Related papers: A Microbenchmark Characterization of the Emu Chick
Processing large numbers of key/value lookups is an integral part of modern server databases and other "Big Data" applications. Prior work has shown that hash table based key/value lookups can benefit significantly from using a dedicated…
The limited HBM capacity has become the primary bottleneck for hosting an increasing number of larger-scale GPU tasks. While demand paging extends capacity via host DRAM, it incurs up to 78x slowdown due to the massive working sets and poor…
Recently, single-stage embedding based deep learning algorithms gain increasing attention in cell segmentation and tracking. Compared with the traditional "segment-then-associate" two-stage approach, a single-stage algorithm not only…
As an extension of cloud computing, fog computing at the edge of networks provides low latency, location awareness, and real-time interactions. At the same time, millimeter wave (mmWave) communications are able to provide directional…
What if you could piece together your own custom biometrics and AI analysis system, a bit like LEGO blocks? We aim to bring that technology to field operators in the field who require flexible, high-performance edge AI system that can be…
Although deep learning-based personalized recommendation systems provide qualified recommendations, they strain data center resources. The main bottleneck is the embedding layer, which is highly memory-intensive due to its sparse, irregular…
Web application performance is heavily reliant on the hit rate of memory-based caches. Current DRAM-based web caches statically partition their memory across multiple applications sharing the cache. This causes under utilization of memory…
We present and evaluate the ExaNeSt Prototype, a liquid-cooled rack prototype consisting of 256 Xilinx ZU9EG MPSoCs, 4 TBytes of DRAM, 16 TBytes of SSD, and configurable interconnection 10-Gbps hardware. We developed this testbed in…
Computing-in-memory (CIM) has attracted significant attentions in recent years due to its massive parallelism and low power consumption. However, current CIM designs suffer from large area overhead of small CIM macros and bad programmablity…
Electromagnetic fault injection (EMFI) is a well known technique used to disturb the behaviour of a chip for weakening its security. These attacks are mostly done on simple microcontrollers. On these targets, the fault effects are…
The rise of IoT has increased the need for on-edge machine learning, with TinyML emerging as a promising solution for resource-constrained devices such as MCU. However, evaluating their performance remains challenging due to diverse…
We investigate the utility of augmenting a microprocessor with a single execution pipeline by adding a second copy of the execution pipeline in parallel with the existing one. The resulting dual-hardware-threaded microprocessor has two…
Graph processing is typically considered to be a memory-bound rather than compute-bound problem. One common line of thought is that more available memory bandwidth corresponds to better graph processing performance. However, in this work we…
The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have primarily focused on improving the efficiency of protection…
Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm of edge model…
ExaScale systems will be a key driver for simulations that are essential for advance of science and economic growth. We aim to present a new concept of microprocessor for floating-point computations useful for being a basic building block…
This paper presents the Neural Cache architecture, which re-purposes cache structures to transform them into massively parallel compute units capable of running inferences for Deep Neural Networks. Techniques to do in-situ arithmetic in…
Real-time multimodal inference on resource-constrained edge devices is essential for applications such as autonomous driving, human-computer interaction, and mobile health. However, prior work often overlooks the tight coupling between…
Concurrent priority queues are widely used in important workloads, such as graph applications and discrete event simulations. However, designing scalable concurrent priority queues for NUMA architectures is challenging. Even though several…
We propose EdgeSpike, a co-designed spiking neural network (SNN) framework for autonomous low-power sensing in edge Internet of Things (IoT) architectures. EdgeSpike unifies (i) a hybrid surrogate-gradient and direct-encoding training…