Department of Computer Science and Engineering

Indian Institute of Technology Hyderabad (IITH) is a premier institute of science and technology established in 2008. IITH has been consistently ranked in the&nbsp;<a href="https://iith.ac.in/reports/" rel="noopener noreferrer">top 10 institutes</a>&nbsp;in India for Engineering&nbsp;<a href="https://www.nirfindia.org/2021/EngineeringRanking.html" rel="noopener noreferrer" target="_blank">according to NIRF</a>&nbsp;making it one of the most coveted schools for science and technology in the country.

IITH offers&nbsp;<a href="https://iith.ac.in/academics/under-graduate/">undergraduate programs</a>&nbsp;in all the classical engineering disciplines, applied sciences, design, as well as several modern interdisciplinary areas. Students are given a flexibility to explore a broad set of areas, and potentially pursue a minor or double major in a discipline that is not their own. Students who wish to seek a deeper understanding of their own discipline are strongly encouraged to get involved in cutting-edge research with the help of a faculty to mentor them, and earn an Honors in their own field.

The very foundation of IIT Hyderabad is based on&nbsp;<a href="https://iith.ac.in/research/">research and innovation</a>. The vibrant research culture is evident from the number of patents and publications that IITH produces consistently every year. IITH offers&nbsp;<a href="https://iith.ac.in/academics/programmes-offered/">graduate programs</a>&nbsp;at both a masters, and a doctoral level, in several diverse areas. There are separate programs for technology, design, science, and liberal arts. The&nbsp;<a href="https://iith.ac.in/academics/post-graduate/">MTech program</a>&nbsp;is offered in various modes and durations to cater to the ever-growing need of postgraduate level professionals in the country.

IITH encourages and supports&nbsp;<a href="https://iic-iith.netlify.app/index.html" rel="noopener noreferrer" target="_blank">innovation and entrepreneurship</a>&nbsp;at every stage. The minor program in entrepreneurship is open to all students of IITH, and many of the courses are offered by industrialists who are entrepreneurs themselves. There are various&nbsp;<a href="https://iith.ac.in/research/centres-incubators/">innovation centers and incubators</a>&nbsp;that promote entrepreneurship and help mentor young innovators. IITH has been very successful in building tie-ups with leading academic institutions around the globe.

IITH enjoys a very special relationship with Japanese universities and industries that goes beyond academic and research collaborations. In fact, some of the iconic buildings in IITH campus will carry the signature of Japanese architecture.

IITH creates a unique holistic ecosystem for education that offers interactive learning, a very flexible academic structure, cutting-edge research, strong industry collaboration, and entrepreneurship. This is an environment which enables students and faculty to translate their dreams into realities.

IIT Hyderabad

The ever increasing memory requirements of several applications has led to increased demands which might not be met by embedded devices. Constraining the usage of memory in such cases is of paramount importance. It is important that such code size improvements should not have a negative impact on the runtime. Improving the execution time while optimizing for code size is a non-trivial but a significant task.The ordering of standard optimization sequences in modern compilers is fixed, and are heuristically created by the compiler domain experts based on their expertise. However, this ordering is sub-optimal, and does not generalize well across all the cases.We present a reinforcement learning based solution to the phase ordering problem, where the ordering improves both the execution time and code size. We propose two different approaches to model the sequences: one by manual ordering, and other based on a graph called Oz Dependence Graph (ODG). Our approach uses minimal data as training set, and is integrated with LLVM.We show results on x86 and AArch64 architectures on the benchmarks from SPEC-CPU 2006, SPEC-CPU 2017 and MiBench. We observe that the proposed model based on ODG outperforms the current Oz sequence both in terms of size and execution time by 6.19% and 11.99% in SPEC 2017 benchmarks, on an average. © 2022 IEEE.

World University root node

Proceedings - 2022 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2022

POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning

Many applications deployed in the cloud are usually refactored into small components called microservices that are deployed as containers in a Kubernetes environment. Such applications are deployed on a cluster of physical servers which are connected via the datacenter network.In such deployments, resources such as compute, memory, and network, are shared and hence some microservices (culprits) can misbehave and consume more resources. This interference among applications hosted on the same node leads to performance issues (e.g., high latency, packet loss) in the microservices (victims) followed by a delayed or low-quality response. Given the highly distributed and transient nature of the workloads, it's extremely challenging to debug performance issues. Especially, given the nature of existing monitoring tools, which collect traces and analyze them at individual points (network, host, etc) in a disaggregated manner.In this paper, we argue toward a case for a cross-domain (network & host) monitoring and debugging framework which could provide the end-to-end observability to debug performance issues of applications and pin-point the root-cause whether it is on the sender-host, receiver-host or the network. We present the design and provide preliminary implementation details using eBPF (extended Berkeley Packet Filter) to elucidate the feasibility of the system. © 2022 IEEE.

IEEE International Conference on Cloud Computing, CLOUD

A Case For Cross-Domain Observability to Debug Performance Issues in Microservices

Arrayed Waveguide Grating Router (AWGR) based optical networks are emerging as a promising solution for handling modern data centers due to their wide bandwidth, scalability, high data rates, and lower latency. However, link failures in AWGR based optical networks can significantly impact the network performance and lead to the loss of reachability due to the rigid, passive wavelength routing. In this paper, we present ResiConnect, a scalable, and resilient optical network architecture. ResiConnect is a 3-stage Clos network of AWGR, space switches, and AWGR (ASA) which is managed by a centralized controller. ResiConnect introduces an alternative path to redirect the affected traffic by vertically connecting transmitters, and incorporates an active link fault detection and the failover traffic steering. The evaluation results on various performance metrics confirm that ResiConnect is 1) resilient and scalable against multiple link faults, 2) efficient in detecting any link fault with minimum resource overhead, and 3) efficient in handling uneven traffic demand during link failure. © 2022 IEICE.

APNOMS 2022 - 23rd Asia-Pacific Network Operations and Management Symposium: Data-Driven Intelligent Management in the Era of beyond 5G

ResiConnect - Fault Detection and Resilience for Multi-Stage AWGR-based Optical Networks

In this paper, we propose a novel encoding framework to learn the multi-scale context information of the visual scene for image captioning task. The devised multi-scale context information constitutes spatial, semantic, and instance level features of an input mage. We draw spatial features from early convolutional layers, and multi-scale semantic features are achieved by employing a feature pyramid network on top of deep convolutional neural networks. Then, we concatenate the spatial and multi-scale semantic features to harvest fine-to-coarse details of the visual scene. Further, the instance level features are captured by employing a bi-linear interpolation technique on fused representation to hold object-level semantics of an image. We exploit an attention mechanism on attained features to guide the caption decoding module. In addition, we explore various combinations of encoding techniques to acquire global and local features of an image. The efficacy of the proposed approaches is demonstrated on the COCO dataset. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Multimedia Tools and Applications

Incorporating attentive multi-scale context information for image captioning

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model the principle of diminishing returns. A new formulation for learning a deep submodular set function that is consistent with the real-valued attribution maps obtained by existing attribution methods is proposed. The final attribution value of a feature is then defined as the marginal gain in the induced submodular score of the feature in the context of other highly attributed features, thus decreasing the attribution of redundant yet discriminatory features. Experiments on multiple datasets illustrate that the proposed attribution method achieves higher specificity along with good discriminative power. The implementation of our method is publicly available at https://github.com/Piyushi-0/SEA-NN. Copyright © 2022 by the author(s)

Proceedings of Machine Learning Research

Improving Attribution Methods by Learning Submodular Functions

Neuromorphic computing is a trending area in computer architecture which deals with the simulation of the brain on hardware. Machine learning problems are very complex to solve by a simple computer that works based on Von Neumann architecture, so we need to find architectures that are inspired by the brain and efficient for machine learning, artificial intelligence, and more complex applications. Neuromorphic computing deals with how the brain works; another thing is to find the material for simulating the brain on hardware and efficient algorithm for neuromorphic architecture. Simulating the working of neurons on hardware is very challenging because of the structure of neurons and communication mechanisms. In this paper, we have discussed the challenges in designing the communication mechanism for such neuromorphic computing when implemented in hardware. Each node in such hardware needs to multicast a message to many other nodes. The existing on-chip interconnects architectures are not enough to support such communication. We are presenting a survey on neuromorphic computing algorithms and architecture that have been proposed. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Networks and Systems

A Survey on Efficient Interconnects for Neuromorphic Systems

The primary factor responsible for increasing the refresh rate is the presence of weak rows in a DRAM. They have a shorter retention time and lose charge faster than regular rows. Recently, a technique known as in-DRAM cache was introduced in which some DRAM rows act as a separate module. The in-DRAM cache can be used for a variety of purposes in DRAM. We present WinDRAM, an in-DRAM cache comprised of all the DRAM's weak rows. The most recently accessed rows are copied into the in-DRAM cache so that when the row is accessed again, both rows (original and copy) can be activated at the same time. Such simultaneous activation reduces activation time and, as a result, DRAM access latency. Dual-row activation is the term for this concept. Because weak rows are part of the in-DRAM cache and are frequently accessed, WinDRAM does not perform a periodic refresh on them. Existing techniques based on in-DRAM cache do not design the in-DRAM cache using weak rows. WinDRAM proposes a novel idea by designing the in-DRAM cache using weak rows. Because the weak rows do not need to be refreshed, the refresh interval of the remaining rows can be increased, resulting in a refresh rate reduction of 80% to 90%. The speedup is 15% to 25% faster than standard DRAM and 12.77% faster than previous work for high memory-intensive workloads. Overall energy consumption is also reduced by 10% to 15%. © 2022 John Wiley & Sons, Ltd.

Concurrency and Computation: Practice and Experience

WinDRAM: Weak rows as in-DRAM cache

There has been a gradual shift from traditional computing to technologies involving more data-centric architectures. This has led to tremendous growth in the amount of data and, furthermore, the data-intensive applications. The major bottleneck with such applications is the data movement that is required between memory/storage and CPU. To improve the performance of such applications and reduce the movement of data from memory to CPU for computation, near data processing (NDP) is the alternative, which moves the computation from CPU to memory. This helps to improve performance, utilize bandwidth properly and reduce energy consumption to a great extent, which helps to execute data-intensive applications efficiently. In this paper, we have discussed the basics of NDP and the methods which have been proposed for the implementation of NDP. We have also discussed the applications that require NDP for better performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Near Data Processing and Its Applications

The community question and answering (CQA) sites such as Stack Overflow are used by many users around the world to obtain answers to technical questions. Here, the reliability of a user is determined using metrics such as reputation score. It is important for the CQA sites to assess the reputation score of the new users joining the site. Accurate estimation of reputation scores of these cold start users can help in tasks like question routing, expert recommendation and ranking etc. However, lack of activity information makes it quite difficult to assess the reputation score for new users. We propose an approach which makes use of alternate data associated with the users to predict the reputation score of the new users. We show that the alternate data obtained using users’ personal websites could improve the reputation score performance. We develop deep learning models based on feature distillation, such as the student-teacher models, to improve the reputation score prediction of new users from the alternate data. We demonstrate the effectiveness of the proposed approaches on the publicly available stack overflow data and publicly available alternate data. Copyright © 2022 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K - Proceedings

Predicting Reputation Score of Users in Stack-overflow with Alternate Data

A Conflict-Free Open Neighborhood coloring, abbreviated CFON*coloring, of a graph G = (V,E) using k colors is an assignment of colors from a set of k colors to a subset of vertices of V (G) such that every vertex sees some color exactly once in its open neighborhood. The minimum k for which G has a CFON*coloring using k colors is called the CFON*chromatic number of G, denoted by X*ON(G). The analogous notion for closed neighborhood is called CFCN*coloring and the analogous parameter is denoted by X*CN(G). The problem of deciding whether a given graph admits a CFON*(or CFCN*) coloring that uses k colors is NP-complete. Below, we describe briefly the main results of this paper. For k ≥ 3, we show that if G is a K1,k-free graph then X*ON(G)= O(k2 log Δ), where Δ denotes the maximum degree of G. Debski and Przybylo in [J. Graph Theory, 2021] had shown that if G is a line graph, then X*CN(G)= O(log Δ). As an open question, they had asked if their result could be extended to claw-free (K1,3-free) graphs, which are a superclass of line graphs. Since it is known that the CFCN*chromatic number of a graph is at most twice its CFON*chromatic number, our result positively answers the open question posed by Debski and Przybyło. We show that if the minimum degree of any vertex in G is Ω(Δ logϵ Δ) for some ϵ ≥ 0, then X*ON(G)= O(log1+ϵ Δ). This is a generalization of the result given by Debski and Przybyło in the same paper where they showed that if the minimum degree of any vertex in G is Ω(Δ), then X*ON(G)= O(log Δ). We give a polynomial time algorithm to compute X*ON(G) for interval graphs G. This answers in positive the open question posed by Reddy [Theoretical Comp. Science, 2018] to determine whether the CFON*chromatic number can be computed in polynomial time on interval graphs. We explore biconvex graphs, a subclass of bipartite graphs and give a polynomial time algorithm to compute their CFON*chromatic number. This is interesting as Abel et al. [SIDMA, 2018] had shown that it is NP-complete to decide whether a planar bipartite graph G has X*ON(G) = k where k ∈ {1, 2, 3}. © 2022 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. All rights reserved.