tag: accelerators

The High But Often Unnecessary Cost Of Coherence
By Brian Bailey - 22 Dec, 2021 - Comments: 4

Cache coherency, a common technique for improving performance in chips, is becoming less useful as general-purpose processors are supplemented with, and sometimes supplanted by, highly specialized accelerators and other processing elements. While cache coherency won't disappear anytime soon, it is increasingly being viewed as a luxury necessary to preserve a long-standing programming paradig... » read more

Bandwidth Utilization Side-Channel On ML Inference Accelerators
By Arm - 10 Nov, 2021 - Comments: 0

Abstract—Accelerators used for machine learning (ML) inference provide great performance benefits over CPUs. Securing confidential model in inference against off-chip side-channel attacks is critical in harnessing the performance advantage in practice. Data and memory address encryption has been recently proposed to defend against off-chip attacks. In this paper, we demonstrate that bandwidth... » read more

New Approaches For Processor Architectures
By Ed Sperling - 26 Aug, 2021 - Comments: 0

Processor vendors are starting to emphasize microarchitectural improvements and data movement over process node scaling, setting the stage for much bigger performance gains in devices that narrowly target what end users are trying to accomplish. The changes are a recognition that domain specificity, and the ability to adjust or adapt designs to unique workloads, are now the best way to impro... » read more

Working With RISC-V
By Ed Sperling - 17 Aug, 2021 - Comments: 0

RISC-V is coming on strong, but working with this open-source processor core isn't as simple as plugging in a commercial piece of IP. Zdenek Prikryl, CTO at Codasip, talks about utilizing hypervisors and open source tools and extensions to the RISC-V instruction set architecture, where design teams can run into problems, what will change as the architecture becomes more mature, the difference b... » read more

New Power, Performance Options At The Edge
By Heidi Elliott - 21 Jul, 2021 - Comments: 0

Increasing compute intelligence at the edge is forcing chip architects to rethink how computing gets partitioned and prioritized, and what kinds of processing elements and memory configurations work best for a particular application. Sending raw data to the cloud for processing is both time- and resource-intensive, and it's often unnecessary because most of the data collected by a growing nu... » read more

An Introduction To Domain-Specific Accelerators
By Roddy Urquhart - 24 Jun, 2021 - Comments: 0

After 50 years, Moore’s Law, Dennard Scaling, and Amdahl’s Law are failing. The semiconductor industry much change, and processor paradigms must change with it. So what exactly are domain-specific accelerators and why are they so important in light of the failure of these semiconductor scaling laws? » read more

Shifting Toward Data-Driven Chip Architectures
By Ed Sperling and Ann Mutschler - 16 Jun, 2021 - Comments: 0

An explosion in data is forcing chipmakers to rethink where to process data, which are the best types of processors and memories for different types of data, and how to structure, partition and prioritize the movement of raw and processed data. New chips from systems companies such as Google, Facebook, Alibaba, and IBM all incorporate this approach. So do those developed by vendors like Appl... » read more

Customizing Chips For Power And Performance
By Ed Sperling - 10 Jun, 2021 - Comments: 0

Sandro Cerato, senior vice president and CTO of the Power & Sensor Systems Business Unit at Infineon Technologies, sat down with Semiconductor Engineering to talk about fundamental shifts in chip design with the rollout of the edge, AI, and more customized solutions. What follows are excerpts of that conversation. SE: The chip market is starting to fall into three distinct buckets, the e... » read more

The Road To Domain-Specific Accelerators
By Roddy Urquhart - 27 May, 2021 - Comments: 0

For about fifty years, IC designers have been relying on different types of semiconductor scaling to achieve gains in performance. Best known is Moore’s Law, which predicted that the number of transistors in a given silicon area and clock frequency would double every two years. This was combined with Dennard scaling, which predicted that with silicon geometries and supply voltages shrinki... » read more

Shifting Auto Architectures
By Ed Sperling - 29 Apr, 2021 - Comments: 0

Domain controllers and gateways are being replaced by central processing modules and zonal gateways to handle all of the data traffic in a vehicle. Ron DiGiuseppe, automotive IP segment manager at Synopsys, talks with Semiconductor Engineering about how automotive applications are changing, what that means for engineering teams, and how they will shift as AI is increasingly deployed. » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2026 SMG   |  Terms of Service  |  Privacy Policy