Analyzing and improving performance scalability of commercial server workloads on a chip multiprocessor

Ishizaki, Kazuaki; Nakatani, Toshio; Daijavad, S.

doi:10.1109/iiswc.2009.5306781

Cited by 8 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Ishizaki et al [11] reported that the performance of Java server workloads running on a Niagara2 processor was improved by up to 132% by removing the contended locks. We found that appropriate use of the parallelization model is also an important factor in improving the performance of programs on multi-core SMT processors.…”

Section: Related Workmentioning

confidence: 98%

“…Many previous studies identified lock contention as the dominant cause of poor scalability on multi-core SMT processors [9][10][11]. For example, Ishizaki et al [11] reported that the performance of Java server workloads running on a Niagara2 processor was improved by up to 132% by removing the contended locks.…”

Section: Related Workmentioning

confidence: 98%

“…For example, most of the memory allocators used in modern UNIX systems support local memory allocation in NUMA systems to avoid costly remote memory accesses. Tikir and Hollingsworth [11] also implemented a NUMA-aware memory allocator in a JVM. With our core-aware allocator, we seek to show that a memory allocator that is aware of the physical location of the requester at a finer granularity can improve the performance of the running programs even on a non-NUMA system.…”

Section: B Implementationmentioning

confidence: 99%

“…There are many papers that have measured performance scalability on systems with high thread-level parallelism using multi-core SMT processors [6][7][8][9][10][11]. For example, Kaseridis and John [7] studied the scalability of the SPECjbb2005 on a Niagara processor.…”

Section: Related Workmentioning

confidence: 99%

“…To test the SMT scalability, we increased the number of SMT threads in each core. Although many previous studies [6][7][8][9][10][11] measured core scalability and SMT scalability of programs on multi-core SMT processors, this is the first work to focus on the effects of the parallelization model on multi-core SMT processors.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Performance of multi-process and multi-thread processing on multi-core SMT processors

Inoue

Nakatani

2010

IEEE International Symposium on Workload Characterization (IISWC'10)

Self Cite

View full text Add to dashboard Cite

Many modern high-performance processors support multiple hardware threads in the form of multiple cores and SMT (Simultaneous Multi-Threading). Hence achieving good performance scalability of programs with respect to the numbers of cores (core scalability) and SMT threads in one core (SMT scalability) is critical. To identify a way to achieve higher performance on the multi-core SMT processors, this paper compares the performance scalability with two parallelization models (using multiple processes and using multiple threads in one process) on two types of hardware parallelism (core scalability and SMT scalability). We tested standard Java benchmarks and a real-world server program written in PHP on two platforms, Sun's UltraSPARC T1 (Niagara) processor and Intel's Xeon (Nehalem) processor. We show that the multi-thread model achieves better SMT scalability compared to the multi-process model by reducing the number of cache misses and DTLB misses. However both models achieve roughly equal core scalability. We show that the multi-thread model generates up to 7.4 times more DTLB misses than the multi-process model when multiple cores are used. To take advantage of the both models, we implemented a memory allocator for a PHP runtime to reduce DTLB misses on multi-core SMT processors. The allocator is aware of the core that is running each software thread and allocates memory blocks from same memory page for each processor core. When using all of the hardware threads on a Niagara, the core-aware allocator reduces the DTLB misses by 46.7% compared to the default allocator, and it improves the performance by 3.0%.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 98%

Section: B Implementationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Performance of multi-process and multi-thread processing on multi-core SMT processors

Inoue

Nakatani

2010

IEEE International Symposium on Workload Characterization (IISWC'10)

Self Cite

View full text Add to dashboard Cite

show abstract

Experiences in building and scaling an enterprise application on multicore systems

Seelam

Liu

Dube

et al. 2011

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYEven though Java is the de facto programming language for enterprise applications, there exist only a limited number of Java-based benchmarks to understand the performance on emerging multicore systems. To bridge this gap, this paper presents a report generation benchmark that is developed on top of Open Source Apache Geronimo's DayTrader benchmark. Report generation and rendering is at the heart of many enterprise business analytics and business intelligence software products, and it is used by many enterprise applications. We evaluate the performance scalability of this benchmark on a state-of-the-art Power7 multicore system with 8 Power7 cores and 32 hardware threads. The benchmark throughput scales linearly up to eight hardware threads, but beyond that point, the throughput falls sharply. Significant locking in the Java class libraries for non-shared objects results in this performance drop. Splitting the locks on these shared classes results in near linear scaling from eight to 32 threads and improved the throughput by 80%. We also show that the Linux operating system load balancing could result in a degraded application performance in hardware multithreaded systems and simultaneous-multithreads-aware task scheduling results in uniform core-resource utilization as well as improved application performance.

show abstract

Model-driven optimal resource scaling in cloud

et al. 2017

View full text Add to dashboard Cite

Analyzing and improving performance scalability of commercial server workloads on a chip multiprocessor

Cited by 8 publications

References 14 publications

Performance of multi-process and multi-thread processing on multi-core SMT processors

Performance of multi-process and multi-thread processing on multi-core SMT processors

Experiences in building and scaling an enterprise application on multicore systems

Model-driven optimal resource scaling in cloud

Contact Info

Product

Resources

About