当前位置: X-MOL 学术ACM Trans. Archit. Code Optim. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Simple Model for Portable and Fast Prediction of Execution Time and Power Consumption of GPU Kernels
ACM Transactions on Architecture and Code Optimization ( IF 1.6 ) Pub Date : 2020-12-30 , DOI: 10.1145/3431731
Lorenz Braun 1 , Sotirios Nikas 2 , Chen Song 2 , Vincent Heuveline 2 , Holger Fröning 1
Affiliation  

Characterizing compute kernel execution behavior on GPUs for efficient task scheduling is a non-trivial task. We address this with a simple model enabling portable and fast predictions among different GPUs using only hardware-independent features. This model is built based on random forests using 189 individual compute kernels from benchmarks such as Parboil, Rodinia, Polybench-GPU, and SHOC. Evaluation of the model performance using cross-validation yields a median Mean Average Percentage Error (MAPE) of 8.86–52.0% for time and 1.84–2.94% for power prediction across five different GPUs, while latency for a single prediction varies between 15 and 108 ms.

中文翻译:

一种可移植且快速预测 GPU 内核执行时间和功耗的简单模型

表征 GPU 上的计算内核执行行为以实现高效的任务调度是一项不平凡的任务。我们通过一个简单的模型来解决这个问题,该模型仅使用独立于硬件的特性在不同的 GPU 之间实现可移植和快速的预测。该模型基于随机森林构建,使用来自 Parboil、Rodinia、Polybench-GPU 和 SHOC 等基准的 189 个单独的计算内核。使用交叉验证对模型性能进行评估产生的平均平均百分比误差 (MAPE) 为 8.86-52.0% 的时间和 1.84-2.94% 的功率预测跨五个不同 GPU,而单个预测的延迟在 15 到 108 之间变化小姐。
更新日期:2020-12-30
down
wechat
bug