dlarray — Create a dlarray compatibility object around host or gpuArray data.

dlarray(X) wraps host or provider-resident gpuArray data and optional dimension labels in a RunMat compatibility object.

Syntax

X = dlarray(data)
X = dlarray(data, fmt)

How dlarray works

  • The underlying Data value is preserved without conversion, including provider-resident gpuArray handles.
  • A second text argument is stored as Format and Labels.
  • Additional constructor options are rejected with explicit compatibility errors.
  • Inside dlfeval, host dlarray values become traced leaves for the bounded dlgradient tape. Supported arithmetic preserves the wrapper and dimension-label metadata.

GPU memory and residency

dlarray preserves provider-resident gpuArray data as wrapper metadata outside autodiff. GPU-backed dlarray tracing is rejected with an explicit provider-gap error until Deep Learning tape kernels are available in the acceleration provider.

Example

Wrap Data

X = dlarray(rand(3,4), 'CB')

Expected output:

dlarray compatibility object.

Using dlarray with coding agents

Open a RunMat example with live inputs, then ask the agent to explain how dlarray changes the result.

Run a small dlarray example, explain the result, then change one input and compare the output.

About RunMat

RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.

  • RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
  • Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.

Getting started · Benchmarks · Pricing

Download RunMat

Download RunMat for full performance, or use RunMat in your browser for zero setup.