Filters








7,797 Hits in 0.74 sec

Dissecting GPU Memory Hierarchy through Microbenchmarking [article]

Xinxin Mei, Xiaowen Chu
2016 arXiv   pre-print
Our microbenchmark results offer a better understanding of the mysterious GPU memory hierarchy, which will facilitate the software optimization and modelling of GPU architectures.  ...  In this paper, we propose a novel fine-grained microbenchmarking approach and apply it to three generations of NVIDIA GPUs, namely Fermi, Kepler and Maxwell, to expose the previously unknown characteristics  ...  We summarize the related GPU microbenchmark work in Table 1 .  ... 
arXiv:1509.02308v2 fatcat:suiu2noanjbsddykue3wvqwf7e

A Microbenchmark Suite for OpenMP Tasks [chapter]

J. Mark Bull, Fiona Reid, Nicola McDonnell
2012 Lecture Notes in Computer Science  
We present a set of extensions to an existing microbenchmark suite for OpenMP.  ...  We extend the microbenchmark suite to measure the overheads associated with the new constructs.  ...  Conclusions We have presented an extension to our existing suite of OpenMP microbenchmarks to cover the task construct and associated synchronisation.  ... 
doi:10.1007/978-3-642-30961-8_24 fatcat:awi4scuiljbozeveuqy7fm3wsq

Demystifying GPU microarchitecture through microbenchmarking

Henry Wong, Misel-Myrto Papadopoulou, Maryam Sadooghi-Alvandi, Andreas Moshovos
2010 2010 IEEE International Symposium on Performance Analysis of Systems & Software (ISPASS)  
Microbenchmark Methodology To explore the GT200 architecture, we create microbenchmarks to expose each characteristic we wish to measure.  ...  Listings 1 and 2 show the structure of our memory microbenchmarks.  ... 
doi:10.1109/ispass.2010.5452013 dblp:conf/ispass/WongPSM10 fatcat:kuvxhuy6gzakjktvquoac6drk4

Assessing Performance Implications of Deep Copy Operations via Microbenchmarking [article]

Millad Ghane, Sunita Chandrasekaran, Margaret S. Cheung
2019 arXiv   pre-print
All the source codes of our microbenchmark are accessible on Github 1 .  ... 
arXiv:1906.01128v2 fatcat:mbzjuat6tjg3verk37bamzbdd4

Microbenchmarks for determining branch predictor organization

Milena Milenkovic, Aleksandar Milenkovic, Jeffrey Kulick
2004 Software, Practice & Experience  
The proposed experiment flow is illustrated with microbenchmarks tuned for Intel Pentium III and Pentium 4 processors, although they can easily be adapted for other architectures.  ...  This paper presents an experiment flow with a series of microbenchmarks that determine the organization and size of a branch predictor using on-chip performance monitoring registers.  ...  Figure 15 Step 4 microbenchmark. Step 5.  ... 
doi:10.1002/spe.572 fatcat:zeugcpbpqfckrmd2icym6sxlrm

A Microbenchmark Characterization of the Emu Chick [article]

Jeffrey S. Young, Eric Hein, Srinivas Eswar, Patrick Lavin, Jiajia Li, Jason Riedy, Richard Vuduc, Thomas M. Conte
2018 arXiv   pre-print
As Equation 1 shows, one GC can achieve up to 200 MB/s for the STREAM ADD kernel, which we have used as our "peak" achievable bandwidth for comparison with other microbenchmarks.  ...  Our study uses microbenchmarks and small kernels-namely, STREAM, pointer chasing, and sparse matrix-vector multiplication (SpMV)-as proxies that reflect some of the key characteristics of our motivating  ... 
arXiv:1809.07696v2 fatcat:ocywhfk4cfckpg65vjikh672su

nanoBench: A Low-Overhead Tool for Running Microbenchmarks on x86 Systems [article]

Andreas Abel, Jan Reineke
2020 arXiv   pre-print
Such code is common in microbenchmark-based hardware analysis techniques. Unlike previous tools, nanoBench can execute microbenchmarks directly in kernel space.  ...  We present nanoBench, a tool for evaluating small microbenchmarks using hardware performance counters on Intel and AMD x86 systems.  ...  Agner Fog [28] provides a framework for running microbenchmarks similar to the microbenchmarks considered in this paper.  ... 
arXiv:1911.03282v2 fatcat:jcejyzjlwrhgpgfzwimr5sbeji

A microbenchmark case study and lessons learned

Joseph Yossi Gil, Keren Lenz, Yuval Shimron
2011 Proceedings of the compilation of the co-located workshops on DSM'11, TMC'11, AGERE!'11, AOOPES'11, NEAT'11, & VMIL'11 - SPLASH '11 Workshops  
Background: Benchmarking and Microbenchmarking of Java Benchmarking of computer systems is a notoriously delicate task [9] .  ...  Micro-benchmarking of JAVA functions raises its own set of intriguing issues. 1 There are two major hurdles for JAVA microbenchmarks: First, the Just In Time (JIT) compiler, may change the code as it  ... 
doi:10.1145/2095050.2095100 dblp:conf/oopsla/GilLS11 fatcat:mr73c6otjra4bjmrq5fqbwmki4

Microbenchmarks for Question Answering Systems Using QaldGen

Qaiser Mehmood, Abhishek Nadgeri, Muhammad Saleem, Kuldeep Singh, Axel-Cyrille Ngonga Ngomo, Jens Lehmann
2019 International Semantic Web Conference  
Microbenchmarks are used to test the individual components of the given systems. Thus, such benchmarks can provide a more detailed analysis pertaining to the different components of the systems.  ...  On the other hand, microbenchmarks are more specific, designed to test fine-grained components of the complete system [1] .  ...  To fill this gap, we propose QaldGen [5] , a framework for automatic selection of components-level microbenchmarks for QA systems over knowledge graphs.  ... 
dblp:conf/semweb/MehmoodN0SN019 fatcat:k3x3isurmjg4fnxzpixvyifnsa

Dissecting the Graphcore IPU Architecture via Microbenchmarking [article]

Zhe Jia and Blake Tillman and Marco Maggioni and Daniele Paolo Scarpazza
2019 arXiv   pre-print
We dissect the IPU's performance behavior using microbenchmarks that we crafted for the purpose. We study the IPU's memory organization and performance.  ...  This report is the natural extension to a novel architecture of a continuing effort of ours that focuses on the microbenchmark-based discovery of massively parallel architectures.  ...  Our microbenchmarks reveal that proximity matters.  ... 
arXiv:1912.03413v1 fatcat:dxlnjj2icrhilou2awfexs2tca

Applying test case prioritization to software microbenchmarks

Christoph Laaber, Harald C. Gall, Philipp Leitner
2021 Empirical Software Engineering  
., with software microbenchmarks, is hardly investigated.  ...  However, it is unclear whether traditional unit testing TCP techniques work equally well for software microbenchmarks.  ...  In the remainder of the paper, we use both benchmark and microbenchmark to refer to software microbenchmarks.  ... 
doi:10.1007/s10664-021-10037-x pmid:34776757 pmcid:PMC8550681 fatcat:qsx2j33beffjzbio35lipdr7ny

Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking [article]

Zhe Jia, Marco Maggioni, Benjamin Staiger, Daniele P. Scarpazza
2018 arXiv   pre-print
To address this dearth of public, microarchitectural-level information on the novel NVIDIA GPUs, independent researchers have resorted to microbenchmarks-based dissection and discovery.  ...  In this technical report, we continue this line of research by presenting the microarchitectural details of the NVIDIA Volta architecture, discovered through microbenchmarks and instruction set disassembly  ... 
arXiv:1804.06826v1 fatcat:obbd5jmwebcxxa7gifbvjeecx4

Microbenchmark performance comparison of high-speed cluster interconnects

Jiuxing Liu, B. Chandrasekaran, Weikuan Yu, Jiesheng Wu, D. Buntinas, S. Kini, D.K. Panda, P. Wyckoff
2004 IEEE Micro  
Microbenchmarks and performance To provide more insight into the communication behavior of the three interconnects, we designed a set of microbenchmarks and performance parameters to reveal different aspects  ...  We have designed a set of microbenchmarks to characterize different aspects of the interconnects.  ... 
doi:10.1109/mm.2004.1268994 fatcat:2tmrx5boybgtxkvbhlmvweey3y

From micro-OPs to abstract resources: constructing a simpler CPU performance model through microbenchmarking [article]

Nicolas Derumigny, Fabian Gruber, Théophile Bastian, Guillaume Iooss, Christophe Guillon, Louis-Noel Pouchet, Fabrice Rastello
2021 arXiv   pre-print
microbenchmarks that saturate resources.  ...  The Core mapping also computes a set of saturating microbenchmarks that individually saturate each of the individual abstract resource.  ... 
arXiv:2012.11473v3 fatcat:jax3bt5xtjaw3og6ec2i6dpuhi

Comparing Operating Systems Scalability on Multicore Processors by Microbenchmarking

Yan CUI, Yu CHEN, Yuanchun SHI
2012 IEICE transactions on information and systems  
research and industry communities, in this paper we choose three operating systems (Linux, Solaris and FreeBSD) to systematically evaluate and compare their scalability by using a set of highly-focused microbenchmarks  ...  Microbenchmarks The microbenchmark suite has five programs (forkbench, mmapbench, dupbench, sembench and sockbench), each generating workload to stress one component of an operating system (process management  ...  Sembench Sembench is a microbenchmark designed to reveal the scalability of System V IPC in operating systems.  ... 
doi:10.1587/transinf.e95.d.2810 fatcat:ketv335yvrdivc4eeerza3xb24
« Previous Showing results 1 — 15 out of 7,797 results