A survey of techniques for modeling and improving reliability of computing systems
Recent trends of aggressive technology scaling have greatly exacerbated the occurrences
and impact of faults in computing systems. This has madereliability'a first-order design …
and impact of faults in computing systems. This has madereliability'a first-order design …
Verifying quantitative reliability for programs that execute on unreliable hardware
Emerging high-performance architectures are anticipated to contain unreliable components
that may exhibit soft errors, which silently corrupt the results of computations. Full detection …
that may exhibit soft errors, which silently corrupt the results of computations. Full detection …
Chisel: Reliability-and accuracy-aware optimization of approximate computational kernels
The accuracy of an approximate computation is the distance between the result that the
computation produces and the corresponding fully accurate result. The reliability of the …
computation produces and the corresponding fully accurate result. The reliability of the …
Asac: Automatic sensitivity analysis for approximate computing
The approximation based programming paradigm is especially attractive for develo**
error-resilient applications, targeting low power embedded devices. It allows for program …
error-resilient applications, targeting low power embedded devices. It allows for program …
Approximate circuits
Approximate computing has emerged as a new paradigm to reduce the resources (eg,
design area and power) required to realize digital systems at the expense of a negligible or …
design area and power) required to realize digital systems at the expense of a negligible or …
Harnessing soft computations for low-budget fault tolerance
A growing number of applications from various domains such as multimedia, machine
learning and computer vision are inherently fault tolerant. However, for these soft workloads …
learning and computer vision are inherently fault tolerant. However, for these soft workloads …
Mitigating silent data corruptions in HPC applications across multiple program inputs
With the ever-shrinking size of transistors, silent data corruptions (SDCs) are becoming a
common yet serious issue in HPC. Selective instruction duplication (SID) is a widely used …
common yet serious issue in HPC. Selective instruction duplication (SID) is a widely used …
Approximate computation with outlier detection in topaz
We present Topaz, a new task-based language for computations that execute on
approximate computing platforms that may occasionally produce arbitrarily inaccurate …
approximate computing platforms that may occasionally produce arbitrarily inaccurate …
Confronting the variability issues affecting the performance of next-generation SRAM design to optimize and predict the speed and yield
Effectively confronting device and circuit parameter variations to maintain or improve the
design of high performance and energy efficient systems while satisfying historical …
design of high performance and energy efficient systems while satisfying historical …
Software controlled memories for scalable many-core architectures
Technology scaling along with the ever evolving demand for media-rich software stacks
have motivated the need for many-core platforms. With the increase in compute power and …
have motivated the need for many-core platforms. With the increase in compute power and …