More Like this

1. ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs

   Quach, Ryan; Wang, Yidi; Jahanshahi, Ali; Wong, Daniel; Kim, Hyoseung (August 2025, IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED))

   As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU’s compute resources and waste power from idling components. To improve utilization and energy efficiency, multiple models can co-locate and share the GPU. However, typical GPU spatial partitioning techniques often experience significant overheads when reconfiguring spatial partitions, which can waste additional energy through repartitioning overheads or non-optimal partition configurations. In this paper, we present ECLIP, a framework to enable low-overhead energy-efficient kernel-wise resource partitioning between co-located inference kernels. ECLIP minimizes repartitioning overheads by pre-allocating pools of CU masked streams and assigns optimal CU assignments to groups of kernels through our resource allocation optimizer. Overall, ECLIP achieves an average of 13% improvement to throughput and 25% improvement to energy efficiency. 

   more » « less
2. Dynamics of finite width Kernel and prediction fluctuations in mean field neural networks

   https://doi.org/10.1088/1742-5468/ad642b  

   Bordelon, Blake; Pehlevan, Cengiz (October 2024, Journal of Statistical Mechanics: Theory and Experiment)

   Abstract We analyze the dynamics of finite width effects in wide but finite feature learning neural networks. Starting from a dynamical mean field theory description of infinite width deep neural network kernel and prediction dynamics, we provide a characterization of the $O\left(1/\sqrt{\text{width}}\right)$fluctuations of the dynamical mean field theory order parameters over random initializations of the network weights. Our results, while perturbative in width, unlike prior analyses, are non-perturbative in the strength of feature learning. We find that once the mean field/µP parameterization is adopted, the leading finite size effect on the dynamics is to introduce initialization variance in the predictions and feature kernels of the networks. In the lazy limit of network training, all kernels are random but static in time and the prediction variance has a universal form. However, in the rich, feature learning regime, the fluctuations of the kernels and predictions are dynamically coupled with a variance that can be computed self-consistently. In two layer networks, we show how feature learning can dynamically reduce the variance of the final tangent kernel and final network predictions. We also show how initialization variance can slow down online learning in wide but finite networks. In deeper networks, kernel variance can dramatically accumulate through subsequent layers at large feature learning strengths, but feature learning continues to improve the signal-to-noise ratio of the feature kernels. In discrete time, we demonstrate that large learning rate phenomena such as edge of stability effects can be well captured by infinite width dynamics and that initialization variance can decrease dynamically. For convolutional neural networks trained on CIFAR-10, we empirically find significant corrections to both the bias and variance of network dynamics due to finite width. 

   more » « less
3. 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
4. Scalable Irregular Parallelism with GPUs: Getting CPUs Out of the Way

   https://doi.org/10.1109/SC41404.2022.00055  

   Chen, Yuxin; Brock, Benjamin; Porumbescu, Șerban; Buluc, Aydın; Yelick, Katherine; Owens, John D. (November 2022, International Conference for High Performance Computing Networking Storage and Analysis)

   We present Atos, a dynamic scheduling framework for multi-node-GPU systems that supports PGAS-style lightweight one-sided memory operations within and between nodes. Atos's lightweight GPU-to-GPU communication enables latency hiding and can smooth the interconnection usage for bisection-limited problems. These benefits are significant for dynamic, irregular applications that often involve fine-grained communication at unpredictable times and without predetermined patterns. Some principles for high performance: (1) do not involve the CPU in the communication control path; (2) allow GPU communication within kernels, addressing memory consistency directly rather than relying on synchronization with the CPU; (3) perform dynamic communication aggregation when interconnections have limited bandwidth. By lowering the overhead of communication and allowing it within GPU kernels, we support large, high-utilization GPU kernels but with more frequent communication. We evaluate Atos on two irregular problems: Breadth-First-Search and PageRank. Atos outperforms the state-of-the-art graph libraries Gunrock, Groute and Galois on both single-node-multi-GPU and multi-node-GPU settings. 

   more » « less
5. Protecting Real-Time GPU Kernels on Integrated CPU-GPU SoC Platforms

   https://doi.org/10.4230/LIPIcs.ECRTS.2018.19  

   Ali, Waqar; Yun, Heechul (July 2018, Leibniz international proceedings in informatics)

   Integrated CPU-GPU architecture provides excellent acceleration capabilities for data parallel applications on embedded platforms while meeting the size, weight and power (SWaP) requirements. However, sharing of main memory between CPU applications and GPU kernels can severely affect the execution of GPU kernels and diminish the performance gain provided by GPU. For example, in the NVIDIA Jetson TX2 platform, an integrated CPU-GPU architecture, we observed that, in the worst case, the GPU kernels can suffer as much as 3X slowdown in the presence of co-running memory intensive CPU applications. In this paper, we propose a software mechanism, which we call BWLOCK++, to protect the performance of GPU kernels from co-scheduled memory intensive CPU applications. 

   more » « less