Wednesday, April 24, 2024

Stitch: Fastest, independent novel chip for wearables

Wearable technology is one of the biggest innovations in recent time. These are becoming increasingly popular and a key part of our life. These devices allow people to keep track of their physical activity and health, run applications and receive notifications remotely from a smartphone. And in coming years most people worldwide are expected to own at least one of these tiny devices.

However, when compared with smartphones, wearable devices are more limited in terms of their battery size, storage capacity, and computational power. Besides, wearables usually need to be paired with a smartphone in order to function effectively.

To overcome these drawbacks of wearables, NUS Computing researchers led by Professors Tulika Mitra and Peh Li-Shiuan have developed a novel processor chip called “Stitch”.

We are looking for solutions where the wearable device can do everything for you without having to rely on any other device. The challenge is achieving such high performance at low power on a very small device,” said Prof Mitra.

Stitch is a novel processing chip
Stitch is a novel processing chip

Most processor chips used in wearable devices rely mainly on software solutions to carry out their various functions. Whereas Stitch is quite different, it makes the use of both hardware and software solutions.

Software is important as it gives a chip the flexibility to be used across a variety of different applications, whether it is to allow a user to interact with the wearable through finger gestures or to guide a user through his daily commute. Hardware is needed to drive the performance of a wearable device,” Prof Peh explained.

Stitch consists of 16 cores or processing units that are put together on a mesh network. Having a huge, complex hardware accelerator within each core would bulk up the chip. So, the team integrated each core with a tiny accelerator patch that are “stitched” together virtually to create large accelerators.

The creativity in the design also lies in the diversity of the multiple cores of the novel chip. It contains patches with different functionalities, which allows each patch to function individually and follow its own set of instructions or computational patterns.

PhD student Manupa Karunaratne (left) with Professor Tulika Mitra (right).
PhD student Manupa Karunaratne (left) with Professor Tulika Mitra (right).

Compared with LOCUS, a homogeneous-core chip they developed in 2014 when the project first began, Stitch’s performance was two times better despite being 7.5 times smaller.

Also, it chalked remarkably high scores when tested for various applications such as finger gesture recognition, image classification, and pinpointing user location.

The benefit of such a hardware-software co-design is that you get low-power, high-performance across multiple application domains. We now can match the needs of each application to the patch with the corresponding functionality, hence enable the wearable device to perform effectively and independently,” Prof Mitra added.

Yet, the current version of Stitch is unable to perform multiple functions simultaneously. It requires the developer to pre-determine each task.

So, in coming months, the team want to take Stitch one step further, by making the chip more dynamic.