Damitha Lenadora

Damitha Lenadora

Auto-generated profile, based on publicly available information

Damitha Lenadora

University of Illinois at Urbana-Champaign, Urbana, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2023
Verified
Conference Paper
Open access
GGGerasimos Gerogiannis
Gerasimos Gerogiannis
SYSerif Yesil
Serif Yesil
DLDamitha Lenadora
Damitha Lenadora
DCDingyuan Cao
Dingyuan Cao
CMCharith Mendis
Charith Mendis
JTJosep Torrellas
Josep Torrellas
The widespread use of Sparse Matrix Dense Matrix Multiplication (SpMM) and Sampled Dense Matrix Dense Matrix Multiplication (SDDMM) kernels makes them candidates for hardware acceleration. However, accelerator design for these kernels faces two main challenges: (1) the overhead of moving data between CPU and accelerator (often including an address space conversion from the CPU's virtual addresses) and (2) marginal flexibility to leverage the fact that different sparse input matrices benefit from different variations of the SpMM and SDDMM algorithms. To address these challenges, this paper proposes SPADE, a new SpMM and SDDMM hardware accelerator. SPADE avoids data transfers by tightly-coupling accelerator processing elements (PEs) with the cores of a multicore, as if the accelerator PEs were advanced functional units---allowing the accelerator to reuse the CPU memory system and its virtual addresses. SPADE attains flexibility and programmability by supporting a tile-based ISA---high level enough to eliminate the overhead of fetching and decoding fine-grained instructions. To prove the SPADE concept, we have taped-out a simplified SPADE chip. Further, simulations of a SPADE system with 224--1792 PEs show its high performance and scalability. A 224-PE SPADE system is on average 2.3x, 1.3x and 2.5x faster than a 56-core CPU, a server-class GPU, and an SpMM accelerator, respectively, without accounting for the host-accelerator data transfer overhead. If such overhead is taken into account, the 224-PE SPADE system is on average 43.4x and 52.4x faster than the GPU and the accelerator, respectively. Further, SPADE has a small area and power footprint.

28 April 2021 in International Journal of Disability, Development and Education
Verified
Journal Article
Closed access
CSChamath Samarawickrama
Chamath Samarawickrama
DLDamitha Lenadora
Damitha Lenadora
RRRakhitha Ranathunge
Rakhitha Ranathunge
YSYumantha De Silva
Yumantha De Silva
IPIndika Perera
Indika Perera
KWKalpani Welivita
Kalpani Welivita
Visual impairment can affect a student’s ability to learn since their concept development when interacting with educational material is being limited. Learning activities based on images and visually rich content are mainstream learning methods, where facilitating students with visual impairments for engaged learning can be challenging. For comic books, which have shown promising results in engaged student learning, this problem is more severe. To overcome this challenge, this research presents a novel voice synthesised learning method to reduce the gap between the learning experience of a student with visual impairments compared to a mainstream learning activity. Utilising comic books, the proposed technique and the tool developed extracts semantic content, stores them in a database, and generates an audio stream in multiple languages on the user’s demand. To assess the usability of the system, a survey for a selected set of students with visual impairments was carried out. The results showed a mean rating of 5.76 out of 7 for the Informative Interest. Furthermore, a concept-mapping approach was used to analyse the feedback given through the open-ended questions. From the analysis, key concepts with an emphasis on positive emotions, willingness to try again, and features to be improved, were identified.

14 January 2022
Verified
Book Chapter
Closed access
Dulani MeedeniyaDulani Meedeniya
Dulani Meedeniya
IMI. Mahakalanda
I. Mahakalanda
DLD.S. Lenadora
D.S. Lenadora
IPI. Perera
I. Perera
SHS.G.S. Hewawalpita
S.G.S. Hewawalpita
SNSoumya Ranjan Nayak
Soumya Ranjan Nayak

9 October 2025 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
DLDamitha Lenadora
Damitha Lenadora
NJNikhil Jayakumar
Nikhil Jayakumar
CSChamika Sudusinghe
Chamika Sudusinghe
CMCharith Mendis
Charith Mendis
Multiple frameworks and optimizations have been proposed for accelerating Graph Neural Network (GNN) workloads over the years, achieving sizable runtime performance improvements. However, we notice that existing systems usually explore optimizing either at the intra-operator level or at the inter-operator level, missing synergies that exist due to their compositions. Further, most existing works focus primarily on optimizing the forward computation of GNNs, often overlooking opportunities for training-specific optimizations. To exploit these missed optimization opportunities, we introduce GALA, a domain-specific language (DSL) and a compiler that allows composing optimizations at different levels. The GALA DSL exposes intra-operator transformations as scheduling commands, while we introduce novel inter-operator transformations as part of the compiler. The composition of these transformations is made possible through the introduction of two novel intermediate representations (IR) in the GALA compiler that tracks and composes transformations at both the intra- and inter-operator levels. Further, the IRs maintain a global view of the GNN program, including its training process. This allows us to introduce training-specific transformations to aggressively optimize GNN training. Our evaluations show that GALA achieves a geo-mean speedup of 2.55× for inference and 2.52× for training across multiple systems, graphs, and GNN models. We also show that GALA performs well across different graph sizes and GNN model configurations, as well as allows users to explore different methods of performing similar optimizations leading to different tradeoff spaces.

13 September 2022 in arXiv
Verified
Preprint
Open access
PDF file
NPNiranda Perera
Niranda Perera
SKSupun Kamburugamuve
Supun Kamburugamuve
CWChathura Widanage
Chathura Widanage
VAVibhatha Abeykoon
Vibhatha Abeykoon
AUAhmet Uyar
Ahmet Uyar
GFGeoffrey Fox
Geoffrey Fox
The data science community today has embraced the concept of Dataframes as the de facto standard for data representation and manipulation. Ease of use, massive operator coverage, and popularization of R and Python languages have heavily influenced this transformation. However, most widely used serial Dataframes today (R, pandas) experience performance limitations even while working on even moderately large data sets. We believe that there is plenty of room for improvement by investigating the generic distributed patterns of dataframe operators. In this paper, we propose a framework that lays the foundation for building high performance distributed-memory parallel dataframe systems based on these parallel processing patterns. We also present Cylon, as a reference runtime implementation. We demonstrate how this framework has enabled Cylon achieving scalable high performance. We also underline the flexibility of the proposed API and the extensibility of the framework on different hardware. To the best of our knowledge, Cylon is the first and only distributed-memory parallel dataframe system available today.