CUDA Package
use CUDA(R) technology to accelerate certain LinearAlgebra routines
Calling Sequence
Introduction
List of CUDA Package Commands
Examples
CUDA:-command( arguments )
command( arguments )
The CUDA package allows Maple to use the graphics processing unit (GPU) of your NVIDIA(R) Compute Unified Device Architecture (CUDA)-enabled hardware to accelerate certain LinearAlgebra routines.
For more information about NVIDIA and CUDA technology, visit http://www.nvidia.com and http://www.nvidia.com/object/cuda_home.html.
To use this package, you need NVIDIA CUDA-enabled hardware and the most recent drivers for that hardware installed on your computer. For more information about supported hardware and a complete list of requirements, see the Supported Hardware for CUDA Acceleration help page.
For more information about the routines that are accelerated when CUDA technology is turned on, see the Routines Accelerated by the CUDA Package help page.
ComputeLevel
Enable
HasDoubleSupport
IsEnabled
Properties
The Enable function turns CUDA acceleration on and off.
The IsEnabled function returns a value of true if CUDA acceleration is turned on and false otherwise.
The ComputeLevel function indicates the compute level of the CUDA-enabled devices available on your computer.
The HasDoubleSupport function checks whether the CUDA-enabled devices available on your computer support double precision computations.
The Properties function displays information about the CUDA-enabled devices available on your computer.
n≔4000:
M1≔LinearAlgebra:-RandomMatrix⁡n,n,datatype=float4:
M2≔LinearAlgebra:-RandomMatrix⁡n,n,datatype=float4:
CUDA:-IsEnabled⁡
false
tNoCUDA≔timereal⁡M1·M2
tNoCUDA≔13.823
CUDA:-Enable⁡true
true
tCUDA≔timereal⁡M1·M2
tCUDA≔1.163
evalf⁡tNoCUDAtCUDA
11.88564058
CUDA:-Enable⁡false
See Also
LinearAlgebra
Download Help Document