Robust Processing-In-Memory with Multi-bit ReRAM using Hessian-driven Mixed-Precision Computation

Author(s):  
Saurabh Dash ◽  
Yandong Luo ◽  
Anni Lu ◽  
Shimeng Yu ◽  
Saibal Mukhopadhyay
2021 ◽  
Vol 47 (2) ◽  
pp. 1-28
Author(s):  
Goran Flegar ◽  
Hartwig Anzt ◽  
Terry Cojean ◽  
Enrique S. Quintana-Ortí

The use of mixed precision in numerical algorithms is a promising strategy for accelerating scientific applications. In particular, the adoption of specialized hardware and data formats for low-precision arithmetic in high-end GPUs (graphics processing units) has motivated numerous efforts aiming at carefully reducing the working precision in order to speed up the computations. For algorithms whose performance is bound by the memory bandwidth, the idea of compressing its data before (and after) memory accesses has received considerable attention. One idea is to store an approximate operator–like a preconditioner–in lower than working precision hopefully without impacting the algorithm output. We realize the first high-performance implementation of an adaptive precision block-Jacobi preconditioner which selects the precision format used to store the preconditioner data on-the-fly, taking into account the numerical properties of the individual preconditioner blocks. We implement the adaptive block-Jacobi preconditioner as production-ready functionality in the Ginkgo linear algebra library, considering not only the precision formats that are part of the IEEE standard, but also customized formats which optimize the length of the exponent and significand to the characteristics of the preconditioner blocks. Experiments run on a state-of-the-art GPU accelerator show that our implementation offers attractive runtime savings.


Author(s):  
Wei-Fan Chiang ◽  
Mark Baranowski ◽  
Ian Briggs ◽  
Alexey Solovyev ◽  
Ganesh Gopalakrishnan ◽  
...  

2021 ◽  
Vol 18 (2) ◽  
pp. 1-24
Author(s):  
Nhut-Minh Ho ◽  
Himeshi De silva ◽  
Weng-Fai Wong

This article presents GRAM (<underline>G</underline>PU-based <underline>R</underline>untime <underline>A</underline>daption for <underline>M</underline>ixed-precision) a framework for the effective use of mixed precision arithmetic for CUDA programs. Our method provides a fine-grain tradeoff between output error and performance. It can create many variants that satisfy different accuracy requirements by assigning different groups of threads to different precision levels adaptively at runtime . To widen the range of applications that can benefit from its approximation, GRAM comes with an optional half-precision approximate math library. Using GRAM, we can trade off precision for any performance improvement of up to 540%, depending on the application and accuracy requirement.


2011 ◽  
Vol 1295 ◽  
Author(s):  
Marc Thomas

ABSTRACTOne of the main driving force for the development of advanced structural materials is weight saving especially in the transportation industry in order to reduce CO2 emission. The utilization of gamma aluminides, as good candidates for aerospace applications, is strongly related to the development of a cost-effective and robust processing route, as far as possible. It is well established that the processing route, i.e. cast, wrought or PM, has a dramatic effect on the microstructure and texture of gamma-TiAl alloys. Therefore, significant microstructural variations through post-heat treatments coupled with compositional modifications can only guarantee a proper balance of desired properties. However, a number of metallurgical factors during the processing steps can contribute to some scattering in properties. This review will highlight several critical process variables in terms of the resulting g-TiAl microstructures. Of primary importance is the as-cast texture which is difficult to control and may contribute to prefer some alternative processing routes to ensure a better repeatability in mechanical results. Some innovative processing techniques for controlling the structure will then be presented. The main point which will be discussed in this paper is whether an approach leading to a robust process would not be at the expense of the high performance of the structural material.


2014 ◽  
Vol 36 (2) ◽  
pp. C240-C263 ◽  
Author(s):  
M. Petschow ◽  
E. S. Quintana-Ortí ◽  
P. Bientinesi

Sign in / Sign up

Export Citation Format

Share Document