Publication: QuCo: efficient and flexible hardware-driven automatic configuration of tile transfers in GPUs
Authors
Meseguer, Nicolás ; Xu, Daoxuan ; Sun, Yifan ; Pellauer, Michael ; Abellán Miguel, José Luis ; Acacio Sánchez, Manuel Eugenio
item.page.secondaryauthor
Facultades de la UMU::Facultad de Informática
item.page.director
Publisher
IEEE Computer Society Press
publication.page.editor
publication.page.department
DOI
item.page.type
info:eu-repo/semantics/article
Description
Abstract
The growing complexity and parallelism demands of modern GPU workloads have driven architectural innovations toward \emph{asynchronous tile transfers} (ATTs) to overlap computation and data movement. While ATT units such as the NVIDIA’s Tensor Memory Accelerator (TMA) introduce high-throughput memory transfers, programmers must deal with wavefront specialization, select tile sizes, queue slots, and synchronization primitives, all of which are hardware-specific and workload-dependent. Existing GPU libraries fall short—offering limited ATT support and configurability—so developers still resort to manual exploration of this vast parameter space, which is laborious, error-prone, and fundamentally limits performance portability across GPUs. In this work, we present QuCo (Queue Configurator), a single lightweight hardware unit embedded in the GPU that fully automates the ATT configuration process. Inspired by Blackwell GPU design, QuCo includes a compact \mbox{RISC-V} processor, small memory structures for instructions and data, and a GPU Specification Table (GST) storing key architectural parameters. Using the GST and workload characteristics, along with built-in heuristics, QuCo computes optimal queue configurations at kernel launch. This relieves the programmer of the tedious, time-consuming task of tuning and offline profiling, while simultaneously increasing post-compilation performance portability.
publication.page.subject
Citation
item.page.embargo
Collections
Ir a Estadísticas
Sin licencia Creative Commons.