I received the M.S. degree in Computer and Communication Network Engineering and the Ph.D. degree in Control and Computer Engineering both from Politecnico di Torino, Italy, in 2015, and 2019, respectively. Furthermore, I investigated control and management plane in cloud-native environment in Cisco System. Currently, I am investigating In-network Machine Learning in UiT and Simula Research Laboratory.
I am working on in-network Machine Learning solutions.
I am working on in-network computing devices including FPGA and Soc based SmartNIC as well as programmable switch.
I am working on in-network computing devices including FPGA and Soc based SmartNIC as well as programmable switch.
I developed a monitoring system based on YANG model in Software Defined Network (SDN) for a cloud network using VPP forwarder. I wrote an agent between VPP and SDN controller (NSO and OpenDaylight). Moreover, I wrote an interface for both OpenDaylight and NSO, one with python API and another with REST API to push the routing configuration to the network as well as receiving telemetry from the network. This work was a collaborative project with Linux Foundation. You can find the details HERE.
In-memory key-value stores have quickly become a key enabling technology to build high-performance applications that must cope with massively distributed workloads. In-memory key-value stores (also referred to as NoSQL) primarly aim to offer low-latency and high-throughput data access which motivates the rapid adoption of modern network cards such as Remote Direct Memory Access (RDMA). The goal is to have a novel In-memory key-value store.
To reduce injuries due to unintentional falls, different types of fall avoidance systems have been developed, but most of them are fall detections that activate an alarm after the fall occurrence. Since predicting and preventing a fall is the most promising approach to avoid a fall injury, we proposed a fall prediction and prevention system.
Some processors (e.g., Tilera, Kalray, and Intel SCC) have ability to transmit message between the cores. In this research we have chosen TILE-Gx8036 processor to implement our novel synchronization mechanism over message passing algorithms. To compare our algorithms with original one in Linux kernel over shared memory , we implemented original mechanism on TILE-Gx8036 processor, since original does not support TILE-Gx8036 processor.
Pasargad J was started in 2009 in Esfahan, when founders noticed that small-medium business owners require open source solutions. Passargad J provides specialized Linux services in particular networking, and specialist training in Iran (Isfahan). To this end and to be suited for the task of promoting Linux professionalism we officially became LPI institute partner. LPI is a non-profit organization in Canada which provides a global framework, industry leadership and services to enhance, develop professional careers in Linux.
I am very interested in exploring universities around the world. I believe that visiting different campuses will not only provide me with a broader perspective on academic opportunities but also allow me to experience diverse cultures and environments. I visited different highly ranked schools such as École Politechnique Fédérale de Lausanne (EPFL), Purdue University, and University of California Davis, Stanford, ETH, Berkeley, and UCLA. My research interest includes In-network computing, High Performance Computing (HPC) in the context of concurrent programming and dynamic memory management in parallel and distributed systems utilizing modern hardware, such as hardware message passing and Remote Direct Memory Access (RDMA). Moreover, I have interest on healthcare systems and biology.