Search

Showing top 114 results for "AI chips & CUDA"

NVIDIA CUDA

Live now NVIDIA Built Its AVO Coding Agent To Optimize CUDA GPU Kernels, And It Just Achieved A 100% Score On A Public Test Without Receiving Any Prior Instruction

Live sources: WCCFTech

1 live sources Latest signal 1d ago See topic hub

Huawei-led team claims it post-trained DeepSeek's 1.6-trillion-parameter model — 1,000 Ascend 910C chips used in training

…The Ascend 910C is Huawei's current flagship AI accelerator, a dual-die part that returned roughly 60% of an Nvidia H100's inference performance in earlier DeepSeek testing. Chinese chips have…

Jun 6, 2026 · Luke James

Taiwan weighs criminal ban on AI chip exports to all of China — stricter measures beyond blacklisted firms would make smuggling servers a crime

…government plans tariff exemptions for TSMC Nvidia wants China's market share to secure the future of CUDA in the region Taiwan doesn’t currently classify unauthorized AI chip exports to China…

Jun 9, 2026 · Luke James

Surface Laptop Ultra: Initial RTX Spark performance in prototype

…with 48 Streaming Multiprocessors, or 6,144 CUDA cores. This makes RTX Spark not a normal notebook SoC, but rather a compact AI / creator chip with a shared memory architecture. Earlier reports…

Jul 29, 2026 · Karsten Rabeneck-Ketme

Surface Laptop Ultra: Erste RTX-Spark-Leistung im Prototyp

…mit 48 Streaming Multiprocessors beziehungsweise 6.144 CUDA-Kernen. Damit ist RTX Spark kein normaler Notebook-SoC, sondern eher ein kompakter AI-/Creator-Chip mit gemeinsamer Speicherarchitektur. Frühere Berichte nennen für das…

Jul 29, 2026 · Karsten Rabeneck-Ketme

Cadence announced a must-have AI tool for PCB Advanced Packaging – Fudzilla.com

…Agentic AI for Packaging and PCB Design · ai · AI Advanced Packaging · Anirudh Devgan · cadence · Chipstack · ChipStack AI Super Agent · Michael Jackson · Nvidia · PCB design Latest articles News PC Hardware Jul 16, 2026…

Jul 16, 2026 · Fuad Abazovic

NVIDIA Floods Europe With 35 Supercomputers Spanning 23 Countries, Stacking Up To 800 Exaflops Of AI Compute

…The systems will span national supercomputing centers, AI factories, and academic research, harnessing NVIDIA's Quantum InfiniBand Networking, NVIDIA CUDA-X and CUDA-Q libraries, NVIDIA NIM microservices, NVIDIA AI Enterprise Software…

Jun 22, 2026 · Hassan Mujtaba

Wall Street bets Nvidia chips will age like gold – Fudzilla.com

…Nvidia has stretched chip life by regularly updating CUDA, its software platform. CUDA is central to Nvidia’s grip on AI processing, letting customers use GPUs to speed up AI applications. Bajarin…

Aug 13, 2026 · Nick Farrell

China’s Huawei to enter South Korean AI chip market with new Atlas SuperPods, clusters pack 8,192 Ascend 950 accelerators per deployment — reportedly challenges Nvidia dominance with 'tripled inference performance' of H20 at one-quarter the cost

China’s Huawei to enter South Korean AI chip market with new Atlas SuperPods, clusters pack 8,192 Ascend 950 accelerators per deployment — reportedly challenges Nvidia dominance with 'tripled inference performance' of…

Jul 6, 2026 · Etiido Uko

NVIDIA GB200 NVL72 Systems Accelerate the Journey to Useful Quantum Computing

…of quantum hardware with access to state-of-the-art AI supercomputing, such as the capabilities offered by GB200 NVL72. NVIDIA CUDA-Q is such a platform. It can draw on GB200…

Jun 11, 2025 · Timothy Costa

Microsoft and NVIDIA Jointly Tease Possible N1X Debut as a "New Era of PC"

…The chip will feature LPDDR5X interface, with a unified memory architecture. NVIDIA's plan is to outclass Apple M5 Pro and AMD Ryzen AI Max 400. There's nothing in this class…

May 29, 2026

Followed topics