The continuous growth of on-chip transistors driven by technology scaling urges architecture developers to design and implement novel architectures to effectively utilize the excessive on-chip resources.Due to the challenges of programming in register-transfer level (RTL) languages, performance modeling based on simulation is typically developed alongside hardware implementation, allowing the exploration of high-level design decisions before dealing with the error-prone, low-level RTL details.However, this approach also introduces new challenges in coordinating across multiple teams to align implementation details separate codebases.In this paper, we address this issue by presenting Assassyn, a unified, high-level, and general-purpose programming framework for architectural simulation and implementation.By taking advantage of the concept of asynchronous event handling, a widely existing behavior in both hardware design and implementation and software engineering, a general-purpose, and high-level programming abstraction is proposed to mitigate the difficulties of RTL programming.Moreover, the unified programming interface naturally enables an accurate and faithful alignment between the simulation-based performance modeling and RTL implementation.Our evaluation demonstrates that Assassyn's high-level programming interface is sufficiently expressive to implement a wide range * Serve as both the first and correspondence author.

Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference. However, existing tuning techniques fall short because of the high computation and memory overhead. To this end, we introduce a computation- and memory-efficient LLM tuning framework, called Edge-LLM, to facilitate affordable and effective LLM adaptation on edge devices. Specifically, Edge-LLM features three core components: (1) a layer-wise unified compression (LUC) technique to reduce the computation overhead by generating layer-wise pruning sparsity and quantization bit-width policies, (2) an adaptive layer tuning and voting scheme to reduce the memory overhead by reducing the backpropagation depth, and (3) a complementary hardware scheduling strategy to handle the irregular computation patterns introduced by LUC and adaptive layer tuning, thereby achieving improved real hardware efficiency. Extensive experiments demonstrate that Edge-LLM achieves on-device adaptation with comparable task accuracy as vanilla tuning methods with a 2.92× speed up and a 4× reduction in memory overhead. Our code is available at https://github.com/GATECH-EIC/Edge-LLM

Mare Humorum is located on the nearside of the Moon, at 24.4S and 38.6W. This region has rich geological structures, which not only experienced early lunar volcanic activity but also obtained a mascon. The research on thermal behaviors in Mare Humorum can bring new insights into the multiring impact basins. In this study, Chang’e-2 lunar microwave sounder (CELMS) data were used to obtain brightness temperature (TB) maps. To highlight the characteristics of Mare Humorum, the normalized TB (nTB) was generated. By analyzing the daytime and nighttime nTB maps, we found that there are both hot regions and cold spots in Mare Humorum. Combining Clementine UVVIS data with LRO Diviner data, some intuitive figures were made to find the reasons for these thermal anomalies in the study area. The results showed that TiO2 abundance (TA) and rock abundance (RA) are the factors for TB anomalies in Mare Humorum.

Infrared image has received much attention, but the weak features and multi noise in it bring difficulties to object detection. In this letter, an improved YOLOX called YOLOX-IRI is proposed to improve the detection accuracy on infrared images. First, an improved CBAM is proposed to make the network focus on the object area. This module enriches the feature information by mixing three kinds of pooling methods properly, which helps the network distinguish between background and object. Second, class-balanced loss is introduced to suppress adverse effects caused by unbalanced sample distribution problems. This loss function can balance the contribution of each class to the total loss by assigning weights, thereby improving the classification result. Experimental results indicate that our method is superior to other object detection algorithms.