Multi-level Memory-Centric Profiling on ARM Processors with ARM SPE
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910628736663552 |
|---|---|
| author | Miksits, Samuel Shi, Ruimin Gokhale, Maya Wahlgren, Jacob Schieffer, Gabin Peng, Ivy |
| author_facet | Miksits, Samuel Shi, Ruimin Gokhale, Maya Wahlgren, Jacob Schieffer, Gabin Peng, Ivy |
| contents | High-end ARM processors are emerging in data centers and HPC systems, posing as a strong contender to x86 machines. Memory-centric profiling is an important approach for dissecting an application's bottlenecks on memory access and guiding optimizations. Many existing memory profiling tools leverage hardware performance counters and precise event sampling, such as Intel PEBS and AMD IBS, to achieve high accuracy and low overhead. In this work, we present a multi-level memory profiling tool for ARM processors, leveraging Statistical Profiling Extension (SPE). We evaluate the tool using both HPC and Cloud workloads on the ARM Ampere processor. Our results provide the first quantitative assessment of time overhead and sampling accuracy of ARM SPE for memory-centric profiling at different sampling periods and aux buffer sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01514 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-level Memory-Centric Profiling on ARM Processors with ARM SPE Miksits, Samuel Shi, Ruimin Gokhale, Maya Wahlgren, Jacob Schieffer, Gabin Peng, Ivy Distributed, Parallel, and Cluster Computing High-end ARM processors are emerging in data centers and HPC systems, posing as a strong contender to x86 machines. Memory-centric profiling is an important approach for dissecting an application's bottlenecks on memory access and guiding optimizations. Many existing memory profiling tools leverage hardware performance counters and precise event sampling, such as Intel PEBS and AMD IBS, to achieve high accuracy and low overhead. In this work, we present a multi-level memory profiling tool for ARM processors, leveraging Statistical Profiling Extension (SPE). We evaluate the tool using both HPC and Cloud workloads on the ARM Ampere processor. Our results provide the first quantitative assessment of time overhead and sampling accuracy of ARM SPE for memory-centric profiling at different sampling periods and aux buffer sizes. |
| title | Multi-level Memory-Centric Profiling on ARM Processors with ARM SPE |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2410.01514 |