A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf
.
Filters
Exploiting reuse information to reduce refresh energy in on-chip eDRAM caches
2013
Proceedings of the 27th international ACM conference on International conference on supercomputing - ICS '13
This work introduces a novel refresh mechanism that leverages reuse information to decide which blocks should be refreshed in an energy-aware eDRAM last-level cache. ...
Experimental results show that, compared to a conventional eDRAM cache, the energy-aware approach achieves refresh energy savings up to 71%, while the reduction on the overall dynamic energy is by 65% ...
The devised refresh policy exploits reuse information to decide whether a cache block should be refreshed. ...
doi:10.1145/2464996.2467278
dblp:conf/ics/ValeroSPD13
fatcat:pu2tpvlxrffmjmrdqghlniz5e4
Dynamic and discrete cache insertion policies for managing shared last level caches in large multicores
2017
Journal of Parallel and Distributed Computing
Acknowledgment The authors would like to thank the members of the ALF team for their feedback on this work. ...
Problem: Prior studies [4, 3, 12, 1, 5, 2] have proposed novel approaches to predict the reuse behavior of applications and, hence their ability to utilize the cache. ...
Several prior mechanisms [3, 1, 12, 5, 2] have used this approach: the general goal being to assign cache space (not explicitly but by reuse prediction) to applications that could utilize the cache better ...
doi:10.1016/j.jpdc.2017.02.004
fatcat:24hmq6ycqnhhxcmyt2hzaxrmpu
Enhancing LTP-Driven Cache Management Using Reuse Distance Information
2009
Journal of Instruction-Level Parallelism
On a predicted last touch, the referenced cache block is marked for early eviction. ...
This permits cache blocks lower in the LRU stack-but with shorter reuse distances-to remain in cache longer, resulting in additional cache hits. ...
Acknowledgements The authors would like to thank Xuanhua Li, Hameed Badawy, Steve Crago, Vida Kianzad, Seungryul Choi, Inseok Choi, Aamer Jaleel, Janice McMahon, Priyanka Rajkhowa, and Meng-Ju Wu for helpful ...
dblp:journals/jilp/LiuY09
fatcat:eqf5mahskrbmbkwfboo5xaab2a
Learning Forward Reuse Distance
[article]
2020
arXiv
pre-print
In this work, we propose a learning-aided approach to predict future data accesses. ...
We find that a powerful LSTM-based recurrent neural network model can provide high prediction accuracy based on only a cache trace as input. ...
This paper strives to predict forward reuse distance based on only the past cache trace by applying a novel learningaided approach. ...
arXiv:2007.15859v1
fatcat:qn5topsvfrhvzc4dqavkm656oy
Discrete Cache Insertion Policies for Shared Last Level Cache Management on Large Multicores
2016
2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
We propose a monitoring mechanism that dynamically samples cache sets to estimate the Footprint-number of applications and classifies them into discrete (distinct and more than two) priority buckets. ...
The cache replacement policy leverages this classification and assigns priorities to cache lines of applications during cache replacement operations. ...
ACKNOWLEDGMENT The authors would like to thank the members of the ALF team for their suggestions. This work is partially supported by ERC Advanced Grant DAL No. 267175. ...
doi:10.1109/ipdps.2016.30
dblp:conf/ipps/SridharanS16
fatcat:bq2i7o7kn5be7jkhda424erpwe
Tighter WCET analysis of input dependent programs with classified-cache memory architecture
2008
2008 15th IEEE International Conference on Electronics, Circuits and Systems
To solve this problem, we have developed a novel architecture and a WCET analysis framework for this architecture. ...
Our work classifies predictable and unpredictable accesses and allocates them into predictable caches and unpredictable caches respectively, using the CME (Cache Miss Equations) and reuse-distance based ...
Predictable Cache Architectures Cache partitioning [8] is a mechanism developed to reserve blocks of cache for individual tasks such that cache hits becomes predictable. ...
doi:10.1109/icecs.2008.4674877
dblp:conf/icecsys/LiFYCHT08
fatcat:b4ou52jjlzhrlngkqucczgtsxy
Machine Learning Enabled Scalable Performance Prediction of Scientific Codes
[article]
2020
arXiv
pre-print
access patterns that it uses to build memory reuse distance distribution models for each basic block, (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. ...
We analyze the application of multi-variate regression models that accurately predict the reuse profiles and the basic block counts. ...
The goal of the AMMP approach is to predict the performance of a software on a target architecture. ...
arXiv:2010.04212v2
fatcat:53bor5hw5zgxpp5feymwg5imsy
Kill the Program Counter
2017
SIGPLAN notices
KPC cache management has three novel contributions. First, a prefetcher which approximates the future use distance of prefetch requests based on its prediction confidence. ...
Finally, KPC removes the need to propagate the PC through entire on-chip cache hierarchy while providing a holistic cache management approach with better performance than state-of-the-art PC-, and non-PC-based ...
Blocks predicted to have high reuse will be inserted with a high priority, i.e., at the MRU position, blocks predicted to have low reuse will be inserted in a low priority position such as the LRU position ...
doi:10.1145/3093336.3037701
fatcat:d2twfr4cuzcwpcgaytopglk2eu
Addressing Variability in Reuse Prediction for Last-Level Caches
[article]
2020
arXiv
pre-print
Once identified, dead blocks are evicted from LLC to make space for potentially high reuse cache blocks. ...
In this thesis, we identify variability in the reuse behavior of cache blocks as the key limiting factor in maximizing cache efficiency for state-of-the-art predictive techniques. ...
approach to classify a cache block as low or high reuse at the time of inserting a new block in the cache. ...
arXiv:2006.08487v1
fatcat:4stqscurbbcb3am5lw33c4pksm
Examining partitioned caches performance in heterogeneous multi-core processors
2022
International journal of communication and information technology
In multithreaded applications, it guides the replacement strategy by monitoring the shared reuse state of every cache block inside the partition during runtime. ...
For huge cores to make more efficient LLC visits, cache replacement algorithms generally modify the leftover state while preserving cache blocks needed by them. ...
This work presents the first of its kind a novel core-to-core communications approach that relies on cache-aware data lookups. ...
doi:10.33545/2707661x.2022.v3.i2a.70
fatcat:u3zu4wrttjav5ig6jjgmmuqqqe
A Survey of Cache Bypassing Techniques
2016
Journal of Low Power Electronics and Applications
Cache bypassing is a promising technique to increase effective cache capacity without incurring power/area costs of a larger sized cache. ...
However, injudicious use of cache bypassing can lead to bandwidth congestion and increased miss-rate and hence, intelligent techniques are required to harness its full potential. ...
A block with no predicted reuse is stored in a bypass buffer while remaining blocks are stored in the cache. ...
doi:10.3390/jlpea6020005
fatcat:rkiqtcjbcvggde5utaqogg5xxa
A Novel Chaining Approach to Indirect Control Transfer Instructions
[chapter]
2011
Lecture Notes in Computer Science
A novel indirect control transfer chaining approach is proposed in this paper. ...
Translated code is usually organized as code blocks in the code cache and each code block transfer control to the next one through a control transfer instruction. ...
A software prediction approach is proposed in [11] to predict the target address of the indirect control transfer instructions. ...
doi:10.1007/978-3-642-23300-5_24
fatcat:xc65vdlaijgczcbhhedcg7akhq
Leeway: Addressing Variability in Dead-Block Prediction for Last-Level Caches
2017
2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT)
In response, we introduce a new metric -Live Distance -that uses the stack distance to learn the temporal reuse characteristics of cache blocks, thus enabling a dead block predictor that is robust to variability ...
This paper identifies variability in generational behavior of cache blocks as a key challenge for cache management policies that aim to identify dead blocks as early and as accurately as possible to maximize ...
If predicted-live-distance is 0, the block is expected to have no reuse and is bypassed to higher level cache. ...
doi:10.1109/pact.2017.32
dblp:conf/IEEEpact/FalduG17
fatcat:7nu4squeivg6xe4mwqr2wqngda
Path-Based Reuse Distance Analysis
[chapter]
2006
Lecture Notes in Computer Science
The experimental results show that the path-based reuse distance is highly predictable, as a function of the data size, for a set of SPEC CPU2000 programs. ...
Based on memory profiling, reuse distance analysis has shown much promise in predicting data locality for a program using inputs other than the profiled ones. ...
Conclusions and Future Work In this paper, we have proposed a novel approach for path-based reuse-distance analysis. ...
doi:10.1007/11688839_4
fatcat:p7ihzzhuijdinazoztpv7l6jmm
SHiP
2011
Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture - MICRO-44 '11
We also propose a novel Signature-based Hit Predictor (SHiP) to learn the re-reference behavior of cache lines belonging to each signature. ...
A fundamental challenge, however, is how to best predict the re-reference pattern of an incoming cache line. ...
We also thank Yu-Yuan Chen, Daniel Lustig, and the anonymous reviewers for their useful insights related to this work. This material is based upon work supported by the National Science
References ...
doi:10.1145/2155620.2155671
dblp:conf/micro/WuJHMSE11
fatcat:mafbit5x7bbcpnq6i2zahkuwpe
« Previous
Showing results 1 — 15 out of 8,736 results