American startup Substrate promises 2nm-class chipmaking with particle accelerators, at a tenth of the cost of EUV — X-ray lithography system has potential to surpass ASML’s EUV scanners

[ad_1] American startup Substrate is developing a new X-ray lithography (XRL) system, powered by a particle accelerator-based light source, that promises superior performance and cost efficiency compared to standard EUV lithography, aiming to achieve resolutions equivalent to ASML’s 2nm-class processes. The firm also claims it can advance beyond that. Substrate also claims that its efforts…

Read More

MLPerf Inference v5.1 (2025): Results Explained for GPUs, CPUs, and AI Accelerators

[ad_1] What MLPerf Inference Actually Measures? MLPerf Inference quantifies how fast a complete system (hardware + runtime + serving stack) executes fixed, pre-trained models under strict latency and accuracy constraints. Results are reported for the Datacenter and Edge suites with standardized request patterns (“scenarios”) generated by LoadGen, ensuring architectural neutrality and reproducibility. The Closed division…

Read More