Flexible software profiling of GPU architectures

Stephenson, Mark W.; Hari, Siva Kumar Sastry; Lee, Yunsup; Ebrahimi, Eiman; Johnson, D.; Nellans, David; O'Connor, Mike; Keckler, Stephen W.

doi:10.1145/2749469.2750375

Cited by 64 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SPE subsumes software engineering activities that are applied to meet performance requirements and achieve improvements. Profiling tools can be used to measure performance (e.g., for energy consumption [252], [253], GPUs [254], responsiveness [255], and memory [256]).…”

Section: Optimization In Software Engineeringmentioning

confidence: 99%

A Survey of Performance Optimization for Mobile Applications

Hort

Kechagia

Sarro

et al. 2022

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

To ensure user satisfaction and success of mobile applications, it is important to provide highly performant applications. This is particularly important for resource-constrained systems such as mobile devices. Thereby, non-functional performance characteristics, such as energy and memory consumption, play an important role for user satisfaction. This paper provides a comprehensive survey of non-functional performance optimization for Android applications. We collected 156 unique publications, published between 2008 and 2020, that focus on the optimization of performance of mobile applications. We target our search at four performance characteristics: responsiveness, launch time, memory and energy consumption. For each performance characteristic, we categorize optimization approaches based on the method used in the corresponding publications. Furthermore, we identify research gaps in the literature for future work.

show abstract

Section: Optimization In Software Engineeringmentioning

confidence: 99%

A Survey of Performance Optimization for Mobile Applications

Hort

Kechagia

Sarro

et al. 2022

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

show abstract

“…Moreover, SASSI is able to read the values residing in memory location and registers. As demonstrated in the paper [47], SASSI supports to build effective fine-grained profilers. However, SASSI has several limitations in its portability, expansibility, complexity, and coverage.…”

Section: Existing Gpu Profilers and Limitationsmentioning

confidence: 99%

“…As shown in Figure 10, the runtime overhead mostly ranges from 10× to 120×. It is much faster than simulators such as GPGPU-Sim that usually incurs 1-10 millions of slow down to the native execution [47].…”

Section: Tool's Overhead Analysismentioning

confidence: 99%

“…We have distinguished CUDAAdvisor from the most related workÐSASSI [47] in Section 2. In this section, we review other profilers that work on GPUs.…”

Section: Related Workmentioning

confidence: 99%

“…To support fine-grained profiling, NVIDIA released a research prototype named SASSI [47] Ða tool that instruments GPU codes to support fine-grained analysis. However, as a close-source tool, SASSI has several limitations in practice, in terms of portability (i.e., not portable across CUDA runtime and architectures), expansibility (i.e., instrumentation engine is not open sourced), complexity (i.e., implementation level can be too low for common developers) and coverage (i.e., overlooks the interaction between CPU host and GPU).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CUDAAdvisor: LLVM-based runtime profiling for modern GPUs

Shen

Song

et al. 2018

Proceedings of the 2018 International Symposium on Code Generation and Optimization - CGO 2018

View full text Add to dashboard Cite

General-purpose GPUs have been widely utilized to accelerate parallel applications. Given a relatively complex programming model and fast architecture evolution, producing efficient GPU code is nontrivial. A variety of simulation and profiling tools have been developed to aid GPU application optimization and architecture design. However, existing tools are either limited by insufficient insights or lacking in support across different GPU architectures, runtime and driver versions. This paper presents CUDAAdvisor, a profiling framework to guide code optimization in modern NVIDIA GPUs. CUDAAdvisor performs various fine-grained analyses based on the profiling results from GPU kernels, such as memory-level analysis (e.g., reuse distance and memory divergence), control flow analysis (e.g., branch divergence) and code-/data-centric debugging. Unlike prior tools, CU-DAAdvisor supports GPU profiling across different CUDA versions and architectures, including CUDA 8.0 and Pascal architecture. We demonstrate several case studies that derive significant insights to guide GPU code optimization for performance improvement.

show abstract