Static MIG partitioning cuts GPU underutilization in scientific workloads but leaves interference and coarse-grained mismatches; a Nvlink-C2C offloading scheme is introduced to bridge those gaps.
Optimal workload placement on multi-instance gpus
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SMART-MIG applies MF-MARL for constant-complexity MIG repartitioning plus heuristics for scheduling, reporting 18% better energy-tardiness efficiency than static partitioning and 27% above a theoretical energy lower bound.
citing papers explorer
-
Taming GPU Underutilization via Static Partitioning and Fine-grained CPU Offloading
Static MIG partitioning cuts GPU underutilization in scientific workloads but leaves interference and coarse-grained mismatches; a Nvlink-C2C offloading scheme is introduced to bridge those gaps.
-
SMART-MIG: A Learning Framework for Scalable and Energy-Efficient GPU Scheduling
SMART-MIG applies MF-MARL for constant-complexity MIG repartitioning plus heuristics for scheduling, reporting 18% better energy-tardiness efficiency than static partitioning and 27% above a theoretical energy lower bound.