Advanced Micro Devices (United States)

This paper summarizes the opportunities of in-network collective operations for accelerated collective operations in artificial intelligence (AI) workloads. We provide sufficient detail to make this important field accessible to nonexperts in AI or networking, fostering a connection between these communities.

Far-end crosstalk between coupled microstrip lines with varying spacing is analyzed. The difference between the capacitive and inductive coupling coefficients is used to quantify this crosstalk, as it is directly proportional to this difference. It is demonstrated that, due to the presence of the solder mask, the far-end crosstalk does not always increase as the spacing between lines decreases, but it follows non-monotonic behavior. Considering this finding, data calculated from the coupling coefficients versus spacing is then used to determine the optimal spacing between a single-ended channel and a differential pair channel, in which the far-end crosstalk is minimized. Furthermore, experimental results show that the contrast between the PCB dielectric laminate and the solder mask causes the crosstalk to significantly differ in magnitude for microstrips with identical cross-sections, highlighting the importance of selecting the right combination of solder mask and dielectric laminate as a key design parameter for applications with stringent crosstalk noise specifications.

Anticipating the rise of the Internet of Things (IoT) era, we have proposed an object detection framework that employs a CMOS image sensor with binary feature extraction to reduce power requirements. Initially, we presented a lightweight deep neural network for the feature data based on the YOLOv7, comparable to the YOLOv7-tiny in the number of parameters and FLOPs, but it enhances large object recognition accuracy (APL50) by 6.6%. Moreover, our approach achieves a 48.8% reduction of GPU power consumption compared to the YOLOv7. Additionally, we introduce an on-chip signal processing method for the binary feature data. The proposed method achieves a compression rate of 64.1% and increases GPU power consumption by only 14.9% during the decoding process preceding object detection. Moreover, the size of 1-bit feature data is reduced by 96.0%, and object recognition accuracy is improved by 4.0% relative to 1-bit RGB color images.

Several hyperscalers have recently disclosed the occurrence of silent data corruptions (SDCs) in their system fleets, sparking concerns about the severity of known and the existence of unidentified root causes of faults in CPUs. These incidents reveal that CPUs may generate incorrect results due to latent manufacturing defects, variability, marginalities, bugs, and aging. To tackle this, we present Harpocrates, an automated methodology for the generation of short, constrained-random functional test programs that maximize fault detection in target CPU structures and can be employed at different stages of system lifecycle. Harpocrates adopts a hardware-model-in-the-loop approach, iteratively refining the generated test programs via a detailed simulation-based microarchitecture engine that models and grades for multiple fault types. Harpocrates adapts to various program generators, ISAs, microarchitectures, and fault types. Our results on seven important CPU structures show that Harpocrates outperforms open-source test suites in fault detection capability while attaining much shorter generation times.

Abstract Vibrational strong coupling (VSC) has been shown to significantly modify the chemical and physical properties of molecules and materials. Here we report the non‐resonant Rayleigh scattering of various molecules in liquid phase, such as toluene and water, and find that it is enhanced by ca. two orders of magnitude in the visible upon VSC of vibrational bands of the solvent in the infrared (IR). The results show that the enhanced scattering is due to the formation of new phase possibly consisting of clusters. The VSC phase undergoes a well‐defined transition with temperature and solvent composition. This finding has significant consequences for understanding how VSC influences molecular processes such as chemical reactivity and self‐assembly.

Stardust load emulator (SDLE) is AMD’s proprietary tool that is used to validate voltage regulator (VR) power delivery (PD) design on motherboards that are dedicated to AMD’s CPU. This paper proposed a new full system simulation methodology to incorporate three major segments of design into a single framework to evaluate system performance. The simulation and lab measurement data are highly correlated with less than 3% discrepancy.

Up to the current fall patterns that started at the end of 2021, the Chinese real estate market has developed at such a rapid pace over the course of the previous few decades. Investors and the government have found it more difficult to accurately forecast future property values as a consequence of this challenge. It is because of the current status of the economy that this has come about. For the purpose of this study, we use Gaussian process regressions using a wide range of kernels and basis functions to investigate the monthly residential property prices in Ningbo City, which is located in Zhejiang Province, China. The time period covered by this study is from May 2011 to July 2024. Estimated models are used in our forecasting endeavors. These models are trained using a mix of cross-validation and Bayesian optimizations. The models that were developed were effective in accurately forecasting the prices that would be seen out of sample from December 2021 to July 2024. With a relative root mean square error of 0.1626 percent, these models may be considered accurate. It is possible that our results might be utilized on their own or in conjunction with further forecasts in order to construct hypotheses about variations in the values of residential real estate and to carry out additional policy research.