Related papers: The ARM Scalable Vector Extension

Support Vector Machine (SVM) algorithm requires a high computational cost (both in memory and time) to solve a complex quadratic programming (QP) optimization problem during the training process. Consequently, SVM necessitates high…

The performance of AI accelerators is increasingly limited by data movement, memory access, and orchestration overheads rather than raw compute capability. This paper presents MAVeC, a messaging-based adaptive vector computing accelerator…

Non-volatile main memory (NVRAM) technologies provide an attractive set of features for large-scale graph analytics, including byte-addressability, low idle power, and improved memory-density. NVRAM systems today have an order of magnitude…

In this paper, we propose Vo-Ve, a novel voice-vector embedding that captures speaker identity. Unlike conventional speaker embeddings, Vo-Ve is explainable, as it contains the probabilities of explicit voice attribute classes. Through…

Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid…

Vector data is prevalent across business and scientific applications, and its popularity is growing with the proliferation of learned embeddings. Vector data collections often reach billions of vectors with thousands of dimensions, thus,…

Self- and alien-FEXT disturbances on the same cable severely limit performance in the commonly employed VDSL2 17a, i.e. 17.6 MHz, standard profile. Then, in a multi-operator environment, VDSL2 may be unable to provide the 100 Mbit/s speed…

Spiking Neural Networks (SNNs) and transformers represent two powerful paradigms in neural computation, known for their low power consumption and ability to capture feature dependencies, respectively. However, transformer architectures…

Many machine learning tasks can benefit from external knowledge. Large knowledge graphs store such knowledge, and embedding methods can be used to distill it into ready-to-use vector representations for downstream applications. For this…

Modern computing systems are embracing non-volatile memory (NVM) to implement high-capacity and low-cost main memory. Elevated operating voltages of NVM accelerate the aging of CMOS transistors in the peripheral circuitry of each memory…

With an increasing number of value-flow properties to check, existing static program analysis still tends to have scalability issues when high precision is required. We observe that the key design flaw behind the scalability problem is that…

As modern software systems expand in scale and complexity, the challenges associated with their modeling and formulation grow increasingly intricate. Traditional approaches often fall short in effectively addressing these complexities,…

We accelerate the 4-bit product quantization (PQ) on the ARM architecture. Notably, the drastic performance of the conventional 4-bit PQ strongly relies on x64-specific SIMD register, such as AVX2; hence, we cannot yet achieve such good…

We propose a novel end-to-end pipeline for online long-range vectorized high-definition (HD) map construction using on-board camera sensors. The vectorized representation of HD maps, employing polylines and polygons to represent map…

AMD SEV is a hardware feature designed for the secure encryption of virtual machines. SEV aims to protect virtual machine memory not only from other malicious guests and physical attackers, but also from a possibly malicious hypervisor.…

This work focuses on an efficient Agile design methodology for domain-specific accelerators. We employ feature-by-feature enhancement of a vertical development stack and apply it to the TVM/VTA inference accelerator. We have enhanced the…

Single-issue processor cores are very energy efficient but suffer from the von Neumann bottleneck, in that they must explicitly fetch and issue the loads/storse necessary to feed their ALU/FPU. Each instruction spent on moving data is a…

The computational complexity of solving nonlinear support vector machine (SVM) is prohibitive on large-scale data. In particular, this issue becomes very sensitive when the data represents additional difficulties such as highly imbalanced…

Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high…

Experimental results from a 65 nm CMOS commercial technology SRAM test chip reveal a linear correlation between a new electrical parameter -- the word-line voltage margin (VWLVM) -- and the measured circuit alpha-SER. Additional experiments…