activity
20132023
most citedVariant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices

12 citations · 37 across the 8 of their papers we have counts for

collaborators

9 papers

cs.AR2023

By-Software Branch Prediction in Loops

Maziar Goudarzi, Reza Azimi, Julian Humecki +5

Load-Dependent Branches (LDB) often do not exhibit regular patterns in their local or global history and thus are inherently hard to predict correctly by conventional branch predic…

cs.DC2023★ 2 cited

An Ensemble Mobile-Cloud Computing Method for Affordable and Accurate Glucometer Readout

Navidreza Asadi, Maziar Goudarzi

Despite essential efforts towards advanced wireless medical devices for regular monitoring of blood properties, many such devices are not available or not affordable for everyone i…

cs.PF2022

FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs

Hossein Katebi, Navidreza Asadi, Maziar Goudarzi

Although prior art has demonstrated negligible accuracy drop in sub-byte quantization -- where weights and/or activations are represented by less than 8 bits -- popular SIMD instru…

cs.DC2022★ 12 cited

Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices

Navidreza Asadi, Maziar Goudarzi

Two major techniques are commonly used to meet real-time inference limitations when distributing models across resource-constrained IoT devices: (1) model parallelism (MP) and (2)…

cs.NI2020

On Coordination of Smart Grid and Cooperative Cloud Providers

Monireh Mohebbi Moghaddam, Mohammad Hossein Manshaei, Mehdi Naderi Soorki +3

Cooperative cloud providers in the form of cloud federations can potentially reduce their energy costs by exploiting electricity price fluctuations across different locations. In t…

cs.DC2020

Workload Scheduling on heterogeneous Mobile Edge Cloud in 5G networks to Minimize SLA Violation

Mostafa Hadadian Nejad Yousefi, Amirmasoud Ghiassi, Boshra Sadat Hashemi +1

Smart devices have become an indispensable part of our lives and gain increasing applicability in almost every area. Latency-aware applications such as Augmented Reality (AR), auto…