Imagination Technologies

Imagination: Back in Black

Imagination Technologies is on its fourth CEO in three years, is in the process of losing its major customer, and is still dealing with the aftermath of the disastrous acquisition and subsequent fire-sale disposal of MIPS.  A job like that seems nearer the nightmare than the dream job end of the spectrum so I took advantage of the whole world … Read more

First look at the Arm Machine Learning Processor

Arm chose this year’s IEEE Hot Chips Symposium to show off their first-generation Machine Learning Processor claiming a design that delivers ‘massive’ efficiency improvements over GPU, CPU, or DSP implementations as well as the ability to scale from IoT to server applications. Being an English design, it probably serves tea in a porcelain cup, as well. Leaving aside the issue … Read more

Talent Wars

The revolving doors in Silicon Valley are nothing new, but within the last two or so years the migration at the superstar techno level has been particularly intense—especially in the GPU and CPU space. Some recent examples: Martin Ashton served as EVP of PowerVR Multimedia IP at Imagination Technologies Group Plc until December 1, 2016 where he was instrumental in … Read more

New boss at Imagination Technologies

Sends a strong message about the company’s future. Imagination Technologies announced this week that Dr. Leo Li will be the company’s Chief Executive Officer. That is very good news for Imagination, its suppliers, shareholders, employees, and friends. Dr. Li is Chairman of the Global Semiconductor Alliance and a well-known and respected figure in the semiconductor industry. He has over 30 … Read more

Imagination introduces its own VPU

New NNA steps up to compete in ML Citing the burgeoning intelligent vision market, Imagination Technologies announced on September 21st that it has joined the ever-growing list of companies with hardware acceleration for deep learning. Up to now, they have relied on their PowerVR GPUs running in GPU compute mode to provide an ad hoc solution for inferencing but with … Read more