🐯虎嗅•較早收集於 21m
矽仙人反GPU AI晶片解析
💡Keller RISC-V AI晶片勝GPU內迴圈－開發者友善替代。（28字）
⚡ 30-Second TL;DR
有什麼變化
NoC網格Tensix：5x RISC-V、1.5MB SRAM、向量/矩陣單元
為什麼重要
挑戰GPU壟斷，提供高效低成本AI硬體可擴至機架。吸引尋NVIDIA替代的自訂加速開發者。
下一步行動
下載tt-Metalium SDK在Tensix原型32x32分塊矩陣乘法。
誰應關注：Developers & AI Engineers
關鍵要點
- •NoC網格Tensix：5x RISC-V、1.5MB SRAM、向量/矩陣單元
- •顯式SRAM管理免緩存確保可預測效能
- •以太網400Gbps多晶片擴展勝昂貴NVLink
- •原生32x32矩陣分塊優化深度學習
🧠 深度解析
本篇為 AI 生成分析，非原文內容。
🔑 增強重點摘要
- •Tenstorrent's architecture utilizes a 'dataflow' execution model, which fundamentally differs from the instruction-driven SIMT model of GPUs by allowing data to flow directly between cores without constant memory round-trips.
- •The Wormhole chip incorporates a proprietary 'Packetized' interconnect protocol that allows for seamless scaling across heterogeneous clusters, specifically targeting the reduction of latency in large-scale distributed training.
- •Tenstorrent has shifted its business model to include IP licensing of its RISC-V and Tensix core technology to third-party silicon vendors, aiming to create a broader ecosystem beyond its own hardware.
📊 競品分析▸ Show
| Feature | Tenstorrent Wormhole | NVIDIA Blackwell (B200) | Groq LPU |
|---|---|---|---|
| Architecture | Dataflow / RISC-V | SIMT / Hopper-Blackwell | Tensor Streaming Processor |
| Interconnect | Ethernet-based (Scale-out) | NVLink (Scale-up) | Proprietary Low-Latency |
| Memory Model | Explicit SRAM (Managed) | HBM3e (Cache-based) | SRAM-centric (Deterministic) |
| Primary Focus | Efficiency/Flexibility | Raw Throughput/Ecosystem | Inference Latency |
🛠️ 技術深入
- Tensix Core: Comprises a 5-core RISC-V cluster (1 control, 4 worker) paired with a high-performance matrix math engine and a vector engine.
- Memory Hierarchy: Employs a distributed, software-managed SRAM architecture rather than traditional hardware-managed L1/L2 caches to ensure deterministic execution timing.
- Dataflow Engine: Designed to execute graphs of operations where data movement is scheduled at compile-time, minimizing the overhead of instruction fetching and decoding.
- tt-Metalium SDK: Provides a low-level abstraction layer that allows developers to manage data movement and compute scheduling directly on the Tensix cores, bypassing standard driver overhead.
🔮 前景展望AI analysis grounded in cited sources
Tenstorrent will prioritize IP licensing revenue over direct hardware sales by 2027.
The company's strategic pivot toward licensing RISC-V and Tensix IP suggests a long-term goal of becoming a foundational silicon provider rather than a pure-play hardware vendor.
Wormhole-based clusters will achieve lower TCO than GPU clusters for specific inference workloads.
The use of standard Ethernet for scaling and the elimination of expensive, proprietary interconnects like NVLink significantly reduces infrastructure capital expenditure.
⏳ 時間線
2016-05
Tenstorrent founded by Ljubisa Bajic, Ivan Hamer, and Milos Trajkovic.
2021-01
Jim Keller joins Tenstorrent as President and CTO.
2023-08
Tenstorrent secures $100 million in strategic funding led by Hyundai and Samsung Catalyst Fund.
2024-02
Tenstorrent announces the availability of its Wormhole development kits for enterprise partners.
📰
AI 週報
閱讀本週精選 AI 大事摘要 →
👉相關動態
AI 策展新聞聚合。所有內容版權歸原始發布者所有。
原始來源： 虎嗅 ↗
每週 AI 簡報
每週一封，可隨時退訂。