Tenstorrent DOCUMENTATION
  • Get Started
    Overview Installing Tenstorrent Software Manual Installation Deploy LLMs Learn by Building
  • Software
    TT-Forge TT-NN TT-Lang TT-MLIR TT-XLA TT-Metalium
  • Hardware
    Blackhole Blackhole™ PCIe Cards TT-QuietBox TT-QuietBox 2 Wormhole Wormhole™ PCIe Cards TT-QuietBox TT-LoudBox™
  • Tools
    TT-Inference-Server TT-Studio TT-SMI TT-Toplike TT-NN Visualizer TT-Topology TT-VSCode-Toolkit TT-Blacksmith
  • Resources
    Request Support Developer Hub Join our Discord FAQ
Explore Github
    Start typing to search the documentation.
    Type a question above and press Enter — or jump right in:
    Logo TT-Metalium

    Get Started

    • Getting Started
    • Install

    TT-Metalium

    • Programming Model
    • Programming Examples
      • DRAM Loopback
      • Eltwise binary
      • Eltwise SFPU
      • Matmul (Single Core)
      • Matmul (Multi Core)
      • Matmul (Multi Core Optimized)
      • Writing Custom SFPU Operations using SFPI
    • Lab Exercises
      • Lab 1: Single Core Matrix Multiplication
      • Lab 2: Multi Core Matrix Multiplication
      • Lab 3: Multicast for Improved Data Reuse in Multi Core Matrix Multiplication
    • Advanced Topics
      • Tiles
      • Memory from a kernel developer’s perspective
      • Compute Engines and Data Flow within Tensix
      • Achieving FP32 Accuracy for Computation
    • APIs
      • Host APIs
      • Kernel APIs
    • Environment Variables
    • Tools
      • Debug Checkpoints
      • Device Debug Print
      • Watcher
      • Tracy Profiler
      • Device Program Profiler
      • Lightweight Kernel Asserts
      • LLK Asserts
      • Inspector
      • tt-triage
      • NOC Debug Dump

    Resources

    • Support
    • Contributing as a developer
    TT-Metalium
    • Advanced Topics
    • View page source

    Advanced Topics

    This section provides an overview of the details of the Tensix architecture and how Metalium integrates with it. The documents here are intended for developers looking to understand the underlying hardware and software interactions.

    Hardware implications and the effects

    • Tiles
      • Internal structure of a Tile
      • Conversion between tiles and row-major format
    • Memory from a kernel developer’s perspective
      • Data addressing on Tenstorrent processors
        • RISC-V Address Space
        • DRAM tiles
        • Memory access via the NoC
      • Tensor Layout
      • Memory placement
        • Lock step allocation
        • Interleaved memory
        • SRAM buffers
        • Sharded tensor
    • Compute Engines and Data Flow within Tensix
      • Component introduction
      • Dst register
      • Matrix engine/FPU
      • Vector engine/SFPU
    • Achieving FP32 Accuracy for Computation
      • Host-Side Configuration
      • Kernel-Side Implementation
      • Distinguishing Between matrix and vector engine APIs
    Previous Next

    © Copyright Tenstorrent.

    Built with Sphinx using a theme provided by Read the Docs.

    Was this article helpful?

    How would you describe this article?

    Thank you for your feedback!

    Sorry, something went wrong. Please try again later.

    Version: latest
    Versions
    ('latest', 'https://firdovsimammedovk.github.io/tt-metal-sandbox/tt-metalium/latest/')
    ('v1.1', 'https://firdovsimammedovk.github.io/tt-metal-sandbox/tt-metalium/v1.1/')
    ('v1.0', 'https://firdovsimammedovk.github.io/tt-metal-sandbox/tt-metalium/v1.0/')