The rich, complementary data provided by Sentinel-1 and Sentinel-2 satellite constellations host considerable potential to transform Earth observation (EO) applications. However, a substantial amount of effort and infrastructure is still required for the generation of analysis-ready data (ARD) from the low-level products provided by the European Space Agency (ESA). Here, a flexible Python framework able to generate a range of consistent ARD aligned with the ESA-recommended processing pipeline is detailed. Sentinel-1 Synthetic Aperture Radar (SAR) data are radiometrically calibrated, speckle-filtered and terrain-corrected, and Sentinel-2 multi-spectral data resampled in order to harmonise the spatial resolution between the two streams and to allow stacking with multiple scene classification masks. The global coverage and flexibility of the framework allows users to define a specific region of interest (ROI) and time window to create geo-referenced Sentinel-1 and Sentinel-2 images, or a combination of both with closest temporal alignment. The framework can be applied to any location and is user-centric and versatile in generating multi-modal and multi-temporal ARD. Finally, the framework handles automatically the inherent challenges in processing Sentinel data, such as boundary regions with missing values within Sentinel-1 and the filtering of Sentinel-2 scenes based on ROI cloud coverage.
The RISC-V "V" extension introduces vector processing to the RISC-V architecture. Unlike most SIMD extensions, it supports long vectors which can result in significant improvement of multiple applications. In this paper, we present our ongoing research to implement and optimize a vectorized Winograd algorithm used in convolutional layers on RISC-V Vector(RISC-VV) processors. Our study identifies effective techniques for optimizing the kernels of Winograd on RISC-VV using intrinsic instructions, and showcases how certain instructions offer better performance. Our co-design findings suggest that the Winograd algorithm benefits from vector lengths up to 2048 bits and cache sizes up to 64MB. We use our experience with Winograd to highlight potential enhancements for the standard that would simplify code generation and aid low-level programming. Finally, we share our experience from experimenting with forks of gem5 for RISC-VV and stress the importance of a mature software ecosystem, to facilitate design space exploration and architectural optimization. Our study identifies effective techniques for optimizing the kernels of Winograd on RISC-VV using the available intrinsic instructions and showcases that certain instructions offer better performance to the vectorized algorithm. Furthermore, our co-design study reveals that the Winograd algorithm benefits from vector lengths up to 2048 bits and cache sizes up to 64MB.
The performance of convolutional algorithm depends on the size, stride, and input/output channels of the convolutional kernel. Moreover, the varying computational demands of convolutional layers influence the requirement for SIMD support on multicore processors. Finally, sharing cache resources in scenarios such as inference serving also impacts the runtime choice of the best algorithm. To identify the best settings, we perform a co-design exploration, focusing on the software parameters of the convolutional layers of convolutional neural networks (CNNs), and three distinct algorithmic implementations: Direct, im2col+GEMM, and Winograd, jointly with hardware parameters for vector architectures. Our simulation-based study identifies that Winograd is suitable for convolutional layers with a 3 × 3 kernel size and stride 1, specifically for shorter vector lengths and L2 cache sizes. For layers with more input/output channels, im2col+GEMM performs better. Looking at VGG-16, our study shows that not all the layers benefit from our biggest simulated cache memory when using the Direct and Winograd implementations, while the im2col+GEMM implementation scales to an L2 cache memory of 64MB with all layers. In contrast, all the simulated layers of YOLOv3 benefit from an L2 cache memory of 64MB, for all convolutional algorithms. To select the best implementation at runtime, we develop a random forest predictor that selects the best algorithm in over 90% of the cases, with limited degradation when a sub-optimal configuration is selected. We conclude with a Pareto analysis of the area-performance trade-off in an inference serving scenario, on a 7nm RISC-V multicore model with a vector unit supporting vectors of 512 up to 4096 bits.
3 August 2023 in IEEE Transactions on Computational Social Systems
Forced displacement of people worldwide, for example, due to violent conflicts, is common in the modern world, and today more than 82 million people are forcibly displaced. This puts the problem of migration at the forefront of the most important problems of humanity. The Flee simulation code is an agent-based modeling tool that can forecast population displacements in civil war settings, but performing accurate simulations requires nonnegligible computational capacity. In this article, we present our approach to Flee parallelization for fast execution on multicore platforms, as well as discuss the computational complexity of the algorithm and its implementation. We benchmark parallelized code using supercomputers equipped with AMD EPYC Rome 7742 and Intel Xeon Platinum 8268 processors and investigate its performance across a range of alternative rule sets, different refinements in the spatial representation, and various numbers of agents representing displaced persons. We find that Flee scales excellently to up to 8192 cores for large cases, although very detailed location graphs can impose a large initialization time overhead.
14 December 2023 in ACM Transactions on Architecture and Code Optimization
Dense linear algebra operations appear very frequently in high-performance computing (HPC) applications, rendering their performance crucial to achieve optimal scalability. As many modern HPC clusters contain multi-GPU nodes, BLAS operations are frequently offloaded on GPUs, necessitating the use of optimized libraries to ensure good performance. Unfortunately, multi-GPU systems are accompanied by two significant optimization challenges: data transfer bottlenecks as well as problem splitting and scheduling in multiple workers (GPUs) with distinct memories. We demonstrate that the current multi-GPU BLAS methods for tackling these challenges target very specific problem and data characteristics, resulting in serious performance degradation for any slightly deviating workload. Additionally, an even more critical decision is omitted because it cannot be addressed using current scheduler-based approaches: the determination of which devices should be used for a certain routine invocation. To address these issues we propose a model-based approach: using performance estimation to provide problem-specific autotuning during runtime. We integrate this autotuning into an end-to-end BLAS framework named PARALiA. This framework couples autotuning with an optimized task scheduler, leading to near-optimal data distribution and performance-aware resource utilization. We evaluate PARALiA in an HPC testbed with 8 NVIDIA-V100 GPUs, improving the average performance of GEMM by 1.7× and energy efficiency by 2.5× over the state-of-the-art in a large and diverse dataset and demonstrating the adaptability of our performance-aware approach to future heterogeneous systems.