Related papers: A Benchmarking Platform for DDR4 Memory Performanc…
Emerging computing architectures such as near-memory computing (NMC) promise improved performance for applications by reducing the data movement between CPU and memory. However, detecting such applications is not a trivial task. In this…
Over the past two decades, the storage capacity and access bandwidth of main memory have improved tremendously, by 128x and 20x, respectively. These improvements are mainly due to the continuous technology scaling of DRAM (dynamic…
We present the Cuckoo Trie, a fast, memory-efficient ordered index structure. The Cuckoo Trie is designed to have memory-level parallelism -- which a modern out-of-order processor can exploit to execute DRAM accesses in parallel -- without…
Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance, energy efficiency, and rack density constraints. The NVIDIA T4 GPU has become widely deployed due to strong performance per watt…
High Performance Computing (HPC) platforms allow scientists to model computationally intensive algorithms. HPC clusters increasingly use General-Purpose Graphics Processing Units (GPGPUs) as accelerators; FPGAs provide an attractive…
The increasing growth of applications' memory capacity and performance demands has led the CPU vendors to deploy heterogeneous memory systems either within a single system or via disaggregation. For instance, systems like Intel's Knights…
This article provides a survey of academic literature about field programmable gate array (FPGA) and their utilization for energy efficiency acceleration in data centers. The goal is to critically present the existing FPGA energy…
Energy-efficiency is a key concern for neural network applications. To alleviate this issue, hardware acceleration using FPGAs or GPUs can provide better energy-efficiency than general-purpose processors. However, further improvement of the…
In this paper we provide a comprehensive, memory-centric characterization of the SPEC CPU2017 benchmark suite, using a number of mechanisms including dynamic binary instrumentation, measurements on native hardware using hardware performance…
Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities. Recently, modern embedded platforms started being equipped with such accelerators, resulting in a…
Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…
The increasing adoption of large language models (LLMs) on heterogeneous computing platforms poses significant challenges to achieving high inference efficiency. To address these efficiency bottlenecks across diverse platforms, this paper…
Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped to a dedicated hardware unit, making them well-suited for…
FPGA-based hardware accelerators are becoming increasingly popular due to their versatility, customizability, energy efficiency, constant latency, and scalability. FPGAs can be tailored to specific algorithms, enabling efficient hardware…
Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…
Many modern workloads, such as neural networks, databases, and graph processing, are fundamentally memory-bound. For such workloads, the data movement between main memory and CPU cores imposes a significant overhead in terms of both latency…
Many convolutional neural network (CNN) accelerators face performance- and energy-efficiency challenges which are crucial for embedded implementations, due to high DRAM access latency and energy. Recently, some DRAM architectures have been…
Contemporary memory systems contain a variety of memory types, each possessing distinct characteristics. This trend empowers applications to opt for memory types aligning with developer's desired behavior. As a result, developers gain…
Flexibility and customization are key strengths of Field-Programmable Gate Arrays (FPGAs) when compared to other computing devices. For instance, FPGAs can efficiently implement arbitrary-precision arithmetic operations, and can perform…
The predictive power of Convolutional Neural Networks (CNNs) has been an integral factor for emerging latency-sensitive applications, such as autonomous drones and vehicles. Such systems employ multiple CNNs, each one trained for a…