Abhiram

Abhiram

Electrical Engineering undergrad at IIT Madras

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

G-MAP: A Graph-Neural Network Based Framework for Memory Access Prediction

Published in IEEE HPEC, 2023

In this paper, we introduce G-MAP, a novel Graph Neural Network-based framework for Memory Access Prediction. First, we propose Mem2Graph, a novel approach mapping a memory access sequence to a graph representation, capturing both the spatial and temporal locality in the memory access sequence which most existing methods fail to do. Second, we implement various GNNs for G-MAP, including Graph Convolutional Network (GCN), Gated Graph Sequence Neural Network (GG-NN), and Graph Attention Network (GAT).

Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1). http://academicpages.github.io/files/paper1.pdf

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

Photo 1

Short description of portfolio item number 1

publications

G-MAP: A Graph-Neural Network Based Framework for Memory Access Prediction

Published in IEEE HPEC, 2023

In this paper, we introduce G-MAP, a novel Graph Neural Network-based framework for Memory Access Prediction. First, we propose Mem2Graph, a novel approach mapping a memory access sequence to a graph representation, capturing both the spatial and temporal locality in the memory access sequence which most existing methods fail to do. Second, we implement various GNNs for G-MAP, including Graph Convolutional Network (GCN), Gated Graph Sequence Neural Network (GG-NN), and Graph Attention Network (GAT).

Recommended citation: A. R. Gorle, P. Zhang, R. Kannan and V. K. Prasanna, "G-MAP: A Graph Neural Network-Based Framework for Memory Access Prediction," 2023 IEEE High Performance Extreme Computing Conference (HPEC), Boston, MA, USA, 2023, pp. 1-7, doi: 10.1109/HPEC58863.2023.10363605. https://ieeexplore.ieee.org/document/10363605

talks

Toppers’ Talk: JEE Advanced 2020

Published:

Isn’t it your dream to land into an IIT? If it is, learn how to get there in this masterclass by Abhiram Rao, IIT Madras, JEE Advanced 2020, AIR 565.

Tutorial: Kaggle’s Predict Future Sales

Published:

Have you ever wondered how big businesses forecast their sales? Or maybe try to predict times when they need to stock up on their inventory? In order to help you build this reference code for most data science pipelines and develop your thought process we bring to you a session where we walk you through building this reference code for the Predict Future Sales contest on Kaggle. Here is an opportunity for you to explore the problem, learn the different ways to approach it and to get yourself your base reference code for building complete pipelines.

The Idea Factory: How Bell Labs invented the future

Published:

My talk on Bell Labs as a part of the final presentation for EE5004: Seminar on History of Electrical Engineering course. Bell Labs has been shaping the future with innovations over the past 90 years. Be it the first ever transistor, the first silicon solar cell, the first ever laser or the first communication satellite, involved in nearly every technological milestone in the last nine decades. A total of 9 Nobel Prizes and 5 Turing Prizes awarded to the work here. So how exactly did Bell Labs create the future that we live in today?

Workshop on AI Alignment

Published:

Selected from IITM to attend this 3-day workshop on AI Alignment Research from 28 August, 2022 to 30 August, 2022.

Reflections on Research by Dr. David Koilpillai

Published:

The EE Research Club, a newly formed entity under the EEA, is excited to invite you to its inaugural session, featuring a talk by Prof. David Koilpillai on his reflections on research, and a brief overview of various research areas in our department.

Integration Bee

Published:

Extremely glad to have hosted IITM’s first ever Integration Bee alongside Haricharan. You can find the contents from Integration Bee here.

Lempel-Ziv Compression, guided by prof. Andrew Thangaraj

Published:

In many practical scenarios in communications and data processing, we work with large volumes of data. A single minute of an uncompressed HD video can be over 1 GB. How do we then fit a two-hour film on a 25 GB Blu-ray disc? So, there is a need for robust, lossless data compression techniques. Most compression techniques (like Huffman encoding) although optimal, need prior knowledge of the source distribution.

IUSSTF Viterbi Showcase

Published:

This was an amazing opportunity for me to present my work from Summer 2023, under the guidance of Prof. Viktor Prasanna and my PhD guide Pengmiao Zhang on ML-based Memory Access Prediction.

Talk: Research Internships for UGs

Published:

Thank you for attending the session and for your overwhelming response! Here is the link to the presentation/slides used in the session.

EE6133: Multirate Signal Processing

Published:

My first time ever, conducting a tutorial session for a batch of 53 EE undergraduate students on Multirate Signal Processing. It was an amazing exprience, excited to do this more often.

Adaptive Signal Processing Project

Published:

Compressed sensing is a classical signal processing technique of reconstructing a sparse signal (’compressible’ signal) from as minimum number of measurements as possible. Let’s now consider the problem of reconstructing time sequences of spatially sparse signals (with unknown and time-varying sparsity patterns) from a limited number of linear “incoherent” measurements, in real-time. The signals are sparse in some transform domain referred to as the sparsity basis. For a single spatial signal,we can apply Compressed sensing (CS) to solve the problem.

Convex Poster Day

Published:

Ruban and I got a chance to present a poster titled: ‘Signal Decomposition via Quadratic-Separable Optimization’.

Price of Anarchy

Published:

Rushill and I gave an hour long critical talk on Price of Anarchy, as a part of our course project for EE6418: Game Theory for Engineering Applications.

A review of Blind Algorithms

Published:

As a part of the end-semester (finals) for EE4140: Digital Communication Systems, I did an extensive review of existing blind algorithms (Godard, Sato, CMA, APA-CM, RCA, MMA, Stop-and-Go) and simulated them for a variety of channel models and samples generated from a QPSK/16-QAM constellation.

teaching

GN1101/1102

Undergraduate course, IIT Madras, 2022

Teaching assistant for a group of 15 freshies in their core Life Skills course. Involved in conducting sessions for a batch of 150 enthusiastic EE students, and grading their assignments.

EE2025: Engineering Electromagnetics

Course, EE Department, IITM, 2023

I have the fortunate opportunity to be the only B.Tech TA for this course, involved in setting tutorials, mini-quizzes, and the quiz/endsem marking scheme cum grading.

EE2016: Microprocessor Theory & Lab

Course, EE Department, IITM, 2023

I will be a TA for second half of the course, which will be instructed by Prof. Manivasakan. This will build upon ARM processor from the first half, and focus on AVR Microcontroller, various funtionalities of the same such as Assembly, Hardware, Interrupt and C-interfacing will be demonstrated in the lab sessions.