DTexL: Decoupled Raster Pipeline for Texture Locality

Contemporary GPU architectures have multiple shader cores and a scheduler that distributes work (threads) among them, focusing on load balancing. These load balancing techniques favor thread distributions that are detrimental to texture memory locality for graphics applications in the L1 Texture Cac...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO) s. 213 - 227
Hlavní autoři: Joseph, Diya, Aragon, Juan L., Parcerisa, Joan-Manuel, Gonzalez, Antonio
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2022
Témata:
Caches
Focusing
GPU
Graphics
Graphics processing units
Instruction sets
Low-power
Microarchitecture
Pipelines
Scheduling
Texture Locality
Upper bound
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Contemporary GPU architectures have multiple shader cores and a scheduler that distributes work (threads) among them, focusing on load balancing. These load balancing techniques favor thread distributions that are detrimental to texture memory locality for graphics applications in the L1 Texture Caches. Texture memory accesses make up the majority of the traffic to the memory hierarchy in typical low power graphics architectures. This paper focuses on improving the L1 Texture cache locality by focusing on a new workload scheduler by exploring various methods to group the threads, assign the groups to shader cores and also to reorder threads without violating the correctness of the pipeline. To overcome the resulting load imbalance, we also propose a minor modification in the GPU architecture that helps translate the improvement in cache locality to an improvement in the GPU's performance. We propose DTexL that envelops these ideas and evaluate it over a benchmark suite of ten commercial games, to obtain a 46.8% decrease in L2 Accesses, a 19.3% increase in performance and a 6.3% decrease in total GPU energy. All this with a negligible overhead.
DOI:10.1109/MICRO56248.2022.00028