ARM Media Processing Group VP, GM and Fellow, Jem Davies announces the ARM Mali-G72 GPU for Machine Learning, VR & High Fidelity Mobile Gaming. 1 billion Mali-based chips were shipped in 2016, With 1.4x the performance of last year’s ARM Mali-G71 GPU, 17% more performance in machine learning (ML) efficiency, for local offline GPU compute computer vision facilitated by ALU and data path improvements to reduce energy consumed by data movements with 25% higher energy efficiency and 20% better area efficiency, with multiple Bifrost optimizations including increased tile buffer memory, tiler scalability and L1 cache.

For faster ARM Powered laptops, smartphones, servers and more, Nandan Nayampally, GM & VP of ARM’s Compute Processing Group announces the ARM Cortex-A75 and ARM Cortex-A55, the new fastest performance, most power efficient ARM designs for high end performance and for mid-range to entry level processing, the first processors launched on ARM DynamIQ technology, designed from the ground up for AI improvements, low latency, acceleration connections, ARM Cortex-A75 delivers 50% improvement in raw integer performance, even greater gains for specialized workloads at given nanometer manufacturing, with these also working even better on newer smaller nanometer manufacturing making these all that faster. ARM Cortex-A75’s new performance enables faster ARM Powered Laptops and Smartphones with faster performance and better power efficiency, also suitable for infrastructure (servers, networking, more) and self driving cars and other uses in the automotive industry. ARM Cortex-A55 provides the new LITTLE to Cortex-A75’s big, with 2.5x the power efficiency of its predecessor, bringing performance to the edge across a variety of applications and performance points from IOT edge gateways to mainstream. Combining the two new CPUs in a DynamIQ big.LITTLE cluster gives you multiple configurations, and specifically doubles performance in a 1+7 configuration for example.