Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Tsinghua ByteDance: CUDA Agent Beats Human Experts | Flash News Detail
12+ hour, 29+ min ago (158+ words) Tsinghua ByteDance: CUDA Agent Beats Human Experts blockchain.news Tsinghua ByteDance: CUDA Agent Beats Human Experts Tsinghua ByteDance CUDA Agent hits 100% faster PyTorch execution on KernelBench and 40% gains over Claude Opus 4.5, eroding NVIDIA CUDA software moat. Tsinghua University and ByteDance…...
ByteDance Seed and Tsinghua AIR Introduces CUDA Agent: A Large-Scale Agentic RL System for CUDA Kernel Generation
6+ hour, 55+ min ago (200+ words) Partly, but the trained agent is not released. It is built on Seed1.6, a proprietary MoE model with 23B active and 230B total parameters, and the paper ships no weights. Public: the CUDA-Agent-Ops-6K dataset, the SKILL.md spec and the reward and warm-up…...
Overview of the RTOS Kernel Project
15+ hour, 49+ min ago (286+ words) In previous tutorial, I've gave you the theoretical background about ARM Cortex-M3/4 processors. In here, I will explain the RTOS kernel project structure. You can access and inspect the kernel implementation from here. The project gives the end-to-end development environment…...
The GPU that says yes and does nothing: debugging real-time hair segmentation on mid-range Android
18+ hour, 50+ min ago (1010+ words) We build a virtual mirror for hair salons: a tablet camera feed where the customer's hair changes colour in real time while they move their head. Two constraints shaped every decision. The first is privacy: no frame ever leaves the…...
ARM64 BBML3 Feature Ready With Linux 7.3, NVIDIA Olympus Workarounds
22+ hour, 4+ min ago (164+ words) AI/LLM patch craziness hurt ARM64 development for the Linux 7.2 cycle that no real features landed for that kernel version on AArch64. Fortunately, the ARM Linux developers are more prepared now and for Linux 7.3 are introducing some new ARM64 features... - Categories Computers Display…...
Spain Unveils BER10: Europe’s First RISC-V Chip for Supercomputing
1+ day, 15+ hour ago (135+ words) August 17, 2026 - By Lara Carter, russpain.com A Spanish-designed RISC-V chip, BER10, is now available for validation in supercomputing and data center projects. Developed by Openchip, this 64-bit processor aims to boost Europe’s independence in advanced silicon and support future AI accelerators....
NVIDIA, Google and Microsoft Push 800 VDC AI Platforms for Second Half of 2026
2+ day, 6+ min ago (255+ words) NVIDIA is preparing to roll out its first 800 VDC platforms in the second half of 2026, with Google, Microsoft and more than 80 infrastructure companies supporting the shift toward higher-voltage direct current power for large AI data centers. The company says 800 VDC…...
Intel Razor Lake-AX APU reportedly locked for overclocking and based on Nova Lake
1+ day, 21+ hour ago (191+ words) João Silva 2 hours ago CPU Intel's rumoured Razor Lake-AX processor will reportedly not be unlocked for overclocking, according to new details shared by leaker Jaykihn. The chip is set to feature Nova Lake CPU architecture on a large APU platform…...
Marek Olšák's 19 Latest Patches Further Optimizing RADV & ACO
2+ day, 7+ hour ago (164+ words) Legendary Mesa Radeon Gallium3D driver developer Marek Olšák who was a longtime AMD employee and then joined Valve's Linux graphics driver team earlier this year has continued his focus now on perfecting his art around the RADV Vulkan driver and ACO…...
121 Blog Posts To Learn About K8s
2+ day, 11+ hour ago (33+ words) HackerNoon How is it different? Visit the /Learn Repo to find the most read blog posts about any technology. 93 Blog Posts To Learn About Json...