DAN-Scheduler is presented, a deterministic offline scheduling and compiler optimization framework for intra-core NPU execution that co-optimizes these decisions in three stages that show that deterministic stage-wise co-optimization is an effective and broadly applicable compiler optimization strategy for memory-constrained NPU execution.
SA-Scheduler is presented, a structure-derived bottleneck-aware scheduling framework for multitasking MCM-GPUs that determines chip placement without hardware modification or runtime bottleneck profiling, and provides a principled and scalable foundation for multitasking on future MCM-GPUs.
Tie-Jian Zhang, Guangda Zhang, Lu Wang et al.· ACM Transactions on Design A...· 0 citations
Loom, a tuning-free symbolic compiler framework for tile-based SPMD programs on spatial dataflow architectures, is presented, suggesting that hardware-derived symbolic compilation provides a retargetable alternative to profiling-based tuning for spatial dataflow architectures while remaining interpretable by keeping op...
He-Ru Wang, Wei Li, Zhen-Yu Bai et al.· 0 citations
LazyTrain is proposed, an optimization layer over a layer-streaming executor that formulates checkpoint selection, activation placement, recomputation, and CPU-GPU-NVMe communication overlap as a mixed-integer scheduling problem, then executes the solved policy during training.
Xiao-Jun Wu, Ce-Hao Yang, Hong-Hao Liu et al.· 1 citation
OptPipe is presented, a unified framework that jointly optimises partitioning and scheduling for pipeline parallelism and introduces a memory-aware directed acyclic graph (DAG) that captures both task dependencies and the lifetime of intermediate tensors, enabling explicit reasoning about the trade-off between executio...
Ning Wang, A. Raith, Oliver Sinnen· Proceedings of the Internati...· 0 citations
A wave-quantized analytical model and launch-time resource manager for dependency-coupled overlap pipelines that selects the communication-CTA count and resource partition before each launch without candidate execution, per-workload profiling, or kernel recompilation is presented.
This paper proposes a compile-time instruction scheduling method that models sub-cycle resource usage and analyzes both data and structural dependencies at fine granularity, enabling precise detection of structural hazards in complex execution units.
