mlsanityData to 14 Oct 2026

Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration

arXiv 2608.24664 ↗First posted 25 Aug 2026cs.AR cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce Maia 200, an advanced AI accelerator delivering high performance-10 145 Tflop/s FP4 and 5072 Tflop/s FP8 within a 750W TDP and 7 TB/s HBM bandwidth. Maia exemplifies a new class of Software Defined Locally Accessed Dataflow Architectures (SDLA), which explicitly program dataflow engines to orchestrate highly specialized memories and data movement engines. This approach shifts the focus from today's thread-centric to data-movement-centric architecture, improving efficiency and scalability. Our taxonomy of data management, inspired by Flynn's classification, highlights how SDLA addresses challenges in modern AI computing. Maia 200 achieves significant cost and energy savings while supporting massive parallelism for AI inference workloads, making it a compelling solution for next-generation high-performance computing systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 80 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

35 of 80 references.

References · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  6. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  7. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  8. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  9. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  10. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  11. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  12. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
23 more
  1. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 519
  2. 2023Cognitive Architectures for Language Agentscited by 429
  3. 2023TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddingscited by 202
  4. 2018Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysiscited by 156
  5. 2020Data Movement Is All You Need: A Case Study on Optimizing Transformerscited by 108
  6. 2026FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scalingcited by 66
  7. 2025Reasoning Language Models: A Blueprintcited by 42
  8. 2024Benchmarking and Dissecting the Nvidia Hopper GPU Architecturecited by 24
  9. 2019Stateful Dataflow Multigraphs: A Data-Centric Model for Performance Portability on Heterogeneous Architecturescited by 21
  10. 2019Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplicationcited by 21
  11. 2025Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithmscited by 20
  12. 2024SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Expertscited by 18
  13. 2025MSCCL++: Rethinking GPU Communication Abstractions for AI Inferencecited by 10
  14. 2022HammingMesh: A Network Topology for Large-Scale Deep Learningcited by 8
  15. 2024REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigationcited by 6
  16. 2014Quantifying performance bottlenecks of stencil computations using the Execution-Cache-Memory modelcited by 2
  17. 2022Deinsum: Practically I/O Optimal Multilinear Algebracited by 2
  18. 2023A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable Processorscited by 2
  19. 2023Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebracited by 2
  20. 2025A System Level Compiler for Massively-Parallel, Spatial, Dataflow Architecturescited by 1
  21. 2025Ultra Ethernet's Design Principles and Architectural Innovationscited by 1
  22. 2025Bine Trees: Enhancing Collective Operations by Optimizing Communication Localitycited by 1
  23. 2025SpaDA: A Spatial Dataflow Architecture Programming Languagecited by 1

Built on by

Not cited yet.