ARM processors have been making forays into hitherto shallow markets, with it’s technology and processor architectures winning an ever increasing amount of design wins. Most recently, Microsoft itself announced a platform meant to use ARM processors in a server environment. Now, ARM has put forward its plans towards achieving a grand total of 100 billion chips shipped in the 2017-2021 time frame.
To put that goal in perspective, ARM is looking to ship as many ARM-powered processors in this 2017-2021 time frame as it did between 1991 and 2017. This is no easy task – at least if ARM were to stay in its known markets, where it has already achieved almost total saturation. The plan: to widen the appeal of its processor design, with big bets in the AI, Automotive, XR (which encompasses the Virtual Reality, Augmented Reality, and Mixed Reality markets), leveraged by what ARM does best: hyper-efficient processors.
Enter DynamIQ, which is ARM’s next-generation processor platform design. It develops upon the BIG.little design, where heterogeneous, high-performance or high power-efficiency clusters stood together in the same chip. This meant that processor designers had to look towards two different power and speed characteristics of the two processor clusters (usually, 4+4 cores). DynamIQ turns the tables by allowing truly heterogeneous clustering of processors: this means companies can now mix and match their choice of high-performance or high efficiency cores in the same processor cluster. Now, there can be up to 8 cores per cluster, each of these cores individually controlled for power and performance. Each core can operate at a specified, different frequency from any other core, thus allowing it to consume just the amount of power needed to complete its given task. Add to this the fact that DynamIQ also allows for advanced memory management (with only the in-use memory banks being on at any given point in time), and performance should increase while power consumption decreases (and isn’t that the holy grail of semiconductors?)
According to the company, DynamIQ technology brings to the table dedicated instructions for both machine learning and AI, which “can be optimized to deliver up to a 50x boost in AI performance over the next 3-5 years relative to Cortex-A73-based systems today.” Expect some more technical details to be let out of the proverbial bag in the coming months. And one can also expect that this kind of advancements in ARM’s designs will only bring more sales and market penetration in emerging opportunities. With Microsoft already on the bandwagon for ARM-powered chips, and with the efficiency levels (and specific instruction set support) of the new DynamIQ design, we should see ARM becoming even more ubiquitous in our daily (and behind the scenes) computing needs. This kind of announcement comes in the wake of news regarding ARM’s owner, SoftBank, selling a 25% stake in the company to a Saudi investment group. With such an announcement being made, and such bold plans for world processing domination, one has to wonder what exactly is SoftBank doing by alienating a property that only looks to value… But maybe they know something we don’t.[small]Source: ARM Community
