MoRS: An Approximate Fault Modelling Framework for Reduced-Voltage SRAMs

by   Ismail Emir Yuksel, et al.

On-chip memory (usually based on Static RAMs-SRAMs) are crucial components for various computing devices including heterogeneous devices, e.g., GPUs, FPGAs, ASICs to achieve high performance. Modern workloads such as Deep Neural Networks (DNNs) running on these heterogeneous fabrics are highly dependent on the on-chip memory architecture for efficient acceleration. Hence, improving the energy-efficiency of such memories directly leads to an efficient system. One of the common methods to save energy is undervolting i.e., supply voltage underscaling below the nominal level. Such systems can be safely undervolted without incurring faults down to a certain voltage limit. This safe range is also called voltage guardband. However, reducing voltage below the guardband level without decreasing frequency causes timing-based faults. In this paper, we propose MoRS, a framework that generates the first approximate undervolting fault model using real faults extracted from experimental undervolting studies on SRAMs to build the model. We inject the faults generated by MoRS into the on-chip memory of the DNN accelerator to evaluate the resilience of the system under the test. MoRS has the advantage of simplicity without any need for high-time overhead experiments while being accurate enough in comparison to a fully randomly-generated fault injection approach. We evaluate our experiment in popular DNN workloads by mapping weights to SRAMs and measure the accuracy difference between the output of the MoRS and the real data. Our results show that the maximum difference between real fault data and the output fault model of MoRS is 6.21 maximum difference between real data and random fault injection model is 23.2 In terms of average proximity to the real data, the output of MoRS outperforms the random fault injection approach by 3.21x.


page 1

page 3

page 4

page 6

page 12


On the Resilience of Deep Learning for Reduced-voltage FPGAs

Deep Neural Networks (DNNs) are inherently computation-intensive and als...

SoC Memory Management for Reducing Fault Problem from Reserved Memory Components

In this paper, the author proposes an optimal management for system on c...

Reduce: A Framework for Reducing the Overheads of Fault-Aware Retraining

Fault-aware retraining has emerged as a prominent technique for mitigati...

Lightning: Striking the Secure Isolation on GPU Clouds with Transient Hardware Faults

GPU clouds have become a popular computing platform because of the cost ...

Evaluating Built-in ECC of FPGA on-chip Memories for the Mitigation of Undervolting Faults

Voltage underscaling below the nominal level is an effective solution fo...

Power and Accuracy of Multi-Layer Perceptrons (MLPs) under Reduced-voltage FPGA BRAMs Operation

In this paper, we exploit the aggressive supply voltage underscaling tec...

ISimDL: Importance Sampling-Driven Acceleration of Fault Injection Simulations for Evaluating the Robustness of Deep Learning

Deep Learning (DL) systems have proliferated in many applications, requi...

Please sign up or login with your details

Forgot password? Click here to reset