Peipei Zhou

Shixin Ji, Zhuoping Yang, Xingzhen Chen et al.

Recent improvements in energy efficiency and renewable energy integration have increased the relative importance of embodied carbon in data centers, motivating improved provisioning strategies. Conventional approaches primarily minimize operational energy, but this perspective is increasingly insufficient for sustainability. In this paper, we propose carbon depreciation models to encourage longer hardware lifetimes. Carbon depreciation assigns a larger portion of embodied carbon to newly provisioned servers, discouraging unnecessary deployment of new hardware. As a result, new servers are provisioned mainly for jobs with strict quality-of-service (QoS) constraints, while older servers, whose embodied carbon has largely been recovered, are used for other workloads. We further argue that both embodied carbon and operational carbon from server idle time should be recovered during active jobs, encouraging provisioning strategies that maintain high utilization. We show that prior carbon accounting strategies can be counterproductive: under a greedy scheduler minimizing carbon under QoS constraints, jobs are priced as 25% cheaper on new hardware than on older hardware. In contrast, our approach uses a greedy scheduler that prioritizes older hardware through non-linear carbon depreciation, promoting sustainable provisioning. Experimental results show carbon reductions of 28-57%, depending on server lifetime assumptions.

Xingzhen Chen, Zhuoping Yang, Jinming Zhuang et al.

As deep neural networks develop significantly more diverse and complex, achieving high performance and efficiency on complicated DNN models faces pressing challenges. Modern DNN workloads are increasingly diverse in operation types, tensor shapes, and execution dependencies, making it difficult to sustain high hardware efficiency across models. In addition, a generic accelerator often incurs substantial overhead when executing diverse workloads. To address these problems, we propose DORA, an instruction-based overlay architecture that explicitly describes dataflow via a proposed ISA, enabling fine-grained control of data movement, computation, and synchronization at the layer level. To support flexibility while achieving high performance, DORA adopts a novel on-chip memory management and computation parallelism management mechanism. DORA proposes a compilation framework that can generate instructions for given DNN workloads after a two-stage design space exploration. DORA framework also incorporates a MILP-based and a heuristic-based search engine to generate the schedule solution for different needs and constraints. We prototype DORA on the AMD Versal VCK190 platform, demonstrating its deployability on existing reconfigurable systems. Experimental results show that DORA maintains stable efficiency, with less than 5\% variation on a single vector processor across workloads exhibiting up to 6$\times$ variation in operation counts. Compared to state-of-the-art accelerators, DORA consistently achieves higher performance, delivering up to 5$\times$ throughput improvement. The heuristic-based scheduler further achieves up to 90\% optimality under practical time constraints. DORA is open-sourced at https://github.com/arc-research-lab/DORA.git.

Xinyi Zhang, Cong Hao, Peipei Zhou et al.

The complex nature of real-world problems calls for heterogeneity in both machine learning (ML) models and hardware systems. The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i.e., multi-modality multi-task (MMMT), resulting in diverse deep neural network (DNN) layers and computation patterns. The heterogeneity in systems comes from diverse processing components, as it becomes the prevailing method to integrate multiple dedicated accelerators into one system. Therefore, a new problem emerges: heterogeneous model to heterogeneous system mapping (H2H). While previous mapping algorithms mostly focus on efficient computations, in this work, we argue that it is indispensable to consider computation and communication simultaneously for better system efficiency. We propose a novel H2H mapping algorithm with both computation and communication awareness; by slightly trading computation for communication, the system overall latency and energy consumption can be largely reduced. The superior performance of our work is evaluated based on MAESTRO modeling, demonstrating 15%-74% latency reduction and 23%-64% energy reduction compared with existing computation-prioritized mapping algorithms.

Sébastien Ollivier, Sheng Li, Yue Tang et al.

Edge computing is a popular target for accelerating machine learning algorithms supporting mobile devices without requiring the communication latencies to handle them in the cloud. Edge deployments of machine learning primarily consider traditional concerns such as SWaP constraints (Size, Weight, and Power) for their installations. However, such metrics are not entirely sufficient to consider environmental impacts from computing given the significant contributions from embodied energy and carbon. In this paper we explore the tradeoffs of convolutional neural network acceleration engines for both inference and on-line training. In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM. Replacing PIM-enabled DDR3 with Racetrack memory PIM can recover its embodied energy as quickly as 1 year. For high activity ratios, mobile GPUs can be more sustainable but have higher embodied energy to overcome compared to PIM-enabled Racetrack memory.

Shixin Ji, Jinming Zhuang, Zhuoping Yang et al.

Heterogeneous reconfigurable platforms with tensor cores, such as AMD ACAP, are increasingly adopted for deep neural network (DNN) inference due to their high throughput and flexibility. However, their suitability for microsecond-scale inference on small problem sizes remains underexplored. In jet-tagging applications in high-energy physics, inefficient on-chip communication and large inter-layer latency prevent existing frameworks from meeting the 1-μs latency budget. Moreover, hardware overheads such as synchronization and VLIW processor prologue are often overlooked, making it infeasible to optimize accelerators correctly. To address these problems, we propose μ-ORCA, a customized heterogeneous accelerator framework for ultra-low-latency model inference. μ-ORCA enables direct inter-layer communication between DNN layers on the AIE array, instead of using shared memory tiles or FPGA fabric. Moreover, a 512-bit/cycle cascade connection is applied instead of a 32-bit/cycle DMA connection. μ-ORCA also provides an overhead-aware performance model that adapts to different NN layer sizes, and conducts design space exploration to optimize end-to-end latency. μ-ORCA supports MLP and DeepSets models with non-MM kernels, including bias, ReLU, and global aggregation on AIE. We evaluate μ-ORCA on the AMD ACAP VEK280 platform. Experimental results show that μ-ORCA achieves average latency reduction of >1.70$\times$ and >1.83$\times$ compared with different state-of-the-art ACAP frameworks, and achieves 0.93 μs latency for a 6-layer real-world DeepSets model, satisfying the latency budget. We open source μ-ORCA at https://github.com/arc-research-lab/u-ORCA.

Ruiyang Qin, Jun Xia, Zhenge Jia et al.

After a large language model (LLM) is deployed on edge devices, it is desirable for these devices to learn from user-generated conversation data to generate user-specific and personalized responses in real-time. However, user-generated data usually contains sensitive and private information, and uploading such data to the cloud for annotation is not preferred if not prohibited. While it is possible to obtain annotation locally by directly asking users to provide preferred responses, such annotations have to be sparse to not affect user experience. In addition, the storage of edge devices is usually too limited to enable large-scale fine-tuning with full user-generated data. It remains an open question how to enable on-device LLM personalization, considering sparse annotation and limited on-device storage. In this paper, we propose a novel framework to select and store the most representative data online in a self-supervised way. Such data has a small memory footprint and allows infrequent requests of user annotations for further fine-tuning. To enhance fine-tuning quality, multiple semantically similar pairs of question texts and expected responses are generated using the LLM. Our experiments show that the proposed framework achieves the best user-specific content-generating capability (accuracy) and fine-tuning speed (performance) compared with vanilla baselines. To the best of our knowledge, this is the very first on-device LLM personalization framework.

Xingzhen Chen, Shixin Ji, Zheng Dong et al.

In this work, we present a systematic study of this trade-off from a deployment-centric perspective, focusing on an autonomous driving scenario. Instead of treating overlay and customized acceleration as isolated design points, we analyze when each approach is preferable under practical conditions, including workload variation, architectural design, reconfiguration latency, and switching frequency. Our analysis shows that overlay-based architecture is more suitable for highly frequent model switching under the state-of-the-art architecture. However, as bitstream reload overhead continues to reduce, customized architectures may become increasingly attractive, especially for workloads with efficiency requirements. Conversely, if overlay architectures become more capable and flexible, they may further expand their advantage over customized architectures. These observations provide design insights for future architectural design, and the optimal deployment strategy will be flipped according to the technique development.

Yue Tang, Yawen Wu, Peipei Zhou et al.

Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize the temporal position where the action happens. Such a task is called temporal action location (TAL), which is always trained on the cloud where multiple untrimmed videos are collected and labeled. It is desirable for a TAL model to continuously and locally learn from new data, which can directly improve the action detection precision while protecting customers' privacy. However, it is non-trivial to train a TAL model, since tremendous video samples with temporal annotations are required. However, annotating videos frame by frame is exorbitantly time-consuming and expensive. Although weakly-supervised TAL (W-TAL) has been proposed to learn from untrimmed videos with only video-level labels, such an approach is also not suitable for on-device learning scenarios. In practical on-device learning applications, data are collected in streaming. Dividing such a long video stream into multiple video segments requires lots of human effort, which hinders the exploration of applying the TAL tasks to realistic on-device learning applications. To enable W-TAL models to learn from a long, untrimmed streaming video, we propose an efficient video learning approach that can directly adapt to new environments. We first propose a self-adaptive video dividing approach with a contrast score-based segment merging approach to convert the video stream into multiple segments. Then, we explore different sampling strategies on the TAL tasks to request as few labels as possible. To the best of our knowledge, we are the first attempt to directly learn from the on-device, long video stream.

Shixin Ji, Jinming Zhuang, Sarah Schultz et al.

Spatially partitioned heterogeneous accelerators (HAs) are increasingly adopted in embedded systems for their performance and flexibility. Yet most existing HA design frameworks optimize primarily for throughput or quality-of-service (QoS) metrics. They often overlook safety-critical real-time requirements, including hardware support for predictable execution, real-time-aware design space exploration (DSE), and rigorous schedulability analysis. These requirements are essential in safety-critical applications such as smart transportation, where schedulability guarantees directly affect system safety. To address this gap, we present PHAROS, a real-time-centric HA design framework. PHAROS introduces preemption mechanisms and scheduler designs for spatially partitioned HAs under first-in-first-out (FIFO) and earliest-deadline-first (EDF) policies. Leveraging modern real-time theory, we further develop a soft real-time (SRT) schedulability-oriented DSE with objectives and constraints tailored to SRT schedulability. Through comprehensive modeling, analysis, and evaluation across diverse applications, we show that PHAROS's DSE discovers more feasible configurations for a broader range of task sets than throughput-oriented DSE baselines while delivering improved real-time performance. We also provide response-time analyses for the supported scheduling algorithms.

Peipei Zhou, Zheng Dong, Insup Lee et al.

This report summarizes the discussions and recommendations from the NSF Workshop on Algorithm-Hardware Co-design for Medical Applications, held on September 26-27, 2024, in Pittsburgh, PA. The workshop assembled an interdisciplinary cohort of researchers, clinicians, and industry leaders to examine foundational challenges and develop a strategic roadmap for algorithm-hardware co-design in medical computing. The workshop focuses on four thematic areas: (1) teleoperations, telehealth, and surgical operations; (2) wearable and implantable medicine, including implantable living pharmacies; (3) home ICU, hospital systems, and elderly care; and (4) medical sensing, imaging, and reconstruction. This report calls for a fundamental shift in how next-generation medical technologies are conceived, designed, validated, and translated into practice. The report recommends that NSF sustain investment in shared standardized data infrastructures and compute infrastructures, develop clinic workflow-aware systems and human-AI collaboration frameworks, promote scalable validation ecosystems grounded in objective, continuous measures, and physics-informed, and enable safe, accountable, and resilient platforms, including virtual-physical healthcare ecosystems, to de-risk translational pathways. The workshop information can be found on the website: https://sites.google.com/view/nsfworkshop.

Xingzhen Chen, Jinming Zhuang, Zhuoping Yang et al.

With the development of deep neural network (DNN) enabled applications, achieving high hardware resource efficiency on diverse workloads is non-trivial in heterogeneous computing platforms. Prior works discuss dedicated architectures to achieve maximal resource efficiency. However, a mismatch between hardware and workloads always exists in various diverse workloads. Other works discuss overlay architecture that can dynamically switch dataflow for different workloads. However, these works are still limited by flexibility granularity and induce much resource inefficiency. To solve this problem, we propose a flexible composing architecture, FILCO, that can efficiently match diverse workloads to achieve the optimal storage and computation resource efficiency. FILCO can be reconfigured in real-time and flexibly composed into a unified or multiple independent accelerators. We also propose the FILCO framework, including an analytical model with a two-stage DSE that can achieve the optimal design point. We also evaluate the FILCO framework on the 7nm AMD Versal VCK190 board. Compared with prior works, our design can achieve 1.3x - 5x throughput and hardware efficiency on various diverse workloads.

Yue Tang, Xinyi Zhang, Peipei Zhou et al.

Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the models to adapt to new environments, domains, or new users. In order to realize such domain adaption or personalization, the models on devices need to be continuously trained on the device. In this work, we design EF-Train, an efficient DNN training accelerator with a unified channel-level parallelism-based convolution kernel that can achieve end-to-end training on resource-limited low-power edge-level FPGAs. It is challenging to implement on-device training on resource-limited FPGAs due to the low efficiency caused by different memory access patterns among forward, backward propagation, and weight update. Therefore, we developed a data reshaping approach with intra-tile continuous memory allocation and weight reuse. An analytical model is established to automatically schedule computation and memory resources to achieve high energy efficiency on edge FPGAs. The experimental results show that our design achieves 46.99 GFLOPS and 6.09GFLOPS/W in terms of throughput and energy efficiency, respectively.