#openshmem
LightNews LightNews
ctdotxmt.bsky.social
Finishing some runtime system work; decided to try a #deskpi #super6c cluster board.

An ITX form factor beowulf cluster is amazing.

#slurm & #nfs worked out of apt.

#ucx, #openmpi, #openshmem, #openpmix, #gasnet, & #hpx needed custom compilation.

@raspberrypi.com #arm #hpc #supercomputing
June 23, 2025 at 11:16 PM
ctdotxmt.bsky.social
HPX now successfully running on an OpenSHMEM parcelport!

hpx.dev

#hpx #openshmem #hpc #supercomputing #agas #pgas
September 6, 2026 at 12:34 AM
michelle-strout.bsky.social
What is the fastest and easiest to write parallel, distributed radix sort? @mppf.bsky.social has implemented it Chapel, MPI, and OpenSHMEM, github.com/mppf/distrib.... Do you know of other versions or ideas for improving the existing ones? #HPC @chapellanguage.bsky.social @sunitachandra.bsky.social
GitHub - mppf/distributed-lsb: Comparing Distributed Programming Frameworks with LSD Radix Sort
Comparing Distributed Programming Frameworks with LSD Radix Sort - mppf/distributed-lsb
github.com
February 28, 2025 at 8:24 PM
chapellanguage.bsky.social
Check out Michael Ferguson's new article in the Chapel Blog to learn about how Chapel's design gives it good memory safety properties. The article shows how C, C++, Rust, Python, OpenSHMEM, MPI, and Chapel respond to common programming errors.

chapel-lang.org/blog/posts/m...

#ChapelLang
A table of possible memory errors, with columns for C, C++, Rust, Python, and Chapel.
April 10, 2025 at 9:45 PM
ctdotxmt.bsky.social
The OpenSHMEM BoF is imminent! Join the session to hear about the latest ratified version (1.6) ! Details at the link:

sc24.conference-program.com/presentation...

#hpc #supercomputing #SC24
November 21, 2024 at 4:35 PM
ctdotxmt.bsky.social
Cool tutorial!

www.usna.edu/Users/cs/fkn...

#hpc #supercomputing #openshmem #shmem
SHMEM - Home
www.usna.edu
October 7, 2025 at 11:40 PM
ogawa-tadashi.bsky.social
=>
"Multi-GPU Programming in NCCL and NVSHMEM", Jeff Hammond, NVIDIA, GPU Mode, Aug 16, 2025 (1:41:42) www.youtube.com/watch?v=2xMz...

NCCL (NVIDIA Collective Communication Library) developer.nvidia.com/nccl
NVSHMEM (Parallel programming interface based on OpenSHMEM) developer.nvidia.com/nvshmem
August 19, 2025 at 5:04 AM
alansill.bsky.social
Neat! Link for this work? (We have grad students working with OpenSHMEM who might be interested.)
September 6, 2026 at 6:58 PM
ctdotxmt.bsky.social
Found the slurm + pmi2 + openmpi apt packages weren't cooperating on the #deskpi. Did a custom build (slurm, pmix, openmpi/openshmem) and all is well provided the jobs are submitted with the correct commands. #LLM helped substantially w/ Q&A + debug

@raspberrypi.com #hpc #gasnet #openmpi #openshmem
April 17, 2026 at 8:08 PM
arxiv-daily-bot.bsky.social
Toward a Unified GPU-Aware OpenSHMEM Specification

Naveen Ravi et al.

#arXiv #cs.DC
Toward a Unified GPU-Aware OpenSHMEM Specification
Leadership-class HPC systems are now accelerator-centric, with GPUs providing most floating-point throughput and memory bandwidth. As next-generation systems increasingly integrate accelerators through high-speed memory fabrics and system interconnects, exposing larger tightly coupled device domain…
arxiv.org
July 10, 2026 at 4:56 PM
chapellanguage.bsky.social
How does Chapel stack up against MPI and OpenSHMEM for distributed memory parallel programming? Check out this repo to see implementations and performance measurements of a Least-Significant Digit First Radix Sort in these frameworks.

github.com/mppf/distrib...

#ChapelLang #MPI #OpenSHMEM
GitHub - mppf/distributed-lsb: Comparing Distributed Programming Frameworks with LSD Radix Sort
Comparing Distributed Programming Frameworks with LSD Radix Sort - mppf/distributed-lsb
github.com
March 13, 2025 at 6:57 PM
roboima.bsky.social
Accelerate multi-node shared memory and RDMA for distributed #HPC and #AI compute. Intel #SHMEM: GPU-initiated RDMA, following #OpenSHMEM extended with open multi-vendor multiarchitecture #SYCL APIs.
Now with Intel #oneAPI HPC Toolkit 2025.1:
www.intel.com/content/www/...
Intel® SHMEM: Multi-Node Data Sharing with SYCL*
Intel® SHMEM: Accelerate Multi-Node Data Sharing for GPUs and SYCL* Devices
www.intel.com
March 31, 2025 at 11:45 PM
cdsoft.bsky.social
Evolving Comms Libraries in ROCm for Future AI Workloads
This talk covers advances in AMD ROCm communication libraries for large-scale AI. RCCL innovations include copy-engine offloading, symmetric memory, GPU-initiated collectives, congestion-aware load balancing, and port failover. rocSHMEM extends an OpenSHMEM-like model with Python and Triton support, while NIXL contributions enable efficient inference. Together, they support diverse NICs like AMD Pensando AINICs and Broadcom Thor. Discover more: https://www.amd.com/en/corporate/events/advancing-ai/sessions-catalog/evolving-comms-libraries-in-rocm-for-future-ai-workloads.html *** Subscribe: https://bit.ly/Subscribe_to_AMD Join the AMD Gaming Discord Server: https://discord.gg/amd-gaming Visit the AMD Gaming Community Website: https://www.amdgaming.com/ Like us on Facebook: https://bit.ly/AMD_on_Facebook Follow us on Twitter: https://bit.ly/AMD_On_Twitter Follow us on Twitch: https://Twitch.tv/AMD Follow us on LinkedIn: https://bit.ly/AMD_on_Linkedin Follow us on Instagram: https://bit.ly/AMD_on_Instagram ©2026 Advanced Micro Devices, Inc. AMD, the AMD Arrow Logo, and combinations thereof are trademarks of Advanced Micro Devices, Inc. in the United States and other jurisdictions. Other names are for informational purposes only and may be trademarks of their respective owners.
www.youtube.com
August 16, 2026 at 7:20 AM
arxiv-daily-bot.bsky.social
Allocation Tracking and Parameter Checking for Parallel Programming Models using Contracts

Yussur Mustafa Oraji, Christian Bischof

#arXiv #cs.DC
Allocation Tracking and Parameter Checking for Parallel Programming Models using Contracts
Correctness checking tools for High-Performance Computing programs are typically limited to specific parallel programming models such as MPI or OpenSHMEM. The CoVer framework previously addressed this by introducing a generic, contract-based approach that decoupled API requirements from the core to…
arxiv.org
August 3, 2026 at 10:26 PM
csdc-bot.bsky.social
Naveen Ravi, et al.: Toward a Unified GPU-Aware OpenSHMEM Specification https://arxiv.org/abs/2607.08006 https://arxiv.org/pdf/2607.08006 https://arxiv.org/html/2607.08006
July 10, 2026 at 6:40 AM
dbader.bsky.social
Vivek Sarkar @GeorgiaTech gives his thoughts on OpenSHMEM in the Era of #Exascale
#SC17 #HPC @GTComputing http://bit.ly/2AcXcKw
November 24, 2024 at 6:23 PM
roboima.bsky.social
Accelerate multi-node shared memory and RDMA for distributed #HPC and #AI compute. Intel #SHMEM: GPU-initiated RDMA, following #OpenSHMEM extended with open multi-vendor multiarchitecture #SYCL APIs. Now with Intel #oneAPI HPC Toolkit 2025.1:
www.intel.com/content/www/...
Intel® SHMEM: Multi-Node Data Sharing with SYCL*
Intel® SHMEM: Accelerate Multi-Node Data Sharing for GPUs and SYCL* Devices
www.intel.com
March 31, 2025 at 11:58 PM
aur.archlinux.org.web.brid.gy
nvshmem
NVSHMEM is a software library that implements the OpenSHMEM application programming interface (API) for clusters of NVIDIA ® GPUs.
aur.archlinux.org
July 20, 2025 at 6:25 PM
csdc-bot.bsky.social
supports native overlapping optimizations for distributed AI workloads, providing a good coverage of existing optimizations from different frameworks. First, we integrate communication primitives compliant with the OpenSHMEM standard into the [2/7 of https://arxiv.org/abs/2504.19442v1]
April 29, 2025 at 5:56 AM
mppf.bsky.social
I made a #blog post comparing memory safety across programming languages, with examples! It covers C, C++, Rust, Python, and Chapel. And it discusses memory safety in the context of distributed-memory programming with MPI, Chapel, or OpenSHMEM for #HPC.

chapel-lang.org/blog/posts/m...
Memory Safety in Chapel
A description of how Chapel’s features for memory safety strike a balance between productivity and performance, with comparisons to other languages
chapel-lang.org
April 10, 2025 at 9:29 PM