CUDA ENGINEERING

THE ATLAS · SEVEN DOMAINS · EVERY CONCEPT

The whole machine, mapped.

Reference coverage of the full CUDA surface: hardware, threads, memory, performance, asynchrony, tooling and libraries — exhibits where seeing beats reading.

Grids, blocks, threads, indexing math, divergence, synchronization.

Three levels of organization: launch a grid, schedule blocks, execute threads.

Linearize coordinates: row-major math for images and volumes.

If lanes disagree at a branch, the warp executes both paths serially.

__syncthreads() barriers within a block; warp intrinsics need no barrier.

◈ entries are hands-on exhibits. Everything else expands in place. The full narrative version of core topics lives in the journey.

Agent-native web · research mode

Experimental WebMCP · evolving community-group draft, not a W3C Standard or on the Standards Track.

Native status: Initializing. Registered: none

DOM → inferred capabilities · WebMCP → declared capabilities. Tools read real CUDA/Inference Atlas content. Calls may highlight temporary UI state. No backend or remote telemetry.

Local harness verifies application logic; it does not demonstrate native discovery or a browser agent.

Input schema
{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
Local log: last 100 calls while this panel is open. Inputs may contain personal text; review before sharing.
 
[]