Quantifying Data Locality in Dynamic Parallelism in GPUs

Xulong Tang, Ashutosh Pattnaik, Onur Kayiran, Adwait Jog, Mahmut Taylan Kandemir, Chita Das

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Dynamic parallelism (DP) is a new feature of emerging GPUs that allows new kernels to be generated and scheduled from the deviceside (GPU) without the host-side (CPU) intervention. To eiciently support DP, one of the major challenges is to saturate the GPU processing elements and provide them with the required data in a timely fashion. In this paper, we irst conduct a limit study on the performance improvements that can be achieved by hardware schedulers that are provided with accurate data reuse information. We next propose LASER, a Locality-Aware SchedulER, where the hardware schedulers employ data reuse monitors to help make scheduling decisions to improve data locality at runtime. Experimental results on 16 benchmarks show that LASER, on an average, can improve performance by 11.3%.

Original languageEnglish (US)
Pages (from-to)25-26
Number of pages2
JournalPerformance Evaluation Review
Issue number1
StatePublished - Dec 17 2019

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications


Dive into the research topics of 'Quantifying Data Locality in Dynamic Parallelism in GPUs'. Together they form a unique fingerprint.

Cite this