activity
20182021
most citedExceeding Conservative Limits: A Consolidated Analysis on Modern Hardware Margins

36 citations · 61 across the 7 of their papers we have counts for

collaborators

11 papers

cs.DC20211 cited

On the Impact of Device-Level Techniques on Energy-Efficiency of Neural Network Accelerators

Seyed Morteza Nabavinejad, Behzad Salami

Energy-efficiency is a key concern for neural network applications. To alleviate this issue, hardware acceleration using FPGAs or GPUs can provide better energy-efficiency than gen…

cs.AR2020

Understanding Power Consumption and Reliability of High-Bandwidth Memory with Voltage Underscaling

Seyed Saber Nabavi Larimi, Behzad Salami, Osman S. Unsal +3

Modern computing devices employ High-Bandwidth Memory (HBM) to meet their memory bandwidth requirements. An HBM-enabled device consists of multiple DRAM layers stacked on top of on…

cs.AR202036 cited

Exceeding Conservative Limits: A Consolidated Analysis on Modern Hardware Margins

George Papadimitriou, Athanasios Chatzidimitriou, Dimitris Gizopoulos +5

Modern large-scale computing systems (data centers, supercomputers, cloud and edge setups and high-end cyber-physical systems) employ heterogeneous architectures that consist of mu…

eess.SP2020

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

Behzad Salami, Osman Unsal, Adrian Cristal

In this paper, we exploit the aggressive supply voltage underscaling technique in Block RAMs (BRAMs) of Field Programmable Gate Arrays (FPGAs) to improve the energy efficiency of M…

cs.LG2020

An Experimental Study of Reduced-Voltage Operation in Modern FPGAs for Neural Network Acceleration

Behzad Salami, Erhan Baturay Onural, Ismail Emir Yuksel +6

We empirically evaluate an undervolting technique, i.e., underscaling the circuit supply voltage below the nominal level, to improve the power-efficiency of Convolutional Neural Ne…

cs.LG2019

On the Resilience of Deep Learning for Reduced-voltage FPGAs

Kamyar Givaki, Behzad Salami, Reza Hojabr +6

Deep Neural Networks (DNNs) are inherently computation-intensive and also power-hungry. Hardware accelerators such as Field Programmable Gate Arrays (FPGAs) are a promising solutio…