Functions — github.com/Protryon/cuda-oxide

CodeHub MCPcopy Create free account

hub / github.com/Protryon/cuda-oxide / functions

Functions194 in github.com/Protryon/cuda-oxide

⨍ Functions 194◇ Types & classes 138

Functionbindgen_test_layout___pthread_cond_s

src/sys.rs:1233

Functionbindgen_test_layout___pthread_cond_s__bindgen_ty_1

src/sys.rs:1100

Functionbindgen_test_layout___pthread_cond_s__bindgen_ty_1__bindgen_ty_1

src/sys.rs:1055

Functionbindgen_test_layout___pthread_cond_s__bindgen_ty_2

src/sys.rs:1194

Functionbindgen_test_layout___pthread_cond_s__bindgen_ty_2__bindgen_ty_1

src/sys.rs:1149

Functionbindgen_test_layout___pthread_internal_list

Functionbindgen_test_layout___pthread_internal_slist

Functionbindgen_test_layout___pthread_mutex_s

Functionbindgen_test_layout___pthread_rwlock_arch_t

Functionbindgen_test_layout___sigset_t

Functionbindgen_test_layout_div_t

Functionbindgen_test_layout_drand48_data

src/sys.rs:1892

Functionbindgen_test_layout_fd_set

Functionbindgen_test_layout_ldiv_t

Functionbindgen_test_layout_lldiv_t

Functionbindgen_test_layout_pthread_attr_t

src/sys.rs:1413

Functionbindgen_test_layout_pthread_barrier_t

src/sys.rs:1642

Functionbindgen_test_layout_pthread_barrierattr_t

src/sys.rs:1681

Functionbindgen_test_layout_pthread_cond_t

src/sys.rs:1503

Functionbindgen_test_layout_pthread_condattr_t

src/sys.rs:1372

Functionbindgen_test_layout_pthread_mutex_t

src/sys.rs:1453

Functionbindgen_test_layout_pthread_mutexattr_t

src/sys.rs:1333

Functionbindgen_test_layout_pthread_rwlock_t

src/sys.rs:1553

Functionbindgen_test_layout_pthread_rwlockattr_t

src/sys.rs:1602

Functionbindgen_test_layout_random_data

src/sys.rs:1741

Functionbindgen_test_layout_timespec

Functionbindgen_test_layout_timeval

Methodcopy_from

Synchronously copies data from `source` to `self`. Panics if length is not equal.

Methodcopy_from_stream

Asynchronously copies data from `source` to `self`. Panics if length is not equal.

src/module.rs:41

Methodderef_mut

Methodderef_mut

src/module.rs:215

src/stream.rs:183

src/future.rs:71

src/context.rs:62

(&self, f: &mut fmt::Formatter<'_>)

src/version.rs:40

(&self, f: &mut fmt::Formatter<'_>)

src/error.rs:303

(inner: (u32, u32, u32))

src/version.rs:16

Constructs a [`DeviceBox`] from a device pointer.

Methodfrom_raw_parts

(handle: Rc<Handle<'a>>, ptr: u64, len: u64)

Methodget_attribute

Returns information about a function.

Methodget_global

Get a pointer to a global variable defined by a CUDA module.

src/module.rs:268

Methodget_limit

Get a CUDA context limit

src/context.rs:45

Methodget_texture_1d_linear_max_width

Calculates the linear max width of 1D textures for a given native array format

src/device.rs:69

Gets a reference to the owning handle

Functionhost_callback

(arg: *mut std::ffi::c_void)

src/stream.rs:27

Initialize the CUDA library. Can be called repeatedly at no cost.

Methodis_synced

Returns `Ok(true)` if the stream has finished processing all queued tasks.

src/stream.rs:57

Leaks the DeviceBox, similar to [`Box::leak`].

Methodlist_devices

List all CUDA-enabled devices on the host

src/device.rs:89

Takes a raw CUDA kernel image and loads the corresponding module module into the current context. The pointer can be a cubin or PTX or fatbin file as

src/module.rs:231

Methodload_fatcubin

Same as [`Module::load`] but uses `fatCubin` format.

src/module.rs:243

Methodload_stream

Asynchronously loads the data from this slice into a local buffer. The contents of the buffer are undefined until `stream.sync` is called. The output

examples/enumerate.rs:3

examples/matrix_mul_jit/main.rs:20

examples/matrix_mul/main.rs:20

Methodmemory_size

Gets the total available memory size of the device, in bytes

src/device.rs:43

Methodmemset_d16

Synchronously set the contents of `self` to `data` repeated to fill length. Panics if [`Self::len`] is not a multiple of 2.

Methodmemset_d16_stream

Asynchronously set the contents of `self` to `data` repeated to fill length. Panics if [`Self::len`] is not a multiple of 2.

Methodmemset_d32

Synchronously set the contents of `self` to `data` repeated to fill length. Panics if [`Self::len`] is not a multiple of 4.

Methodmemset_d32_stream

Asynchronously set the contents of `self` to `data` repeated to fill length. Panics if [`Self::len`] is not a multiple of 4.

Methodmemset_d8

Synchronously set the contents of `self` to `data` repeated to fill length

Methodmemset_d8_stream

Asynchronously set the contents of `self` to `data` repeated to fill length

Returns a module handle.

Fetches a human-readable name from the device

src/device.rs:26

Creates a new [`Linker`] for the given context handle, compute capability, and linker options.

src/module.rs:53

Creates a new stream for a handle

src/stream.rs:34

(handle: Rc<Handle<'a>>, stream: Stream<'a>)

src/future.rs:61

Allocate a new initialized buffer on the device matching the size and content of `input`.

Creates a new [`Context`] for a given [`Device`]

src/context.rs:14

Allocates a new initialized buffer on the device matching the size and content of `input`. Note that memory is directly copied, so [`T`] must be [`Siz

Methodnew_ffi_stream

Allocates a new uninitialized buffer on the device, then synchronously fills it with `input`. Note that memory is directly copied, so [`T`] must be [`

Methodnew_ffi_stream_buf

Allocates a new uninitialized buffer on the device, then synchronously fills it with `input`. Note that memory is directly copied, so [`T`] must be [`

Methodnew_stream

Allocates a new uninitialized buffer on the device, then asynchronously fills it with `input`. `input` must not be dropped or mutated until `stream.sy

Methodnew_stream_buf

Allocates a new uninitialized buffer on the device, then synchronously fills it with `input`. `input` will be dropped when the stream is synced or dro

(mut self: Pin<&mut Self>, cx: &mut Context<'_>)

src/future.rs:28

Methodset_attribute

Sets information about a function.

Methodset_cache_config

Sets the preferred cache configuration for a device function.

Methodset_limit

Set a CUDA context limit

src/context.rs:40

Methodset_shared_mem_config

Sets the shared memory configuration for a device function.

Gets a subslice of this slice from `[from:to]`

Gets a UUID from the device

src/device.rs:36

Gets the local driver version (not to be confused with device compute capability)

src/version.rs:47

Gets the API version of the [`Context`]. This is not the compute capability of the device and probably not what you are looking for. See [`Device::com

src/context.rs:28

Wait for a 4-byte value in a specific location to compare to `value` by `mode`.

src/stream.rs:66

Wait for a 8-byte value in a specific location to compare to `value` by `mode`.

src/stream.rs:83

Writes a 4-byte value to device memory asynchronously

src/stream.rs:100

Writes a 8-byte value to device memory asynchronously

src/stream.rs:116

← previous101–194 of 194, ranked by callers