The Enable function turns Compute Unified Device Architecture (CUDA) acceleration on and off. By default, CUDA acceleration is turned off.

Note: The Enable function returns the previous setting for CUDA acceleration. For example, if you run the CUDA:-Enable(true) function when CUDA acceleration is turned off, CUDA acceleration will then be turned on, but the function will return a value of  false because CUDA acceleration was previously turned off. See the examples below.

If your computer does not support CUDA, an error will be displayed. For more information about supported hardware, see Supported Hardware for CUDA Acceleration.

$n≔4000\:$

$\mathrm{M1}≔\mathrm{LinearAlgebra}:-\mathrm{RandomMatrix}\left(n\,n\,\mathrm{datatype}=\mathrm{float}\left[4\right]\right)\:$

$\mathrm{M2}≔\mathrm{LinearAlgebra}:-\mathrm{RandomMatrix}\left(n\,n\,\mathrm{datatype}=\mathrm{float}\left[4\right]\right)\:$

$\mathrm{CUDA}:-\mathrm{IsEnabled}\left(\right)$

$\mathrm{false}$

$\mathrm{tNoCUDA}≔\mathrm{time}\left[\mathrm{real}\right]\left(\mathrm{M1}·\mathrm{M2}\right)$

$\mathrm{tNoCUDA}≔13.823$

$\mathrm{CUDA}:-\mathrm{Enable}\left(\mathrm{true}\right)$

$\mathrm{false}$

$\mathrm{CUDA}:-\mathrm{IsEnabled}\left(\right)$

$\mathrm{true}$

$\mathrm{tCUDA}≔\mathrm{time}\left[\mathrm{real}\right]\left(\mathrm{M1}·\mathrm{M2}\right)$

$\mathrm{tCUDA}≔1.163$

$\mathrm{evalf}\left(\frac{\mathrm{tNoCUDA}}{\mathrm{tCUDA}}\right)$

$11.88564058$

$\mathrm{CUDA}:-\mathrm{Enable}\left(\mathrm{false}\right)$

$\mathrm{true}$

$\mathrm{CUDA}:-\mathrm{IsEnabled}\left(\right)$

$\mathrm{false}$