Struct CudaStream 

pub struct CudaStream { /* private fields */ }

A wrapper around sys::CUstream that you can schedule work on.

• Create with [CudaContext::new_stream()], [CudaContext::default_stream()], or CudaStream::fork().

Work done on this is asynchronous with respect to the host.

See CUDA C/C++ Streams and Concurrency See 3. Stream synchronization behavior See 6.6. Event Management See Out-of-order execution See Dependence analysis

Implementations

impl CudaStream

pub fn fork(&self) -> Result<Arc<CudaStream>, DriverError>

Create’s a new stream and then makes the new stream wait on self

pub fn cu_stream(&self) -> *mut CUstream_st

The underlying cuda stream object

Safety

Do not destroy this value.

pub fn context(&self) -> &Arc<CudaContext>

The context the stream belongs to.

pub fn synchronize(&self) -> Result<(), DriverError>

Will only block CPU if you call [CudaContext::set_flags()] with sys::CUctx_flags::CU_CTX_SCHED_BLOCKING_SYNC.

See cuda docs

pub fn record_event( &self, flags: Option<CUevent_flags_enum>, ) -> Result<CudaEvent, DriverError>

Creates a new [CudaEvent] and records the current work in the stream to the event.

pub fn wait(&self, event: &CudaEvent) -> Result<(), DriverError>

Waits for the work recorded in [CudaEvent] to be completed.

You can record new work in event after calling this method without affecting this call.

See cuda docs

pub fn join(&self, other: &CudaStream) -> Result<(), DriverError>

Ensures this stream waits for the current workload in other to complete. This is shorthand for self.wait(other.record_event())

impl CudaStream

pub fn null<T>(self: &Arc<CudaStream>) -> Result<CudaSlice<T>, DriverError>

Allocates an empty CudaSlice with 0 length.

pub unsafe fn alloc<T>( self: &Arc<CudaStream>, len: usize, ) -> Result<CudaSlice<T>, DriverError>

where T: DeviceRepr,

Allocates a CudaSlice with len elements of type T.

Safety

This is unsafe because the memory is unset.

pub fn alloc_zeros<T>( self: &Arc<CudaStream>, len: usize, ) -> Result<CudaSlice<T>, DriverError>

where T: DeviceRepr + ValidAsZeroBits,

Allocates a CudaSlice with len elements of type T. All values are zero’d out.

pub fn memset_zeros<T, Dst>( self: &Arc<CudaStream>, dst: &mut Dst, ) -> Result<(), DriverError>

where T: DeviceRepr + ValidAsZeroBits, Dst: DevicePtrMut<T>,

Set’s all the memory in dst to 0. dst can be a CudaSlice or CudaViewMut

pub fn memcpy_stod<T, Src>( self: &Arc<CudaStream>, src: &Src, ) -> Result<CudaSlice<T>, DriverError>

where T: DeviceRepr, Src: HostSlice<T> + ?Sized,

👎Deprecated:

Use clone_htod

Copy a [T]/Vec<T>/[PinnedHostSlice<T>] to a new CudaSlice.

pub fn clone_htod<T, Src>( self: &Arc<CudaStream>, src: &Src, ) -> Result<CudaSlice<T>, DriverError>

where T: DeviceRepr, Src: HostSlice<T> + ?Sized,

Copy a [T]/Vec<T>/[PinnedHostSlice<T>] to a new CudaSlice.

pub fn memcpy_htod<T, Src, Dst>( self: &Arc<CudaStream>, src: &Src, dst: &mut Dst, ) -> Result<(), DriverError>

where T: DeviceRepr, Src: HostSlice<T> + ?Sized, Dst: DevicePtrMut<T>,

Copy a [T]/Vec<T>/[PinnedHostSlice<T>] into an existing CudaSlice/CudaViewMut.

pub fn memcpy_dtov<T, Src>( self: &Arc<CudaStream>, src: &Src, ) -> Result<Vec<T>, DriverError>

where T: DeviceRepr, Src: DevicePtr<T>,

👎Deprecated:

Use clone_dtoh

Copy a CudaSlice/CudaView to a new Vec<T>.

pub fn clone_dtoh<T, Src>( self: &Arc<CudaStream>, src: &Src, ) -> Result<Vec<T>, DriverError>

where T: DeviceRepr, Src: DevicePtr<T>,

Copy a CudaSlice/CudaView to a new Vec<T>.

pub fn memcpy_dtoh<T, Src, Dst>( self: &Arc<CudaStream>, src: &Src, dst: &mut Dst, ) -> Result<(), DriverError>

where T: DeviceRepr, Src: DevicePtr<T>, Dst: HostSlice<T> + ?Sized,

Copy a CudaSlice/CudaView to a existing [T]/Vec<T>/[PinnedHostSlice<T>].

pub fn memcpy_dtod<T, Src, Dst>( self: &Arc<CudaStream>, src: &Src, dst: &mut Dst, ) -> Result<(), DriverError>

where Src: DevicePtr<T>, Dst: DevicePtrMut<T>,

Copy a CudaSlice/CudaView to a existing CudaSlice/CudaViewMut.

pub fn clone_dtod<T, Src>( self: &Arc<CudaStream>, src: &Src, ) -> Result<CudaSlice<T>, DriverError>

where T: DeviceRepr, Src: DevicePtr<T>,

Copy a CudaSlice/CudaView to a new CudaSlice.

impl CudaStream

pub unsafe fn upgrade_device_ptr<T>( self: &Arc<CudaStream>, cu_device_ptr: u64, len: usize, ) -> CudaSlice<T>

Creates a CudaSlice from a sys::CUdeviceptr. Useful in conjunction with CudaSlice::leak().

Safety

• cu_device_ptr must be a valid allocation
• cu_device_ptr must space for len * std::mem::size_of<T>() bytes
• The memory may not be valid for type T, so some sort of memset operation should be called on the memory.

impl CudaStream

pub fn begin_capture( &self, mode: CUstreamCaptureMode_enum, ) -> Result<(), DriverError>

See cuda docs

pub fn end_capture( self: &Arc<CudaStream>, flags: CUgraphInstantiate_flags_enum, ) -> Result<Option<CudaGraph>, DriverError>

See cuda docs

flags is passed to cuGraphInstantiate

pub fn capture_status(&self) -> Result<CUstreamCaptureStatus_enum, DriverError>

See cuda docs

impl CudaStream

pub fn launch_builder<'a>(&'a self, func: &'a CudaFunction) -> LaunchArgs<'a>

Creates a new kernel launch builder that will launch func on stream self.

Add arguments to the builder using [LaunchArgs::arg()], and submit it to the stream using [LaunchArgs::launch()].

Trait Implementations

impl Debug for CudaStream

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Drop for CudaStream

fn drop(&mut self)

Executes the destructor for this type.

impl PartialEq for CudaStream

fn eq(&self, other: &CudaStream) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Eq for CudaStream

impl Send for CudaStream

impl StructuralPartialEq for CudaStream

impl Sync for CudaStream