Presentation
GPU Mangrove - Execution Time and Power Prediction
SessionResearch Poster Session
Event Type
Research Poster
Pre-Recorded
TimeTuesday, June 23rd3:40pm - 3:45pm
LocationAnalog 1
DescriptionCharacterizing compute kernel execution behavior on GPUs for efficient task scheduling is a non trivial task. We address this with a simple model called GPU Mangrove enabling portable and fast predictions among different GPUs using only hardware-independent features extracted. The 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 [13.45%, 44.56%] and [1.81%, 2.91%], for time respectively power prediction on five different GPUs, while latency for a single prediction
varies between 0.1 and 0.2 seconds.
varies between 0.1 and 0.2 seconds.
Poster PDF
Poster Authors
