csTuner: Scalable Auto-tuning Framework for Complex Stencil Computation on GPUs

Sun, Qingxiao; Liu, Yi; Yang, Hailong; Jiang, Zhonghui; Liu, Xiaoyan; Dun, Ming; Luan, Zhongzhi; Qian, Depei

doi:10.1109/cluster48925.2021.00037

Cited by 9 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPU. GPUs [3,182,183] have been shown to increase performance due to the high degree of parallelism present in the stencil computation. Wahib et al [184] develop an analytical performance model for choosing an optimal GPU-based execution strategy for various scientific stencil kernels.…”

Section: Related Workmentioning

confidence: 99%

Casper: Accelerating Stencil Computations Using Near-Cache Processing

Denzler¹,

Oliveira²,

Hajinazar³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Stencil computations are commonly used in a wide variety of scientific applications, ranging from largescale weather prediction to solving partial differential equations. Stencil computations are characterized by three properties: (1) low arithmetic intensity, (2) limited temporal data reuse, and (3) regular and predictable data access pattern. As a result, stencil computations are typically bandwidth-bound workloads, which only experience limited benefits from the deep cache hierarchy of modern CPUs. In this work, we propose Casper, a near-cache accelerator consisting of specialized stencil computation units connected to the last-level cache (LLC) of a traditional CPU. Casper is based on two key ideas: (1) avoiding the cost of moving rarely reused data throughout the cache hierarchy, and (2) exploiting the regularity of the data accesses and the inherent parallelism of stencil computations to increase overall performance. With minimal changes in LLC address decoding logic and data placement, Casper performs stencil computations at the peak LLC bandwidth. We show that by tightly coupling lightweight stencil computation units near LLC, Casper improves performance of stencil kernels by 1.65× on average (up to 4.16×) compared to a commercial high-performance multi-core processor, while reducing system energy consumption by 35% on average (up to 65%). Casper provides 37× (up to 190×) improvement in performance-per-area compared to a state-of-the-art GPU.

show abstract

Section: Related Workmentioning

confidence: 99%

Casper: Accelerating Stencil Computations Using Near-Cache Processing

Denzler¹,

Oliveira²,

Hajinazar³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…An auto tuning approach, which is an alternative to performance prediction as proposed by our method, is described by [17]. They show that an auto tuning approach can work without exhaustive scanning of the whole parameter space.…”

Section: Related Workmentioning

confidence: 99%

Analytical Performance Estimation during Code Generation on Modern GPUs

Ernst¹,

Holzer²,

Hager³

et al. 2022

Preprint

View full text Add to dashboard Cite

Analytical Performance Modeling helps to find the best tuning parameters for code generation • Analytical Performance Modeling gives insight that is unavailable to black box machine learning or auto tuning • The thread block size is a decisive factor for GPU cache data volumes and performance • GPU cache behavior and GPU performance can be accurately predicted based only on high level information

show abstract

“…Tiling (or blocking) and streaming [33] are widely adopted methods for improving parallelism and data locality of stencil computation. In addition, analysis algorithm [29] and auto-tuning technique [6,37,38] have also been used to specify the optimal blocking parameters. There are also research works focus on improving the arithmetic intensity in order to relieve the memory bottleneck of stencil computation, such as kernel fusion [34], and loop unrolling [46].…”

mentioning

confidence: 99%

Toward accelerated stencil computation by adapting tensor core unit on GPU

Liu

Yang

et al. 2022

Proceedings of the 36th ACM International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

The Tensor Core Unit (TCU) has been increasingly adopted on modern high performance processors, specialized in boosting the performance of general matrix multiplication (GEMM). Due to its highly optimized hardware design, TCU can significantly accelerate GEMM-based operations widely used in scientific as well as deep learning applications. However, there is few work exploiting TCU to accelerate non-GEMM operations such as stencil computation that is also important in the field of high performance computing. To the best of our knowledge, there is no previous work that adapts stencil computation to TCU efficiently by considering its unique characteristics. In this paper, we propose a new method called TCstencil to adapt TCU for accelerating stencil computation. Specifically, we re-design the stencil computation as a series of reduction and summation operations in order to leverage the computing power of TCU. In addition, we propose corresponding optimizations for better exploiting TCU and memory hierarchy on GPU. We evaluate our method with different stencils and input mesh sizes on NVIDIA A100 and V100 GPUs. The experiment results demonstrate our method can achieve superior performance compared to the state-of-the-art stencil optimization frameworks.

show abstract

csTuner: Scalable Auto-tuning Framework for Complex Stencil Computation on GPUs

Cited by 9 publications

References 39 publications

Casper: Accelerating Stencil Computations Using Near-Cache Processing

Casper: Accelerating Stencil Computations Using Near-Cache Processing

Analytical Performance Estimation during Code Generation on Modern GPUs

Toward accelerated stencil computation by adapting tensor core unit on GPU

Contact Info

Product

Resources

About