Unkreativ retweeted
The White House Memory Safety Appeal is a Security Red Herring
hackaday.com/2024/02/29/the-…
Unkreativ retweeted
[#cpp20][reflect] Minimal static reflection library
* C++20 - single header (gcc, clang, msvc)
* Minimal API (no dependencies)
* Verifies itself upon include (via static_asserts)
* Compiler changes agnostic (no ifdefs)
github.com/boost-ext/reflect godbolt.org/z/qYjP41vP5
Unkreativ retweeted
The @AMDRadeon Developer Tool Suite has a new member: Radeon #GPU Detective (RGD) 🕵️
RGD is a tool for post-mortem analysis of GPU crashes so you can:
🎆 Capture and analyze crash dumps
🎆 Narrow down the root cause of a crash
Take a look now! #D3D12
gpuopen.com/radeon_gpu_detec…
Unkreativ retweeted
We are happy to announce the Release 2.9.3 of C-Blosc2 🥳🥳. This is a maintenance release were we fixed several issues and improved docs and code. For more info github.com/Blosc/c-blosc2/re….
Enjoy!
Unkreativ retweeted
.@HPCpodcast: @sunitachandra29 on #Exascale Programming and the Emergence of the #RSE
insidehpc.com/2023/06/hpcpod…
#HPC #AI via @insideHPC
Unkreativ retweeted
We released openPMD-api 0.15!
Highlights include C++17 transition, Error Recovery, ADIOS2 BP5, Append & Read-Linear Modes, Performance & Memory!
@BerkeleyLab @CASUSscience @LBNLatap @exascaleproject @doescience
Read about all new features here:
openpmd-api.readthedocs.io/e…
Unkreativ retweeted
1/2 Our #LLAMA is developing splendidly! 🦙 Have a close look if you want to decouple #algorithms from #memorylayouts. With #LLAMA there is no need to rewrite your programs with different data structures for every new platform. What's new in v0.5? A lot! github.com/alpaka-group/llam…
Unkreativ retweeted
hipSYCL is now Open SYCL!This change, while painful, was necessary to reflect what the project is about and wants to be:A generic, community-driven SYCL implementation.The new repo is at github.com/OpenSYCL/OpenSYCL - links will be redirected. See here details: github.com/OpenSYCL/OpenSYCL…
Unkreativ retweeted
It's always a great idea to every now and then visit our #jobpostings. Currently, we heavily expand 📈 our professional support team. But @CASUSScience also offers scientific & admin positions. Have a closer 🔎 look here: casus.science/join-us/
#CloudNative #MLOps #DevOps #HPC
Unkreativ retweeted
A team studying plasma physics used #exascale supercomputer Frontier to achieve an eightfold speed increase in their code’s performance. The result is an exciting demonstration of what we can expect from Frontier in the years to come. @ORNL @OLCFGOV olcf.ornl.gov/2022/11/18/exa…
Unkreativ retweeted
Our @sunitachandra29's team is one of the only 8 CAAR (center for accelerated application readiness) teams in the US to stress test the 1st exascale system ever, Frontier! CAAR is the program from ORNL that chose the 8 teams.
olcf.ornl.gov/2022/11/18/exa…
Unkreativ retweeted
Related work by @sunitachandra29 and her colleagues is described here: ascr-discovery.org/2021/12/s… [2/3]
Unkreativ retweeted
What can you do with a computer that can complete a quintillion calculations/second? Sunita Chandrasekaran @UDelaware is working to ensure a key application for plasma physics and X-ray research will be able to run on @OLCFGOV's Frontier: udel.edu/udaily/2022/october…
Unkreativ retweeted
Our meta-data standard can do way more than file I/O 😎Check out Franz Poeschel, @WilliamFGodoy1, @axccl et al.:
"Transitioning from file-based HPC workflows to streaming data pipelines with openPMD and ADIOS2"
arxiv.org/abs/2107.06108
Unkreativ retweeted
Exascale software should be in the hands of the #hpc community! That's why we at AMD have open sourced HPL. This is AMD's software that contributed to the Exaflop runs on Frontier. github.com/ROCmSoftwarePlatf…
Unkreativ retweeted
Second place: Michael Bussmann, @HZDR_Dresden, “Laser Wakefield Acceleration for Electrons”! #physics #physicspics #imaging
Unkreativ retweeted
NEW release (0.9.0) with an experimental #SYCL back-end published today! Kudos to team #alpaka! 🥳 @psychocoderHPC @GuidoJuckeland @j_stephan_dd @axccl
release adds support for Intel oneAPI hardware targets (CPUs, GPUs, FPGAs) as well as AMD/Xilinx FPGAs
github.com/alpaka-group/alpa…
Unkreativ retweeted
New release 🎉 ! Do you want to avoid rewriting your programs with different data structures for every new platform? Then have a look at our Low-Level Abstraction of Memory Access (#LLAMA) decoupling #algorithms from #memorylayouts. Try out LLAMA v0.4: github.com/alpaka-group/llam…
Unkreativ retweeted
By optimizing a code for @ORNL’s forthcoming #exascale system, Frontier, researchers from @HZDR_Dresden, @GeorgiaTech, @ORNL, @UDelaware, and @BrookhavenLab hope to enable better simulations of plasma behavior. #DiscoverFrontier bit.ly/34kxpR3
Unkreativ retweeted
Just in time for Christmas:
alpaka 0.8.0 is here! github.com/alpaka-group/alpa…
Featuring a new portable Philox-based RNG, memory fences, an experimental namespace, and more!
@HZDR_Dresden @CASUSscience @psychocoderHPC @BernhardManfre1 @axccl @GuidoJuckeland @sunitachandra29






















