AI

Faster on-die memory access for AI processing could spring from a collaboration between network-on-chip intellectual property company Arteris and the Fraunhofer Institute for Experimental Software Engineering (Fraunhofer IESE). Memory access is important with neural network algorithms as their execution requires large quantities of data to be transferred between processing elements and memory, increasing emphasis on the performance of the access ...

AI rock fall detection has been installed on the railway between Dawlish and Dawlish Warren stations in Devon, where it runs beneath cliffs. The “platform uses cutting-edge analytics and machine learning to provide automated incident alerts and previously hidden data insights”, according to Warwick-based infrastructure company Telenet. It “can send incident alerts in real time to station control rooms by ...

Qualcomm has developed a smartphone processor for on-device generative AI. Called Snapdragon 8 Gen 3, “this platform unlocks a new era of generative AI enabling users to generate unique content, help with productivity, and other breakthrough use cases,” claimed company general manager Chris Patrick. Certain large language (LLM) and language vision models (LVM) will be supported locally, as will transformer ...

AI represents 4.3GW of power demand today, according to an estimate by Schneider Electric, growing at a CAGR between 26 and 36%, to reach 13.5 to 20GW by 2028. 4.3GW is about as much as Denmark consumes*. “This growth is two to three times that of overall data center power demand CAGR of 11%,” according to the company. “One key ...

Novocomms, the UK antenna design and manufacturing specialist, has announced it is restructuring as part of growth plans for the next five years, including the establishment of three manufacturing divisions. The plans have the potential to create up to 300 new jobs in Birmingham, said the company. Note that we have already previously reported on 100 of these in June. Operating ...

Infineon has opened a quantum electronics and AI-based power analysis laboratory. Established near Munich, its objectives are to develop and test support ICs for ion trap quantum computers, and to develop AI algorithms for the early detection of variances in power systems. ~20 researchers will be employed, and the lab has a cryostat for research down to 4K (-269°C). One ...

Neurxcore, the French AI processor startup, has launched a Neural Processor Unit (NPU) line for AI inference applications. It is built on an enhanced and extended version of the open-source NVIDIA’s Deep Learning Accelerator (Open NVDLA) technology, combined with patented in-house architectures. The primary focus of the SNVDLA IP  from Neurxcore is  on image processing, including classification and object detection. SNVDLA ...

AI has become a transformative force in various sectors, driving a global wave of innovation and automation, say Ioannis Konstantelos and Dennis Xenos. AI systems have acquired their capabilities through learning, fuelled by training on vast amounts of data. This ongoing revolution prompts the question: what is the next frontier to be conquered? Beyond the novel consumer applications the implications ...

SiFive has announced a pair of high-end RISC-V cores for AI and machine learning in consumer, automotive and infrastructure markets. “Performance P870 and Intelligence X390 offer a new level of low power compute density and vector compute capability, and when combined provide performance for data intensive compute,” according to the company, which is advocating combining the general-purpose scalar P870 with ...

AMD says it will buy Nod.ai to boost its AI capabilities. Nod.ai, a Santa Clara startup, has raised around $36.5 million, says PitchBook. Nod.ai created the SHARK Machine Learning Distribution, which is built on LLVM, MLIR, OpenXLA’s IREE and Nod.ai’s tuning. Nod.ai’s software can accelerate the deployment of AI models across systems using AMD’s Instinct data centre accelerators, Ryzen AI ...