Y Kobayashi「UALink 2.0」仕様が公開：In-Network Collectivesや管理仕様を追加。 オープンなAI相互接続の論点が運用層まで広がる
UALink Consortiumは、AIアクセラレータを接続するオープン規格「UALink 2.0」を公表した。今回の更新では、UALink 1.0で示された低遅延、高帯域のアクセラレータ間接続を土台に、In-Network […]
TECHiU.S. eases AI chip export rules to China Nvidia & AMD win big!
Nvidia resumes H20 GPU sales, AMD reopens MI308 exports. Billions in revenue unlocked, stocks soar
#Nvidia #AMD #AIChips #TechNews #StockMarket #China #GPUs #AITech #CUDA #UALink #Semiconductors #TECHi
Read Full Article Here :- https://www.techi.com/nvidia-amd-stock-rise-us-relaxes-ai-chip-export-to-china/
Benjamin Carr, Ph.D. 👨🏻💻🧬#UALink debuts its first #AI interconnect spec – usable in just 18 short months
Consortium (UAC) was formed in May 2024 by vendors – AMD, AWS, Broadcom, Cisco, Google, HPE, Intel, Meta, Microsoft, and Astera Labs – who think world needs an open alternative to #Nvidia's #NVLink tech that allows creation of networked GPU clusters needed to run AI workloads at scale.
The Ultra Accelerator Link Consortium has delivered first GPU interconnect specification: UALink 200G 1.0.
https://www.theregister.com/2025/04/08/ualink_200g_version_1/
Consortium (UAC) was formed in May 2024 by vendors – AMD, AWS, Broadcom, Cisco, Google, HPE, Intel, Meta, Microsoft, and Astera Labs – who think world needs an open alternative to #Nvidia's #NVLink tech that allows creation of networked GPU clusters needed to run AI workloads at scale.
The Ultra Accelerator Link Consortium has delivered first GPU interconnect specification: UALink 200G 1.0.
https://www.theregister.com/2025/04/08/ualink_200g_version_1/
MacGenerationApple adopte UALink pour accélérer ses centres de données consacrés à l’intelligence artificielle http://dlvr.it/THMt9H #Apple #UALink
Apple adopte UALink pour accélérer ses centres de données consacrés à l’intelligence artificielle
Le consortium Ultra Accelerator Link annonce la nomination de trois nouveaux membres à son conseil d’administration : Alibaba, Synopsys, mais aussi et surtout Apple. La firme de Cupertino adopte ainsi la norme de référence pour l’interconnexion à gra...
HPC Guru#HPC News Bytes: Doug Black and Shahin Khan discuss
The Next New Big Thing in #AI?
#UALink and Optical I/O
Arm vs. Qualcomm courtroom slugfest
insidehpc.com/2024/12/hpc-...
HPC News Bytes: The Next New B...
HPC News Bytes: The Next New B...
HPC GuruDigging Into The Ultra Accelerator Link Consortium
o Nvidia's proprietary #NVLink addresses GPU-to-GPU connectivity
o #UALink looks to broaden this capability across the industry - not just for GPUs, but any accelerator
https://forbes.com/sites/moorinsights/2024/11/07/digging-into-the-ultra-accelerator-link-consortium/
#AMD & #Intel Team Up For #UALink As Open Alternative To #NVIDIA's #NVLink
UALinks aims to be an open standard for scaling of tens to hundreds of #GPU /accelerators within pods. In addition to Intel and AMD, #Broadcom, #Cisco, #Google, #HPE, #Meta, and #Microsoft have also been involved in the formation of the #UltraAcceleratorLink. #UltraEthernet high speed networking will still have its role for #scaleout purposes.
https://www.phoronix.com/news/Ultra-Accelerator-Link-UALink
UALinks aims to be an open standard for scaling of tens to hundreds of #GPU /accelerators within pods. In addition to Intel and AMD, #Broadcom, #Cisco, #Google, #HPE, #Meta, and #Microsoft have also been involved in the formation of the #UltraAcceleratorLink. #UltraEthernet high speed networking will still have its role for #scaleout purposes.
https://www.phoronix.com/news/Ultra-Accelerator-Link-UALink
