GPU News & Updates
The latest news articles relevant to datacenter GPUs, systems and the things that will impact the engineers working to bring AI to life.
New Provider: GPU Mart Monthly GPU Servers Now on Flopper
GPU Mart is now a Verified provider on Flopper, and the first in our new monthly GPU server section: 37 plans from $29 a month, on 1-month to 2-year terms.
Skynet Ran at 60 Teraflops. That Is One Gaming GPU Now.
In Terminator 3 (2003), Skynet runs at "60 teraflops per second", which beat the fastest computer on Earth at the time. In 2026 that is one RTX 4090, or 1/18,000th of a GB300 NVL72 rack at FP4. Count in FP64, the precision a 2003 supercomputer meant, and the whole rack is only 1.7 Skynets. A Halloween look at why a TFLOPS figure without a precision is a plot device, not a spec.
New Provider: Lium.io Prices Now Available
Lium is now a Verified provider on Flopper. Live prices for 20 GPU models, Secure and Spot tiers, SSH and Docker access, and an API built for AI agents.
Dense vs Sparse TFLOPS: How to Read a 2:4 Sparsity Figure
Structured 2:4 sparsity doubles a tensor-core TFLOPS figure on paper. Where the 2x comes from, when it applies, and which number to compare.
How to Set Up NVIDIA DCGM for GPU Metrics on Ubuntu
Install NVIDIA DCGM on Ubuntu 22.04 or 24.04, start the host engine, read tensor and memory activity with dcgmi, and export it all to Prometheus.
NVIDIA Wants GPU Code to Care Less About the GPU
NVIDIA is bringing native Rust support to CUDA with two projects, cuda-oxide and cutile-rs. The bigger story may be CUDA Tile, a programming model where developers describe operations on tiles of data and the compiler decides how they map onto the GPU. The hardware differences between an A100, an H100 and a B200 are not going anywhere, but software may need to know less about them.
Stay Updated
Get the latest GPU news and benchmarks delivered to your inbox