Compiler flags

Pass additional flags to GPU compiler

Description

App Configuration Pane: GPU Code

Configuration Objects: coder.gpuConfig

The Compiler flags parameter passes additional flags to the GPU compiler.

For example, to instruct the nvcc compiler to disable contraction of floating-point multiply and add to a floating-point multiply-add (FMAD) instruction, specify this for the Compiler flags parameter:

--fmad=false

For similar NVIDIA^® compiler options, see the topic on "NVCC Command Options" in the CUDA^® Toolkit documentation.

Settings

no default

Enter the flags to pass to the GPU compiler.

Programmatic Use

Property: CompilerFlags

Values: "" | character vector

Default: ""

Version History

Introduced in R2018a