Related papers: Exploring the Behavior of Coherent Accelerator Pro…

Transformer uses GPU as the initial design platform, but GPU can only perform limited hardware customization. Although FPGA has strong customization ability, the design solution space is huge and the design difficulty is high. Versal ACAP…

Lossless compression imposes significant computational over head on datacenters when performed on CPUs. Hardware compression and decompression processing units (CDPUs) can alleviate this overhead, but optimal algorithm selection,…

Compute-in-memory (CiM) is a promising approach to improving the computing speed and energy efficiency in dataintensive applications. Beyond existing CiM techniques of bitwise logic-in-memory operations and dot product operations, this…

In this paper, we propose TAPA, an end-to-end framework that compiles a C++ task-parallel dataflow program into a high-frequency FPGA accelerator. Compared to existing solutions, TAPA has two major advantages. First, TAPA provides a set of…

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are…

In this paper, we present GATSPI, a novel GPU accelerated logic gate simulator that enables ultra-fast power estimation for industry sized ASIC designs with millions of gates. GATSPI is written in PyTorch with custom CUDA kernels for ease…

The emerging need for fast and power-efficient AI/ML deployment on-board spacecraft has forced the space industry to examine specialized accelerators, which have been successfully used in terrestrial applications. Towards this direction,…

Processing in memory (PIM) moves computation into memories with the goal of improving throughput and energy-efficiency compared to traditional von Neumann-based architectures. Most existing PIM architectures are either general-purpose but…

Existing deep convolutional neural networks (CNNs) generate massive interlayer feature data during network inference. To maintain real-time processing in embedded systems, large on-chip memory is required to buffer the interlayer feature…

In 2013 Intel introduced the Xeon Phi, a new parallel co-processor board. The Xeon Phi is a cache-coherent many-core shared memory architecture claiming CPU-like versatility, programmability, high performance, and power efficiency. The…

Memory bandwidth is known to be a performance bottleneck for FPGA accelerators, especially when they deal with large multi-dimensional data-sets. A large body of work focuses on reducing of off-chip transfers, but few authors try to improve…

Accelerating finite automata processing is critical for advancing real-time analytic in pattern matching, data mining, bioinformatics, intrusion detection, and machine learning. Recent in-memory automata accelerators leveraging SRAMs and…

We present a tightly integrated and unified near-memory GPU architecture that delivers 6 to 16 times speedup and 6 to 13 times energy savings across Convolutional Neural Networks, Graph Convolutional Networks, Linear Programming, Large…

As the computing landscape evolves, system designers continue to explore design methodologies that leverage increased levels of heterogeneity to push performance within limited size, weight, power, and cost budgets. One such methodology is…

We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core - MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core…

This paper presents a programmable in-memory-computing processor, demonstrated in a 65nm CMOS technology. For data-centric workloads, such as deep neural networks, data movement often dominates when implemented with today's computing…

Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it minimizes data movement and provides large computational parallelism. Similar to machine learning accelerators, application mapping, which determines the…

This paper presents Flash, an optimized private inference (PI) hybrid protocol utilizing both homomorphic encryption (HE) and secure two-party computation (2PC), which can reduce the end-to-end PI latency for deep CNN models less than 1…

Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and pharmaceuticals. In these settings, systems must balance…

Artificial intelligence (AI) is increasingly deployed in real-time and energy-constrained environments, driving demand for hardware platforms that can deliver high performance and power efficiency. While central processing units (CPUs) and…