Sriseshan Srikanth

Sriseshan Srikanth

Auto-generated profile, based on publicly available information

Sriseshan Srikanth

Meta, Sunnyvale, CA, United States

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
29 January 2021 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
BDBobin Deng
Bobin Deng
SSSriseshan Srikanth
Sriseshan Srikanth
AJAnirudh Jain
Anirudh Jain
TCThomas M. Conte
Thomas M. Conte
EDErik DeBenedictis
Erik DeBenedictis
JCJeanine Cook
Jeanine Cook
Due to high leakage current, Dennard scaling has reached its limit on conventional semiconductor technology. Energy reduction at the transistor level by simply lowering supply voltage has proven to be infeasible for these devices. Some recently proposed millivolt switch techniques aim to mitigate these issues. However, Vdd reduction is constrained by high intermittent error probabilities in millivolt switches. Energy-efficient microarchitectures that are computationally error-tolerant are therefore urgently needed. This paper systematically leverages the properties of Redundant Residue Number Systems(RRNS) by varying the number of non-redundant (n) and redundant (r) residues. First, we propose a scalable RRNS microarchitecture that simultaneously supports both, error-correction, as well as checkpointing&restart capabilities. Second, we design novel RRNS-based adaptive checkpointing&restart mechanisms that automatically guarantee reliability while minimizing the energy-delay product(EDP). To the best of our knowledge, these are the first set of checkpointing mechanisms targeting the RRNS infrastructure. Moreover, these mechanisms optimize the usage efficiency of memory capacity. Third, we systematically explore the RRNS design space to find the best (n, r) configuration point. For similar reliability when compared to a conventional binary core, the proposed RRNS scalable microarchitecture reduces EDP by 53% on average for memory-intensive workloads and by 67% on average for non-memory-intensive workloads.

3 September 2021 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
SSSriseshan Srikanth
Sriseshan Srikanth
AJAnirudh Jain
Anirudh Jain
TCThomas M. Conte
Thomas M. Conte
EDErik DeBenedictis
Erik DeBenedictis
JCJeanine Cook
Jeanine Cook
Sparse data applications have irregular access patterns that stymie modern memory architectures. Although hyper-sparse workloads have received considerable attention in the past, moderately-sparse workloads prevalent in machine learning applications, graph processing and HPC have not. Where the former can bypass the cache hierarchy, the latter fit in the cache. This article makes the observation that intelligent, near-processor cache management can improve bandwidth utilization for data-irregular accesses, thereby accelerating moderately-sparse workloads. We propose SortCache, a processor-centric approach to accelerating sparse workloads by introducing accelerators that leverage the on-chip cache subsystem, with minimal programmer intervention.

11 October 2019 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
SSSriseshan Srikanth
Sriseshan Srikanth
AJAnirudh Jain
Anirudh Jain
JLJoseph M. Lennon
Joseph M. Lennon
TCThomas M. Conte
Thomas M. Conte
EDErik Debenedictis
Erik Debenedictis
JCJeanine Cook
Jeanine Cook
Reduction is an operation performed on the values of two or more key-value pairs that share the same key. Reduction of sparse data streams finds application in a wide variety of domains such as data and graph analytics, cybersecurity, machine learning, and HPC applications. However, these applications exhibit low locality of reference, rendering traditional architectures and data representations inefficient. This article presents MetaStrider, a significant algorithmic and architectural enhancement to the state-of-the-art, SuperStrider. Furthermore, these enhancements enable a variety of parallel, memory-centric architectures that we propose, resulting in demonstrated performance that scales near-linearly with available memory-level parallelism.

27 April 2024
Verified
Conference Paper
Open access
ABArmand Behroozi
Armand Behroozi
YCYuxiang Chen
Yuxiang Chen
VFVlad Fruchter
Vlad Fruchter
LSLavanya Subramanian
Lavanya Subramanian
SSSriseshan Srikanth
Sriseshan Srikanth
SMScott Mahlke
Scott Mahlke

30 September 2024
Verified
Conference Paper
Open access
LYLita Yang
Lita Yang
CKChangjung Kao
Changjung Kao
SSSriseshan Srikanth
Sriseshan Srikanth
HSH. Ekin Sumbul
H. Ekin Sumbul
TWTony F. Wu
Tony F. Wu
EBEdith Beigne
Edith Beigne

1 November 2018
Verified
Conference Paper
Open access
AJAnirudh Jain
Anirudh Jain
SSSriseshan Srikanth
Sriseshan Srikanth
EDErik DeBenedictis
Erik DeBenedictis
TKTushar Krishna
Tushar Krishna
Logic-memory integration helps mitigate the von Neumann bottleneck, and this has enabled a new class of architectures that helps accelerate graph analytics and operations on sparse data streams. These utilize merge networks as a key unit of computation. Such networks are highly parallel and their performance increases with tighter coupling between logic and memory when a bitonic algorithm is used. This paper presents energy-efficient on-chip network architectures for merging key-value pairs using both word-parallel and bit-serial paradigms. The proposed architectures are capable of merging two rows of high bandwidth memory (HBM)worth of data in a manner that is completely overlapped with the reading from and writing back to such a row. Furthermore, their energy consumption is about an order of magnitude lower when compared to a naive crossbar based design.