اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures
76
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Designing efficient and scalable sparse linear algebra kernels on modern multi-GPU based HPC systems is a daunting task due to significant irregular memory references and workload imbalance across the GPUs. This is particularly the case for Sparse Triangular Solver (SpTRSV) which introduces additional two-dimensional computation dependencies among subsequent computation steps. Dependency information is exchanged and shared among GPUs, thus warrant for efficient memory allocation, data partitioning, and workload distribution as well as fine-grained communication and synchronization support. In this work, we demonstrate that directly adopting unified memory can adversely affect the performance of SpTRSV on multi-GPU architectures, despite linking via fast interconnect like NVLinks and NVSwitches. Alternatively, we employ the latest NVSHMEM technology based on Partitioned Global Address Space programming model to enable efficient fine-grained communication and drastic synchronization overhead reduction. Furthermore, to handle workload imbalance, we propose a malleable task-pool execution model which can further enhance the utilization of GPUs. By applying these techniques, our experiments on the NVIDIA multi-GPU supernode V100-DGX-1 and DGX-2 systems demonstrate that our design can achieve on average 3.53x (up to 9.86x) speedup on a DGX-1 system and 3.66x (up to 9.64x) speedup on a DGX-2 system with 4-GPUs over the Unified-Memory design. The comprehensive sensitivity and scalability studies also show that the proposed zero-copy SpTRSV is able to fully utilize the computing and communication resources of the multi-GPU system.
قيم البحث
اقرأ أيضاً
The rapidly growing popularity and scale of data-parallel workloads demand a corresponding increase in raw computational power of GPUs (Graphics Processing Units). As single-GPU systems struggle to satisfy the performance demands, multi-GPU systems h
ave begun to dominate the high-performance computing world. The advent of such systems raises a number of design challenges, including the GPU microarchitecture, multi-GPU interconnect fabrics, runtime libraries and associated programming models. The research community currently lacks a publically available and comprehensive multi-GPU simulation framework and benchmark suite to evaluate multi-GPU system design solutions. In this work, we present MGSim, a cycle-accurate, extensively validated, multi-GPU simulator, based on AMDs Graphics Core Next 3 (GCN3) instruction set architecture. We complement MGSim with MGMark, a suite of multi-GPU workloads that explores multi-GPU collaborative execution patterns. Our simulator is scalable and comes with in-built support for multi-threaded execution to enable fast and efficient simulations. In terms of performance accuracy, MGSim differs $5.5%$ on average when compared against actual GPU hardware. We also achieve a $3.5times$ and a $2.5times$ average speedup in function emulation and architectural simulation with 4 CPU cores, while delivering the same accuracy as the serial simulation. We illustrate the novel simulation capabilities provided by our simulator through a case study exploring programming models based on a unified multi-GPU system (U-MGPU) and a discrete multi-GPU system (D-MGPU) that both utilize unified memory space and cross-GPU memory access. We evaluate the design implications from our case study, suggesting that D-MGPU is an attractive programming model for future multi-GPU systems.
COVID-19 has claimed more 1 million lives and resulted in over 40 million infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. In response, the DOE recently established the Medical Therapeutics project as part of the Nat
ional Virtual Biotechnology Laboratory, and tasked it with creating the computational infrastructure and methods necessary to advance therapeutics development. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation and characterize their performance, and highlight science advances that these capabilities have enabled.
We present new results on the strong parallel scaling for the OpenACC-accelerated implementation of the high-order spectral element fluid dynamics solver Nek5000. The test case considered consists of a direct numerical simulation of fully-developed t
urbulent flow in a straight pipe, at two different Reynolds numbers $Re_tau=360$ and $Re_tau=550$, based on friction velocity and pipe radius. The strong scaling is tested on several GPU-enabled HPC systems, including the Swiss Piz Daint system, TACCs Longhorn, Julichs JUWELS Booster, and Berzelius in Sweden. The performance results show that speed-up between 3-5 can be achieved using the GPU accelerated version compared with the CPU version on these different systems. The run-time for 20 timesteps reduces from 43.5 to 13.2 seconds with increasing the number of GPUs from 64 to 512 for $Re_tau=550$ case on JUWELS Booster system. This illustrates the GPU accelerated version the potential for high throughput. At the same time, the strong scaling limit is significantly larger for GPUs, at about $2000-5000$ elements per rank; compared to about $50-100$ for a CPU-rank.
Graphics Processing Units (GPUs) have been widely used to accelerate artificial intelligence, physics simulation, medical imaging, and information visualization applications. To improve GPU performance, GPU hardware designers need to identify perform
ance issues by inspecting a huge amount of simulator-generated traces. Visualizing the execution traces can reduce the cognitive burden of users and facilitate making sense of behaviors of GPU hardware components. In this paper, we first formalize the process of GPU performance analysis and characterize the design requirements of visualizing execution traces based on a survey study and interviews with GPU hardware designers. We contribute data and task abstraction for GPU performance analysis. Based on our task analysis, we propose Daisen, a framework that supports data collection from GPU simulators and provides visualization of the simulator-generated GPU execution traces. Daisen features a data abstraction and trace format that can record simulator-generated GPU execution traces. Daisen also includes a web-based visualization tool that helps GPU hardware designers examine GPU execution traces, identify performance bottlenecks, and verify performance improvement. Our qualitative evaluation with GPU hardware designers demonstrates that the design of Daisen reflects the typical workflow of GPU hardware designers. Using Daisen, participants were able to effectively identify potential performance bottlenecks and opportunities for performance improvement. The open-sourced implementation of Daisen can be found at gitlab.com/akita/vis. Supplemental materials including a demo video, survey questions, evaluation study guide, and post-study evaluation survey are available at osf.io/j5ghq.
FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a higher throughput than GPU coun
terparts. In this paper, we demonstrate that FPGA acceleration can be a superior solution in terms of both throughput and energy efficiency when a CNN is trained with binary constraints on weights and activations. Specifically, we propose an optimized FPGA accelerator architecture tailored for bitwise convolution and normalization that features massive spatial parallelism with deep pipelines stages. A key advantage of the FPGA accelerator is that its performance is insensitive to data batch size, while the performance of GPU acceleration varies largely depending on the batch size of the data. Experiment results show that the proposed accelerator architecture for binary CNNs running on a Virtex-7 FPGA is 8.3x faster and 75x more energy-efficient than a Titan X GPU for processing online individual requests in small batch sizes. For processing static data in large batch sizes, the proposed solution is on a par with a Titan X GPU in terms of throughput while delivering 9.5x higher energy efficiency.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
