Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nearly 100 million molecules and over 3000 sparsely defined tasks, totaling more than 13 billion individual labels of both quantum and biological nature. In comparison, our datasets contain 300 times more data points than the widely used OGB-LSC PCQM4Mv2 dataset, and 13 times more than the quantum-only QM1B dataset. In addition, to support the development of foundational models based on our proposed datasets, we present the Graphium graph machine learning library which simplifies the process of building and training molecular machine learning models for multi-task and multi-level molecular datasets. Finally, we present a range of baseline results as a starting point of multi-task and multi-level training on these datasets. Empirically, we observe that performance on low-resource biological datasets show improvement by also training on large amounts of quantum data. This indicates that there may be potential in multi-task and multi-level training of a foundation model and fine-tuning it to resource-constrained downstream tasks. The Graphium library is publicly available on Github and the dataset links are available in Part 1 and Part 2.

Decoupled architectures provide a key to the problem of sustained supercomputer performance through their ability to hide large memory latencies. When a program executes in a decoupled mode the perceived memory latency at the processor is zero; effectively the entire physical memory has an access time equivalent to the processor's register file, and latency is completely hidden. However, the asynchronous functional units within a decoupled architecture must occasionally synchronize, incurring a high penalty. The goal of compiling and optimizing for decoupled architectures is to partition the program between the asynchronous functional units in such a way that latencies are hidden but synchronization events are executed infrequently. This paper describes a model for decoupled compilation, and explains the effectiveness of compilation for decoupled systems. A number of new compiler optimizations are introduced and evaluated quantitatively using the Perfect Club scientific benchmarks. We show that with a suitable repertoire of optimizations, it is possible to hide large latencies most of the time for most of the programs in the Perfect Club.