futhark cuda [options…] <program.fut>


futhark cuda translates a Futhark program to C code invoking CUDA kernels, and either compiles that C code with gcc(1) to an executable binary program, or produces a .h and .c file that can be linked with other code. The standard Futhark optimisation pipeline is used, and GCC is invoked with -O, -lm, and -std=c99. The resulting program will otherwise behave exactly as one compiled with futhark c.

futhark cuda uses -lcuda -lnvrtc to link. If using --library, you will need to do the same when linking the final binary.



Print help text to standard output and exit.


Generate a library instead of an executable. Appends .c/.h to the name indicated by the -o option to determine output file names.

-o outfile

Where to write the result. If the source program is named foo.fut, this defaults to foo.


Ignore unsafe in program and perform safety checks unconditionally.

-v verbose

Enable debugging output. If compilation fails due to a compiler error, the result of the last successful compiler step will be printed to standard error.


Print version information on standard output and exit.


Do not print any warnings.


Treat warnings as errors.


Generated executables accept the same options as those generated by futhark-c. The -t option behaves as with futhark-opencl. For commonality, the options use OpenCL nomenclature (“group” instead of “thread block”).

The following additional options are accepted.


The default size of thread blocks that are launched. Capped to the hardware limit if necessary.


The default number of thread blocks that are launched.


The default parallelism threshold used for comparisons when selecting between code versions generated by incremental flattening. Intuitively, the amount of parallelism needed to saturate the GPU.


The default tile size used when performing two-dimensional tiling (the workgroup size will be the square of the tile size).


Don’t run the program, but instead dump the embedded CUDA kernels to the indicated file. Useful if you want to see what is actually being executed.


Don’t run the program, but instead dump the PTX-compiled version of the embedded kernels to the indicated file.


Instead of using the embedded CUDA kernels, load them from the indicated file.


Load PTX code from the indicated file.


Add an additional build option to the string passed to NVRTC. Refer to the CUDA documentation for which options are supported. Be careful - some options can easily result in invalid results.


Print all sizes that can be set with -size or --tuning.


Set a configurable run-time parameter to the given value. ASSIGNMENT must be of the form NAME=INT Use --print-sizes to see which names are available.


Read size=value assignments from the given file.


If run without --library, futhark cuda will invoke gcc(1) to compile the generated C program into a binary. This only works if gcc can find the necessary CUDA libraries. On most systems, CUDA is installed in /usr/local/cuda, which is not part of the default gcc search path. You may need to set the following environment variables before running futhark cuda: