Improving GPU performance via large warps and two-level warp scheduling
By Veynu Narasiman, Michael Shebanow, Chang Joo Lee, Rustam Miftakhutdinov, Onur Mutlu, Yale N. Patt. Micro, 2011
443 citations recorded by the source corpus.
Subfields: Computer Networks and Communications, Hardware and Architecture
View Paper: https://www.semanticscholar.org/paper/fb970e9fdd270f56bdd1bbda0621e6992eab9d1c
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
- Onur Mutlu
- Saugata Ghose
- Rachata Ausavarungnirun
- Adwait Jog
- Mahmut Taylan Kandemir
- Juan Gómez-Luna
- Christopher J. Rossbach
- Timothy G. Rogers
In Hardware and Architecture
- Onur Mutlu
- Saugata Ghose
- Mahmut Taylan Kandemir
- Rachata Ausavarungnirun
- Adwait Jog
- Juan Gómez-Luna
- Christopher J. Rossbach
- Phillip B. Gibbons
Citations in the corpus
- OWL: cooperative thread array aware scheduling techniques for improving GPGPU performance (2013, methodology): “Warps associated with CTAs are scheduled in a round-robin (RR) fashion on the assigned cores [5, 44] and get equal priority.”
- Processing Data Where It Makes Sense: Enabling In-Memory Computation (2019, background): “Despite that, many GPU applications are still very memory-bound [198, 199, 200, 201, 202, 203, 204, 205, 206, 207], because the limited off-chip pin bandwidth cannot supply enough data to the running threads.”
- GPUWattch: enabling energy optimizations in GPGPUs (2013, methodology): “…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 to the…”
- AvA: Accelerated Virtualization of Accelerators (2020, background): “Despite evidence of accelerator under-utilization [19, 21, 70, 72, 100], and abundant research [19, 70, 72, 100, 105, 109], no practical alternative yet exists.”
- Cache-Conscious Wavefront Scheduling (2012, methodology): “[31] exploits inter-wavefront locality while ensuring wavefronts reach long latency operations at different times by scheduling groups of wavefronts together.”
- Zorua: A holistic approach to resource virtualization in GPUs (2016, methodology): “Our decoupled design allows this challenge to be addressed independently from the coordinator using more intelligent scheduling algorithms [36, 50, 58] and cache management schemes [3, 44, 45, 78].”