C++
Cling
Jupyter
Clang/LLVM
llvm-develops
<p>Jupyter Notebooks are omnipresent in the modern scientist's and engineer's toolbox just as CUDA C++ is in accelerated computing. We present the first implementation of a CUDA C++ enabled read-eval-print-loop (REPL) that allows to interactively "script" the popular CUDA C++ runtime syntax in Notebooks. With our novel implementation, based on LLVM, Clang and CERN's C++ interpreter Cling, the modern CUDA C++ developer can work as interactively and productively as (I)Python developers while keeping all the benefits of the vast C++ computing and library ecosystem coupled with first-class performance.<br>
<br>
Knowledge in developing applications with GPU acceleration is recommended for the talk.</p>
Zenodo
2020-10-08
info:eu-repo/semantics/doctoralThesis
4021876
1.0
1602505614.793947
661512
md5:493518fe653c1fec9b4af87c7a455224
https://zenodo.org/records/4021877/files/presentation_with_jupyter_slides.pdf
575973
md5:ebf5c7a7be77d3544cca535051aeab46
https://zenodo.org/records/4021877/files/llvm_develop_meeting_2020_Simeon_Ehrig_Cling-CUDA.pdf
228940727
md5:66e498df0c18c5dfe55ce6d26098371c
https://zenodo.org/records/4021877/files/Cling-CUDA_SimeonEhrig_Final.mp4
89048
md5:91fff7803a4b1ad56c6ff26cb50af6fd
https://zenodo.org/records/4021877/files/jupyter_notebook_demo.pdf
public
10.5281/zenodo.4021876
isVersionOf
doi