Show
Sort by
-
- Journal Article
- open access
NUBA: Non-Uniform Bandwidth GPUs
(2023) PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, VOL 2, ASPLOS 2023. p.Assoc Comp Machinery, ACM SIGARCH, ACM SIGOPS, ACM SIGPLAN, ACM SIGBED-559 -
Delegated replies : alleviating network clogging in heterogeneous architectures
-
- Conference Paper
- P1
- open access
HSM : a hybrid slowdown model for multitasking GPUs
-
Selective replication in memory-side GPU caches
-
- PhD Thesis
- open access
Exploiting application diversity in throughput processors
(2019) -
- Journal Article
- A1
- open access
HeteroCore GPU to exploit TLP-resource diversity
-
- Journal Article
- A1
- open access
CD-Xbar : a converge-diverge crossbar network for high-performance GPUs
-
- Journal Article
- A1
- open access
Intra-cluster coalescing and distributed-block scheduling to reduce GPU NoC pressure
-
- Conference Paper
- P1
- open access
Adaptive memory-side last-level GPU caching
-
Classification-driven search for effective sm partitioning in multitasking GPUs
-
- Conference Paper
- P1
- open access
Intra-cluster coalescing to reduce GPU NoC pressure
-
- Conference Paper
- P1
- open access
Get Out of the Valley: Power-Efficient Address Mapping for GPUs
-
LA-LLC : inter-core locality-aware last-level cache to exploit many-to-many traffic in GPGPUs
-
BACM : barrier-aware cache management for irregular memory-intensive GPGPU workloads
-
A low-cost conflict-free NoC for GPGPUs