Sai Rahul Chalamalasetti

Sai Rahul Chalamalasetti

Auto-generated profile, based on publicly available information

Sai Rahul Chalamalasetti

D-Matrix, Santa Clara, California, 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
27 November 2023
Verified
Conference Paper
Open access
TPTobias Pfandzelter
Tobias Pfandzelter
ADAditya Dhakal
Aditya Dhakal
EFEitan Frachtenberg
Eitan Frachtenberg
SCSai Rahul Chalamalasetti
Sai Rahul Chalamalasetti
DEDarel Emmot
Darel Emmot
DMDejan Milojicic
Dejan Milojicic
With the slowing of Moore's law and decline of Dennard scaling, computing systems increasingly rely on specialized hardware accelerators in addition to general-purpose compute units. Increased hardware heterogeneity necessitates disaggregating applications into workflows of fine-grained tasks that run on a diverse set of CPUs and accelerators. Current accelerator delivery models cannot support such applications efficiently, as (1) the overhead of managing accelerators erases performance benefits for fine-grained tasks; (2) exclusive accelerator use per task leads to underutilization; and (3) specialization increases complexity for developers. We propose adopting concepts from Function-as-a-Service (FaaS), which has solved these challenges for general-purpose CPUs in cloud computing. Kernel-as-a-Service (KaaS) is a novel serverless programming model for generic compute accelerators that aids heterogeneous workflows by combining the ease-of-use of higher-level abstractions with the performance of low-level hand-tuned code. We evaluate KaaS with a focus on the breadth of the idea and its generality to diverse architectures rather than on an in-depth implementation for a single accelerator. Using proof-of-concept prototypes, we show that this programming model provides performance, performance efficiency, and ease-of-use benefits across a diverse range of compute accelerators. Despite increased levels of abstraction, when compared to a naive accelerator implementation, KaaS reduces completion times for fine-grained tasks by up to 96.0% (GPU), 68.4% (FPGA), 98.6% (TPU), and 34.9% (QPU) in our experiments.

3 January 2024 in Computer
Verified
Journal Article
Closed access
PBPedro Bruel
Pedro Bruel
SCSai Rahul Chalamalasetti
Sai Rahul Chalamalasetti
ADAditya Dhakal
Aditya Dhakal
EFEitan Frachtenberg
Eitan Frachtenberg
NHNinad Hogade
Ninad Hogade
GRGourav Rattihalli
Gourav Rattihalli
Traditional high-performance computing and modern artificial intelligence computing are converging with workflows as a common paradigm. We predict nine principles of heterogeneity and serverless computing for this convergence, from high-level programming to low-level hardware.

1 July 2021
Verified
Conference Paper
Closed access
PSPlínio Silveira
Plínio Silveira
CRCesar Augusto De Rose
Cesar Augusto De Rose
FZFrancisco Avelino Zorzo
Francisco Avelino Zorzo
MXMiguel Gomes Xavier
Miguel Gomes Xavier
DMDejan Milojicic
Dejan Milojicic
SSSergey Serebryakov
Sergey Serebryakov
Due to the increasing adoption of Machine Learning (ML) and in particular Deep Learning (DL), many specialized energy efficient accelerators are being proposed by academia and industry. A number of these accelerators are designed to run a single application at a time in exclusive access mode. This approach gives applications maximum performance but reduces resource efficiency, resulting in increased costs over time. Sharing the device among multiple jobs increases resource utilization and amplifies return on investment. This study is driven by a broad investigation of various spatial resource sharing strategies in machine learning hardware accelerators and performance evaluation in a novel memristor-based accelerator called PUMA [1]. Two methods of spatial sharing are discussed: Model Packing and Logical Allocation. Simulations showed that both methods can be implemented on the PUMA accelerator and have advantages in terms of increased resource utilization. The former spatial sharing strategy achieves higher level of parallelism, fitting more models per device (7 models on 11 tiles), but has higher interference overhead (up to 49%), still being in most cases better than the overhead found for GPUs. The latter spatial sharing strategy achieves better isolation with almost no interference overhead (<1%) with the cost of leaving resources unused (same 7 models consumed 16 tiles). Finally, we discuss security implications of resource sharing for ML and other concerns, presenting a novel ML model integrity check and model bias verification.

15 April 2026 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
JLJiayong Li
Jiayong Li
JDJonas Dann
Jonas Dann
ZHZhenhao He
Zhenhao He
GAGustavo Alonso
Gustavo Alonso
SCSai Rahul Chalamalasetti
Sai Rahul Chalamalasetti
RSRunbin Shi
Runbin Shi
Efficient data reduction techniques, including deduplication and compression, are essential in storage systems, affecting performance and longevity. Existing data deduplication approaches often focus on intra-SSD deduplication, missing opportunities for cross-node deduplication, or have scalability issues when aiming for low latency and high-throughput data reduction on large-scale, distributed SSD arrays. We propose StreamDedup, a distributed stream accelerator implementing a transparent layer of deduplication as a network-attached, middle-tier service between the compute and storage tiers. StreamDedup manages all aspects of data deduplication and compression and can be seamlessly integrated into existing systems. It is RDMA-enabled and highly scalable, enhancing data processing capacities for large-scale storage systems. Our prototype, deployed on FPGAs, demonstrates that StreamDedup achieves a throughput of 12.7 GB/s on a single node, matching the network bandwidth of disaggregated storage, with a latency of less than 50 µs. Across 10 nodes, StreamDedup shows an almost linear increase in throughput with less than 60 µs of latency.