#KOKKOS

High Performance Software Foundation (HPSF)

@hpsf.bsky.social

1 month ago

Kokkos Quo Vadis: Shaping the Future of the Ecosystem Join the Kokkos leadership team for an interactive Birds-of-a-Feather (BoF) session hosted by the Consortium for the Advancement of Scientific Software (CASS). This session, “Kokkos Quo Vadis&rd...

Kokkos Quo Vadis: Shaping the Future of the Ecosystem - Thurs. February 12 at 1 PM EST, virtual via Zoom

Join the #Kokkos leadership team for an interactive BoF session. Hear about the long-term roadmap & influence the direction of the Kokkos Ecosystem.

Details: kokkos.org/community/ev...

2 2 0 0

ilhan özgen xian

@hanbruder.ecoevo.social.ap.brid.gy

3 months ago

Daniel's talk on the current state of SERGHEI, our #HPC hydrodynamic code that leverages the #kokkos framework:
https://youtu.be/scI8jB2e5UQ

0 0 0 0

High Performance Software Foundation (HPSF)

@hpsf.bsky.social

3 months ago

CExA is organizing a #Kokkos Hackathon 🇫🇷 open to anyone / geared for PhD & post-doc level researchers
📅 January 12–16, 2026
📍 Maison de la Simulation (MdlS), Saclay / Gif-sur-Yvette, France
🆓 Registration is FREE (but required!)
👉 Learn more & register now: indico.math.cnrs.fr/event/15313/

0 0 0 0

HGPU group

@hgpu.bsky.social

4 months ago

A Performance Portable Matrix Free Dense MTTKRP in GenTen We extend the GenTen tensor decomposition package by introducing an accelerated dense matricized tensor times Khatri-Rao product (MTTKRP), the workhorse kernel for canonical polyadic (CP) tensor de…

A Performance Portable Matrix Free Dense MTTKRP in GenTen

#Kokkos #CUDA #OpenMP #Package

hgpu.org?p=30302

0 0 0 0

GetNews.me

@getnews-me.bsky.social

5 months ago

LAMMPS Uses Kokkos for Portable Molecular Dynamics on Exascale Systems

LAMMPS now uses Kokkos, enabling the same MD code to run on CPUs and GPUs on exascale systems. Strong‑scaling shows high efficiency on OLCF Frontier, ALCF Aurora and NNSA El Capitan. getnews.me/lammps-uses-kokkos-for-p... #lammps #kokkos #exascale

0 0 0 0

GetNews.me

@getnews-me.bsky.social

5 months ago

Autonomous AI System Translates Legacy Fortran Code to Portable Kokkos

An LLM pipeline translates legacy Fortran kernels to Kokkos C++, outperforms the original on GPU‑accelerated partitions; OpenAI models (GPT‑5, o4‑mini‑high) ran it for a few dollars. Read more: getnews.me/autonomous-ai-system-tra... #ai #kokkos

0 0 0 0

HGPU group

@hgpu.bsky.social

6 months ago

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision This paper presents a portable, GPU-accelerated implementation of a QR-based singular value computation algorithm in Julia. The singular value ecomposition (SVD) is a fundamental numerical tool in …

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision

#OpenCL #SYCL #HIP #Kokkos #Julia

hgpu.org?p=30096

0 0 0 0

HGPU group

@hgpu.bsky.social

7 months ago

Performance Portable Gradient Computations Using Source Transformation Derivative computation is a key component of optimization, sensitivity analysis, uncertainty quantification, and nonlinear solvers. Automatic differentiation (AD) is a powerful technique for evalua…

Performance Portable Gradient Computations Using Source Transformation

#Kokkos #HIP #CUDA #Performance

hgpu.org?p=30070

0 0 0 0

Tom Deakin

@tomdeakin.bsky.social

10 months ago

If you’re interested in getting fluid codes running fast on GPUs, be sure to check out this role with Ben Thornber at Queen's University Belfast.
hrwebapp.qub.ac.uk/tlive_webrec...
#Kokkos

0 1 0 0

Rob Mueller-Albrecht

@roboima.bsky.social

1 year ago

SC24 The Importance of Open Standards in High Performance Computing A Quick Snapshot from Supercomputing 2024 (SC24) In November, at SC24 in Atlanta, Dr. Tom Deakin, Senior Lecturer in Advanced Computer Systems, University of Bristol (UK), took to the stage in Inte...

Quick Take-Away from #SC24 in Atlanta last November:

Join Dr Tom Deakin at University of Bristol down the yellow brick road on the quest to achieve scalability across compute configurations with performance portability.
#SYCL #OpenMP #KOKKOS #OpenCL ...

community.intel.com/t5/Blogs/Tec...

1 1 0 0

HGPU group

@hgpu.bsky.social

1 year ago

Leveraging LLVM OpenMP GPU Offload Optimizations for Kokkos Applications OpenMP provides a cross-vendor API for GPU offload that can serve as an implementation layer under performance portability frameworks like the Kokkos C++ library. However, recent work identified so…

Leveraging LLVM OpenMP GPU Offload Optimizations for Kokkos Applications

#Kokkos #CUDA #HIP #OpenMP #PerformancePortability #Package

hgpu.org?p=29747

1 1 0 0

@ctdotxmt.bsky.social

1 year ago

Kokkos 4.5 Release Introduces New Auto-tuning Features Motivation By default, internal Kokkos execution space parameters are empirically or heuristically hand-tuned with fixed parameter values to provide “one-size-fits-most” performance, with ...

Great news!

kokkos.org/blog/blog-po...

#hpc #supercomputing #autotuning #apex #kokkos #cplusplus

0 0 0 0

@ctdotxmt.bsky.social

1 year ago

Preparing for HPC on RISC-V: Examining Vectorization and Distributed Performance of an Astrophysics Application with HPX and Kokkos | Proceedings of the SC '24 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis You will be notified whenever a record that you have chosen has been cited.

dl.acm.org/doi/10.1109/...

#hpx #risc_v #hpc #supercomputing #kokkos #cplusplus #SC24

1 0 0 1

@ctdotxmt.bsky.social

1 year ago

Evaluating HPX and Kokkos on RISC-V using an astrophysics application Octo-Tiger | Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, ...

dl.acm.org/doi/10.1145/...

#hpx #risc_v #hpc #supercomputing #kokkos #cplusplus #SC23

0 0 0 0

HGPU group

@hgpu.bsky.social

1 year ago

Asynchronous-Many-Task Systems: Challenges and Opportunities – Scaling an AMR Astrophysics Code on Exascale machines using Kokkos and HPX Dynamic and adaptive mesh refinement is pivotal in high-resolution, multi-physics, multi-model simulations, necessitating precise physics resolution in localized areas across expansive domains. Tod…

Asynchronous-Many-Task Systems: Challenges and Opportunities – Scaling an AMR Astrophysics Code on Exascale machines using Kokkos and HPX

#CUDA #HIP #Kokkos #Astrophysics #Exascale #Package

hgpu.org?p=29620

2 1 2 0

Will Killian

@willkill07.bsky.social

1 year ago

Full room at #P3HPC workshop at #SC24 this morning. Julien Bigot is gave a great featured talk on CEA’s CExA project’s adoption of @hpsf.bsky.social and #Kokkos and what led them to using it as their preferred application ecosystem.

3 1 0 0

HGPU group

@hgpu.bsky.social

1 year ago

Kokkidio: Fast, expressive, portable code, based on Kokkos and Eigen Kokkidio is a newly developed C++ template library that combines the performance portability framework Kokkos and its strength in utilising GPUs with the expressive syntax and CPU optimisations of …

Kokkidio: Fast, expressive, portable code, based on Kokkos and Eigen
#GPU #Kokkos #PerformancePortability #Package
hgpu.org?p=29541

3 0 0 0

Posts tagged #KOKKOS