warp.Scalar

warp.Scalar

Generic annotation for any Warp integer or floating-point scalar type.

Use Scalar to annotate parameters of generic Warp kernels and functions, either directly or as the dtype of a generic array, vector, or matrix. Scalar matches the types that Int and Float match:

• int8, int16, int32, or int64.

• uint8, uint16, uint32, or uint64.

• float16, float32, or float64.

• bfloat16.

• Python int or float, which Warp treats as int32 or float32, respectively.

bool doesn’t match Scalar.

For more on writing generic kernels and functions with Scalar, see Generic Type Annotations.