Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow

By Wilson W. L. Fung, Ivan Sham, George L. Yuan, Tor M. Aamodt. Micro, 2007

542 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture, Information Systems

View Paper: https://www.semanticscholar.org/paper/4308295a2eaef30be423520918ad224dc2f3ffe2

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

In Hardware and Architecture

In Information Systems

Citations in the corpus

OWL: cooperative thread array aware scheduling techniques for improving GPGPU performance (2013, background): “Recent works that have tackled this problem include [14, 15, 44, 49].”
Analyzing CUDA workloads using a detailed GPU simulator (2009, methodology): “After parsing the PTX assembly code, but before beginning simulation, GPGPU-Sim performs an immediate post-dominator analysis on each kernel to annotate branch instructions with reconvergence points for the stack-based SIMD control ﬂow handling mechanism described by Fung et al. [11].”
GPUWattch: enabling energy optimizations in GPGPUs (2013, methodology): “…performance models, such as GPGPU-Sim [4], Multi2Sim [34] and MacSim [1], have enabled performance oriented research on branch divergence [11,12,27], memory bandwidth pressure [5, 32], and so forth, similar eﬀorts to investigate and optimize GPU energy-eﬃciency problems have been diﬃcult owing…”
Improving GPU performance via large warps and two-level warp scheduling (2011, methodology): “[7, 8] were the first to propose the idea of combining threads from different warps to address underutilized SIMD resources due to branch divergence on GPU cores.”
Cache-Conscious Wavefront Scheduling (2012, background): “Fung et al. [12] explore the impact of wavefront scheduling policy on the effectiveness of their Dynamic Warp Formation (DWF) technique.”
A quantitative study of irregular programs on GPUs (2012, background): “There are also papers that propose hardware improvements to better support the execution of irregular codes on GPUs [16], [17], [31], [33].”
Multi2Sim: A simulation framework for CPU-GPU computing (2012, methodology): “This simulator has been used as experi mental support for recent studies on GPU computing, explori ng alternative memory controller implementations [18] and dynamic grouping of threads (work-items) to minimize thread divergence penalty [15], for example.”