The Role of Memories in Transprecision Computing

Weis, Christian; Jung, Matthias; Zulian, Éder F.; Sudarshan, Chirag; Mathew, Deepak M.; Wehn, Norbert

doi:10.1109/iscas.2018.8351768

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A class of very promising approaches, generally called approximate memory techniques, is based on allowing controlled occurrence of errors in memory cells. 2 The effective introduction of approximate memory units in a hardware platform relies on the possibility of using them for allocating selected data structures in software applications. Although memory errors may degrade the quality of output results, the effects can be tolerated by applications known as ETAs (error tolerant applications).…”

Section: Introductionmentioning

confidence: 99%

Full System Emulation of Approximate Memory Platforms with AppropinQuo

Stazi¹,

Mastrandrea²,

Olivieri³

et al. 2019

Journal of Low Power Electronics

View full text Add to dashboard Cite

In this work we present an emulation framework for hardware platforms provided with approximate memory units, called AppropinQuo. The specific characteristic of AppropinQuo is to reveal the effects, on the hardware platform and on software, of errors introduced by approximate memory circuits and architectures. The emulator allows to execute software code without any modification with respect to the target physical board, since it includes the CPU, the memory hierarchy and the peripherals, capturing as well software-hardware interactions and faults due to approximate memory units. The final scope is reproducing the effects of errors generated by approximate memory circuits, allowing to evaluate the impact (quality degradation) on the output produced by the software. In fact, output quality is related to error rate, but their relationship strongly depends on the application, the implementation and its data representation on physical memory. The idea behind approximate memory circuits and approximate computing in general is to trade off energy consumption at the expense of computational accuracy and degradation of output quality. Memory is accounted for a large part of total power consumption in advanced architectures and it is supposed to increase as new memory hungry applications migrate toward the implementation on embedded systems (embedded machine learning, high definition video codecs, etc.). By relaxing design constraints regarding error probability on bit cells, researchers have proposed techniques that significantly reduce memory energy consumption. These techniques, which can be accounted in the general topic of approximate memory design, are implemented at circuit or architecture level, and are specific to the memory technology (i.e., SRAM or DRAM memories). However, the level of acceptable output degradation is the final metric that must be used to assess if, and to what extent, an approximate memory technique can be introduced. Our emulator allows to run actual applications as on the physical platform, to expose the effects of specific approximate memory circuits and architectures on output quality and to vary their parameters (e.g., error rate, number of affected bits, etc.). By exploring the approximate memory design space and its effects on the output of a software application, it is possible to characterize the application behavior, as a step toward the determination of the trade-off between saved energy and output quality (energy-quality tradeoff).

show abstract

Section: Introductionmentioning

confidence: 99%

Full System Emulation of Approximate Memory Platforms with AppropinQuo

Stazi¹,

Mastrandrea²,

Olivieri³

et al. 2019

Journal of Low Power Electronics

View full text Add to dashboard Cite

show abstract

“…Techniques for reducing energy consumption in SRAM and DRAM memories have been proposed in many works. A class of very promising approaches, generally called approximate memory techniques, is based on allowing controlled occurrence of errors in memory cells [2]. Although errors may degrade quality of output results, the effects can be tolerated by many applications, known as ETAs (error tolerant applications) [3].…”

Section: Introductionmentioning

confidence: 99%

AppropinQuo: A Platform Emulator for Exploring the Approximate Memory Design Space

Stazi

Mastrandrea

Olivieri

et al. 2018

2018 New Generation of CAS (NGCAS)

View full text Add to dashboard Cite

In this work we present AppropinQuo, a flexible and configurable emulator for embedded platforms with approximate memory. The emulator includes models of the effects of approximate memory circuits and architectures, that depend on the internal structure and organization of the cells. The ability to emulate a complete platform, including CPU, peripherals and hardware-software interactions, is particularly important since it allows to execute the application as on the real board, reproducing the effects of errors on output. In fact, output quality is related not only to error rate but it also depends on the application, implementation and its data representation.AppropinQuo allows to run actual applications and operating system as on the physical platform, to analyze the behavior and to expose the effects of specific approximate memory circuits and architectures on output quality. By exploring the design space regarding approximate memories, a complete characterization of the application is possible, as a step toward the determination of the trade-off between saved energy and output quality (energyquality tradeoff).

show abstract

“…Configuration interfaces act to prevent such waste of effort by controlling the probability of error insertion in the computation or recalibrating the approximation at runtime [56,129]. The configuration of an approximate memory is application-specific and depends on memory access patterns of the application [126]. Several configuration interfaces [56,77,112,129,130] also depend on annotations or on application-specific metrics to evaluate the acceptance of the results and adjust the parameters of the approximation as knobs.…”

Section: Approximate Memoriesmentioning

confidence: 99%

Software and hardware interfaces for approximate memories

Fabrício Filho

View full text Add to dashboard Cite

I would like to thank the many people that give me support during this Ph.D.To my wife, Aline Maria Gonçalves Fabrício, for walking alongside me on this journey giving me support, and making me happy every day.To my advisor Lucas Wanner, for all the mentoring and guidance that were fundamental in formulating research questions and in my professional development.To Isaías Bittencourt Felzmann, for the feedback, ideas, collaborations on manuscripts, and the several discussions about the topics of this research.To Rodolfo Azevedo, for the support that improves the contributions of this work.

show abstract

The Role of Memories in Transprecision Computing

Cited by 4 publications

References 12 publications

Full System Emulation of Approximate Memory Platforms with AppropinQuo

Full System Emulation of Approximate Memory Platforms with AppropinQuo

AppropinQuo: A Platform Emulator for Exploring the Approximate Memory Design Space

Software and hardware interfaces for approximate memories

Contact Info

Product

Resources

About