Home Artificial Intelligence Methodology recognized to double pc processing speeds

Methodology recognized to double pc processing speeds

0
Methodology recognized to double pc processing speeds

[ad_1]

Think about doubling the processing energy of your smartphone, pill, private pc, or server utilizing the prevailing {hardware} already in these gadgets.

Hung-Wei Tseng, a UC Riverside affiliate professor {of electrical} and pc engineering, has laid out a paradigm shift in pc structure to do exactly that in a current paper titled, “Simultaneous and Heterogeneous Multithreading.”

Tseng defined that at the moment’s pc gadgets more and more have graphics processing items (GPUs), {hardware} accelerators for synthetic intelligence (AI) and machine studying (ML), or digital sign processing items as important elements. These elements course of info individually, shifting info from one processing unit to the subsequent, which in impact creates a bottleneck.

Of their paper, Tseng and UCR pc science graduate scholar Kuan-Chieh Hsu introduce what they name “simultaneous and heterogeneous multithreading” or SHMT. They describe their growth of a proposed SHMT framework on an embedded system platform that concurrently makes use of a multi-core ARM processor, an NVIDIA GPU, and a Tensor Processing Unit {hardware} accelerator.

The system achieved a 1.96 instances speedup and a 51% discount in vitality consumption.

“You do not have so as to add new processors as a result of you have already got them,” Tseng stated.

The implications are enormous.

Simultaneous use of current processing elements might cut back pc {hardware} prices whereas additionally decreasing carbon emissions from the vitality produced to maintain servers working in warehouse-size information processing facilities. It additionally might cut back the necessity for scarce freshwater used to maintain servers cool.

Tseng’s paper, nevertheless, cautions that additional investigation is required to reply a number of questions on system implementation, {hardware} help, code optimization, and how much functions stand to learn essentially the most, amongst different points.

The paper was introduced on the 56th Annual IEEE/ACM Worldwide Symposium on Microarchitecture held in October in Toronto, Canada. The paper garnered recognition from Tseng’s skilled friends within the Institute of Electrical and Electronics Engineers, or IEEE, who chosen it as one in all 12 papers included within the group’s “Prime Picks from the Laptop Structure Conferences” situation to be revealed this coming summer season.

[ad_2]