Architectural implications of function-as-a-service computing

M Shahrad, J Balkind, D Wentzlaff - … of the 52nd annual IEEE/ACM …, 2019 - dl.acm.org
Serverless computing is a rapidly growing cloud application model, popularized by
Amazon's Lambda platform. Serverless cloud services provide fine-grained provisioning of …

Llmcompass: Enabling efficient hardware design for large language model inference

H Zhang, A Ning, RB Prabhakar… - 2024 ACM/IEEE 51st …, 2024 - ieeexplore.ieee.org
The past year has witnessed the increasing popularity of Large Language Models (LLMs).
Their unprecedented scale and associated high hardware cost have impeded their broader …

Optimus prime: Accelerating data transformation in servers

A Pourhabibi, S Gupta, H Kassir, M Sutherland… - Proceedings of the …, 2020 - dl.acm.org
Modern online services are shifting away from monolithic applications to loosely-coupled
microservices because of their improved scalability, reliability, programmability and …

BYOC: a" bring your own core" framework for heterogeneous-ISA research

J Balkind, K Lim, M Schaffner, F Gao… - Proceedings of the …, 2020 - dl.acm.org
Heterogeneous architectures and heterogeneous-ISA designs are growing areas of
computer architecture and system software research. Unfortunately, this line of research is …

Dalorex: A data-local program execution and architecture for memory-bound applications

M Orenes-Vera, E Tureci, D Wentzlaff… - … Symposium on High …, 2023 - ieeexplore.ieee.org
Applications with low data reuse and frequent irregular memory accesses, such as graph or
sparse linear algebra workloads, fail to scale well due to memory bottlenecks and poor core …

A deep reinforcement learning framework for architectural exploration: A routerless NoC case study

TR Lin, D Penney, M Pedram… - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
Machine learning applied to architecture design presents a promising opportunity with broad
applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable …

[PDF][PDF] OpenPiton+ Ariane: The first open-source, SMP Linux-booting RISC-V system scaling from one to many cores

J Balkind, K Lim, F Gao, J Tu… - … Research with RISC …, 2019 - parallel.princeton.edu
ABSTRACT This paper introduces OpenPiton+ Ariane, a permissively-licensed open-source
framework designed to enable scalable architecture research prototypes. With the recent …

Simmani: Runtime power modeling for arbitrary RTL with automatic signal selection

D Kim, J Zhao, J Bachrach, K Asanović - … of the 52nd Annual IEEE/ACM …, 2019 - dl.acm.org
This paper presents a novel runtime power modeling methodology which automatically
identifies key signals for power dissipation of any RTL design. The toggle-pattern matrix is …

[HTML][HTML] Energy efficiency of inference algorithms for clinical laboratory data sets: Green artificial intelligence study

JR Yu, CH Chen, TW Huang, JJ Lu, CR Chung… - Journal of Medical …, 2022 - jmir.org
Background The use of artificial intelligence (AI) in the medical domain has attracted
considerable research interest. Inference applications in the medical domain require energy …

FlooNoC: A 645-Gb/s/link 0.15-pJ/B/hop Open-Source NoC With Wide Physical Links and End-to-End AXI4 Parallel Multistream Support

T Fischer, M Rogenmoser, T Benz… - … Transactions on Very …, 2025 - ieeexplore.ieee.org
The new generation of domain-specific AI accelerators is characterized by rapidly increasing
demands for bulk data transfers, as opposed to small, latency-critical cache line transfers …