Zorua: A holistic approach to resource virtualization in GPUs

67 citations recorded by the source corpus.

How researchers see this paper

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

Pathways: Asynchronous Distributed Dataflow for ML (2022, background): “Recent work shows that ﬁner-grained sharing can improve resource efﬁciency further: virtualizing accelerators (Yu et al., 2020; Gupta et al., 2011; Vijaykumar et al., 2016) avoids dedicating a whole accelerator to a single user.”
Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks (2020, background): “There is a large swath of related work on multi-tenancy for CPUs [36, 66, 97–103] and GPUs [29, 35, 37–42, 66, 104–110] due to its vitality for cloud-scale computing.”
MASK: Redesigning the GPU Memory Hierarchy to Support Multi-Application Concurrency (2018, background): “4More detailed information about the GPU execution model and its memory hierarchy can be found in [14, 16, 17, 59, 61, 62, 63, 68, 90, 104, 111, 136, 137].”
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.”