C++ CUDA-compatible template class that provides an interface for generic purpose matrix related algorithms and computations. Includes Matlab-like functions. This is mainly an example of how to use CUDA code with C++. Don't expect such high performance.

Compute the cube root of each element in a strided array.

Element-wise subtraction of two strided arrays via a callback function.

Compute the arctangent of each element retrieved from an input strided array via a callback function.

Apply a function to each element in an array and assign the result to an element in an output array.

Compute the multiplicative inverse for each element in a strided array.

Round each element in a double-precision floating-point strided array toward negative infinity according to a strided mask array.

Round each element in a strided array toward positive infinity.

Compute the arccosine of each element retrieved from an input strided array via a callback function.

Compute the sine of each element retrieved from an input strided array via a callback function.

Compute the absolute value for each element in a strided array.

Compute the absolute value.

Compute the absolute value of each element retrieved from a strided input array via a callback function and assign each result to an element in a strided output array.

Evaluate the ramp function for each element in a strided array.

Strided array math operations.

Evaluate Binet's formula extended to real numbers for each element retrieved from an input strided array via a callback function.

Apply a function to each element in an array and assign the result to an element in an output array, iterating from right to left.

Compute the cosine for each element retrieved from an input strided array via a callback function.

Compute the absolute value for each element in a single-precision floating-point strided array.

Round each element in a double-precision floating-point strided array toward positive infinity.