More Like this

1. GSLICE: controlled spatial sharing of GPUs for a scalable inference platform

   https://doi.org/10.1145/3419111.3421284  

   Dhakal, Aditya; Kulkarni, Sameer G; Ramakrishnan, K. K. (October 2020, SoCC '20: Proceedings of the 11th ACM Symposium on Cloud Computing)

   null (Ed.)

   The increasing demand for cloud-based inference services requires the use of Graphics Processing Unit (GPU). It is highly desirable to utilize GPU efficiently by multiplexing different inference tasks on the GPU. Batched processing, CUDA streams and Multi-process-service (MPS) help. However, we find that these are not adequate for achieving scalability by efficiently utilizing GPUs, and do not guarantee predictable performance. GSLICE addresses these challenges by incorporating a dynamic GPU resource allocation and management framework to maximize performance and resource utilization. We virtualize the GPU by apportioning the GPU resources across different Inference Functions (IFs), thus providing isolation and guaranteeing performance. We develop self-learning and adaptive GPU resource allocation and batching schemes that account for network traffic characteristics, while also keeping inference latencies below service level objectives. GSLICE adapts quickly to the streaming data's workload intensity and the variability of GPU processing costs. GSLICE provides scalability of the GPU for IF processing through efficient and controlled spatial multiplexing, coupled with a GPU resource re-allocation scheme with near-zero (< 100μs) downtime. Compared to default MPS and TensorRT, GSLICE improves GPU utilization efficiency by 60--800% and achieves 2--13X improvement in aggregate throughput. 

   more » « less
2. Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems

   https://doi.org/10.4230/lipics.ecrts.2025.21  

   Bakita, Joshua; Anderson, James H (January 2025, Schloss Dagstuhl – Leibniz-Zentrum für Informatik)

   Mancuso, Renato (Ed.)

   As GPU-using tasks become more common in embedded, safety-critical systems, efficiency demands necessitate sharing a single GPU among multiple tasks. Unfortunately, existing ways to schedule multiple tasks onto a GPU often either result in a loss of ability to meet deadlines, or a loss of efficiency. In this work, we develop a system-level spatial compute partitioning mechanism for NVIDIA GPUs and demonstrate that it can be used to execute tasks efficiently without compromising timing predictability. Our tool, called nvtaskset, supports composable systems by not requiring task, driver, or hardware modifications. In our evaluation, we demonstrate sub-1-μs overheads, stronger partition enforcement, and finer-granularity partitioning when using our mechanism instead of NVIDIA’s Multi-Process Service (MPS) or Multi-instance GPU (MiG) features. 

   more » « less
3. PILOT: a Runtime System to Manage Multi-tenant GPU Unified Memory Footprint

   https://doi.org/10.1109/HiPC53243.2021.00063  

   Ravi, John; Nguyen, Tri; Zhou, Huiyang; Becchi, Michela (January 2022, 2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC))

   Concurrent kernel execution on GPU has proven an effective technique to improve system throughput by maximizing the resource utilization. In order to increase programmability and meet the increasing memory requirements of data-intensive applications, current GPUs support Unified Virtual Memory (UVM), which provides a virtual memory abstraction with demand paging. By allowing applications to oversubscribe GPU memory, UVM provides increased opportunities to share GPU resources across applications. However, in the presence of applications with competing memory requirements, GPU sharing can lead to performance degradation due to thrashing. NVIDIA's Multiple Process Service (MPS) offers the capability to space share bare metal GPUs, thereby enabling cluster workload managers, such as Slurm, to share a single GPU across MPI ranks with limited control over resource partitioning. However, it is not possible to preempt, schedule, or throttle a running GPU process through MPS. These features would enable new OS-managed scheduling policies to be implemented for GPU kernels to dynamically handle resource contention and offer consistent performance. The contribution of this paper is two-fold. We first show how memory oversubscription can impact the performance of concurrent GPU applications. Then, we propose three methods to transparently mitigate memory interference through kernel preemption and scheduling policies. To implement our policies, we develop our own runtime system (PILOT) to serve as an alternative to NVIDIA's MPS. In the presence of memory over-subscription, we noticed a dramatic improvement in the overall throughput when using our scheduling policies and runtime hints. 

   more » « less
4. Primitives Enhancing GPU Runtime Support for improved DNN Performance

   Dhakal, Aditya; Kulkarni, Sameer; Ramakrishnan, K. K. (September 2021, IEEE International Conference on Cloud Computing)

   null (Ed.)

   Deep neural networks (DNNs) are increasingly used for real-time inference, requiring low latency, but require significant computational power as they continue to increase in complexity. Edge clouds promise to offer lower latency due to their proximity to end-users and having powerful accelerators like GPUs to provide the computation power needed for DNNs. But it is also important to ensure that the edge-cloud resources are utilized well. For this, multiplexing several DNN models through spatial sharing of the GPU can substantially improve edge-cloud resource usage. Typical GPU runtime environments have significant interactions with the CPU, to transfer data to the GPU, for CPU-GPU synchronization on inference task completions, etc. These result in overheads. We present a DNN inference framework with a set of software primitives that reduce the overhead for DNN inference, increase GPU utilization and improve performance, with lower latency and higher throughput. Our first primitive uses the GPU DMA effectively, reducing the CPU cycles spent to transfer the data to the GPU. A second primitive uses asynchronous ‘events’ for faster task completion notification. GPU runtimes typically preclude fine-grained user control on GPU resources, causing long GPU downtimes when adjusting resources. Our third primitive supports overlapping of model-loading and execution, thus allowing GPU resource re-allocation with very little GPU idle time. Our other primitives increase inference throughput by improving scheduling and processing more requests. Overall, our primitives decrease inference latency by more than 35% and increase DNN throughput by 2-3×. 

   more » « less
5. Latency-guaranteed Co-location of Inference and Training for Reducing Data Center Expenses

   Chen, Guoyu; Subramaniyan, Srinivasan; Wang, Xiaorui (July 2024, IEEE)

   Today's data centers often need to run various machine learning (ML) applications with stringent SLO (Service-Level Objective) requirements, such as inference latency. To that end, data centers prefer to 1) over-provision the number of servers used for inference processing and 2) isolate them from other servers that run ML training, despite both use GPUs extensively, to minimize possible competition of computing resources. Those practices result in a low GPU utilization and thus a high capital expense. Hence, if training and inference jobs can be safely co-located on the same GPUs with explicit SLO guarantees, data centers could flexibly run fewer training jobs when an inference burst arrives and run more afterwards to increase GPU utilization, reducing their capital expenses. In this paper, we propose GPUColo, a two-tier co-location solution that provides explicit ML inference SLO guarantees for co-located GPUs. In the outer tier, we exploit GPU spatial sharing to dynamically adjust the percentage of active GPU threads allocated to spatially co-located inference and training processes, so that the inference latency can be guaranteed. Because spatial sharing can introduce considerable overheads and thus cannot be conducted at a fine time granularity, we design an inner tier that puts training jobs into periodic sleep, so that the inference jobs can quickly get more GPU resources for more prompt latency control. Our hardware testbed results show that GPUColo can precisely control the inference latency to the desired SLO, while maximizing the throughput of the training jobs co-located on the same GPUs. Our large-scale simulation with a 57-day real-world data center trace (6500 GPUs) also demonstrates that GPUColo enables latency-guaranteed inference and training co-location. Consequently, it allows 74.9% of GPUs to be saved for a much lower capital expense. 

   more » « less