ARM just announced 2 new processors, ready to take on Machine Learning and AI. These would be the first processors in their portfolio to be based on ARM DynamIQ tehcnology, boosting AI performance over 50x over the next 3-5 years.
ARM DynamIQ technology was first introduced in March. Now adopting the technology in their product line, the ARM Cortex-A75 and Cortex-A55 processors both come with dedicated instructions for AI performance tasks via DynamIQ technology; increased multicore functionality and flexibility in a single compute cluster with DynamIQ big.LITTLE; ARM TrustZone technology, to fortify the SoC (System on Chip) in edge devices; and increased functional safety capabilities for ADAS and autonomous driving.
Cortex-A75
The Cortex-A75 delivers massive single-thread compute uplift at a massive 50 percent uplift in performance and greater multicore capabilities, enabling multiple high-performance use cases including laptops, networking and servers, all within a smartphone power profile.
Cortex-A55
With dedicated AI instructions and up to 2.5x the performance-per-milliwatt efficiency relative to today’s Cortex-A53 based devices, the Cortex-A55 is the world’s most versatile high-efficiency processor.
Mali-G72 GPU
It’s not just the processors that get an upgrade – ARM is also beefing up the Mali-G72 GPU, with the new design made for demanding use cases of ML on device, as well as High Fidelity mobile gaming and mobile VR with 40 percent more performance. The new design also provides the most efficient and perfomant ML thanks to arithmetic optimisations and increased caches, thus reducing bandwidth for a 17 percent ML efficiency gain.
With 25 percent higher energy efficiency, 20 percent better performance density, and the new ML optimizations, ARM can distribute intelligence more efficiently across the SoC.
Flexible big.LITTLE performance
DynamIQ big.LITTLE provides more multicore flexibility across more tiers of performance and user experiences by enabling configuration of big and LITTLE processors on a single compute cluster for the first time.
The flexibility of DynamIQ big.LITTLE is at the heart of the system-level approach distributed intelligence requires. The combination of flexible CPU clusters, GPU compute technology, dedicated accelerators, and the new ARM Compute Library work together to efficiently enhance and scale AI performance. The free, open-source ARM Compute Library is a collection of low-level software functions optimized for Cortex CPU and Mali GPU architectures. On the CPU alone, ARM Compute Library can boost performance of AI and ML workloads by 10x-15x on both new and existing ARM-based SoCs.
Along with this release, ARM also announced a software development environment, where the ecosystems has the opportunity to develop software optimised for DynamIQ ahead of hardware availability through a combination of ARM virtual prototypes and DS-5 Development Studio.
