14 April 2020 in SAE International Journal of Advances and Current Practices in Mobility
Cast aluminum alloys are used for cylinder heads in internal combustion engines to meet low weight and high strength (lightweight) design requirements. In the combustion chamber, the alloy experiences harsh operating conditions; i.e., temperature variation, constrained thermal expansion, chemical reaction, corrosion, oxidation, and chemical deposition. Under these conditions, thermomechanical fatigue (TMF) damage arises in the form of mechanical damage, environmental (oxidation) damage, and creep damage.In the present work, several important properties that influence the TMF life of the cylinder head have been identified through TMF and finite element analysis (FEA). The results show that improving the strength at high temperatures helps improve TMF life on the exhaust side of the head. On the other hand, improving strength and ductility extend TMF life at low temperature on the intake side. Based on Neu-Sehitoglu TMF damage model, environmental (oxidation) damage is responsible for more than 80% of the total damage on the exhaust side. On the intake side, environmental factors are again a significant contributor to overall damage, but produce a smaller portion of total damage as compared to the exhaust side. Damage due to creep, relative to other categories of damage, is minimal and can therefore be neglected. Environmental (oxidation) damage is strongly influenced by the activation energy for oxidation. A small increase of the activation energy significantly increases the TMF life. The activation energy for oxidation is closely related to the chemical composition of the alloy and the kinetics of oxidation of each element in the alloy. FEA and TMF analysis facilitate optimized selection of target alloys that meet TMF life expectations as engine output increases.
1 August 2023 in Proceedings of the VLDB Endowment
Napa holds Google's critical data warehouses in log-structured merge trees for real-time data ingestion and sub-second response for billions of queries per day. These queries are often multi-key look-ups in highly skewed tables and indexes. In our production experience, only progressive query-specific partitioning can achieve Napa's strict query latency SLOs. Here we advocate good-enough partitioning that keeps the per-query partitioning time low without risking uneven work distribution. Our design combines pragmatic system choices and algorithmic innovations. For instance, B-trees are augmented with statistics of key distributions, thus serving the dual purpose of aiding lookups and partitioning. Furthermore, progressive partitioning is designed to be "good enough" thereby balancing partitioning time with performance. The resulting system is robust and successfully serves day-in-day-out billions of queries with very high quality of service forming a core infrastructure at Google.
23 March 2023 in IEEE Transactions on Parallel and Distributed Systems
Large-scale data transport for data-intensive sciences is a complex multidimensional challenge. The challenge includes optimizing the end-to-end Big Data movement performance in real-time, supporting direct remote data access using NVMe over Fabrics (NVMeoF) and deploying to existing research platforms. AIDTN is the first effort to provide a unique AI system designed to incorporate NVMe over Fabrics (NVMeoF) and optimize coordination among multiple components supporting large-scale, multi-domain Wide Area Network (WAN) data-intensive science. AIDTN's research objective is to integrate next-generation storage architecture using NVMeoF, specialized network design using high-performance network appliances, Data Transfer Nodes (DTNs), catalysts in driving data transport, and a unique AI system explicitly designed for high-performance data movement challenges. AIDTN is the first system that uses network and system features to predict the end-to-end performance of high-performance data movement and further extends the model with NVMe-specific features for NVMeoF remote data access. As a result, AIDTN improves data movement performance by up to 284% while minimizing packet loss compared to other heuristics approaches. It also has a prediction error rate as low as 0.16 compared to AI models with the only network (error rate = 0.29) or network and system features (error rate = 0.19).