Jeff Johnson

Jeff Johnson

Auto-generated profile, based on publicly available information

Jeff Johnson

FAIR, Meta, Paris, France

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
7 June 2019 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
JJJeff Johnson
Jeff Johnson
MDMatthijs Douze
Matthijs Douze
HJHerve Jegou
Herve Jegou
Similarity search finds application in database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better utilizing GPUs for this task. While GPUs excel at data parallel tasks such as distance computation, prior approaches in this domain are bottlenecked by algorithms that expose less parallelism, such as k-min selection, or make poor use of the memory hierarchy. We propose a novel design for k-selection. We apply it in different similarity search scenarios, by optimizing brute-force, approximate and compressed-domain search based on product quantization. In all these setups, we outperform the state of the art by large margins. Our implementation operates at up to 55% of theoretical peak performance, enabling a nearest neighbor implementation that is 8.5x faster than prior GPU state of the art. It enables the construction of a high accuracy k-NN graph on 95 million images from the YFCC100M dataset in 35 minutes, and of a graph connecting 1 billion vectors in less than 12 hours on 4 Maxwell Titan X GPUs. We have open-sourced our approach for the sake of comparison and reproducibility.

13 October 2025 in IEEE Transactions on Big Data
Verified
Journal Article
Open access
MDMatthijs Douze
Matthijs Douze
AGAlexandr Guzhva
Alexandr Guzhva
CDChengqi Deng
Chengqi Deng
JJJeff Johnson
Jeff Johnson
GSGergely Szilvasy
Gergely Szilvasy
HJHervé Jégou
Hervé Jégou
Vector databases typically manage large collections of embedding vectors. As AI applications are growing rapidly, the number of embeddings that need to be stored and indexed is increasing. The Faiss library is dedicated to vector similarity search, a core functionality of vector databases. Faiss is a toolkit of indexing methods and related primitives used to search, cluster, compress and transform vectors. This paper describes the trade-offs in vector search and the design principles of Faiss in terms of structure, approach to optimization and interfacing. We benchmark key features of the library and discuss a few selected use cases to highlight its broad applicability.

17 April 2024
Verified
Conference Paper
Open access
MLMaximilian Lam
Maximilian Lam
JJJeff Johnson
Jeff Johnson
WXWenjie Xiong
Wenjie Xiong
KMKiwan Maeng
Kiwan Maeng
UGUdit Gupta
Udit Gupta
ESEdward Suh
Edward Suh
On-device machine learning (ML) inference can enable the use of private user data on user devices without revealing them to remote servers. However, a pure on-device solution to private ML inference is impractical for many applications that rely on embedding tables that are too large to be stored on-device. In particular, recommendation models typically use multiple embedding tables each on the order of 1--10 GBs of data, making them impractical to store on-device. To overcome this barrier, we propose the use of private information retrieval (PIR) to efficiently and privately retrieve embeddings from servers without sharing any private information. As off-the-shelf PIR algorithms are usually too computationally intensive to directly use for latency-sensitive inference tasks, we 1) propose novel GPU-based acceleration of PIR, and 2) co-design PIR with the downstream ML application to obtain further speedup. Our GPU acceleration strategy improves system throughput by more than 20× over an optimized CPU PIR implementation, and our PIR-ML co-design provides an over 5× additional throughput improvement at fixed model quality. Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to 100,000 queries per second---a > 100× throughput improvement over a CPU-based baseline---while maintaining model accuracy.

1 November 2018 in arXiv
Verified
Preprint
Open access
PDF file
JJJeff Johnson
Jeff Johnson
Reducing hardware overhead of neural networks for faster or lower power inference and training is an active area of research. Uniform quantization using integer multiply-add has been thoroughly investigated, which requires learning many quantization parameters, fine-tuning training or other prerequisites. Little effort is made to improve floating point relative to this baseline; it remains energy inefficient, and word size reduction yields drastic loss in needed dynamic range. We improve floating point to be more energy efficient than equivalent bit width integer hardware on a 28 nm ASIC process while retaining accuracy in 8 bits with a novel hybrid log multiply/linear add, Kulisch accumulation and tapered encodings from Gustafson's posit format. With no network retraining, and drop-in replacement of all math and float32 parameters via round-to-nearest-even only, this open-sourced 8-bit log float is within 0.9% top-1 and 0.2% top-5 accuracy of the original float32 ResNet-50 CNN model on ImageNet. Unlike int8 quantization, it is still a general purpose floating point arithmetic, interpretable out-of-the-box. Our 8/38-bit log float multiply-add is synthesized and power profiled at 28 nm at 0.96x the power and 1.12x the area of 8/32-bit integer multiply-add. In 16 bits, our log float multiply-add is 0.59x the power and 0.68x the area of IEEE 754 float16 fused multiply-add, maintaining the same signficand precision and dynamic range, proving useful for training ASICs as well.

14 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
JJJeff Johnson
Jeff Johnson
The logarithmic number system (LNS) is arguably not broadly used due to exponential circuit overheads for summation tables relative to arithmetic precision. Methods to reduce this overhead have been proposed, yet still yield designs with high chip area and power requirements. Use remains limited to lower precision or high multiply/add ratio cases, while much of linear algebra (near 1:1 multiply/add ratio) does not qualify. We present a dual-base approximate logarithmic arithmetic comparable to floating point in use, yet unlike LNS it is easily fully pipelined, extendable to arbitrary precision with $O(n^2)$ overhead, and energy efficient at a 1:1 multiply/add ratio. Compared to float32 or float64 vector inner product with FMA, our design is respectively 2.3x and 4.6x more energy efficient in 7 nm CMOS. It depends on exp and log evaluation 5.4x and 3.2x more energy efficient, at 0.23x and 0.37x the chip area for equivalent accuracy versus standard hyperbolic CORDIC using shift-and-add and approximated ODE integration in the style of Revol and Yakoubsohn. This technique is a novel design alternative for low power, high precision hardened linear algebra in computer vision, graphics and machine learning applications.