A Detailed GPU Cache Model Based on Reuse Distance Theory

  • Cedric Nugteren
  • Gert-jan Van Den Braak
  • Henk Corporaal
  • Henri Bal
ORKG logo Add to ORKG
Publication date
December 2015

Abstract

As modern GPUs rely partly on their on-chip memories to counter the imminent off-chip memory wall, the efficient use of their caches has become important for performance and energy. However, optimising cache locality system-atically requires insight into and prediction of cache be-haviour. On sequential processors, stack distance or reuse distance theory is a well-known means to model cache be-haviour. However, it is not straightforward to apply this theory to GPUs, mainly because of the parallel execution model and fine-grained multi-threading. This work extends reuse distance to GPUs by modelling: 1) the GPU’s hier-archy of threads, warps, threadblocks, and sets of active threads, 2) conditional and non-uniform latencies, 3) cache associa...

Extracted data

Loading...

Related items

A detailed GPU cache model based on reuse distance theory
  • Nugteren, C.
  • Braak, van den, G.J.W.
  • Corporaal, H.
  • Bal, H.E.
January 2014

As modern GPUs rely partly on their on-chip memories to counter the imminent off-chip memory wall, t...

RDGC: A Reuse Distance-Based Approach to GPU Cache Performance Analysis
  • Kiani, Mohsen
  • Rajabzadeh, Amir
May 2019

In the present paper, we propose RDGC, a reuse distance-based performance analysis approach for GPU ...

A Quantitative Study of Locality in GPU Caches
  • Lal, Sohan
  • Juurlink, Ben
December 2020

Traditionally, GPUs only had programmer-managed caches. The advent of hardware-managed caches accele...

We use cookies to provide a better user experience.