Related papers: RPU: The Ring Processing Unit

Tensor processing units (TPUs), specialized hardware accelerators for machine learning tasks, have shown significant performance improvements when executing convolutional layers in convolutional neural networks (CNNs). However, they…

Vector similarity search is a critical component of modern AI systems, but traditional CPU-based implementations face fundamental scalability bottlenecks for billion-scale corpora due to prohibitive computational overhead and memory…

We propose MRU (Multi-Range Reasoning Units), a new fast compositional encoder for machine comprehension (MC). Our proposed MRU encoders are characterized by multi-ranged gating, executing a series of parameterized contract-and-expand…

The advent of Reconfigurable Intelligent Surfaces (RISs) in wireless communication networks unlocks the way to support high frequency radio access (e.g. in millimeter wave) while overcoming their sensitivity to the presence of deep fading…

FPGAs have shown great potential in providing low-latency and energy-efficient solutions for deep neural network (DNN) inference applications. Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division…

Deep learning implementations on CPUs (Central Processing Units) are gaining more traction. Enhanced AI capabilities on commodity x86 architectures are commercially appealing due to the reuse of existing hardware and virtualization ease. A…

Modern general-purpose accelerators integrate a large number of programmable area- and energy-efficient processing elements (PEs), to deliver high performance while meeting stringent power delivery and thermal dissipation constraints. In…

Simple graph algorithms such as PageRank have been the target of numerous hardware accelerators. Yet, there also exist much more complex graph mining algorithms for problems such as clustering or maximal clique listing. These algorithms are…

Probabilistic reasoning is an essential tool for robust decision-making systems because of its ability to explicitly handle real-world uncertainty, constraints and causal relations. Consequently, researchers are developing hybrid models by…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

High-level synthesis (HLS) accelerates FPGA design by rapidly generating diverse implementations using optimization directives. However, even with cycle-accurate C/RTL co-simulation, the reported clock cycles often differ significantly from…

Matrix-vector multiplication is a fundamental building block in neural networks, vector databases, and large language models, particularly during inference. As a result, efficient matrix-vector multiplication engines directly translate into…

Serving as an essential prerequisite for modern power system operation, robust state estimation (RSE) could effectively resist noises and outliers in measurements. The emerging neural network (NN) based end-to-end (E2E) learning framework…

Tokenization is a critical preprocessing step in large language model pipelines, yet widely-used implementations remain CPU-bound and suboptimal for batch inference workflows on GPU. We present BlockBPE, a parallel GPU implementation of…

Vector architectures are gaining traction for highly efficient processing of data-parallel workloads, driven by all major ISAs (RISC-V, Arm, Intel), and boosted by landmark chips, like the Arm SVE-based Fujitsu A64FX, powering the TOP500…

Today's microprocessors have grown significantly in complexity and functionality. Most of today's processors provide at least three levels of memory hierarchy, are heavily pipelined, and support some sort of cache coherency protocol. These…

We introduce CRPE (Code Reasoning Process Enhancer), an innovative three-stage framework for data synthesis and model training that advances the development of sophisticated code reasoning capabilities in large language models (LLMs).…

As process technology continues to scale aggressively, circuit aging in a neuromorphic hardware due to negative bias temperature instability (NBTI) and time-dependent dielectric breakdown (TDDB) is becoming a critical reliability issue and…

Large Language Models (LLMs) have exhibited strong mathematical reasoning prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle yet critical errors, such as…

In the field of cryptography till date the 2-byte in 1-clock is the best known RC4 hardware design [1], while 1-byte in 1-clock [2], and the 1-byte in 3 clocks [3][4] are the best known implementation. The design algorithm in[2] considers…