Accelerating GPU-Based Out-of-Core Stencil Computation with On-the-Fly Compression

Shen, Jingcheng; Wu, Youfeng; Okita, Masao; Ino, Fumihiko

doi:10.1007/978-3-030-96772-7_1

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the experimental results focus on the reduced execution time and GPU memory usage. The section excludes analyzing accuracy loss caused by compression, because such an analysis was given in our previous work [25], showing that the accuracy loss was tolerable for our real-world stencil code after the code ran for more than 4,000 time steps.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Compression-Based Optimizations for Out-of-Core GPU Stencil Computation

Shen¹,

Deng²,

Wu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

An out-of-core stencil computation code handles large data whose size is beyond the capacity of GPU memory. Whereas, such an code requires streaming data to and from the GPU frequently. As a result, data movement between the CPU and GPU usually limits the performance. In this work, compression-based optimizations are proposed. First, an on-the-fly compression technique is applied to an out-of-core stencil code, reducing the CPU-GPU memory copy. Secondly, a single working buffer technique is used to reduce GPU memory consumption. Experimental results show that the stencil code using the proposed techniques achieved 1.1× speed and reduced GPU memory consumption by 33.0% on an NVIDIA Tesla V100 GPU.

show abstract

Section: Resultsmentioning

confidence: 99%

“…This section provides the basics of integrating on-the-fly compression into outof-core stencil computation. We minimize the length of this section because you can refer to our previous work [25] for more details.…”

Section: Integrating On-the-fly Compressionmentioning

confidence: 99%

Compression-Based Optimizations for Out-of-Core GPU Stencil Computation

Shen¹,

Deng²,

Wu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…GPU-based compression libraries are widely used across broad range of applications ranging from scientific simulations to deep learning [3]. Several lossy and lossless compression efforts such as nvCOMP [14], cuSZ [12], Mgard+ [15], and cuZFP [16] focus on accelerating compression throughput and compression ratio by parameterizing the compressor based on various use-cases.…”

Section: A Gpu-based Compression Librariesmentioning

confidence: 99%

Towards Efficient I/O Pipelines Using Accumulated Compression

Maurya,

Nicolae,

Rafique

et al. 2023

2023 IEEE 30th International Conference on High Performance Computing, Data, and Analytics (HiPC)

View full text Add to dashboard Cite

High-Performance Computing (HPC) workloads generate large volumes of data at high-frequency during their execution, which needs to be captured concurrently at scale. These workloads exploit accelerators such as GPU for faster performance. However, the limited onboard high-bandwidth memory (HBM) on the GPU, and slow device-to-host memory PCIe interconnects lead to I/O overheads during application execution, thereby exacerbating their overall runtime. To overcome the aforementioned limitations, techniques such as compression and asynchronous transfers have been used by data management runtimes. However, compressing small blocks of data leads to a significant runtime penalty on the application. In this paper, we design and develop strategies to optimize the tradeoff between compressing checkpoints instantly and enqueuing transfers immediately versus accumulating snapshots and delaying compression to achieve faster compression throughput. Our evaluations on synthetic and real-life workloads for different systems and workload configurations demonstrate 1.3× to 8.3× speedup compared to the existing checkpoint approaches.

show abstract

A compression-based memory-efficient optimization for out-of-core GPU stencil computation

et al. 2023

Self Cite

View full text Add to dashboard Cite

Stencil computation is an extensively-utilized class of scientific-computing applications that can be efficiently accelerated by graphics processing units (GPUs). Out-of-core approaches enable a GPU to handle large stencil codes whose data size is beyond the memory capacity of the GPU. However, current research on out-of-core stencil computation primarily focus on minimizing the amount of data transferred between the CPU and GPU. Few studies consider simultaneously optimizing data transfer and kernel execution. To fill the research gap, this work presents a synergy between on-and off-chip data reuse for out-of-core stencil codes, termed SO2DR. First, overlapping regions between data chunks are shared in the off-chip memory to eliminate redundant CPU-GPU data transfer. Secondly, redundant computation at the off-chip memory level is intentionally introduced to decouple kernel execution from region sharing, hence enabling data reuse in the onchip memory. Experimental results demonstrate that SO2DR significantly enhances the kernel-execution performance while reducing the CPU-GPU data-transfer time. Specifically, SO2DR achieves average speedups of 2.78× and 1.14× for five stencil benchmarks, compared to an out-of-core stencil code which is free of redundant transfer and computation, and an in-core stencil code which is free of data transfer, respectively.

show abstract

Accelerating GPU-Based Out-of-Core Stencil Computation with On-the-Fly Compression

Cited by 4 publications

References 22 publications

Compression-Based Optimizations for Out-of-Core GPU Stencil Computation

Compression-Based Optimizations for Out-of-Core GPU Stencil Computation

Towards Efficient I/O Pipelines Using Accumulated Compression

A compression-based memory-efficient optimization for out-of-core GPU stencil computation

Contact Info

Product

Resources

About