#hpc

[ follow ]
#supercomputing
Business
from24/7 Wall St.
5 days ago

Can TSM's Stock Reach $600 By 2028?

TSM reports record margins and robust AI-driven HPC demand, but valuation, geopolitical risks, and margin pressures limit near-term upside despite bullish price targets.
Tech industry
fromTheregister
4 months ago

How Nvidia is using emulation to turn AI FLOPS into FP64

Nvidia achieves higher FP64 throughput through software emulation on Rubin GPUs, trading hardware FP64 for emulated matrix performance up to 200 TFLOPS.
Artificial intelligence
fromTheregister
5 months ago

Nvidia pledges more openness as it slurps up Slurm

Nvidia acquired SchedMD, committed to keep Slurm open-source and vendor-neutral, and launched Nemotron 3 MoE AI models spanning 30B to 500B parameters.
#ai
Gadgets
fromTheregister
6 months ago

HPE details Vera Rubin blades for next-gen Cray

HPE's Cray GX5000 offers configurable liquid-cooled racks with Nvidia Vera+Rubin or AMD Venice Epyc compute blades for mixed-precision HPC and large CPU-only clusters.
fromTheregister
7 months ago

NextSilicon eyes HPC market with Maverick-2 accelerators

Researchers and engineers working in particle physics, materials analysis, or drug discovery haven't exactly been spoiled for choice when it comes to chips capable of the highly precise double-precision calculations that these workloads depend. NextSilicon aims to change that with Maverick-2, a chip aimed not at AI but the high-performance computing (HPC) community. This week, the chip startup offered the best look yet at how its dataflow accelerators - now deployed by several customers, including Sandia National labs - hold up in the wild,
Tech industry
Tech industry
fromTechzine Global
10 months ago

Broadcom launches Tomahawk Ultra with 250ns network latency

Broadcom's Tomahawk Ultra switch achieves 250ns latency and 51.2 Tbps throughput, eliminating packet loss and optimizing Ethernet for HPC and AI.
#supercomputers
[ Load more ]