3.5. Supported Python features in CUDA Python¶

This page lists the Python features supported in the CUDA Python. This includes all kernel and device functions compiled with @cuda.jit and other higher level Numba decorators that targets the CUDA GPU.

3.5.1. Language¶

3.5.1.1. Execution Model¶

CUDA Python maps directly to the single-instruction multiple-thread execution (SIMT) model of CUDA. Each instruction is implicitly executed by multiple threads in parallel. With this execution model, array expressions are less useful because we don’t want multiple threads to perform the same task. Instead, we want threads to perform a task in a cooperative fashion.

For details please consult the CUDA Programming Guide.

3.5.1.2. Constructs¶

The following Python constructs are not supported:

Exception handling (try .. except, try .. finally)
Context management (the with statement)
Comprehensions (either list, dict, set or generator comprehensions)
Generator (any yield statements)

The raise and assert statements are supported. See nopython language support.

3.5.2. Built-in types¶

The following built-in types support are inherited from CPU nopython mode.

int
float
complex
bool
None
tuple

See nopython built-in types.

3.5.3. Built-in functions¶

The following built-in functions are supported:

abs()
bool
complex
enumerate()
float
int: only the one-argument form
len()
min(): only the multiple-argument form
max(): only the multiple-argument form
range: semantics are similar to those of Python 3 even in Python 2: a range object is returned instead of an array of values.
round()
zip()

3.5.4. Standard library modules¶

3.5.4.1. `cmath`¶

The following functions from the cmath module are supported:

3.5.4.2. `math`¶

The following functions from the math module are supported:

3.5.4.3. `operator`¶

The following functions from the operator module are supported:

3.5.5. Numpy support¶

Due to the CUDA programming model, dynamic memory allocation inside a kernel is inefficient and is often not needed. Numba disallows any memory allocating features. This disables a large number of NumPy APIs. For best performance, users should write code such that each thread is dealing with a single element at a time.

Supported numpy features:

accessing ndarray attributes .shape, .strides, .ndim, .size, etc..
scalar ufuncs that have equivalents in the math module; i.e. np.sin(x[0]), where x is a 1D array.
indexing and slicing works.

Unsupported numpy features:

array creation APIs.
array methods.
functions that returns a new array.