Porting CUDA-Based Molecular Dynamics Algorithms to AMD ROCm Platform Using HIP Framework: Performance Analysis

Kuznetsov, Evgeny; Stegaĭlov, V. V.

doi:10.1007/978-3-030-36592-9_11

Cited by 12 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the number of adopters and contributors of community software scales only in the presence of good platform portability. The effort of porting a software stack to new architectures is, for example, described for molecular dynamics algorithm in [ 7 ], and for the solution of finite element problems in [ 12 ]. Concerning performance portability, the authors of [ 11 ] compare the algorithm performance for CUDA, HC++, HIP, and OpenCL backends.…”

Section: Introductionmentioning

confidence: 99%

Preparing Ginkgo for AMD GPUs – A Testimonial on Porting CUDA Code to HIP

Tsai

Cojean

Ribizel

et al. 2021

Euro-Par 2020: Parallel Processing Workshops

View full text Add to dashboard Cite

With AMD reinforcing their ambition in the scientific high performance computing ecosystem, we extend the hardware scope of the Ginkgo linear algebra package to feature a HIP backend for AMD GPUs. In this paper, we report and discuss the porting effort from CUDA, the extension of the HIP framework to add missing features such as cooperative groups, the performance price of compiling HIP code for AMD architectures, and the design of a library providing native backends for NVIDIA and AMD GPUs while minimizing code duplication by using a shared code base.

show abstract

Section: Introductionmentioning

confidence: 99%

Preparing Ginkgo for AMD GPUs – A Testimonial on Porting CUDA Code to HIP

Tsai

Cojean

Ribizel

et al. 2021

Euro-Par 2020: Parallel Processing Workshops

View full text Add to dashboard Cite

show abstract

“…Consequently, graphics processing units (GPUs) are extensively used nowadays in DNN models to overcome the inherent computational challenges of healthcare applications [9][10] [11]. Interestingly, computation through GPU has offered impeccable advantages over other accelerators [12].…”

Section: Introductionmentioning

confidence: 99%

A Selective Mitigation Technique of Soft Errors for DNN Models Used in Healthcare Applications: DenseNet201 Case Study

2021

View full text Add to dashboard Cite

Deep neural networks (DNNs) have been successfully deployed in widespread domains, including healthcare applications. DenseNet201 is a new DNN architecture used in healthcare systems (i.e., presence detection of the surgical tool). Specialized accelerators such as GPUs have been used to speed up the execution of DNNs. Nevertheless, GPUs are prone to transient effects and other reliability threats, which can impact DNN models' reliability. Safety-critical systems, such as healthcare applications, must be highly reliable because minor errors might lead to severe injury or death. In this paper, we propose a selective mitigation technique that relies on in-depth analysis. First, we inject the DenseNet201 model implemented on a GPU via NVIDIA's SASSIFI fault injector. Second, we perform a comprehensive analysis from the perspective of kernel and layer to identify the most vulnerable portions of the injected model. Finally, we validate our technique by applying it to the top-vulnerable kernels to selectively protect the only sensitive portions of the model to avoid unnecessary overheads. Our experiments demonstrate that our mitigation technique achieves a significant reduction in the percentage of errors that cause malfunction (errors that lead to misclassification) from 6.463% to 0.21%. Moreover, the performance overhead (the execution time) of our technique is compared with the well-known protection techniques: Algorithm-Based Fault Tolerance (ABFT), Double Modular Redundancy (DMR), and Triple Modular Redundancy (TMR). The proposed solution shows only 0.3035% overhead compared to these techniques while correcting up 84.8% of the SDC errors in DenseNet201, remarkably improving the healthcare domain's model reliability.

show abstract

“…each of which has its own elements, behaviour and execution flow. However, due to their computational power, graphics processing units (GPUs) are extensively used in CNNs to overcome the inherent computational challenges of healthcare applications [9] [10] [11] [12]. Notwithstanding, there are certain GPU units that if exposed to soft errors, can disrupt the reliability of the GPU operations; these units include memory elements such as register file and logic resources such as Arithmetic Logic Units (ALUs) [13].…”

Section: Introductionmentioning

confidence: 99%

Analyzing the Resilience of Convolutional Neural Networks Implemented on GPUs

Adam

Mohd

Ibrahim

2021

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

There have been an extensive use of Convolutional Neural Networks (CNNs) in healthcare applications. Presently, GPUs are the most prominent and dominated DNN accelerators to increase the execution speed of CNN algorithms to improve their performance as well as the Latency. However, GPUs are prone to soft errors. These errors can impact the behaviors of the GPU dramatically. Thus, the generated fault may corrupt data values or logic operations and cause errors, such as Silent Data Corruption. unfortunately, soft errors propagate from the physical level (microarchitecture) to the application level (CNN model). This paper analyzes the reliability of the AlexNet model based on two metrics: (1) critical kernel vulnerability (CKV) used to identify the malfunction and light- malfunction errors in each kernel, and (2) critical layer vulnerability (CLV) used to track the malfunction and light-malfunction errors through layers. To achieve this, we injected the AlexNet which was popularly used in healthcare applications on NVIDIA’s GPU, using the SASSIFI fault injector as the major evaluator tool. The experiments demonstrate through the average error percentage that caused malfunction of the models has been reduced from 3.7% to 0.383% by hardening only the vulnerable part with the overhead only 0.2923%. This is a high improvement in the model reliability for healthcare applications.

show abstract

Porting CUDA-Based Molecular Dynamics Algorithms to AMD ROCm Platform Using HIP Framework: Performance Analysis

Cited by 12 publications

References 4 publications

Preparing Ginkgo for AMD GPUs – A Testimonial on Porting CUDA Code to HIP

Preparing Ginkgo for AMD GPUs – A Testimonial on Porting CUDA Code to HIP

A Selective Mitigation Technique of Soft Errors for DNN Models Used in Healthcare Applications: DenseNet201 Case Study

Analyzing the Resilience of Convolutional Neural Networks Implemented on GPUs

Contact Info

Product

Resources

About