EDGE: Event-Driven GPU Execution

GPUs are known to benefit structured applications with ample parallelism, such as deep learning in a datacenter. Recently, GPUs have shown promise for irregular streaming network tasks. However, the GPU's co-processor dependence on a CPU for task management, inefficiencies with fine-grained tas...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings / International Conference on Parallel Architectures and Compilation Techniques s. 337 - 353
Hlavní autori: Hetherington, Tayler Hicklin, Lubeznov, Maria, Shah, Deval, Aamodt, Tor M.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.09.2019
Predmet:
Central Processing Unit
GPU
Graphics processing units
Hardware
Instruction sets
Kernel
Multiprogramming
Networking
Task analysis
Throughput
ISSN:2641-7936
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:GPUs are known to benefit structured applications with ample parallelism, such as deep learning in a datacenter. Recently, GPUs have shown promise for irregular streaming network tasks. However, the GPU's co-processor dependence on a CPU for task management, inefficiencies with fine-grained tasks, and limited multiprogramming capabilities introduce challenges with efficiently supporting latency-sensitive streaming tasks. This paper proposes an event-driven GPU execution model, EDGE, that enables non-CPU devices to directly launch preconfigured tasks on a GPU without CPU interaction. Along with freeing up the CPU to work on other tasks, we estimate that EDGE can reduce the kernel launch latency by 4.4xcompared to the baseline CPU-launched approach. This paper also proposes a warp-level preemption mechanism to further reduce the end-to-end latency of fine-grained tasks in a shared GPU environment. We evaluate multiple optimizations that reduce the average warp preemption latency by 35.9x over waiting for a preempted warp to naturally flush the pipeline. When compared to waiting for the first available resources, we find that warp-level preemption reduces the average and tail warp scheduling latencies by 2.6x and 2.9x, respectively, and improves the average normalized turnaround time by 1.4x.
ISSN:2641-7936
DOI:10.1109/PACT.2019.00034