The Neoverse N1 CPU is optimized for a wide range of cloud native server workloads executing at a world-class compute efficiency. This enables an infrastructure transformation where processing is pushed to the edge where data is generated, thereby providing more scalability than moving all data to centralized datacenters.
The Arm Neoverse E1 CPU delivers best-in-class throughput efficiency. It incorporates a new simultaneous multithreading (SMT) microarchitecture design. With SMT, the processor can execute two threads concurrently resulting in better aggregate throughput performance.
The Neoverse E1 delivers 2.1x more compute performance, 2.7x more throughput performance and 2.4x better throughput efficiency compared to the Cortex-A53. The design is highly scalable to support throughput demands for next generation edge to core data transport.
Todd Kjos of the Android Kernel team at Google, and Bero of the Linaro Mobile Group, talk at Linaro Connect Vancouver, they talk about running Android on the mainline kernel, trying to get closer to mainline, enabling test boards and devices to run mainline Linux. Getting some of the Android specific things that were kept out of the tree into the Linux tree.
Archos Diamond has a 6.39" HD+ 2160x1080 AMOLED display, powered by the MediaTek Helio P70 ARM Cortex-A73/A53 octa-core CPU with an ARM Mali-G72 GPU. Archos Oxygen 68 at 149eur, 63 at 129eur, 57 at 99eur. Archos also shows their Amazon Alexa smart speakers, the 19.90eur Archos Smart LED Lights that work with Google Assistant and Amazon Alexa. Archos 101S Oxygen Tablet based on MediaTek X20 deca-core with 3GB RAM and 32GB Flash, comes with a special charging and speaker dock.
Jem Davies, ARM VP, Fellow and GM, Machine Learning Group talks about ARM's new Helium Machine Learning architecture for the ARM Cortex-M based microcontrollers, as a follow on to ARM CMSIS-NN Neural Network Kernels which Boosted Efficiency in Microcontrollers by 5x last year, now ARM launches Helium ARMv8.1-M to improve machine learning performance, with up to 50x on machine learning workloads, about 5x improvement in performance for regular DSP based workloads, as open source software and the new ARMv8.1-M architecture to be integrated in Microcontroller designs to come in the future.