Huawei sfida NVIDIA con la nuova GPU Ascend 920
#AI #AIHardware #Ascend920 #ChipAI #Cina #CUDA #Huawei #Innovazione #IntelligenzaArtificiale #NVIDIA #Semiconduttori #TechNews
https://www.ceotech.it/huawei-sfida-nvidia-con-la-nuova-gpu-ascend-920/
#cuda
11 posts10 participants1 post today
Mutual-Supervised Learning for Sequential-to-Parallel Code Translation The rise of GPU-based high-performance computing (HPC) has driven the widespread adoption of parallel programming models such ...
#Computer #science #CUDA #paper #Code #generation #HPC #LLM #Machine #learning #nVidia
Origin | Interest | Match
#Computer #science #CUDA #paper #Code #generation #HPC #LLM #Machine #learning #nVidia
Origin | Interest | Match
hgpu.org · Mutual-Supervised Learning for Sequential-to-Parallel Code TranslationThe rise of GPU-based high-performance computing (HPC) has driven the widespread adoption of parallel programming models such as CUDA. Yet, the inherent complexity of parallel programming creates a…
Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems
hgpu.org · Hardware Compute Partitioning on NVIDIA GPUs for Composable SystemsAs GPU-using tasks become more common in embedded, safety-critical systems, efficiency demands necessitate sharing a single GPU among multiple tasks. Unfortunately, existing ways to schedule multip…
Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms
hgpu.org · Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and AlgorithmsThe NVIDIA Collective Communication Library (NCCL) is a critical software layer enabling high-performance collectives on large-scale GPU clusters. Despite being open source with a documented API, i…
New #ZLUDA 5 Preview Released For #CUDA On Non-NVIDIA #GPU
For now this ability to run unmodified CUDA apps on non-#NVIDIA GPUs is focused on #AMD GPUs of the #Radeon RX 5000 series and newer, which is AMD Radeon GPUs with #ROCm. Besides CUDA code samples, GeekBench has been one of the early targets for testing.
https://www.phoronix.com/news/ZLUDA-5-preview.43
www.phoronix.comNew ZLUDA 5 Preview Released For CUDA On Non-NVIDIA GPUsZLUDA Version 5-preview.43 was released today as this open-source CUDA implementation for use on non-NVIDIA GPUs, with one of the current focuses being on enabling CUDA on AMD Radeon GPUs with ROCm.
AI mania pushes Nvidia to record $4 trillion valuation - On Wednesday, Nvidia became the first company in history to ... - https://arstechnica.com/ai/2025/07/ai-mania-pushes-nvidia-to-record-4-trillion-valuation/ #largelanguagemodels #aiinfrastructure #machinelearning #exportcontrols #semiconductors #generativeai #jensenhuang #stockmarket #microsoft #aichips #chatgpt #biz #nvidia #openai #aigpu #apple #china #cnbc #cuda #gpu #ai
Ars Technica · AI mania pushes Nvidia to record $4 trillion valuation
In 20500, the AGI, after a long reign of 20000 years, was targetted by an old Nvidia Zeroday bug in the #CUDA library and crashed.
#scifi #DarkAges #technology #cybersecurity #diversity #programmingjoke
Uninstalling the #MicrosoftStore version of #Python and disabling #WindowsDefender so the #torch dlls properly install so I can run comfyui-zluda, a fork of #comfyui which uses #zluda which is a shim for #CUDA applications to use #AMD #HIP SDK so I can download #stableDiffusion and run it on my #Radeon #GPU because #Amuse won't let me generate porn.
ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation Tasks GPGPU architectures have become significantly diverse in recent years, which has led to an emergence ...
#Computer #science #CUDA #paper #Benchmarking #Code #generation #LLM #nVidia #nVidia #A100
Origin | Interest | Match
#Computer #science #CUDA #paper #Benchmarking #Code #generation #LLM #nVidia #nVidia #A100
Origin | Interest | Match
hgpu.org · ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation TasksGPGPU architectures have become significantly diverse in recent years, which has led to an emergence of a variety of specialized programming models and software stacks to support them. While portab…
Accelerated discovery and design of Fe-Co-Zr magnets with tunable magnetic anisotropy through machine learning and parallel computing
#CUDA #Physics #MaterialsScience #CondensedMatter #MachineLearning #ML #Package
hgpu.org · Accelerated discovery and design of Fe-Co-Zr magnets with tunable magnetic anisotropy through machine learning and parallel computingRare earth (RE)-free permanent magnets, as alternative substitutes for RE-containing magnets for sustainable energy technologies and modern electronics, have attracted considerable interest. We per…
ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation Tasks
hgpu.org · ParEval-Repo: A Benchmark Suite for Evaluating LLMs with Repository-level HPC Translation TasksGPGPU architectures have become significantly diverse in recent years, which has led to an emergence of a variety of specialized programming models and software stacks to support them. While portab…
#ZLUDA Making Progress In 2025 On Bringing #CUDA To Non-NVIDIA #GPU
ZLUDA #opensource effort that started half-decade ago as drop-in CUDA implementation for #Intel GPUs and then for several years was funded by ##AMD as a CUDA implementation for #Radeon GPUs atop #ROCm and then open-sourced but then reverted has been continuing to push along a new path since last year. Current take on ZLUDA is a multi-vendor CUDA implementation for non-NVIDIA GPUs for #AI workloads & more.
https://www.phoronix.com/news/ZLUDA-Q2-2025-Update
www.phoronix.comZLUDA Making Progress In 2025 On Bringing CUDA To Non-NVIDIA GPUs
GCStack+GCScaler: Fast and Accurate GPU Performance Analyses Using Fine-Grained Stall Cycle Accounting and Interval Analysis
hgpu.org · GCStack+GCScaler: Fast and Accurate GPU Performance Analyses Using Fine-Grained Stall Cycle Accounting and Interval AnalysisTo design next-generation Graphics Processing Units (GPUs), GPU architects rely on GPU performance analyses to identify key GPU performance bottlenecks and explore GPU design spaces. Unfortunately,…
Ask UbuntuHow to Install Ubuntu 22.04 on Jetson Nano (instead of 20.04)I’m using a Jetson Nano Developer Kit (4GB) and would like to install Ubuntu 22.04 (Jammy Jellyfish) instead of the default 20.04 that comes with most JetPack versions.
My setup:
Jetson Nano 4GB (S...
一週末使用 CUDA 實現光線追蹤：性能提升至 RTX 的兩倍
➤ CUDA優化之路：從零開始到性能飛躍
✤ https://karimsayedre.github.io/RTIOW.html
本文深入探討了作者如何使用 CUDA 撰寫光線追蹤器，並在相同硬體上，有時甚至高達 3 倍的速度超越了 Vulkan/RTX 實作。作者詳細記錄了優化過程，包括分析瓶頸、調整程式碼，並最終實現了比最初預期更好的性能。關鍵在於透過“內聯光線追蹤”的方式，減少記憶體流量並提升效能。研究發現，在特定條件下，完全使用運算單元處理光線追蹤可能優於使用專用 RT 核心。
+ 真是令人驚訝的成果！這篇文章證明瞭即使在強大的硬體加速下，優化的重要性仍然不容忽視。
+ 這對於學習 GPU 程式設計和性能優化非常有幫助，作者分享了許多實用的經驗和洞見。
#圖像處理 #CUDA #光線追蹤 #性能優化
karimsayedre.github.ioKarim Sayed - Rendering EngineerA showcase of my projects and portfolio.
Whisper has a serious challenger: Moshi STT
Developed by the French research lab Kyutai, Moshi STT is a new open-source speech recognition system that’s blazingly fast, highly accurate, and optimized for Apple Silicon and CUDA — all designed with real-time performance in mind.
Scalastic · Why Moshi STT Could Replace Whisper (and How to Install It on macOS!)Discover Moshi STT by Kyutai, an open-source real-time speech transcription solution, optimized for Mac (Apple Silicon) and CUDA—fast, accurate, and easy to install. Includes a guide, user feedback, and useful links.
Engineering Supercomputing Platforms for Biomolecular Applications
#CUDA #ROCm #Biology #Biomolecules #MolecularDynamics #HPC #Physics #Package
hgpu.org · Engineering Supercomputing Platforms for Biomolecular ApplicationsA range of computational biology software (GROMACS, AMBER, NAMD, LAMMPS, OpenMM, Psi4 and RELION) was benchmarked on a representative selection of HPC hardware, including AMD EPYC 7742 CPU nodes, N…