Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques

• URL: http://arxiv.org/abs/2507.11506v1
• Date: Tue, 15 Jul 2025 17:21:31 GMT
• Title: Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques
• Authors: Yiqi Liu, Yuqi Xue, Noelle Crawford, Jilong Xue, Jian Huang,
• Abstract summary: Elk is a DL compiler framework to maximize the efficiency of inter-core connected AI chips.<n>It generates globally optimized execution plans that best overlap off-chip data loading and on-chip execution.<n>Elk achieves 94% of the ideal performance of ICCA chips on average.
• Score: 4.967030650006704
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: To meet the increasing demand of deep learning (DL) models, AI chips are employing both off-chip memory (e.g., HBM) and high-bandwidth low-latency interconnect for direct inter-core data exchange. However, it is not easy to explore the efficiency of these inter-core connected AI (ICCA) chips, due to a fundamental tussle among compute (per-core execution), communication (inter-core data exchange), and I/O (off-chip data access). In this paper, we develop Elk, a DL compiler framework to maximize the efficiency of ICCA chips by jointly trading off all the three performance factors discussed above. Elk structures these performance factors into configurable parameters and forms a global trade-off space in the DL compiler. To systematically explore this space and maximize overall efficiency, Elk employs a new inductive operator scheduling policy and a cost-aware on-chip memory allocation algorithm. It generates globally optimized execution plans that best overlap off-chip data loading and on-chip execution. To examine the efficiency of Elk, we build a full-fledged emulator based on a real ICCA chip IPU-POD4, and an ICCA chip simulator for sensitivity analysis with different interconnect network topologies. Elk achieves 94% of the ideal roofline performance of ICCA chips on average, showing the benefits of supporting large DL models on ICCA chips. We also show Elk's capability of enabling architecture design space exploration for new ICCA chip development.

Related papers

• Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive [58.0729162588429]
  Interactive segmentation improves annotation efficiency by segmenting target regions from user prompts.<n>Current approaches face a critical trade-off: dense-token methods achieve superior accuracy but suffer from prohibitively slow processing on CPU devices.<n>We propose Inter2Former to address this challenge by optimizing computation allocation in dense-token processing.
  arXiv  Detail & Related papers  (2025-07-13T12:33:37Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• Scaling Deep Learning Computation over the Inter-Core Connected Intelligence Processor with T10 [13.293273876476512]
  We present T10, the first DL compiler to exploit the inter-core communication bandwidth and distributed on-chip memory on AI chips. T10 makes globally optimized trade-offs between on-chip memory consumption and inter-core communication overhead. Our evaluation with a real inter-core connected AI chip, the Graphcore IPU, shows up to 3.3$times$ performance improvement.
  arXiv  Detail & Related papers  (2024-08-09T01:28:09Z)
• Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms [77.71341200638416]
  ChiPBench is a benchmark designed to evaluate the effectiveness of AI-based chip placement algorithms.<n>We have gathered 20 circuits from various domains (e.g., CPU, GPU, and microcontrollers) for evaluation.<n>Results show that even if intermediate metric of a single-point algorithm is dominant, the final PPA results are unsatisfactory.
  arXiv  Detail & Related papers  (2024-07-03T03:29:23Z)
• CLSA-CIM: A Cross-Layer Scheduling Approach for Computing-in-Memory Architectures [0.1747623282473278]
  We present CLSA-CIM, a cross-layer scheduling algorithm for tiled CIM architectures. We integrate CLSA-CIM with existing weight-mapping strategies and compare performance against state-of-the-art (SOTA) scheduling algorithms.
  arXiv  Detail & Related papers  (2024-01-15T13:35:21Z)
• REED: Chiplet-Based Accelerator for Fully Homomorphic Encryption [4.713756093611972]
  We present the first-of-its-kind multi-chiplet-based FHE accelerator REED' for overcoming the limitations of prior monolithic designs.<n>Results demonstrate that REED 2.5D microprocessor consumes 96.7 mm$2$ chip area, 49.4 W average power in 7nm technology.
  arXiv  Detail & Related papers  (2023-08-05T14:04:39Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems [62.20308752994373]
  We propose a new smart network interface card (NIC) for distributed AI training systems using field-programmable gate arrays (FPGAs) Our proposed FPGA-based AI smart NIC enhances overall training performance by 1.6x at 6 nodes, with an estimated 2.5x performance improvement at 32 nodes, compared to the baseline system using conventional NICs.
  arXiv  Detail & Related papers  (2022-04-22T21:57:00Z)
• Dataflow Aware Mapping of Convolutional Neural Networks Onto Many-Core Platforms With Network-on-Chip Interconnect [0.0764671395172401]
  Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Many-core platforms consisting of several homogeneous cores can alleviate limitations with regard to physical implementation at the expense of an increased dataflow mapping effort. This work presents an automated mapping strategy starting at the single-core level with different optimization targets for minimal runtime and minimal off-chip memory accesses. The strategy is then extended towards a suitable many-core mapping scheme and evaluated using a scalable system-level simulation with a network-on-chip interconnect.
  arXiv  Detail & Related papers  (2020-06-18T17:13:18Z)
• PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices [35.90103072918056]
  Deep neural network (DNN) has emerged as the most important and popular artificial intelligent (AI) technique. The growth of model size poses a key energy efficiency challenge for the underlying computing platform. This paper proposes PermDNN, a novel approach to generate and execute hardware-friendly structured sparse DNN models.
  arXiv  Detail & Related papers  (2020-04-23T02:26:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.