|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectjcuda.runtime.JCuda
public class JCuda
Java bindings for the NVidia CUDA runtime API.
Most comments are extracted from the CUDA online documentation
Field Summary | |
---|---|
static int |
cudaArraySurfaceLoadStore
Must be set in cudaMallocArray in order to bind surfaces to the CUDA array |
static int |
cudaDeviceBlockingSync
Device flag - Use blocking synchronization |
static int |
cudaDeviceLmemResizeToMax
Device flag - Keep local memory allocation after launch |
static int |
cudaDeviceMapHost
Device flag - Support mapped pinned allocations |
static int |
cudaDeviceMask
Device flags mask |
static int |
cudaDeviceScheduleAuto
Device flag - Automatic scheduling |
static int |
cudaDeviceScheduleSpin
Device flag - Spin default scheduling |
static int |
cudaDeviceScheduleYield
Device flag - Yield default scheduling |
static int |
cudaEventBlockingSync
Event uses blocking synchronization |
static int |
cudaEventDefault
Default event flag |
static int |
cudaHostAllocDefault
Default page-locked allocation flag |
static int |
cudaHostAllocMapped
Map allocation into device space |
static int |
cudaHostAllocPortable
Pinned memory accessible by all CUDA contexts |
static int |
cudaHostAllocWriteCombined
Write-combined memory |
static int |
CUDART_VERSION
CUDA runtime version |
Method Summary | |
---|---|
static int |
cudaBindSurfaceToArray(surfaceReference surfref,
cudaArray array,
cudaChannelFormatDesc desc)
Binds an array to a surface. |
static int |
cudaBindTexture(long[] offset,
textureReference texref,
Pointer devPtr,
cudaChannelFormatDesc desc,
long size)
Binds a memory area to a texture. |
static int |
cudaBindTexture2D(long[] offset,
textureReference texref,
Pointer devPtr,
cudaChannelFormatDesc desc,
long width,
long height,
long pitch)
Binds a 2D memory area to a texture. |
static int |
cudaBindTextureToArray(textureReference texref,
cudaArray array,
cudaChannelFormatDesc desc)
Binds an array to a texture. |
static int |
cudaChooseDevice(int[] device,
cudaDeviceProp prop)
Select compute-device which best matches criteria. |
static int |
cudaConfigureCall(dim3 gridDim,
dim3 blockDim,
long sharedMem,
cudaStream_t stream)
Configure a device-launch. |
static cudaChannelFormatDesc |
cudaCreateChannelDesc(int x,
int y,
int z,
int w,
int cudaChannelFormatKind_f)
Returns a channel descriptor using the specified format. |
static int |
cudaDriverGetVersion(int[] driverVersion)
Returns the CUDA driver version. |
static int |
cudaEventCreate(cudaEvent_t event)
Creates an event object. |
static int |
cudaEventCreateWithFlags(cudaEvent_t event,
int flags)
Creates an event object with the specified flags. |
static int |
cudaEventDestroy(cudaEvent_t event)
Destroys an event object. |
static int |
cudaEventElapsedTime(float[] ms,
cudaEvent_t start,
cudaEvent_t end)
Computes the elapsed time between events. |
static int |
cudaEventQuery(cudaEvent_t event)
Query if an event has been recorded. |
static int |
cudaEventRecord(cudaEvent_t event,
cudaStream_t stream)
Records an event. |
static int |
cudaEventSynchronize(cudaEvent_t event)
Wait for an event to be recorded. |
static int |
cudaFree(Pointer devPtr)
Frees memory on the device. |
static int |
cudaFreeArray(cudaArray array)
Frees an array on the device. |
static int |
cudaFreeHost(Pointer ptr)
Frees page-locked memory. |
static int |
cudaFuncGetAttributes(cudaFuncAttributes attr,
java.lang.String func)
Find out attributes for a given function. |
static int |
cudaGetChannelDesc(cudaChannelFormatDesc desc,
cudaArray array)
Get the channel descriptor of an array. |
static int |
cudaGetDevice(int[] device)
Returns which device is currently being used. |
static int |
cudaGetDeviceCount(int[] count)
Returns the number of compute-capable devices. |
static int |
cudaGetDeviceProperties(cudaDeviceProp prop,
int device)
Returns information about the compute-device. |
static java.lang.String |
cudaGetErrorString(int error)
Returns the message string from an error code. |
static int |
cudaGetLastError()
Returns the last error from a runtime call. |
static int |
cudaGetSurfaceAlignmentOffset(long[] offset,
surfaceReference surfref)
NOTE: This function occurs in the documentation and the header filed, but is NOT present in the CUDA runtime library, Version 3.1, Build 9. |
static int |
cudaGetSurfaceReference(surfaceReference surfref,
java.lang.String symbol)
Get the surface reference associated with a symbol. |
static int |
cudaGetSymbolAddress(Pointer devPtr,
java.lang.String symbol)
Finds the address associated with a CUDA symbol. |
static int |
cudaGetSymbolSize(long[] size,
java.lang.String symbol)
Finds the size of the object associated with a CUDA symbol. |
static int |
cudaGetTextureAlignmentOffset(long[] offset,
textureReference texref)
Get the alignment offset of a texture. |
static int |
cudaGetTextureReference(textureReference texref,
java.lang.String symbol)
Get the texture reference associated with a symbol. |
static int |
cudaGLMapBufferObject(Pointer devPtr,
int bufObj)
Maps a buffer object for access by CUDA. |
static int |
cudaGLMapBufferObjectAsync(Pointer devPtr,
int bufObj,
cudaStream_t stream)
Maps a buffer object for access by CUDA. |
static int |
cudaGLRegisterBufferObject(int bufObj)
Registers a buffer object for access by CUDA. |
static int |
cudaGLSetBufferObjectMapFlags(int bufObj,
int flags)
Set usage flags for mapping an OpenGL buffer. |
static int |
cudaGLSetGLDevice(int device)
Sets the CUDA device for use with OpenGL interoperability. |
static int |
cudaGLUnmapBufferObject(int bufObj)
Unmaps a buffer object for access by CUDA. |
static int |
cudaGLUnmapBufferObjectAsync(int bufObj,
cudaStream_t stream)
Unmaps a buffer object for access by CUDA. |
static int |
cudaGLUnregisterBufferObject(int bufObj)
Unregisters a buffer object for access by CUDA. |
static int |
cudaGraphicsGLRegisterBuffer(cudaGraphicsResource resource,
int buffer,
int Flags)
Registers an OpenGL buffer object. |
static int |
cudaGraphicsGLRegisterImage(cudaGraphicsResource resource,
int image,
int target,
int Flags)
Register an OpenGL texture or renderbuffer object. |
static int |
cudaGraphicsMapResources(int count,
cudaGraphicsResource[] resources,
cudaStream_t stream)
Map graphics resources for access by CUDA. |
static int |
cudaGraphicsResourceGetMappedPointer(Pointer devPtr,
long[] size,
cudaGraphicsResource resource)
Get an device pointer through which to access a mapped graphics resource. |
static int |
cudaGraphicsResourceSetMapFlags(cudaGraphicsResource resource,
int flags)
Set usage flags for mapping a graphics resource. |
static int |
cudaGraphicsSubResourceGetMappedArray(cudaArray arrayPtr,
cudaGraphicsResource resource,
int arrayIndex,
int mipLevel)
Get an array through which to access a subresource of a mapped graphics resource. |
static int |
cudaGraphicsUnmapResources(int count,
cudaGraphicsResource[] resources,
cudaStream_t stream)
Unmap graphics resources. |
static int |
cudaGraphicsUnregisterResource(cudaGraphicsResource resource)
Unregisters a graphics resource for access by CUDA. |
static int |
cudaHostAlloc(Pointer ptr,
long size,
int flags)
Allocates page-locked memory on the host. |
static int |
cudaHostGetDevicePointer(Pointer pDevice,
Pointer pHost,
int flags)
Passes back device pointer of mapped host memory allocated by cudaHostAlloc(). |
static int |
cudaLaunch(java.lang.String symbol)
Launches a device function. |
static int |
cudaMalloc(Pointer devPtr,
long size)
Allocate memory on the device. |
static int |
cudaMalloc3D(cudaPitchedPtr pitchDevPtr,
cudaExtent extent)
Allocates logical 1D, 2D, or 3D memory objects on the device. |
static int |
cudaMalloc3DArray(cudaArray arrayPtr,
cudaChannelFormatDesc desc,
cudaExtent extent)
Calls cudaMalloc3DArray wit the default value '0' as the last parameter |
static int |
cudaMalloc3DArray(cudaArray arrayPtr,
cudaChannelFormatDesc desc,
cudaExtent extent,
int flags)
Allocate an array on the device. |
static int |
cudaMallocArray(cudaArray array,
cudaChannelFormatDesc desc,
long width,
long height)
Calls cudaMallocArray wit the default value '0' as the last parameter |
static int |
cudaMallocArray(cudaArray array,
cudaChannelFormatDesc desc,
long width,
long height,
int flags)
Allocate an array on the device. |
static int |
cudaMallocHost(Pointer ptr,
long size)
Allocates page-locked memory on the host. |
static int |
cudaMallocPitch(Pointer devPtr,
long[] pitch,
long width,
long height)
Allocates pitched memory on the device. |
static int |
cudaMemcpy(Pointer dst,
Pointer src,
long count,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpy2D(Pointer dst,
long dpitch,
Pointer src,
long spitch,
long width,
long height,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpy2DArrayToArray(cudaArray dst,
long wOffsetDst,
long hOffsetDst,
cudaArray src,
long wOffsetSrc,
long hOffsetSrc,
long width,
long height,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpy2DAsync(Pointer dst,
long dpitch,
Pointer src,
long spitch,
long width,
long height,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpy2DFromArray(Pointer dst,
long dpitch,
cudaArray src,
long wOffset,
long hOffset,
long width,
long height,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpy2DFromArrayAsync(Pointer dst,
long dpitch,
cudaArray src,
long wOffset,
long hOffset,
long width,
long height,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpy2DToArray(cudaArray dst,
long wOffset,
long hOffset,
Pointer src,
long spitch,
long width,
long height,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpy2DToArrayAsync(cudaArray dst,
long wOffset,
long hOffset,
Pointer src,
long spitch,
long width,
long height,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpy3D(cudaMemcpy3DParms p)
Copies data between 3D objects. |
static int |
cudaMemcpy3DAsync(cudaMemcpy3DParms p,
cudaStream_t stream)
Copies data between 3D objects. |
static int |
cudaMemcpyArrayToArray(cudaArray dst,
long wOffsetDst,
long hOffsetDst,
cudaArray src,
long wOffsetSrc,
long hOffsetSrc,
long count,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpyAsync(Pointer dst,
Pointer src,
long count,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpyFromArray(Pointer dst,
cudaArray src,
long wOffset,
long hOffset,
long count,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpyFromArrayAsync(Pointer dst,
cudaArray src,
long wOffset,
long hOffset,
long count,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpyFromSymbol(Pointer dst,
java.lang.String symbol,
long count,
long offset,
int cudaMemcpyKind_kind)
Copies data from the given symbol on the device. |
static int |
cudaMemcpyFromSymbolAsync(Pointer dst,
java.lang.String symbol,
long count,
long offset,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data from the given symbol on the device. |
static int |
cudaMemcpyToArray(cudaArray dst,
long wOffset,
long hOffset,
Pointer src,
long count,
int cudaMemcpyKind_kind)
Copies data between host and device. |
static int |
cudaMemcpyToArrayAsync(cudaArray dst,
long wOffset,
long hOffset,
Pointer src,
long count,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data between host and device. |
static int |
cudaMemcpyToSymbol(java.lang.String symbol,
Pointer src,
long count,
long offset,
int cudaMemcpyKind_kind)
Copies data to the given symbol on the device. |
static int |
cudaMemcpyToSymbolAsync(java.lang.String symbol,
Pointer src,
long count,
long offset,
int cudaMemcpyKind_kind,
cudaStream_t stream)
Copies data to the given symbol on the device. |
static int |
cudaMemset(Pointer mem,
int c,
long count)
Initializes or sets device memory to a value. |
static int |
cudaMemset2D(Pointer mem,
long pitch,
int c,
long width,
long height)
Initializes or sets device memory to a value. |
static int |
cudaMemset3D(cudaPitchedPtr pitchDevPtr,
int value,
cudaExtent extent)
Initializes or sets device memory to a value. |
static int |
cudaPeekAtLastError()
Returns the last error from a runtime call. |
static int |
cudaRuntimeGetVersion(int[] runtimeVersion)
Returns the CUDA Runtime version. |
static int |
cudaSetDevice(int device)
Set device to be used for GPU executions. |
static int |
cudaSetDeviceFlags(int flags)
Sets flags to be used for device executions. |
static int |
cudaSetupArgument(Pointer arg,
long size,
long offset)
Configure a device launch. |
static int |
cudaSetValidDevices(int[] device_arr,
int len)
Set a list of devices that can be used for CUDA. |
static int |
cudaStreamCreate(cudaStream_t stream)
Create an asynchronous stream. |
static int |
cudaStreamDestroy(cudaStream_t stream)
Destroys and cleans up an asynchronous stream. |
static int |
cudaStreamQuery(cudaStream_t stream)
Queries an asynchronous stream for completion status. |
static int |
cudaStreamSynchronize(cudaStream_t stream)
Waits for stream tasks to complete. |
static int |
cudaThreadExit()
Exit and clean up from CUDA launches. |
static int |
cudaThreadGetLimit(long[] pValue,
int limit)
Returns resource limits. |
static int |
cudaThreadSetLimit(int limit,
long value)
Set resource limits. |
static int |
cudaThreadSynchronize()
Wait for compute device to finish. |
static int |
cudaUnbindTexture(textureReference texref)
Unbinds a texture. |
static void |
initialize()
Initializes the native library. |
static void |
setEmulation(boolean emulation)
Deprecated. The emulation mode has been deprecated in CUDA 3.0. This function no longer has any effect, and will be removed in the next release. |
static void |
setExceptionsEnabled(boolean enabled)
Enables or disables exceptions. |
static void |
setLogLevel(LogLevel logLevel)
Set the specified log level for the JCuda runtime library. |
Methods inherited from class java.lang.Object |
---|
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final int CUDART_VERSION
public static final int cudaHostAllocDefault
public static final int cudaHostAllocPortable
public static final int cudaHostAllocMapped
public static final int cudaHostAllocWriteCombined
public static final int cudaEventDefault
public static final int cudaEventBlockingSync
public static final int cudaDeviceScheduleAuto
public static final int cudaDeviceScheduleSpin
public static final int cudaDeviceScheduleYield
public static final int cudaDeviceBlockingSync
public static final int cudaDeviceMapHost
public static final int cudaDeviceLmemResizeToMax
public static final int cudaDeviceMask
public static final int cudaArraySurfaceLoadStore
Method Detail |
---|
public static void setEmulation(boolean emulation)
public static void setLogLevel(LogLevel logLevel)
logLevel
- The log level to use.public static void setExceptionsEnabled(boolean enabled)
enabled
- Whether exceptions are enabledpublic static void initialize()
public static int cudaGetDeviceCount(int[] count)
cudaError_t cudaGetDeviceCount | ( | int * | count | ) |
Returns in *count
the number of devices with compute
capability greater or equal to 1.0 that are available for execution.
If there is no such device, cudaGetDeviceCount()
returns
1 and device 0 only supports device emulation mode. Since this device
will be able to emulate all hardware features, this device will report
major and minor compute capability versions of 9999.
cudaGetDevice(int[])
,
cudaSetDevice(int)
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaSetDevice(int device)
cudaError_t cudaSetDevice | ( | int | device | ) |
Records device
as the device on which the active host
thread executes the device code. If the host thread has already
initialized the CUDA runtime by calling non-device management runtime
functions or if there exists a CUDA driver context active on the host
thread, then this call returns cudaErrorSetOnActiveProcess.
cudaGetDeviceCount(int[])
,
cudaGetDevice(int[])
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaSetDeviceFlags(int flags)
cudaError_t cudaSetDeviceFlags | ( | int | flags | ) |
Records flags
as the flags to use when the active host
thread executes device code. If the host thread has already initialized
the CUDA runtime by calling non-device management runtime functions or
if there exists a CUDA driver context active on the host thread, then
this call returns cudaErrorSetOnActiveProcess.
The two LSBs of the flags
parameter can be used to control
how the CPU thread interacts with the OS scheduler when waiting for
results from the device.
flags
parameter is zero, uses a heuristic based on the number of active CUDA
contexts in the process C
and the number of logical
processors in the system P
. If C
>
P
, then CUDA will yield to other OS threads when waiting
for the device, otherwise CUDA will not yield while waiting for results
and actively spin on the processor.
cudaGetDeviceCount(int[])
,
cudaGetDevice(int[])
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
,
cudaSetDevice(int)
,
cudaSetValidDevices(int[], int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaSetValidDevices(int[] device_arr, int len)
cudaError_t cudaSetValidDevices | ( | int * | device_arr, | |
int | len | |||
) |
Sets a list of devices for CUDA execution in priority order using
device_arr
. The parameter len
specifies the
number of elements in the list. CUDA will try devices from the list
sequentially until it finds one that works. If this function is not
called, or if it is called with a len
of 0, then CUDA will
go back to its default behavior of trying devices sequentially from a
default list containing all of the available CUDA devices in the
system. If a specified device ID in the list does not exist, this
function will return cudaErrorInvalidDevice. If len
is
not 0 and device_arr
is NULL or if len
is
greater than the number of devices in the system, then
cudaErrorInvalidValue is returned.
cudaGetDeviceCount(int[])
,
cudaSetDevice(int)
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
,
cudaSetDeviceFlags(int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaGetDevice(int[] device)
cudaError_t cudaGetDevice | ( | int * | device | ) |
Returns in *device
the device on which the active host
thread executes the device code.
cudaGetDeviceCount(int[])
,
cudaSetDevice(int)
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaGetDeviceProperties(cudaDeviceProp prop, int device)
cudaError_t cudaGetDeviceProperties | ( | struct cudaDeviceProp * | prop, | |
int | device | |||
) |
Returns in *prop
the properties of device dev
.
The cudaDeviceProp structure is defined as:
struct cudaDeviceProp { char name[256]; size_t totalGlobalMem; size_t sharedMemPerBlock; int regsPerBlock; int warpSize; size_t memPitch; int maxThreadsPerBlock; int maxThreadsDim[3]; int maxGridSize[3]; size_t totalConstMem; int major; int minor; int clockRate; size_t textureAlignment; int deviceOverlap; int multiProcessorCount; int kernelExecTimeoutEnabled; int integrated; int canMapHostMemory; int computeMode; int concurrentKernels; int ECCEnabled; int pciBusID; int pciDeviceID; }
name
is an ASCII string identifying the
device;
totalGlobalMem
is the total amount of
global memory available on the device in
bytes;
sharedMemPerBlock
is the maximum amount of
shared memory available to a thread block in bytes; this amount is
shared by all thread blocks simultaneously resident on a
multiprocessor;
regsPerBlock
is the maximum number
of 32-bit registers available to a thread block; this number is shared
by all thread blocks simultaneously resident on a
multiprocessor;
warpSize
is the warp size in
threads;
memPitch
is the maximum pitch in bytes
allowed by the memory copy functions that involve memory regions
allocated through cudaMallocPitch();
maxThreadsPerBlock
is the maximum number of threads per block;
maxThreadsDim
[3]
contains the maximum size of each dimension of a
block;
maxGridSize
[3] contains the maximum size
of each dimension of a grid;
clockRate
is the
clock frequency in kilohertz;
totalConstMem
is
the total amount of constant memory available on the device in
bytes;
major
, minor
are the major
and minor revision numbers defining the device's compute
capability;
textureAlignment
is the alignment
requirement; texture base addresses that are aligned to
textureAlignment
bytes do not need an offset applied to
texture fetches;
deviceOverlap
is 1 if the device
can concurrently copy memory between host and device while executing a
kernel, or 0 if not;
multiProcessorCount
is the
number of multiprocessors on the
device;
kernelExecTimeoutEnabled
is 1 if there is
a run time limit for kernels executed on the device, or 0 if
not.
integrated
is 1 if the device is an integrated
(motherboard) GPU and 0 if it is a discrete (card)
component
canMapHostMemory
is 1 if the device can
map host memory into the CUDA address space for use with
cudaHostAlloc()/cudaHostGetDevicePointer(), or 0 if
not;
computeMode
is the compute mode that the
device is currently in. Available modes are as follows:
concurrentKernels
is 1 if the device supports
executing multiple kernels within the same context simultaneously, or
0 if not. It is not guaranteed that multiple kernels will be resident
on the device concurrently so this feature should not be relied upon
for correctness;
ECCEnabled
is 1 if the device
has ECC support turned on, or 0 if not.
pciBusID
is the PCI bus identifier of the device.
pciDeviceID
is the PCI device (sometimes called slot) identifier of the
device.
cudaGetDeviceCount(int[])
,
cudaGetDevice(int[])
,
cudaSetDevice(int)
,
cudaChooseDevice(int[], jcuda.runtime.cudaDeviceProp)
public static int cudaChooseDevice(int[] device, cudaDeviceProp prop)
cudaError_t cudaChooseDevice | ( | int * | device, | |
const struct cudaDeviceProp * | prop | |||
) |
Returns in *device
the device which has properties that
best match *prop
.
cudaGetDeviceCount(int[])
,
cudaGetDevice(int[])
,
cudaSetDevice(int)
,
cudaGetDeviceProperties(jcuda.runtime.cudaDeviceProp, int)
public static int cudaMalloc3D(cudaPitchedPtr pitchDevPtr, cudaExtent extent)
cudaError_t cudaMalloc3D | ( | struct cudaPitchedPtr * | pitchedDevPtr, | |
struct cudaExtent | extent | |||
) |
Allocates at least width
* height
*
depth
bytes of linear memory on the device and returns a
cudaPitchedPtr in which ptr
is a pointer to the allocated
memory. The function may pad the allocation to ensure hardware alignment
requirements are met. The pitch returned in the pitch
field of pitchedDevPtr
is the width in bytes of the
allocation.
The returned cudaPitchedPtr contains additional fields xsize
and ysize
, the logical width and height of the allocation,
which are equivalent to the width
and height
extent
parameters provided by the programmer during
allocation.
For allocations of 2D and 3D objects, it is highly recommended that programmers perform allocations using cudaMalloc3D() or cudaMallocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing memory copies involving 2D or 3D objects (whether linear memory or CUDA arrays).
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaMemcpy3D(jcuda.runtime.cudaMemcpy3DParms)
,
cudaMemset3D(jcuda.runtime.cudaPitchedPtr, int, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMalloc3DArray(cudaArray arrayPtr, cudaChannelFormatDesc desc, cudaExtent extent)
cudaMalloc3DArray(cudaArray, cudaChannelFormatDesc, cudaExtent, int)
public static int cudaMalloc3DArray(cudaArray arrayPtr, cudaChannelFormatDesc desc, cudaExtent extent, int flags)
cudaError_t cudaMalloc3DArray | ( | struct cudaArray ** | arrayPtr, | |
const struct cudaChannelFormatDesc * | desc, | |||
struct cudaExtent | extent, | |||
unsigned int | flags | |||
) |
Allocates a CUDA array according to the cudaChannelFormatDesc structure
desc
and returns a handle to the new CUDA array in
*arrayPtr
.
The cudaChannelFormatDesc is defined as:
struct cudaChannelFormatDesc { int x, y, z, w; enum cudaChannelFormatKind f; };
cudaMalloc3DArray() is able to allocate 1D, 2D, or 3D arrays.
flags
provides for future releases. For now, it must be
set to 0.
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMemset3D(cudaPitchedPtr pitchDevPtr, int value, cudaExtent extent)
cudaError_t cudaMemset3D | ( | struct cudaPitchedPtr | pitchedDevPtr, | |
int | value, | |||
struct cudaExtent | extent | |||
) |
Initializes each element of a 3D array to the specified value
value
. The object to initialize is defined by
pitchedDevPtr
. The pitch
field of
pitchedDevPtr
is the width in memory in bytes of the 3D
array pointed to by pitchedDevPtr
, including any padding
added to the end of each row. The xsize
field specifies
the logical width of each row in bytes, while the ysize
field specifies the height of each 2D slice in rows.
The extents of the initialized region are specified as a
width
in bytes, a height
in rows, and a
depth
in slices.
Extents with width
greater than or equal to the
xsize
of pitchedDevPtr
may perform
significantly faster than extents narrower than the xsize
.
Secondarily, extents with height
equal to the
ysize
of pitchedDevPtr
will perform faster
than when the height
is shorter than the
ysize
.
This function performs fastest when the pitchedDevPtr
has
been allocated by cudaMalloc3D().
cudaMemset(jcuda.Pointer, int, long)
,
cudaMemset2D(jcuda.Pointer, long, int, long, long)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
public static int cudaMemcpy3D(cudaMemcpy3DParms p)
cudaError_t cudaMemcpy3D | ( | const struct cudaMemcpy3DParms * | p | ) |
struct cudaExtent { size_t width; size_t height; size_t depth; }; struct cudaExtent make_cudaExtent(size_t w, size_t h, size_t d); struct cudaPos { size_t x; size_t y; size_t z; }; struct cudaPos make_cudaPos(size_t x, size_t y, size_t z); struct cudaMemcpy3DParms { struct cudaArray *srcArray; struct cudaPos srcPos; struct cudaPitchedPtr srcPtr; struct cudaArray *dstArray; struct cudaPos dstPos; struct cudaPitchedPtr dstPtr; struct cudaExtent extent; enum cudaMemcpyKind kind; };
cudaMemcpy3D() copies data betwen two 3D objects. The source and destination objects may be in either host memory, device memory, or a CUDA array. The source, destination, extent, and kind of copy performed is specified by the cudaMemcpy3DParms struct which should be initialized to zero before use:
cudaMemcpy3DParms myParms = {0};
The struct passed to cudaMemcpy3D() must specify one of
srcArray
or srcPtr
and one of
dstArray
or dstPtr
. Passing more than one
non-zero source or destination will cause cudaMemcpy3D() to return an
error.
The srcPos
and dstPos
fields are optional
offsets into the source and destination objects and are defined in
units of each object's elements. The element for a host or device
pointer is assumed to be unsigned char. For CUDA arrays,
positions must be in the range [0, 2048) for any dimension.
The extent
field defines the dimensions of the transferred
area in elements. If a CUDA array is participating in the copy, the
extent is defined in terms of that array's elements. If no CUDA array
is participating in the copy then the extents are defined in elements
of unsigned char.
The kind
field defines the direction of the copy. It must
be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice.
If the source and destination are both arrays, cudaMemcpy3D() will return an error if they do not have the same element size.
The source and destination object may not overlap. If overlapping source and destination objects are specified, undefined behavior will result.
cudaMemcpy3D() returns an error if the pitch of srcPtr
or
dstPtr
is greater than the maximum allowed. The pitch of
a cudaPitchedPtr allocated with cudaMalloc3D() will always be
valid.
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaMemset3D(jcuda.runtime.cudaPitchedPtr, int, jcuda.runtime.cudaExtent)
,
cudaMemcpy3DAsync(jcuda.runtime.cudaMemcpy3DParms, jcuda.runtime.cudaStream_t)
,
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy3DAsync(cudaMemcpy3DParms p, cudaStream_t stream)
cudaError_t cudaMemcpy3DAsync | ( | const struct cudaMemcpy3DParms * | p, | |
cudaStream_t | stream | |||
) |
struct cudaExtent { size_t width; size_t height; size_t depth; }; struct cudaExtent make_cudaExtent(size_t w, size_t h, size_t d); struct cudaPos { size_t x; size_t y; size_t z; }; struct cudaPos make_cudaPos(size_t x, size_t y, size_t z); struct cudaMemcpy3DParms { struct cudaArray *srcArray; struct cudaPos srcPos; struct cudaPitchedPtr srcPtr; struct cudaArray *dstArray; struct cudaPos dstPos; struct cudaPitchedPtr dstPtr; struct cudaExtent extent; enum cudaMemcpyKind kind; };
cudaMemcpy3DAsync() copies data betwen two 3D objects. The source and destination objects may be in either host memory, device memory, or a CUDA array. The source, destination, extent, and kind of copy performed is specified by the cudaMemcpy3DParms struct which should be initialized to zero before use:
cudaMemcpy3DParms myParms = {0};
The struct passed to cudaMemcpy3DAsync() must specify one of
srcArray
or srcPtr
and one of
dstArray
or dstPtr
. Passing more than one
non-zero source or destination will cause cudaMemcpy3DAsync() to return
an error.
The srcPos
and dstPos
fields are optional
offsets into the source and destination objects and are defined in
units of each object's elements. The element for a host or device
pointer is assumed to be unsigned char. For CUDA arrays,
positions must be in the range [0, 2048) for any dimension.
The extent
field defines the dimensions of the transferred
area in elements. If a CUDA array is participating in the copy, the
extent is defined in terms of that array's elements. If no CUDA array
is participating in the copy then the extents are defined in elements
of unsigned char.
The kind
field defines the direction of the copy. It must
be one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice.
If the source and destination are both arrays, cudaMemcpy3DAsync() will return an error if they do not have the same element size.
The source and destination object may not overlap. If overlapping source and destination objects are specified, undefined behavior will result.
cudaMemcpy3DAsync() returns an error if the pitch of srcPtr
or dstPtr
is greater than the maximum allowed. The pitch
of a cudaPitchedPtr allocated with cudaMalloc3D() will always be
valid.
cudaMemcpy3DAsync() is asynchronous with respect to the host, so the
call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaMemset3D(jcuda.runtime.cudaPitchedPtr, int, jcuda.runtime.cudaExtent)
,
cudaMemcpy3D(jcuda.runtime.cudaMemcpy3DParms)
,
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaHostAlloc(Pointer ptr, long size, int flags)
cudaError_t cudaHostAlloc | ( | void ** | ptr, | |
size_t | size, | |||
unsigned int | flags | |||
) |
Allocates size
bytes of host memory that is page-locked
and accessible to the device. The driver tracks the virtual memory
ranges allocated with this function and automatically accelerates calls
to functions such as cudaMemcpy(). Since the memory can be accessed
directly by the device, it can be read or written with much higher
bandwidth than pageable memory obtained with functions such as malloc().
Allocating excessive amounts of pinned memory may degrade system
performance, since it reduces the amount of memory available to the
system for paging. As a result, this function is best used sparingly
to allocate staging areas for data exchange between host and
device.
The flags
parameter enables different options to be
specified that affect the allocation, as follows.
All of these flags are orthogonal to one another: a developer may allocate memory that is portable, mapped and/or write-combined with no restrictions.
cudaSetDeviceFlags() must have been called with the cudaDeviceMapHost flag in order for the cudaHostAllocMapped flag to have any effect.
The cudaHostAllocMapped flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to cudaHostGetDevicePointer() because the memory may be mapped into other CUDA contexts via the cudaHostAllocPortable flag.
Memory allocated by this function must be freed with cudaFreeHost().
cudaSetDeviceFlags(int)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
public static int cudaHostGetDevicePointer(Pointer pDevice, Pointer pHost, int flags)
cudaError_t cudaHostGetDevicePointer | ( | void ** | pDevice, | |
void * | pHost, | |||
unsigned int | flags | |||
) |
Passes back the device pointer corresponding to the mapped, pinned host buffer allocated by cudaHostAlloc().
cudaHostGetDevicePointer() will fail if the cudaDeviceMapHost flag was not specified before deferred context creation occurred, or if called on a device that does not support mapped, pinned memory.
flags
provides for future releases. For now, it must be
set to 0.
cudaSetDeviceFlags(int)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMalloc(Pointer devPtr, long size)
cudaError_t cudaMalloc | ( | void ** | devPtr, | |
size_t | size | |||
) |
Allocates size
bytes of linear memory on the device and
returns in *devPtr
a pointer to the allocated memory. The
allocated memory is suitably aligned for any kind of variable. The
memory is not cleared. cudaMalloc() returns cudaErrorMemoryAllocation
in case of failure.
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMallocHost(Pointer ptr, long size)
cudaError_t cudaMallocHost | ( | void ** | ptr, | |
size_t | size | |||
) |
Allocates size
bytes of host memory that is page-locked
and accessible to the device. The driver tracks the virtual memory
ranges allocated with this function and automatically accelerates calls
to functions such as cudaMemcpy*(). Since the memory can be accessed
directly by the device, it can be read or written with much higher
bandwidth than pageable memory obtained with functions such as malloc().
Allocating excessive amounts of memory with cudaMallocHost() may
degrade system performance, since it reduces the amount of memory
available to the system for paging. As a result, this function is best
used sparingly to allocate staging areas for data exchange between host
and device.
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaHostAlloc(jcuda.Pointer, long, int)
,
cudaFree(jcuda.Pointer)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaFreeHost(jcuda.Pointer)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMallocPitch(Pointer devPtr, long[] pitch, long width, long height)
cudaError_t cudaMallocPitch | ( | void ** | devPtr, | |
size_t * | pitch, | |||
size_t | width, | |||
size_t | height | |||
) |
Allocates at least widthInBytes
* height
bytes of linear memory on the device and returns in *devPtr
a pointer to the allocated memory. The function may pad the allocation
to ensure that corresponding pointers in any given row will continue
to meet the alignment requirements for coalescing as the address is
updated from row to row. The pitch returned in *pitch
by
cudaMallocPitch() is the width in bytes of the allocation. The intended
usage of pitch
is as a separate parameter of the
allocation, used to compute addresses within the 2D array. Given the
row and column of an array element of type T
, the address
is computed as:
T* pElement = (T*)((char*)BaseAddress + Row * pitch) + Column;
For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations using cudaMallocPitch(). Due to pitch alignment restrictions in the hardware, this is especially true if the application will be performing 2D memory copies between different regions of device memory (whether linear memory or CUDA arrays).
cudaMalloc(jcuda.Pointer, long)
,
cudaFree(jcuda.Pointer)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMallocArray(cudaArray array, cudaChannelFormatDesc desc, long width, long height)
cudaMallocArray(cudaArray, cudaChannelFormatDesc, long, long, int)
public static int cudaMallocArray(cudaArray array, cudaChannelFormatDesc desc, long width, long height, int flags)
cudaError_t cudaMallocArray | ( | struct cudaArray ** | arrayPtr, | |
const struct cudaChannelFormatDesc * | desc, | |||
size_t | width, | |||
size_t | height, | |||
unsigned int | flags | |||
) |
Allocates a CUDA array according to the cudaChannelFormatDesc structure
desc
and returns a handle to the new CUDA array in
*array
.
The cudaChannelFormatDesc is defined as:
struct cudaChannelFormatDesc { int x, y, z, w; enum cudaChannelFormatKind f; };
flags
provides for future releases. For now, it must be
set to 0.
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaFree(Pointer devPtr)
cudaError_t cudaFree | ( | void * | devPtr | ) |
Frees the memory space pointed to by devPtr
, which must
have been returned by a previous call to cudaMalloc() or
cudaMallocPitch(). Otherwise, or if cudaFree(devPtr
) has
already been called before, an error is returned. If devPtr
is 0, no operation is performed. cudaFree() returns
cudaErrorInvalidDevicePointer in case of failure.
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaFreeHost(Pointer ptr)
cudaError_t cudaFreeHost | ( | void * | ptr | ) |
Frees the memory space pointed to by hostPtr
, which must
have been returned by a previous call to cudaMallocHost() or
cudaHostAlloc().
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaFreeArray(jcuda.runtime.cudaArray)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaMalloc3D(jcuda.runtime.cudaPitchedPtr, jcuda.runtime.cudaExtent)
,
cudaMalloc3DArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaExtent)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaFreeArray(cudaArray array)
cudaError_t cudaFreeArray | ( | struct cudaArray * | array | ) |
Frees the CUDA array array
, which must have been * returned
by a previous call to cudaMallocArray(). If cudaFreeArray(array
)
has already been called before, cudaErrorInvalidValue is returned. If
devPtr
is 0, no operation is performed.
cudaMalloc(jcuda.Pointer, long)
,
cudaMallocPitch(jcuda.Pointer, long[], long, long)
,
cudaFree(jcuda.Pointer)
,
cudaMallocArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc, long, long)
,
cudaMallocHost(jcuda.Pointer, long)
,
cudaFreeHost(jcuda.Pointer)
,
cudaHostAlloc(jcuda.Pointer, long, int)
public static int cudaMemcpy(Pointer dst, Pointer src, long count, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpy | ( | void * | dst, | |
const void * | src, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the memory area pointed to by dst
,
where kind
is one of cudaMemcpyHostToHost,
cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice,
and specifies the direction of the copy. The memory areas may not
overlap. Calling cudaMemcpy() with dst
and src
pointers that do not match the direction of the copy results in an
undefined behavior.
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyToArray(cudaArray dst, long wOffset, long hOffset, Pointer src, long count, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpyToArray | ( | struct cudaArray * | dst, | |
size_t | wOffset, | |||
size_t | hOffset, | |||
const void * | src, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the CUDA array dst
starting at the
upper left corner (wOffset
, hOffset
), where
kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyFromArray(Pointer dst, cudaArray src, long wOffset, long hOffset, long count, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpyFromArray | ( | void * | dst, | |
const struct cudaArray * | src, | |||
size_t | wOffset, | |||
size_t | hOffset, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the CUDA array src
starting at the upper left corner (wOffset
, hOffset) to
the memory area pointed to by dst
, where kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyArrayToArray(cudaArray dst, long wOffsetDst, long hOffsetDst, cudaArray src, long wOffsetSrc, long hOffsetSrc, long count, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpyArrayToArray | ( | struct cudaArray * | dst, | |
size_t | wOffsetDst, | |||
size_t | hOffsetDst, | |||
const struct cudaArray * | src, | |||
size_t | wOffsetSrc, | |||
size_t | hOffsetSrc, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the CUDA array src
starting at the upper left corner (wOffsetSrc
,
hOffsetSrc
) to the CUDA array dst
starting
at the upper left corner (wOffsetDst
, hOffsetDst
)
where kind
is one of cudaMemcpyHostToHost,
cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice,
and specifies the direction of the copy.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2D(Pointer dst, long dpitch, Pointer src, long spitch, long width, long height, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpy2D | ( | void * | dst, | |
size_t | dpitch, | |||
const void * | src, | |||
size_t | spitch, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the memory area pointed to by src
to the memory
area pointed to by dst
, where kind
is one of
cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost,
or cudaMemcpyDeviceToDevice, and specifies the direction of the copy.
dpitch
and spitch
are the widths in memory
in bytes of the 2D arrays pointed to by dst
and
src
, including any padding added to the end of each row.
The memory areas may not overlap. Calling cudaMemcpy2D() with
dst
and src
pointers that do not match the
direction of the copy results in an undefined behavior. cudaMemcpy2D()
returns an error if dpitch
or spitch
is
greater than the maximum allowed.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DToArray(cudaArray dst, long wOffset, long hOffset, Pointer src, long spitch, long width, long height, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpy2DToArray | ( | struct cudaArray * | dst, | |
size_t | wOffset, | |||
size_t | hOffset, | |||
const void * | src, | |||
size_t | spitch, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the memory area pointed to by src
to the CUDA
array dst
starting at the upper left corner
(wOffset
, hOffset
) where kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy. spitch
is the width in memory in
bytes of the 2D array pointed to by src
, including any
padding added to the end of each row. cudaMemcpy2DToArray() returns an
error if spitch
is greater than the maximum allowed.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DFromArray(Pointer dst, long dpitch, cudaArray src, long wOffset, long hOffset, long width, long height, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpy2DFromArray | ( | void * | dst, | |
size_t | dpitch, | |||
const struct cudaArray * | src, | |||
size_t | wOffset, | |||
size_t | hOffset, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the CUDA array srcArray
starting at the upper
left corner (wOffset
, hOffset
) to the memory
area pointed to by dst
, where kind
is one of
cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost,
or cudaMemcpyDeviceToDevice, and specifies the direction of the copy.
dpitch
is the width in memory in bytes of the 2D array
pointed to by dst
, including any padding added to the end
of each row. cudaMemcpy2DFromArray() returns an error if
dpitch
is greater than the maximum allowed.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DArrayToArray(cudaArray dst, long wOffsetDst, long hOffsetDst, cudaArray src, long wOffsetSrc, long hOffsetSrc, long width, long height, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpy2DArrayToArray | ( | struct cudaArray * | dst, | |
size_t | wOffsetDst, | |||
size_t | hOffsetDst, | |||
const struct cudaArray * | src, | |||
size_t | wOffsetSrc, | |||
size_t | hOffsetSrc, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the CUDA array srcArray
starting at the upper
left corner (wOffsetSrc
, hOffsetSrc
) to the
CUDA array dst
starting at the upper left corner
(wOffsetDst
, hOffsetDst
), where
kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyToSymbol(java.lang.String symbol, Pointer src, long count, long offset, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpyToSymbol | ( | const char * | symbol, | |
const void * | src, | |||
size_t | count, | |||
size_t | offset, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the memory area pointed to by offset
bytes from the start of symbol symbol
. The memory areas
may not overlap. symbol
can either be a variable that
resides in global or constant memory space, or it can be a character
string, naming a variable that resides in global or constant memory
space. kind
can be either cudaMemcpyHostToDevice or
cudaMemcpyDeviceToDevice.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyFromSymbol(Pointer dst, java.lang.String symbol, long count, long offset, int cudaMemcpyKind_kind)
cudaError_t cudaMemcpyFromSymbol | ( | void * | dst, | |
const char * | symbol, | |||
size_t | count, | |||
size_t | offset, | |||
enum cudaMemcpyKind | kind | |||
) |
Copies count
bytes from the memory area pointed to by
offset
bytes from the start of symbol symbol
to the memory area pointed to by dst
. The memory areas
may not overlap. symbol
can either be a variable that
resides in global or constant memory space, or it can be a character
string, naming a variable that resides in global or constant memory
space. kind
can be either cudaMemcpyDeviceToHost or
cudaMemcpyDeviceToDevice.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyAsync(Pointer dst, Pointer src, long count, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpyAsync | ( | void * | dst, | |
const void * | src, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the memory area pointed to by dst
,
where kind
is one of cudaMemcpyHostToHost,
cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice,
and specifies the direction of the copy. The memory areas may not
overlap. Calling cudaMemcpyAsync() with dst
and
src
pointers that do not match the direction of the copy
results in an undefined behavior.
cudaMemcpyAsync() is asynchronous with respect to the host, so the call
may return before the copy is complete. It only works on page-locked
host memory and returns an error if a pointer to pageable memory is
passed as input. The copy can optionally be associated to a stream by
passing a non-zero stream
argument. If kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost and the
stream
is non-zero, the copy may overlap with operations
in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyToArrayAsync(cudaArray dst, long wOffset, long hOffset, Pointer src, long count, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpyToArrayAsync | ( | struct cudaArray * | dst, | |
size_t | wOffset, | |||
size_t | hOffset, | |||
const void * | src, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the CUDA array dst
starting at the
upper left corner (wOffset
, hOffset
), where
kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy.
cudaMemcpyToArrayAsync() is asynchronous with respect to the host, so
the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyFromArrayAsync(Pointer dst, cudaArray src, long wOffset, long hOffset, long count, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpyFromArrayAsync | ( | void * | dst, | |
const struct cudaArray * | src, | |||
size_t | wOffset, | |||
size_t | hOffset, | |||
size_t | count, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies count
bytes from the CUDA array src
starting at the upper left corner (wOffset
, hOffset) to
the memory area pointed to by dst
, where kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy.
cudaMemcpyFromArrayAsync() is asynchronous with respect to the host,
so the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DAsync(Pointer dst, long dpitch, Pointer src, long spitch, long width, long height, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpy2DAsync | ( | void * | dst, | |
size_t | dpitch, | |||
const void * | src, | |||
size_t | spitch, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the memory area pointed to by src
to the memory
area pointed to by dst
, where kind
is one of
cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost,
or cudaMemcpyDeviceToDevice, and specifies the direction of the copy.
dpitch
and spitch
are the widths in memory
in bytes of the 2D arrays pointed to by dst
and
src
, including any padding added to the end of each row.
The memory areas may not overlap. Calling cudaMemcpy2DAsync() with
dst
and src
pointers that do not match the
direction of the copy results in an undefined behavior.
cudaMemcpy2DAsync() returns an error if dpitch
or
spitch
is greater than the maximum allowed.
cudaMemcpy2DAsync() is asynchronous with respect to the host, so the
call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DToArrayAsync(cudaArray dst, long wOffset, long hOffset, Pointer src, long spitch, long width, long height, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpy2DToArrayAsync | ( | struct cudaArray * | dst, | |
size_t | wOffset, | |||
size_t | hOffset, | |||
const void * | src, | |||
size_t | spitch, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the memory area pointed to by src
to the CUDA
array dst
starting at the upper left corner
(wOffset
, hOffset
) where kind
is one of cudaMemcpyHostToHost, cudaMemcpyHostToDevice,
cudaMemcpyDeviceToHost, or cudaMemcpyDeviceToDevice, and specifies the
direction of the copy. spitch
is the width in memory in
bytes of the 2D array pointed to by src
, including any
padding added to the end of each row. cudaMemcpy2DToArrayAsync()
returns an error if spitch
is greater than the maximum
allowed.
cudaMemcpy2DToArrayAsync() is asynchronous with respect to the host,
so the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpy2DFromArrayAsync(Pointer dst, long dpitch, cudaArray src, long wOffset, long hOffset, long width, long height, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpy2DFromArrayAsync | ( | void * | dst, | |
size_t | dpitch, | |||
const struct cudaArray * | src, | |||
size_t | wOffset, | |||
size_t | hOffset, | |||
size_t | width, | |||
size_t | height, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies a matrix (height
rows of width
bytes
each) from the CUDA array srcArray
starting at the upper
left corner (wOffset
, hOffset
) to the memory
area pointed to by dst
, where kind
is one of
cudaMemcpyHostToHost, cudaMemcpyHostToDevice, cudaMemcpyDeviceToHost,
or cudaMemcpyDeviceToDevice, and specifies the direction of the copy.
dpitch
is the width in memory in bytes of the 2D array
pointed to by dst
, including any padding added to the end
of each row. cudaMemcpy2DFromArrayAsync() returns an error if
dpitch
is greater than the maximum allowed.
cudaMemcpy2DFromArrayAsync() is asynchronous with respect to the host,
so the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice or cudaMemcpyDeviceToHost
and stream
is non-zero, the copy may overlap with
operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyToSymbolAsync(java.lang.String symbol, Pointer src, long count, long offset, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpyToSymbolAsync | ( | const char * | symbol, | |
const void * | src, | |||
size_t | count, | |||
size_t | offset, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies count
bytes from the memory area pointed to by
src
to the memory area pointed to by offset
bytes from the start of symbol symbol
. The memory areas
may not overlap. symbol
can either be a variable that
resides in global or constant memory space, or it can be a character
string, naming a variable that resides in global or constant memory
space. kind
can be either cudaMemcpyHostToDevice or
cudaMemcpyDeviceToDevice.
cudaMemcpyToSymbolAsync() is asynchronous with respect to the host, so
the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyHostToDevice and stream
is
non-zero, the copy may overlap with operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromSymbolAsync(jcuda.Pointer, java.lang.String, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemcpyFromSymbolAsync(Pointer dst, java.lang.String symbol, long count, long offset, int cudaMemcpyKind_kind, cudaStream_t stream)
cudaError_t cudaMemcpyFromSymbolAsync | ( | void * | dst, | |
const char * | symbol, | |||
size_t | count, | |||
size_t | offset, | |||
enum cudaMemcpyKind | kind, | |||
cudaStream_t | stream | |||
) |
Copies count
bytes from the memory area pointed to by
offset
bytes from the start of symbol symbol
to the memory area pointed to by dst
. The memory areas
may not overlap. symbol
can either be a variable that
resides in global or constant memory space, or it can be a character
string, naming a variable that resides in global or constant memory
space. kind
can be either cudaMemcpyDeviceToHost or
cudaMemcpyDeviceToDevice.
cudaMemcpyFromSymbolAsync() is asynchronous with respect to the host,
so the call may return before the copy is complete. It only works on
page-locked host memory and returns an error if a pointer to pageable
memory is passed as input. The copy can optionally be associated to a
stream by passing a non-zero stream
argument. If
kind
is cudaMemcpyDeviceToHost and stream
is
non-zero, the copy may overlap with operations in other streams.
cudaMemcpy(jcuda.Pointer, jcuda.Pointer, long, int)
,
cudaMemcpy2D(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int)
,
cudaMemcpy2DToArray(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int)
,
cudaMemcpyFromArray(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DFromArray(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, int)
,
cudaMemcpy2DArrayToArray(jcuda.runtime.cudaArray, long, long, jcuda.runtime.cudaArray, long, long, long, long, int)
,
cudaMemcpyToSymbol(java.lang.String, jcuda.Pointer, long, long, int)
,
cudaMemcpyFromSymbol(jcuda.Pointer, java.lang.String, long, long, int)
,
cudaMemcpyAsync(jcuda.Pointer, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DAsync(jcuda.Pointer, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DToArrayAsync(jcuda.runtime.cudaArray, long, long, jcuda.Pointer, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyFromArrayAsync(jcuda.Pointer, jcuda.runtime.cudaArray, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpy2DFromArrayAsync(jcuda.Pointer, long, jcuda.runtime.cudaArray, long, long, long, long, int, jcuda.runtime.cudaStream_t)
,
cudaMemcpyToSymbolAsync(java.lang.String, jcuda.Pointer, long, long, int, jcuda.runtime.cudaStream_t)
public static int cudaMemset(Pointer mem, int c, long count)
cudaError_t cudaMemset | ( | void * | devPtr, | |
int | value, | |||
size_t | count | |||
) |
Fills the first count
bytes of the memory area pointed to
by devPtr
with the constant byte value
value
.
cudaMemset2D(jcuda.Pointer, long, int, long, long)
,
cudaMemset3D(jcuda.runtime.cudaPitchedPtr, int, jcuda.runtime.cudaExtent)
public static int cudaMemset2D(Pointer mem, long pitch, int c, long width, long height)
cudaError_t cudaMemset2D | ( | void * | devPtr, | |
size_t | pitch, | |||
int | value, | |||
size_t | width, | |||
size_t | height | |||
) |
Sets to the specified value value
a matrix
(height
rows of width
bytes each) pointed to
by dstPtr
. pitch
is the width in bytes of
the 2D array pointed to by dstPtr
, including any padding
added to the end of each row. This function performs fastest when the
pitch is one that has been passed back by cudaMallocPitch().
cudaMemset(jcuda.Pointer, int, long)
,
cudaMemset3D(jcuda.runtime.cudaPitchedPtr, int, jcuda.runtime.cudaExtent)
public static int cudaGetChannelDesc(cudaChannelFormatDesc desc, cudaArray array)
cudaError_t cudaGetChannelDesc | ( | struct cudaChannelFormatDesc * | desc, | |
const struct cudaArray * | array | |||
) |
Returns in *desc
the channel descriptor of the CUDA array
array
.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static cudaChannelFormatDesc cudaCreateChannelDesc(int x, int y, int z, int w, int cudaChannelFormatKind_f)
cudaChannelFormatDesc cudaCreateChannelDesc | ( | void | ) |
Returns a channel descriptor with format f
and number of
bits of each component x
, y
, z
,
and w
. The cudaChannelFormatDesc is defined as:
struct cudaChannelFormatDesc { int x, y, z, w; enum cudaChannelFormatKind f; };
where cudaChannelFormatKind is one of cudaChannelFormatKindSigned, cudaChannelFormatKindUnsigned, or cudaChannelFormatKindFloat.
f
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaGetLastError()
cudaError_t cudaGetLastError | ( | void | ) |
Returns the last error that has been produced by any of the runtime calls in the same host thread and resets it to cudaSuccess.
cudaPeekAtLastError()
,
cudaGetErrorString(int)
public static int cudaPeekAtLastError()
cudaError_t cudaPeekAtLastError | ( | void | ) |
Returns the last error that has been produced by any of the runtime calls in the same host thread. Note that this call does not reset the error to cudaSuccess like cudaGetLastError().
cudaGetLastError()
,
cudaGetErrorString(int)
public static java.lang.String cudaGetErrorString(int error)
const char* cudaGetErrorString | ( | cudaError_t | error | ) |
Returns the message string from an error code.
char*
pointer to a NULL-terminated stringcudaGetLastError()
,
cudaPeekAtLastError()
public static int cudaStreamCreate(cudaStream_t stream)
cudaError_t cudaStreamCreate | ( | cudaStream_t * | pStream | ) |
Creates a new asynchronous stream.
cudaStreamQuery(jcuda.runtime.cudaStream_t)
,
cudaStreamSynchronize(jcuda.runtime.cudaStream_t)
,
cudaStreamDestroy(jcuda.runtime.cudaStream_t)
public static int cudaStreamDestroy(cudaStream_t stream)
cudaError_t cudaStreamDestroy | ( | cudaStream_t | stream | ) |
Destroys and cleans up the asynchronous stream specified by
stream
.
cudaStreamCreate(jcuda.runtime.cudaStream_t)
,
cudaStreamQuery(jcuda.runtime.cudaStream_t)
,
cudaStreamSynchronize(jcuda.runtime.cudaStream_t)
public static int cudaStreamSynchronize(cudaStream_t stream)
cudaError_t cudaStreamSynchronize | ( | cudaStream_t | stream | ) |
Blocks until stream
has completed all operations. If the
cudaDeviceBlockingSync flag was set for this device, the host thread
will block until the stream is finished with all of its tasks.
cudaStreamCreate(jcuda.runtime.cudaStream_t)
,
cudaStreamQuery(jcuda.runtime.cudaStream_t)
,
cudaStreamDestroy(jcuda.runtime.cudaStream_t)
public static int cudaStreamQuery(cudaStream_t stream)
cudaError_t cudaStreamQuery | ( | cudaStream_t | stream | ) |
Returns cudaSuccess if all operations in stream
have
completed, or cudaErrorNotReady if not.
cudaStreamCreate(jcuda.runtime.cudaStream_t)
,
cudaStreamSynchronize(jcuda.runtime.cudaStream_t)
,
cudaStreamDestroy(jcuda.runtime.cudaStream_t)
public static int cudaEventCreate(cudaEvent_t event)
cudaError_t cudaEventCreate | ( | cudaEvent_t * | event | ) |
Creates an event object using cudaEventDefault.
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventCreateWithFlags(cudaEvent_t event, int flags)
cudaError_t cudaEventCreateWithFlags | ( | cudaEvent_t * | event, | |
int | flags | |||
) |
Creates an event object with the specified flags. Valid flags include:
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventRecord(cudaEvent_t event, cudaStream_t stream)
cudaError_t cudaEventRecord | ( | cudaEvent_t | event, | |
cudaStream_t | stream | |||
) |
Records an event. If stream
is non-zero, the event is
recorded after all preceding operations in the stream have been
completed; otherwise, it is recorded after all preceding operations in
the CUDA context have been completed. Since this operation is
asynchronous, cudaEventQuery() and/or cudaEventSynchronize() must be
used to determine when the event has actually been recorded.
If cudaEventRecord() has previously been called and the event has not been recorded yet, this function returns cudaErrorInvalidValue.
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventQuery(cudaEvent_t event)
cudaError_t cudaEventQuery | ( | cudaEvent_t | event | ) |
Returns cudaSuccess if the event has actually been recorded, or cudaErrorNotReady if not. If cudaEventRecord() has not been called on this event, the function returns cudaErrorInvalidValue.
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventSynchronize(cudaEvent_t event)
cudaError_t cudaEventSynchronize | ( | cudaEvent_t | event | ) |
Blocks until the event has actually been recorded. If cudaEventRecord() has not been called on this event, the function returns cudaErrorInvalidValue. Waiting for an event that was created with the cudaEventBlockingSync flag will cause the calling host thread to block until the event has actually been recorded.
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventDestroy(cudaEvent_t event)
cudaError_t cudaEventDestroy | ( | cudaEvent_t | event | ) |
Destroys the specified event
object.
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
,
cudaEventElapsedTime(float[], jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaEvent_t)
public static int cudaEventElapsedTime(float[] ms, cudaEvent_t start, cudaEvent_t end)
cudaError_t cudaEventElapsedTime | ( | float * | ms, | |
cudaEvent_t | start, | |||
cudaEvent_t | end | |||
) |
Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds). If either event has not been recorded yet, this function returns cudaErrorInvalidValue.
When stream is non-zero for either event (even if it uses the same stream ID), the result may be greater than expected. This is because the cudaEventRecord() operation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.
cudaEventCreate(jcuda.runtime.cudaEvent_t)
,
cudaEventCreateWithFlags(jcuda.runtime.cudaEvent_t, int)
,
cudaEventQuery(jcuda.runtime.cudaEvent_t)
,
cudaEventSynchronize(jcuda.runtime.cudaEvent_t)
,
cudaEventDestroy(jcuda.runtime.cudaEvent_t)
,
cudaEventRecord(jcuda.runtime.cudaEvent_t, jcuda.runtime.cudaStream_t)
public static int cudaThreadExit()
cudaError_t cudaThreadExit | ( | void | ) |
Explicitly cleans up all runtime-related resources associated with the calling host thread. Any subsequent API call reinitializes the runtime. cudaThreadExit() is implicitly called on host thread exit.
cudaThreadSynchronize()
public static int cudaThreadSynchronize()
cudaError_t cudaThreadSynchronize | ( | void | ) |
Blocks until the device has completed all preceding requested tasks. cudaThreadSynchronize() returns an error if one of the preceding tasks has failed. If the cudaDeviceBlockingSync flag was set for this device, the host thread will block until the device has finished its work.
cudaThreadExit()
public static int cudaThreadSetLimit(int limit, long value)
cudaError_t cudaThreadSetLimit | ( | enum cudaLimit | limit, | |
size_t | value | |||
) |
Setting limit
to value
is a request by the
application to update the current limit maintained by the thread. The
driver is free to modify the requested value to meet h/w requirements
(this could be clamping to minimum or maximum values, rounding up to
nearest element size, etc). The application can use cudaThreadGetLimit()
to find out exactly what the limit has been set to.
Setting each cudaLimit has its own specific restrictions, so each is discussed here.
cudaThreadGetLimit(long[], int)
public static int cudaThreadGetLimit(long[] pValue, int limit)
cudaError_t cudaThreadGetLimit | ( | size_t * | pValue, | |
enum cudaLimit | limit | |||
) |
Returns in *pValue
the current size of limit
.
The supported cudaLimit values are:
cudaThreadSetLimit(int, long)
public static int cudaGetSymbolAddress(Pointer devPtr, java.lang.String symbol)
cudaError_t cudaGetSymbolAddress | ( | void ** | devPtr, | |
const T & | symbol | |||
) |
Returns in *devPtr
the address of symbol symbol
on the device. symbol
can either be a variable that
resides in global or constant memory space, or it can be a character
string, naming a variable that resides in global or constant memory
space. If symbol
cannot be found, or if symbol
is not declared in the global or constant memory space,
*devPtr
is unchanged and the error cudaErrorInvalidSymbol
is returned. If there are multiple global or constant variables with
the same string name (from separate files) and the lookup is done via
character string, cudaErrorDuplicateVariableName is returned.
cudaGetSymbolAddress(jcuda.Pointer, java.lang.String)
public static int cudaGetSymbolSize(long[] size, java.lang.String symbol)
cudaError_t cudaGetSymbolSize | ( | size_t * | size, | |
const T & | symbol | |||
) |
Returns in *size
the size of symbol symbol
.
symbol
can either be a variable that resides in global or
constant memory space, or it can be a character string, naming a
variable that resides in global or constant memory space. If
symbol
cannot be found, or if symbol
is not
declared in global or constant memory space, *size
is
unchanged and the error cudaErrorInvalidSymbol is returned. If there
are multiple global variables with the same string name (from separate
files) and the lookup is done via character string,
cudaErrorDuplicateVariableName is returned.
cudaGetSymbolAddress(jcuda.Pointer, java.lang.String)
public static int cudaBindTexture(long[] offset, textureReference texref, Pointer devPtr, cudaChannelFormatDesc desc, long size)
cudaError_t cudaBindTexture | ( | size_t * | offset, | |
const struct texture< T, dim, readMode > & | tex, | |||
const void * | devPtr, | |||
const struct cudaChannelFormatDesc & | desc, | |||
size_t | size =
UINT_MAX
|
|||
) |
Binds size
bytes of the memory area pointed to by
devPtr
to texture reference tex
.
desc
describes how the memory is interpreted when fetching
values from the texture. The offset
parameter is an
optional byte offset as with the low-level cudaBindTexture() function.
Any memory previously bound to tex
is unbound.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaBindTexture2D(long[] offset, textureReference texref, Pointer devPtr, cudaChannelFormatDesc desc, long width, long height, long pitch)
cudaError_t cudaBindTexture2D | ( | size_t * | offset, | |
const struct texture< T, dim, readMode > & | tex, | |||
const void * | devPtr, | |||
const struct cudaChannelFormatDesc & | desc, | |||
size_t | width, | |||
size_t | height, | |||
size_t | pitch | |||
) |
Binds the 2D memory area pointed to by devPtr
to the
texture reference tex
. The size of the area is constrained
by width
in texel units, height
in texel
units, and pitch
in byte units. desc
describes
how the memory is interpreted when fetching values from the texture.
Any memory previously bound to tex
is unbound.
Since the hardware enforces an alignment requirement on texture base
addresses, cudaBindTexture2D() returns in *offset
a byte
offset that must be applied to texture fetches in order to read from
the desired memory. This offset must be divided by the texel size and
passed to kernels that read from the texture so they can be applied to
the tex2D() function. If the device memory pointer was returned from
cudaMalloc(), the offset is guaranteed to be 0 and NULL may be passed
as the offset
parameter.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaBindTextureToArray(textureReference texref, cudaArray array, cudaChannelFormatDesc desc)
cudaError_t cudaBindTextureToArray | ( | const struct texture< T, dim, readMode > & | tex, | |
const struct cudaArray * | array, | |||
const struct cudaChannelFormatDesc & | desc | |||
) |
Binds the CUDA array array
to the texture reference
tex
. desc
describes how the memory is
interpreted when fetching values from the texture. Any CUDA array
previously bound to tex
is unbound.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaUnbindTexture(textureReference texref)
cudaError_t cudaUnbindTexture | ( | const struct texture< T, dim, readMode > & | tex | ) |
Unbinds the texture bound to tex
.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaGetTextureAlignmentOffset(long[] offset, textureReference texref)
cudaError_t cudaGetTextureAlignmentOffset | ( | size_t * | offset, | |
const struct texture< T, dim, readMode > & | tex | |||
) |
Returns in *offset
the offset that was returned when
texture reference tex
was bound.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureReference(jcuda.runtime.textureReference, java.lang.String)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
public static int cudaGetTextureReference(textureReference texref, java.lang.String symbol)
cudaError_t cudaGetTextureReference | ( | const struct textureReference ** | texref, | |
const char * | symbol | |||
) |
Returns in *texref
the structure associated to the texture
reference defined by symbol symbol
.
cudaCreateChannelDesc(int, int, int, int, int)
,
cudaGetChannelDesc(jcuda.runtime.cudaChannelFormatDesc, jcuda.runtime.cudaArray)
,
cudaGetTextureAlignmentOffset(long[], jcuda.runtime.textureReference)
,
cudaBindTexture(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long)
,
cudaBindTexture2D(long[], jcuda.runtime.textureReference, jcuda.Pointer, jcuda.runtime.cudaChannelFormatDesc, long, long, long)
,
cudaBindTextureToArray(jcuda.runtime.textureReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaUnbindTexture(jcuda.runtime.textureReference)
public static int cudaBindSurfaceToArray(surfaceReference surfref, cudaArray array, cudaChannelFormatDesc desc)
cudaError_t cudaBindSurfaceToArray | ( | const struct surface< T, dim > & | surf, | |
const struct cudaArray * | array, | |||
const struct cudaChannelFormatDesc & | desc | |||
) |
Binds the CUDA array array
to the surface reference
surf
. desc
describes how the memory is
interpreted when dealing with the surface. Any CUDA array previously
bound to surf
is unbound.
cudaBindSurfaceToArray(jcuda.runtime.surfaceReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaBindSurfaceToArray(jcuda.runtime.surfaceReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
public static int cudaGetSurfaceAlignmentOffset(long[] offset, surfaceReference surfref)
UnsupportedOperationException
Get the alignment offset of a surface.
cudaError_t cudaGetSurfaceAlignmentOffset | ( | size_t * | offset, | |
const struct surfaceReference * | surfref | |||
) |
Returns in *offset
the offset that was returned when
surface reference surface
was bound.
cudaBindSurfaceToArray(jcuda.runtime.surfaceReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaGetSurfaceReference(jcuda.runtime.surfaceReference, java.lang.String)
public static int cudaGetSurfaceReference(surfaceReference surfref, java.lang.String symbol)
cudaError_t cudaGetSurfaceReference | ( | const struct surfaceReference ** | surfref, | |
const char * | symbol | |||
) |
Returns in *surfref
the structure associated to the
surface reference defined by symbol symbol
.
cudaBindSurfaceToArray(jcuda.runtime.surfaceReference, jcuda.runtime.cudaArray, jcuda.runtime.cudaChannelFormatDesc)
,
cudaGetSurfaceAlignmentOffset(long[], jcuda.runtime.surfaceReference)
public static int cudaConfigureCall(dim3 gridDim, dim3 blockDim, long sharedMem, cudaStream_t stream)
cudaError_t cudaConfigureCall | ( | dim3 | gridDim, | |
dim3 | blockDim, | |||
size_t | sharedMem, | |||
cudaStream_t | stream | |||
) |
Specifies the grid and block dimensions for the device call to be executed similar to the execution configuration syntax. cudaConfigureCall() is stack based. Each call pushes data on top of an execution stack. This data contains the dimension for the grid and thread blocks, together with any arguments for the call.
cudaFuncGetAttributes(jcuda.runtime.cudaFuncAttributes, java.lang.String)
,
cudaLaunch(java.lang.String)
,
cudaSetupArgument(jcuda.Pointer, long, long)
public static int cudaSetupArgument(Pointer arg, long size, long offset)
cudaError_t cudaSetupArgument | ( | T | arg, | |
size_t | offset | |||
) |
Pushes size
bytes of the argument pointed to by
arg
at offset
bytes from the start of the
parameter passing area, which starts at offset 0. The arguments are
stored in the top of the execution stack. cudaSetupArgument() must be
preceded by a call to cudaConfigureCall().
cudaConfigureCall(jcuda.runtime.dim3, jcuda.runtime.dim3, long, jcuda.runtime.cudaStream_t)
,
cudaFuncGetAttributes(jcuda.runtime.cudaFuncAttributes, java.lang.String)
,
cudaLaunch(java.lang.String)
,
cudaSetupArgument(jcuda.Pointer, long, long)
public static int cudaFuncGetAttributes(cudaFuncAttributes attr, java.lang.String func)
cudaError_t cudaFuncGetAttributes | ( | struct cudaFuncAttributes * | attr, | |
T * | entry | |||
) |
This function obtains the attributes of a function specified via
entry
. The parameter entry
can either be a
pointer to a function that executes on the device, or it can be a
character string specifying the fully-decorated (C++) name of a function
that executes on the device. The parameter specified by entry
must be declared as a __global__
function. The fetched
attributes are placed in attr
. If the specified function
does not exist, then cudaErrorInvalidDeviceFunction is returned.
cudaConfigureCall(jcuda.runtime.dim3, jcuda.runtime.dim3, long, jcuda.runtime.cudaStream_t)
,
cudaFuncGetAttributes(jcuda.runtime.cudaFuncAttributes, java.lang.String)
,
cudaLaunch(java.lang.String)
,
cudaSetupArgument(jcuda.Pointer, long, long)
public static int cudaLaunch(java.lang.String symbol)
cudaError_t cudaLaunch | ( | T * | entry | ) |
Launches the function entry
on the device. The parameter
entry
can either be a function that executes on the
device, or it can be a character string, naming a function that executes
on the device. The parameter specified by entry
must be
declared as a __global__
function. cudaLaunch() must be
preceded by a call to cudaConfigureCall() since it pops the data that
was pushed by cudaConfigureCall() from the execution stack.
cudaConfigureCall(jcuda.runtime.dim3, jcuda.runtime.dim3, long, jcuda.runtime.cudaStream_t)
,
cudaFuncGetAttributes(jcuda.runtime.cudaFuncAttributes, java.lang.String)
,
cudaLaunch(java.lang.String)
,
cudaSetupArgument(jcuda.Pointer, long, long)
public static int cudaGLSetGLDevice(int device)
cudaError_t cudaGLSetGLDevice | ( | int | device | ) |
Records device
as the device on which the active host
thread executes the device code. Records the thread as using OpenGL
interoperability. If the host thread has already initialized the CUDA
runtime by calling non-device management runtime functions or if there
exists a CUDA driver context active on the host thread, then this call
returns cudaErrorSetOnActiveProcess.
cudaGLRegisterBufferObject(int)
,
cudaGLMapBufferObject(jcuda.Pointer, int)
,
cudaGLUnmapBufferObject(int)
,
cudaGLUnregisterBufferObject(int)
,
cudaGLMapBufferObjectAsync(jcuda.Pointer, int, jcuda.runtime.cudaStream_t)
,
cudaGLUnmapBufferObjectAsync(int, jcuda.runtime.cudaStream_t)
public static int cudaGraphicsGLRegisterImage(cudaGraphicsResource resource, int image, int target, int Flags)
cudaError_t cudaGraphicsGLRegisterImage | ( | struct cudaGraphicsResource ** | resource, | |
GLuint | image, | |||
GLenum | target, | |||
unsigned int | flags | |||
) |
Registers the texture or renderbuffer object specified by
image
for access by CUDA. target
must match
the type of the object. A handle to the registered object is returned
as resource
. The map flags flags
specify the
intended usage, as follows:
The following image classes are currently disallowed:
cudaGLSetGLDevice(int)
,
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
,
cudaGraphicsSubResourceGetMappedArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaGraphicsResource, int, int)
public static int cudaGraphicsGLRegisterBuffer(cudaGraphicsResource resource, int buffer, int Flags)
cudaError_t cudaGraphicsGLRegisterBuffer | ( | struct cudaGraphicsResource ** | resource, | |
GLuint | buffer, | |||
unsigned int | flags | |||
) |
Registers the buffer object specified by buffer
for access
by CUDA. A handle to the registered object is returned as
resource
. The map flags flags
specify the
intended usage, as follows:
cudaGraphicsUnregisterResource(jcuda.runtime.cudaGraphicsResource)
,
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
,
cudaGraphicsResourceGetMappedPointer(jcuda.Pointer, long[], jcuda.runtime.cudaGraphicsResource)
public static int cudaGLRegisterBufferObject(int bufObj)
cudaError_t cudaGLRegisterBufferObject | ( | GLuint | bufObj | ) |
bufObj
for access by
CUDA. This function must be called before CUDA can map the buffer
object. The OpenGL context used to create the buffer, or another
context from the same share group, must be bound to the current thread
when this is called.
cudaGraphicsGLRegisterBuffer(jcuda.runtime.cudaGraphicsResource, int, int)
public static int cudaGLMapBufferObject(Pointer devPtr, int bufObj)
cudaError_t cudaGLMapBufferObject | ( | void ** | devPtr, | |
GLuint | bufObj | |||
) |
bufObj
into the address space
of CUDA and returns in *devPtr
the base pointer of the
resulting mapping. The buffer must have previously been registered by
calling cudaGLRegisterBufferObject(). While a buffer is mapped by CUDA,
any OpenGL operation which references the buffer will result in
undefined behavior. The OpenGL context used to create the buffer, or
another context from the same share group, must be bound to the current
thread when this is called.
All streams in the current thread are synchronized with the current GL context.
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaGLUnmapBufferObject(int bufObj)
cudaError_t cudaGLUnmapBufferObject | ( | GLuint | bufObj | ) |
bufObj
for access by CUDA.
When a buffer is unmapped, the base address returned by
cudaGLMapBufferObject() is invalid and subsequent references to the
address result in undefined behavior. The OpenGL context used to create
the buffer, or another context from the same share group, must be bound
to the current thread when this is called.
All streams in the current thread are synchronized with the current GL context.
cudaGraphicsUnmapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaGLUnregisterBufferObject(int bufObj)
cudaError_t cudaGLUnregisterBufferObject | ( | GLuint | bufObj | ) |
bufObj
for access by
CUDA and releases any CUDA resources associated with the buffer. Once
a buffer is unregistered, it may no longer be mapped by CUDA. The GL
context used to create the buffer, or another context from the same
share group, must be bound to the current thread when this is
called.
cudaGraphicsUnregisterResource(jcuda.runtime.cudaGraphicsResource)
public static int cudaGLSetBufferObjectMapFlags(int bufObj, int flags)
cudaError_t cudaGLSetBufferObjectMapFlags | ( | GLuint | bufObj, | |
unsigned int | flags | |||
) |
bufObj
Changes to flags will take effect the next time bufObj
is
mapped. The flags
argument may be any of the
following:
If bufObj
has not been registered for use with CUDA, then
cudaErrorInvalidResourceHandle is returned. If bufObj
is
presently mapped for access by CUDA, then cudaErrorUnknown is
returned.
cudaGraphicsResourceSetMapFlags(jcuda.runtime.cudaGraphicsResource, int)
public static int cudaGLMapBufferObjectAsync(Pointer devPtr, int bufObj, cudaStream_t stream)
cudaError_t cudaGLMapBufferObjectAsync | ( | void ** | devPtr, | |
GLuint | bufObj, | |||
cudaStream_t | stream | |||
) |
bufObj
into the address space
of CUDA and returns in *devPtr
the base pointer of the
resulting mapping. The buffer must have previously been registered by
calling cudaGLRegisterBufferObject(). While a buffer is mapped by CUDA,
any OpenGL operation which references the buffer will result in
undefined behavior. The OpenGL context used to create the buffer, or
another context from the same share group, must be bound to the current
thread when this is called.
Stream /p stream is synchronized with the current GL context.
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaGLUnmapBufferObjectAsync(int bufObj, cudaStream_t stream)
cudaError_t cudaGLUnmapBufferObjectAsync | ( | GLuint | bufObj, | |
cudaStream_t | stream | |||
) |
bufObj
for access by CUDA.
When a buffer is unmapped, the base address returned by
cudaGLMapBufferObject() is invalid and subsequent references to the
address result in undefined behavior. The OpenGL context used to create
the buffer, or another context from the same share group, must be bound
to the current thread when this is called.
Stream /p stream is synchronized with the current GL context.
cudaGraphicsUnmapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaDriverGetVersion(int[] driverVersion)
cudaError_t cudaDriverGetVersion | ( | int * | driverVersion | ) |
Returns in *driverVersion
the version number of the
installed CUDA driver. If no driver is installed, then 0 is returned
as the driver version (via driverVersion
). This function
automatically returns cudaErrorInvalidValue if the
driverVersion
argument is NULL.
cudaRuntimeGetVersion(int[])
public static int cudaRuntimeGetVersion(int[] runtimeVersion)
cudaError_t cudaRuntimeGetVersion | ( | int * | runtimeVersion | ) |
Returns in *runtimeVersion
the version number of the
installed CUDA Runtime. This function automatically returns
cudaErrorInvalidValue if the runtimeVersion
argument is
NULL.
cudaDriverGetVersion(int[])
public static int cudaGraphicsUnregisterResource(cudaGraphicsResource resource)
cudaError_t cudaGraphicsUnregisterResource | ( | struct cudaGraphicsResource * | resource | ) |
Unregisters the graphics resource resource
so it is not
accessible by CUDA unless registered again.
If resource
is invalid then cudaErrorInvalidResourceHandle
is returned.
cudaGraphicsGLRegisterBuffer(jcuda.runtime.cudaGraphicsResource, int, int)
,
cudaGraphicsGLRegisterImage(jcuda.runtime.cudaGraphicsResource, int, int, int)
public static int cudaGraphicsResourceSetMapFlags(cudaGraphicsResource resource, int flags)
cudaError_t cudaGraphicsResourceSetMapFlags | ( | struct cudaGraphicsResource * | resource, | |
unsigned int | flags | |||
) |
Set flags
for mapping the graphics resource
resource
.
Changes to flags
will take effect the next time
resource
is mapped. The flags
argument may
be any of the following:
resource
will be used. It is therefore assumed that CUDA
may read from or write to
resource
.
resource
.
resource
and will write
over the entire contents of resource
, so none of the data
previously stored in resource
will be
preserved.
If resource
is presently mapped for access by CUDA then
cudaErrorUnknown is returned. If flags
is not one of the
above values then cudaErrorInvalidValue is returned.
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaGraphicsMapResources(int count, cudaGraphicsResource[] resources, cudaStream_t stream)
cudaError_t cudaGraphicsMapResources | ( | int | count, | |
struct cudaGraphicsResource ** | resources, | |||
cudaStream_t | stream | |||
) |
Maps the count
graphics resources in resources
for access by CUDA.
The resources in resources
may be accessed by CUDA until
they are unmapped. The graphics API from which resources
were registered should not access any resources while they are mapped
by CUDA. If an application does so, the results are undefined.
This function provides the synchronization guarantee that any graphics
calls issued before cudaGraphicsMapResources() will complete before
any subsequent CUDA work issued in stream
begins.
If resources
contains any duplicate entries then
cudaErrorInvalidResourceHandle is returned. If any of
resources
are presently mapped for access by CUDA then
cudaErrorUnknown is returned.
cudaGraphicsResourceGetMappedPointer(jcuda.Pointer, long[], jcuda.runtime.cudaGraphicsResource)
public static int cudaGraphicsUnmapResources(int count, cudaGraphicsResource[] resources, cudaStream_t stream)
cudaError_t cudaGraphicsUnmapResources | ( | int | count, | |
struct cudaGraphicsResource ** | resources, | |||
cudaStream_t | stream | |||
) |
Unmaps the count
graphics resources in
resources
.
Once unmapped, the resources in resources
may not be
accessed by CUDA until they are mapped again.
This function provides the synchronization guarantee that any CUDA work
issued in stream
before cudaGraphicsUnmapResources() will
complete before any subsequently issued graphics work begins.
If resources
contains any duplicate entries then
cudaErrorInvalidResourceHandle is returned. If any of
resources
are not presently mapped for access by Cuda then
cudaErrorUnknown is returned.
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
public static int cudaGraphicsResourceGetMappedPointer(Pointer devPtr, long[] size, cudaGraphicsResource resource)
cudaError_t cudaGraphicsResourceGetMappedPointer | ( | void ** | devPtr, | |
size_t * | size, | |||
struct cudaGraphicsResource * | resource | |||
) |
Returns in *devPtr
a pointer through which the mapped
graphics resource resource
may be accessed. Returns in
*size
the size of the memory in bytes which may be accessed
from that pointer. The value set in devPtr
may change
every time that resource
is mapped.
If resource
is not a buffer then it cannot be accessed
via a pointer and cudaErrorUnknown is returned. If resource
is not mapped then cudaErrorUnknown is returned. *
cudaGraphicsMapResources(int, jcuda.runtime.cudaGraphicsResource[], jcuda.runtime.cudaStream_t)
,
cudaGraphicsSubResourceGetMappedArray(jcuda.runtime.cudaArray, jcuda.runtime.cudaGraphicsResource, int, int)
public static int cudaGraphicsSubResourceGetMappedArray(cudaArray arrayPtr, cudaGraphicsResource resource, int arrayIndex, int mipLevel)
cudaError_t cudaGraphicsSubResourceGetMappedArray | ( | cudaArray ** | array, | |
struct cudaGraphicsResource * | resource, | |||
unsigned int | arrayIndex, | |||
unsigned int | mipLevel | |||
) |
Returns in *array
an array through which the subresource
of the mapped graphics resource resource
which corresponds
to array index arrayIndex
and mipmap level
mipLevel
may be accessed. The value set in array
may change every time that resource
is mapped.
If resource
is not a texture then it cannot be accessed
via an array and cudaErrorUnknown is returned. If arrayIndex
is not a valid array index for resource
then
cudaErrorInvalidValue is returned. If mipLevel
is not a
valid mipmap level for resource
then cudaErrorInvalidValue
is returned. If resource
is not mapped then cudaErrorUnknown
is returned.
cudaGraphicsResourceGetMappedPointer(jcuda.Pointer, long[], jcuda.runtime.cudaGraphicsResource)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |