Where is the data? Why you cannot debate CPU vs. GPU performance without the answer

By Chris Gregg, Kim M. Hazelwood. IEEE International Symposium on Performance Analysis of Systems and Software, 2011

320 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/6aebe661168743a0b948229c57be7ffb6217e0e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Srimat T. Chakradhar
2. G. Diamos

In Hardware and Architecture

1. Srimat T. Chakradhar
2. G. Diamos

Citations in the corpus

• Optimizing Data Warehousing Applications for GPUs Using Kernel Fusion/Fission (2012, background): “provide a detailed analysis of this phenomena [12].”
• DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference (2020, unknown): “This includes both data loading and model computation [39]–[44], capturing the performance-critical components of the end-to-end recommendation inference.”
• A Survey of CPU-GPU Heterogeneous Computing Techniques (2015, unknown): “The limited bandwidth of PCIe has conventionally remained a bottleneck in GPU performance, especially for applications which transfer large amount of data between CPU and GPU [Gregg and Hazelwood 2011; Lee et al. 2010].”