c++ arrayfire supported data types

Supported data types

ArrayFire provides one generic container object, the array on which functions and mathematical operations are performed. The array can represent one of many different basic data types:

• f32 real single-precision (float)
• c32 complex single-precision (cfloat)
• f64 real double-precision (double)
• c64 complex double-precision (cdouble)
• f16 real half-precision (half_float::half)
• b8 8-bit boolean values (bool)
• s32 32-bit signed integer (int)
• u32 32-bit unsigned integer (unsigned)
• u8 8-bit unsigned values (unsigned char)
• s64 64-bit signed integer (intl)
• u64 64-bit unsigned integer (uintl)
• s16 16-bit signed integer (short)
• u16 16-bit unsigned integer (unsigned short)

Most of these data types are supported on all modern GPUs; however, some older devices may lack support for double precision arrays. In this case, a runtime error will be generated when the array is constructed.

If not specified otherwise, arrays are created as single precision floating point numbers (f32).

来源： ArrayFire: Getting Started