Caliper: Performance Introspection for HPC Software Stacks

Boehme, David; Gamblin, Todd; Beckingsale, David; Bremer, Peer-Timo; Giménez, Alfredo; Legendre, Matthew; Pearce, Olga; Schulz, Martin

doi:10.1109/sc.2016.46

Cited by 78 publications

(44 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later on, we characterize the impact of DCDB on computational resources and its scalability with various test configurations (Section 6.2.2), stressing the communication and sampling subsystems. In this part, we focus on using the shared-memory version of the High-Performance Linpack (HPL) benchmark [14], supplied with the Intel MKL library 8 . Being a compute-bound application, tests performed against HPL give us insights on the behavior of DCDB in a worst-case scenario.…”

Section: Methodsmentioning

confidence: 99%

From Facility to Application Sensor Data: Modular, Continuous and Holistic Monitoring with DCDB

Netti,

Mueller,

Auweter

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Today's HPC installations are highly-complex systems, and their complexity will only increase as we move to exascale and beyond. At each layer, from facilities to systems, from runtimes to applications, a wide range of tuning decisions must be made in order to achieve efficient operation. This, however, requires systematic and continuous monitoring of system and user data. While many insular solutions exist, a system for holistic and facility-wide monitoring is still lacking in the current HPC ecosystem.In this paper we introduce DCDB, a comprehensive monitoring system capable of integrating data from all system levels. It is designed as a modular and highly-scalable framework based on a plugin infrastructure. All monitored data is aggregated at a distributed noSQL data store for analysis and cross-system correlation. We demonstrate the performance and scalability of DCDB, and describe two use cases in the area of energy management and characterization.

show abstract

Section: Methodsmentioning

confidence: 99%

From Facility to Application Sensor Data: Modular, Continuous and Holistic Monitoring with DCDB

Netti,

Mueller,

Auweter

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A variety of performance measurement and analysis tools co-exist in the HPC ecosystem. Well known examples include TAU [26], Caliper [6], HPCToolkit [1], and LIKWID [28]. Each one of these tools provide their capabilities via design abstractions around the lower-level interfaces for the hardware and generally build upon the work of more specialized libraries such as PAPI [27], CUPTI [9], and Linux perf [11].…”

Section: Need For Composite Componentsmentioning

confidence: 99%

“…i.e., Radiation shielding, particle accelerator simulations, nuclear reactor design 6. i.e., Ability to associate measurements with either the derived or abstract object.…”

mentioning

confidence: 99%

Timemory: Modular Performance Analysis for HPC

Madsen

Awan

Brunie

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

HPC has undergone a significant transition toward heterogeneous architectures. This transition has introduced several issues in code migration to support multiple frameworks for targeting the various architectures. In order to cope with these challenges, projects such as Kokkos and LLVM create abstractions which map a generic frontend API to the backend that supports the targeted architecture. This paper presents a complementary framework for performance measurement and analysis. Several performance measurement and analysis tools in existence provide their capabilities through various methods but the common theme among these tools are prohibitive limitations in terms of user-level extensions. For this reason, software developers commonly have to learn multiple tools and valuable analysis methods, such as the roofline model, are frequently required to be generated manually. The timemory framework provides complete modularity for performance measurement and analysis and eliminates all restrictions on user-level extensions. The timemory framework also provides a highly-efficient and intuitive method for handling multiple tools/measurements (i.e., "components") concurrently. The intersection of these characteristics provide ample evidence that timemory can serve as the common interface for existing performance measurement and analysis tools. Timemory components are developed in C++ but includes multi-language support for C, Fortran, and Python codes. Numerous components are provided by the library itself -including, but not limited to, timers, memory usage, hardware counters, and FLOP and instruction roofline models. Additionally, analysis of the intrinsic overhead demonstrates superior performance in comparison with popular tools.

show abstract

“…The second is the Caliper [31] performance system. Caliper consists of the source-code annotation API, a backend runtime component that manages blackboard buffers and the generalized context tree, add-on support services for control tasks (such as I/O and controlling snapshots), and additional data producer, measurement control, and data consumer services.…”

Section: Related Workmentioning

confidence: 99%

A Plugin Architecture for the TAU Performance System

Malony

Srinivasan

Huck

et al. 2019

Proceedings of the 48th International Conference on Parallel Processing

View full text Add to dashboard Cite

Several robust performance systems have been created for parallel machines with the ability to observe diverse aspects of application execution on different hardware platforms. All of these are designed with the objective to support measurement methods that are efficient, portable, and scalable. For these reasons, the performance measurement infrastructure is tightly embedded with the application code and runtime execution environment. As parallel software and systems evolve, especially towards more heterogeneous, asynchronous, and dynamic operation, it is expected that the requirements for performance observation and awareness will change. For instance, heterogeneous machines introduce new types of performance data to capture and performance behaviors to characterize. Furthermore, there is a growing interest in interacting with the performance infrastructure for in situ analytics and policybased control. The problem is that an existing performance system architecture could be constrained in its ability to evolve to meet these new requirements. The paper reports our research efforts to address this concern in the context of the TAU Performance System. In particular, we consider the use of a powerful plugin model to both capture existing capabilities in TAU and to extend its functionality in ways it was not necessarily conceived originally. The TAU plugin architecture supports three types of plugin paradigms: EVENT, TRIGGER, and AGENT. We demonstrate how each operates under several different scenarios. Results from larger-scale experiments are shown to highlight the fact that efficiency and robustness can be maintained, while new flexibility and programmability can be offered that leverages the power of the core TAU system while allowing significant and compelling extensions to be realized.

show abstract

Caliper: Performance Introspection for HPC Software Stacks

Cited by 78 publications

References 12 publications

From Facility to Application Sensor Data: Modular, Continuous and Holistic Monitoring with DCDB

From Facility to Application Sensor Data: Modular, Continuous and Holistic Monitoring with DCDB

Timemory: Modular Performance Analysis for HPC

A Plugin Architecture for the TAU Performance System

Contact Info

Product

Resources

About