With the increase of complex scientific simulations driven by workflows and heterogeneous workload profiles, managing system resources effectively is essential for improving performance and system throughput, especially due to trends like heterogeneous HPC and deeply integrated systems with on-chip accelerators. For optimal resource utilization, dynamic resource allocation can improve productivity across all system and application levels, by adapting the applications' configurations to the system's resources. In this context, malleable jobs, which can change resources at runtime, can increase the system throughput and resource utilization while bringing various advantages for HPC users (e.g., shorter waiting time). Malleability has received much attention recently, even though it has been an active research area for almost two decades [1]. This paper presents the state-of-the-art of malleable implementations in HPC systems, targeting mainly malleability in compute and I/O resources. Based on our experiences, we state our current concerns and list future opportunities for research.
Because loops execute their body many times, compiler developers place much emphasis on their optimization. Nevertheless, in view of highly diverse source code and hardware, compilers still struggle to produce optimal target code. The sheer number of possible loop optimizations, including their combinations, exacerbates the problem further. Today's compilers use hard-coded heuristics to decide when, whether, and which of a limited set of optimizations to apply. Often, this leads to highly unstable behavior, making the success of compiler optimizations dependent on the precise way a loop has been written. This paper presents LoopLearner, which addresses the problem of compiler instability by predicting which way of writing a loop will lead to efficient compiled code. To this end, we train a neural network to find semantically invariant source-level transformations for loops that help the compiler generate more efficient code. Our model learns to extract useful features from the raw source code and predicts the speedup that a given transformation is likely to yield. We evaluate LoopLearner with 1,895 loops from various performance-relevant benchmarks. Applying the transformations that our model deems most favorable prior to compilation yields an average speedup of 1.14x. When trying the top-3 suggested transformations, the average speedup even increases to 1.29x. Comparing the approach with an exhaustive search through all available code transformations shows that LoopLearner helps to identify the most beneficial transformations in several orders of magnitude less time.
Load or communication imbalance prevents many codes from taking advantage of the parallelism available on modern supercomputers. We present two scalable methods to highlight imbalance in parallel programs: The first method identifies delays that inflict wait states at subsequent synchronization points, and attributes their costs in terms of resource waste to the original cause. The second method combines knowledge of the critical path with traditional parallel profiles to derive a set of compact performance indicators that help answer a variety of important performance-analysis questions, such as identifying load imbalance, quantifying the impact of imbalance on runtime, and characterizing resource consumption. Both methods employ a highly scalable parallel replay of event traces, making them a suitable analysis instrument for massively parallel MPI programs with tens of thousands of processes.