Neural methods for dynamic branch prediction
ACM Transactions on Computer Systems (TOCS)
Automatically characterizing large scale program behavior
Proceedings of the 10th international conference on Architectural support for programming languages and operating systems
Dynamic Branch Prediction with Perceptrons
HPCA '01 Proceedings of the 7th International Symposium on High-Performance Computer Architecture
Fast Path-Based Neural Branch Prediction
Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture
Piecewise Linear Branch Prediction
Proceedings of the 32nd annual international symposium on Computer Architecture
Analysis of the O-GEometric History Length Branch Predictor
Proceedings of the 32nd annual international symposium on Computer Architecture
Low-power, high-performance analog neural branch prediction
Proceedings of the 41st annual IEEE/ACM International Symposium on Microarchitecture
Scalable high performance main memory system using phase-change memory technology
Proceedings of the 36th annual international symposium on Computer architecture
Enhancing lifetime and security of PCM-based main memory with start-gap wear leveling
Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
Dynamically replicated memory: building reliable systems from nanoscale resistive memories
Proceedings of the fifteenth edition of ASPLOS on Architectural support for programming languages and operating systems
Emerging non-volatile memories: opportunities and challenges
CODES+ISSS '11 Proceedings of the seventh IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis
Reconfigurable Hybrid CMOS/Nanodevice Circuits for Image Processing
IEEE Transactions on Nanotechnology
Hi-index | 0.00 |
Memristors offer many potential advantages over more traditional memory-cell technologies, including the potential for extreme densities, and fast read times. Current devices, however, are plagued by problems of yield, and durability. We present a limit study of an aggressive neural network application that has a high update rate and a strict latency requirement, analog neural branch predictor. Of course, traditional analog neural network (ANN) implementations of branch predictors are not built with the idea that the underlying bits are likely to fail due to both manufacturing and wear-out issues. Without some careful precautions, a direct one-to-one replacement will result in poor behavior. We propose a hybrid system that uses SRAM front-end cache, and a distributed-sum scheme to overcome memristors' limitations. Our design can leverage devices with even modest durability (surviving only hours of continuous switching) to provide a system lasting 5 or more years of continuous operation. In addition, these schemes allow for a fault-tolerant design as well. We find that, while a neural predictor benefits from larger density, current technology parameters do not allow high dense, energy-efficient design. Thus, we discuss a range of plausible memristor characteristics that would; as the technology advances; make them practical for our application.