Last updated by
The future of AI is ... analog? Upstart bags $100M to push GPU-like brains on less juice
Interview EnCharge claims 150 TOPS/watt, a 20x performance-per-watt edge
AI + ML17 Feb 2025 | 17
TOPS
TOPS is short for Trillion Operations Per Second. In the context of AI, each operation typically uses INT8 values, which are each equivalent to signed bytes. Thus TOPS is a measurement of AI performance by hardware and software. An AI system capable of 40 TOPS is expected to perform 40 trillion operations per second using INT8 precision.
Intel debuts laptop silicon that doesn't qualify for Microsoft's 'Copilot+ PC' badge
CES TOPS, SCHMOPS, says Chipzilla, our NPUs may be slow but that doesn't matter
Systems07 Jan 2025 | 19
Intel's 120 TOPS Lunar Lake AI PC chips have landed
And all it took was some good old fashioned outsourcing to TSMC
AI + ML03 Sep 2024 | 11
The definition of an AI PC is now even muddier, helping no-one – not even AIs
Computex Analysis Intel CEO Pat Gelsinger wants benchmarks to go beyond TOPS but warns we’re in for months of uncertainty
Personal Tech05 Jun 2024 | 9
Intel details how Lunar Lake PC chips deliver 120 TOPS
Computex A bigger NPU, faster graphics core in GPU, and on-package memory will do that to a chip
Personal Tech04 Jun 2024 | 2
We're the Ryzen force in CPUs for AI PCs: AMD
Computex Arm, schmarm: New 50TOPS NPUs that talk Block FP16 really make AI sing, says CEO Lisa Su
Systems03 Jun 2024 |
BROADER TOPICS
Why Microsoft's Copilot will only kinda run locally on AI PCs for now
Comment Redmond’s strategy for blending cloud and client is finally taking shape
AI + ML31 Mar 2024 | 39
AI PC hype seems to be making PCs better – in hardware terms, at least
Comment 16GB of RAM should be enough for anyone that wants to run models locally. GPUs, NPUs and more kit will be needed, too
Personal Tech23 Jan 2024 | 40
Biting the hand that feeds IT
