ARM on Monday announced a new chip design targeting high-performance computing -- an update to its ARMv8-A architecture, known as the Scalable Vector Extension (SVE). The new design significantly extends the vector processing capabilities associated with AArch64 (64-bit) execution, allowing CPU designers to choose the most appropriate vector length for their application and market, from 128 to 2048 bits. SVE will also allow advanced vectorizing compilers to extract more fine-grain parallelism from existing code. "Immense amounts of data are being collected today in areas such as meteorology, geology, astronomy, quantum physics, fluid dynamics, and pharmaceutical research," ARM fellow Nigel Stephens wrote. HPC systems over the next five to 10 years will shoot for exascale computing, he continued.
Edge computing stands to transform the internet of things (IoT) much the same way that cloud computing is transforming enterprise IT. By creating secure, highly programmable and flexible computing systems that enhance both artificial intelligence (AI) and machine learning (ML), we help usher in the era of local AI, where edge nodes are not only smart, but are trained to be aware of their environment and situation, making them capable of operating offline or with limited cloud connectivity. NXP platforms offer secure edge computing at the hardware and software level, providing the essential technologies that enable low-power, low-latency, high-throughput solutions to deliver greater efficiencies, convenience, privacy and security.
Edge Computing, sometimes referred to as Mobile Edge Computing or Multi-Access Edge Computing, uses physical locations to deliver powerful computational and data storage solutions for IoT and cloud-based devices. Edge computing allows for lower latency rates and the ability to handle much more data than traditional cloud-based technologies.
I saw a video article on Neuromorphic Computing the other day - something I had not really heard much about, though it ties in heavily to Artificial Intelligence which I, of course, do know about. Wow.. the possibilities are now endless. This is what Techopedia says about Neuromorphic Computing... Neuromorphic computing utilizes an engineering approach or method based on the activity of the biological brain. This type of approach can make technologies more versatile and adaptable, and promote more vibrant results than other types of traditional architectures, for instance, the von Neumann architecture that is so useful in traditional hardware design. Neuromorphic computing is also known as neuromorphic engineering.