GPULib API

Tech-X Corporation

Directory: lib/

.pro files

gpu_benchmark.pro

Benchmark routine that indicates the device it is running on and its speedup over regular IDL code.

gpu_errormessage.pro

Returns the error message for a CUDA error code.

gpu_test.pro

Basic sanity test for GPULib.

gpuabs.pro

Return the absolute value of a vector

gpuacos.pro

Compute the acos of a vector

gpuacosh.pro

Return the hyperbolic acos of a vector

gpuadd.pro

Add two vectors

gpuasin.pro

Compute the asin of a vector

gpuasinh.pro

Return the hyperbolic asin of a vector

gpuatan.pro

Compute the atan of a vector

gpuatan2.pro

two argument arc tangent

gpuatanh.pro

Return the hyperbolic atan of a vector

gpuceil.pro

Return the ceil of a vector

gpucindgen.pro

This routine creates an IDL structure representing a complex array on the GPU that other GPULib library routines can use and initializes its elements to the array index.

gpucomplex.pro

This routine converts an input array into a complex GPU array.

gpucomplexarr.pro

This routine creates an IDL structure representing a complex array on the GPU that other GPULib library routines can use.

gpucongrid.pro

Changes the resolution of an array, either using interpolation or nearest grid point sampling.

gpucopy.pro

Copies a GPU vector

gpucos.pro

Compute the cos of a vector

gpucosh.pro

Return the hyperbolic cos of a vector

gpudblarr.pro

This routine creates an IDL structure representing a double array on the GPU that other GPULiblibrary routines can use.

gpudcindgen.pro

This routine creates an IDL structure representing a double precision complex array on the GPU that other GPULib library routines can use and initializes its elements to the array index.

gpudcomplex.pro

This routine converts an input array into a double complex GPU array.

gpudcomplexarr.pro

This routine creates an IDL structure representing a double precision complex array on the GPU that other GPULib library routines can use.

gpudindgen.pro

This routine creates an IDL structure representing a double array on the GPU that other GPULib library routines can use and initializes its elements to the array index.

gpudiv.pro

Divide two vectors

gpudouble.pro

This routine converts an input array into a double GPU array.

gpudoublecapable.pro

Returns whether the given device is capable of double-precision calculations.

gpueq.pro

Compare two vetors for EQ

gpuerf.pro

Compute the erf of a vector

gpuexp.pro

Compute the exp of a vector

gpufft.pro

Perform FFT on the GPU

gpufindgen.pro

This routine creates an IDL structure representing a float array on the GPU that other GPULib library routines can use and initializes its elements to the array index.

gpufix.pro

Converts a GPU array of one type into a GPU array of another type:

gpufloat.pro

This routine converts an input array into a float GPU array.

gpufloor.pro

Return the floor of a vector

gpufltarr.pro

This routine creates an IDL object representing a float array on the GPU that other GPULib library routines can use.

gpufmod.pro

floating point modulo

gpufree.pro

Free resource on GPU held by given variable(s).

gpugetarr.pro

Transfer GPU variables to IDL.

gpugethandle.pro

Creates a variable on the GPU that can be manipulated by the GPULib library routines.

gpugt.pro

Compare two vetors for GT

gpugteq.pro

Compare two vetors for GTEQ

gpuhist_2d.pro

NAME: GPUHIST_2D

gpuhistogram.pro
gpuidlacosh.pro

Inverse hyperbolic cosine.

gpuidlasinh.pro

Inverse hyperbolic sine.

gpuidlatanh.pro

Inverse hyperbolic tangent.

gpuimaginary.pro

Extracts the imaginary part of a complex data object on the GPU

gpuinit.pro

Start up the IDL CUDA interface in either: hardware, emulator, or IDL mode.

gpuinterpolate.pro

Calculates the linear or bilinear interpolates of the given input p_gpu, depending on the number of arguments presented.

gpulgamma.pro

Compute the log gamma function of a vector

gpulog.pro

Compute the log of a vector

gpulog10.pro

Compute the log10 of a vector

gpult.pro

Compare two vetors for LT

gpulteq.pro

Compare two vetors for LTEQ

gpumake_array.pro

This routine creates an IDL structure representing an array on the GPU that other GPULib library routines can use.

gpumatrix_multiply.pro

Performs multiplication of two GPU matrices or their transposes.

gpumax.pro

Calculates the maximum of the elements of the GPU vector.

gpumaxop.pro

Compares the elements of a vector with a scalar or vector and sets the resulting vector to the larger of the two.

gpumemgetinfo.pro

Returns information about total and available memory.

gpumin.pro

Calculates the minimum of the elements of the GPU vector.

gpuminop.pro

Compares the elements of a vector with a scalar or vector and sets the resulting vector to the smaller of the two.

gpumult.pro

Multiply two vectors

gpuneq.pro

Compare two vetors for NEQ

gpupow.pro

power function

gpuprefixsum.pro

Computes the prefix sum on a GPU array

gpuproperties.pro

Returns properties about a graphics device.

gpuputarr.pro

Transfer IDL variables to the GPU.

gpurandomn.pro

This routine generates normally distributed random numbers on the GPU

gpurandomu.pro

This routine generates uniformly distributed random numbers on the GPU

gpureal.pro

Extracts the real part of a complex data object on the GPU

gpureal_part.pro

Extracts the real part of a complex data object on the GPU.

gpureform.pro

Change the dimensions of a GPU variable without changing the total number of elements.

gpurint.pro

Rint a vector

gpuround.pro

Round a vector

gpushift.pro

Perform circular shift.

gpusin.pro

Compute the sin of a vector

gpusinh.pro

Return the hyperbolic sin of a vector

gpusort.pro

Sorts an array.

gpusqrt.pro

Compute the sqrt of a vector

gpustreamcapable.pro

Returns whether the given device is capable of using the streaming API.

gpusub.pro

Subtract two vectors

gpusubarr.pro

Extract a subset of an array and store it in a subset of the result array.

gpusubscript.pro

Subscripts a GPU array with another GPU array

gputan.pro

Compute the tan of a vector

gputanh.pro

Return the hyperbolic tan of a vector

gputgamma.pro

Compute the gamma function of a vector

gputotal.pro

Calculates the total of the elements of the GPU vector.

gputranspose.pro

This routine transposes a 2-dimensional array.

gputrunc.pro

Compute the trunc function of a vector

gpuvalid.pro

Determines if a variable is a valid GPU variable.

gpuvariable__define.pro

Represents a GPU variable.

gpuvariableview__define.pro

Represents a GPU variable.

gpuview.pro

Places a view onto a GPU object

gpuwhere.pro

Scans the (float-boolean) input vector and stores the indices of the true elements in the output vector.

heap_refcount.pro

Need a version of HEAP_REFCOUNT so the unit test runner can compile under versions of IDL before 8.0.

idl_object__define.pro

This class is used to inherit from in IDL versions before 8.0, allowing operator overloaded classes to still compile on earlier versions (though not to offer operator overloading, of course).

trunc.pro

Trunc argument towards 0.0.

tx_src_root.pro

Returns the directory name (with a trailing slash) of the location of the source code for the routine that called this function.

Contents

.idldoc files

CUDA error codes