Ajay Joshi

Ajay Joshi

Auto-generated profile, based on publicly available information

Ajay Joshi

Boston University

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
8 September 2023 in ACM Journal on Emerging Technologies in Computing Systems
Verified
Journal Article
Open access
CDCansu Demirkiran
Cansu Demirkiran
FEFurkan Eris
Furkan Eris
GWGongyu Wang
Gongyu Wang
JEJonathan Elmhurst
Jonathan Elmhurst
NMNick Moore
Nick Moore
DBDarius Bunandar
Darius Bunandar
The number of parameters in deep neural networks (DNNs) is scaling at about 5× the rate of Moore’s Law. To sustain this growth, photonic computing is a promising avenue, as it enables higher throughput in dominant general matrix-matrix multiplication (GEMM) operations in DNNs than their electrical counterpart. However, purely photonic systems face several challenges including lack of photonic memory and accumulation of noise. In this article, we present an electro-photonic accelerator, ADEPT, which leverages a photonic computing unit for performing GEMM operations, a vectorized digital electronic application-specific integrated circuits for performing non-GEMM operations, and SRAM arrays for storing DNN parameters and activations. In contrast to prior works in photonic DNN accelerators, we adopt a system-level perspective and show that the gains while large are tempered relative to prior expectations. Our goal is to encourage architects to explore photonic technology in a more pragmatic way considering the system as a whole to understand its general applicability in accelerating today’s DNNs. Our evaluation shows that ADEPT can provide, on average, 5.73× higher throughput per watt compared to the traditional systolic arrays in a full-system, and at least 6.8× and 2.5× better throughput per watt, compared to state-of-the-art electronic and photonic accelerators, respectively.

28 January 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
ACAyse Coskun
Ayse Coskun
FEFurkan Eris
Furkan Eris
AJAjay Joshi
Ajay Joshi
AKAndrew B. Kahng
Andrew B. Kahng
YMYenai Ma
Yenai Ma
VSVaishnav Srinivas
Vaishnav Srinivas
2.5D integration technology is gaining attention and popularity in manycore computing system design. 2.5D systems integrate homogeneous or heterogeneous chiplets in a flexible and cost-effective way. The design choices of 2.5D systems impact overall system performance, manufacturing cost, and thermal feasibility. This paper proposes a cross-layer co-optimization methodology for 2.5D systems. We jointly optimize the network topology and chiplet placement across logical, physical and circuit layers to improve system performance, reduce manufacturing cost, and lower operating temperature, while ensuring thermal safety and routability. We also propose a novel gas-station link, which enables pipelined inter-chiplet links in passive interposers. Our cross-layer methodology achieves better performance-cost tradeoffs of 2.5D systems and yields better solutions in optimizing inter-chiplet network and 2.5D system designs than prior methods. Compared to single-chip systems, 2.5D systems designed using our new approach achieve 88% higher performance at the same manufacturing cost, or 29% lower cost with the same performance. Compared to the closest state-of-the-art, our new approach achieves 40-68% (49% on average) iso-cost performance improvement and 30-38% (32% on average) iso-performance cost reduction.

20 May 2020 in IEEE Micro
Verified
Journal Article
Closed access
DPDaniel Petrisko
Daniel Petrisko
FGFarzam Gilani
Farzam Gilani
MWMark Wyse
Mark Wyse
DJDai Cheol Jung
Dai Cheol Jung
SDScott Davidson
Scott Davidson
TJTommy Jung
Tommy Jung
This paper introduces BlackParrot, which aims to be the default open-source, Linux-capable, cache-coherent, RV64GC multicore used by the world. Although originally bootstrapped by the University of Washington and Boston University via DARPA funding, BlackParrot strives to be community-driven and infrastructure agnostic; a multicore which is Pareto optimal in terms of power, performance, area and complexity. In order to ensure BlackParrot is easy to use, extend and most importantly trust, development is guided by three core principles: Be Tiny, Be Modular, and Be Friendly. Development efforts have prioritized ease of use and silicon validation as first order design metrics, so that users can quickly get started and trust that their design will perform as expected when deployed. BlackParrot has been validated in a GlobalFoundries 12nm FinFET tapeout. BlackParrot is ideal as a standalone Linux processor or as a malleable fabric for an agile accelerator SoC design flow.

28 October 2023
Verified
Conference Paper
Open access
KSKaustubh Shivdikar
Kaustubh Shivdikar
YBYuhui Bao
Yuhui Bao
RARashmi Agrawal
Rashmi Agrawal
MSMichael Shen
Michael Shen
GJGilbert Jonatan
Gilbert Jonatan
David KaeliDavid Kaeli
David Kaeli
Fully Homomorphic Encryption (FHE) enables the processing of encrypted data without decrypting it. FHE has garnered significant attention over the past decade as it supports secure outsourcing of data processing to remote cloud services. Despite its promise of strong data privacy and security guarantees, FHE introduces a slowdown of up to five orders of magnitude as compared to the same computation using plaintext data. This overhead is presently a major barrier to the commercial adoption of FHE. In this work, we leverage GPUs to accelerate FHE, capitalizing on a well-established GPU ecosystem available in the cloud. We propose GME, which combines three key microarchitectural extensions along with a compile-time optimization to the current AMD CDNA GPU architecture. First, GME integrates a lightweight on-chip compute unit (CU)-side hierarchical interconnect to retain ciphertext in cache across FHE kernels, thus eliminating redundant memory transactions. Second, to tackle compute bottlenecks, GME introduces special MOD-units that provide native custom hardware support for modular reduction operations, one of the most commonly executed sets of operations in FHE. Third, by integrating the MOD-unit with our novel pipelined 64-bit integer arithmetic cores (WMAC-units), GME further accelerates FHE workloads by . Finally, we propose a Locality-Aware Block Scheduler (LABS) that exploits the temporal locality available in FHE primitive blocks. Incorporating these microarchitectural features and compiler optimizations, we create a synergistic approach achieving average speedups of 796 ×, 14.2 ×, and 2.3 × over Intel Xeon CPU, NVIDIA V100 GPU, and Xilinx FPGA implementations, respectively.

28 October 2023
Verified
Conference Paper
Open access
RARashmi Agrawal
Rashmi Agrawal
LCLeo De Castro
Leo De Castro
CJChiraag Juvekar
Chiraag Juvekar
ACAnantha Chandrakasan
Anantha Chandrakasan
VVVinod Vaikuntanathan
Vinod Vaikuntanathan
AJAjay Joshi
Ajay Joshi
Cloud computing has made it easier for individuals and companies to get access to large compute and memory resources. However, it has also raised privacy concerns about the data that users share with the remote cloud servers. Fully homomorphic encryption (FHE) offers a solution to this problem by enabling computations over encrypted data. Unfortunately, all known constructions of FHE require a noise term for security, and this noise grows during computation. To perform unlimited computations on the encrypted data, we need to perform a periodic noise reduction step known as bootstrapping. This bootstrapping operation is memory-bound as it requires several GBs of data. This leads to orders of magnitude increase in the time required for operating on encrypted data as compared to unencrypted data. In this work, we first present an in-depth analysis of the bootstrapping operation in the CKKS FHE scheme. Similar to other existing works, we observe that CKKS bootstrapping exhibits a low arithmetic intensity (< 1 Op/byte). We then propose memory-aware design (MAD) techniques to accelerate the bootstrapping operation of the CKKS FHE scheme. Our proposed MAD techniques are agnostic of the underlying compute platform and can be equally applied to GPUs, CPUs, FPGAs, and ASICs. Our MAD techniques make use of several caching optimizations that enable maximal data reuse and perform reordering of operations to reduce the amount of data that needs to be transferred to/from the main memory. In addition, our MAD techniques include several algorithmic optimizations that reduce the number of data access pattern switches and the expensive NTT operations. Applying our MAD optimizations for FHE improves bootstrapping arithmetic intensity by 3 ×. For Logistic Regression (LR) training, by leveraging our MAD optimizations, the existing GPU design can get up to 3.5 × improvement in performance for the same on-chip memory size. Similarly, the existing ASIC designs can get up to 27 × and 57 × improvement in performance for LR training and ResNet-20 inference, respectively, while reducing the on-chip memory requirement by 16 ×, which proportionally reduces the cost of the solution.

30 April 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
BZBoyou Zhou
Boyou Zhou
AAAydan Aksoylar
Aydan Aksoylar
KVKyle Vigil
Kyle Vigil
RARonen Adato
Ronen Adato
JTJian Tan
Jian Tan
AJAjay Joshi
Ajay Joshi
The high cost of integrated circuit chip production has driven more and more chip design companies to use overseas production services. Since the integrated circuit production cannot be closely monitored, the security of integrated circuit chips has become a major concern. Hardware Trojan (HT) insertion is one type of the hardware attack. HTs are extremely stealthy due to their small sizes and low triggering rates. HTs inserted during manufacturing can have minimum impact on the timing and power. In fact, this impact can be smaller than the timing and power variations caused by the process variations. Therefore, these HTs cannot be easily detected using traditional electrical methods. In this article, we propose a novel optical method, where we image the integrated circuit chip from the backside. Our method, can easily detect any replacements, modifications, or rearrangements of fill cells or functional cells for HT insertion. We use a noise-based detection method to achieve high HT detection rates in different testbenches. To further improve the robustness of our method, we strategically place high reflectance fill cells in the designs. Our approach provides high-resolution, nondestructive, and rapid means to detect HTs inserted during fabrication. We evaluate our approach using various hardware blocks where the HTs can occupy less than 0.1% of the total area or consist of fewer than three gates. In addition, we analyze our method with various magnitudes of noise, process variations, detection window sizes, and resolutions.