EtherFx

Project Title "EtherFx allows users to perform computationally expensive tasks more efficiently by distributing the execution of the computation onto multiple nodes over a network. Modules and classes imported via the EtherFx library are parallelism-native - the computationally intensive tasks occur on different computers, asynchronously."

"By splitting the jobs into discrete, parallelly executable payloads over a low-latency network, significant improvements in execution time can be achieved. Speedup is defined as the ratio of the application's execution time on a single processor, T (1), to the execution time of the same workload on a system composed of P processors. EtherFx allows previously monolithic executions to be broken up and distributed over several different machines with little to no code changes on the part of the user or the library creator."

Team Members

Anish Basu

Anish Basu

ab3576@drexel.edu

Binod Bhandari

Binod Bhandari

bb822@drexel.edu

Sandesh Bhandari

Sandesh Bhandari

sb3728@drexel.edu

Klimentina Krstevska

Klimentina Krstevska

kk866@drexel.edu

Chingiz Mardanov

Chingiz Mardanov

cm3283@drexel.edu

Guruansh Singh

Guruansh Singh

gs474@drexel.edu

Mridul Singhai

Mridul Singhai

ms3998@drexel.edu

Screenshots

System Architecture

System Architecture


The system architecture of EtherFx.

Function Call Flow

Function Call Flow


"Once a function is called in an EtherFx program, this is how it will get distributed across the cluster."