org.bytedeco.cuda.cudart

Class __nv_bfloat162

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.cuda.cudart.__nv_bfloat162

All Implemented Interfaces:

AutoCloseable

@NoOffset
 @Properties(inherit=cudart.class)
public class __nv_bfloat162
extends Pointer

\ingroup CUDA_MATH_INTRINSIC_BFLOAT16 \brief nv_bfloat162 datatype \details This structure implements the datatype for storing two nv_bfloat16 floating-point numbers. The structure implements assignment, arithmetic and comparison operators, and type conversions. - NOTE: __nv_bfloat162 is visible to non-nvcc host compilers

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
__nv_bfloat162(__nv_bfloat16 a, __nv_bfloat16 b) \ingroup CUDA_MATH__BFLOAT16_MISC Constructor from two \p __nv_bfloat16 variables
__nv_bfloat162(__nv_bfloat162_raw h2r) \ingroup CUDA_MATH__BFLOAT16_MISC Constructor from \p __nv_bfloat162_raw
__nv_bfloat162(__nv_bfloat162 src) \ingroup CUDA_MATH__BFLOAT16_MISC Move constructor, available for \p C++11 and later dialects
__nv_bfloat162() \ingroup CUDA_MATH__BFLOAT16_MISC \brief Constructor by default.
__nv_bfloat162(long size) Native array allocator.
__nv_bfloat162(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
__nv_bfloat162_raw	as__nv_bfloat162_raw() \ingroup CUDA_MATH__BFLOAT16_MISC Conversion operator to \p __nv_bfloat162_raw
__nv_bfloat162	getPointer(long i)
__nv_bfloat162	position(long position)
__nv_bfloat162	put(__nv_bfloat162_raw h2r) \ingroup CUDA_MATH__BFLOAT16_MISC Assignment operator from \p __nv_bfloat162_raw
__nv_bfloat162	put(__nv_bfloat162 src) \ingroup CUDA_MATH__BFLOAT16_MISC Move assignment operator, available for \p C++11 and later dialects
__nv_bfloat162	x(__nv_bfloat16 setter)
__nv_bfloat16	x() Storage field holding lower \p __nv_bfloat16 part.
__nv_bfloat162	y(__nv_bfloat16 setter)
__nv_bfloat16	y() Storage field holding upper \p __nv_bfloat16 part.

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

__nv_bfloat162

public __nv_bfloat162(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

__nv_bfloat162

public __nv_bfloat162(long size)

Native array allocator. Access with Pointer.position(long).

__nv_bfloat162

public __nv_bfloat162()

\ingroup CUDA_MATH__BFLOAT16_MISC \brief Constructor by default. \details Emtpy default constructor, result is uninitialized.

__nv_bfloat162

public __nv_bfloat162(@ByRef(value=true)
                      __nv_bfloat162 src)

\ingroup CUDA_MATH__BFLOAT16_MISC Move constructor, available for \p C++11 and later dialects

__nv_bfloat162

public __nv_bfloat162(@Const @ByRef
                      __nv_bfloat16 a,
                      @Const @ByRef
                      __nv_bfloat16 b)

\ingroup CUDA_MATH__BFLOAT16_MISC Constructor from two \p __nv_bfloat16 variables

__nv_bfloat162

public __nv_bfloat162(@Const @ByRef
                      __nv_bfloat162_raw h2r)

\ingroup CUDA_MATH__BFLOAT16_MISC Constructor from \p __nv_bfloat162_raw

Method Detail

position

public __nv_bfloat162 position(long position)

Overrides:

position in class Pointer

getPointer

public __nv_bfloat162 getPointer(long i)

Overrides:

getPointer in class Pointer

x

@ByRef
public __nv_bfloat16 x()

Storage field holding lower \p __nv_bfloat16 part.

x

public __nv_bfloat162 x(__nv_bfloat16 setter)

y

@ByRef
public __nv_bfloat16 y()

Storage field holding upper \p __nv_bfloat16 part.

y

public __nv_bfloat162 y(__nv_bfloat16 setter)

put

@ByRef
 @Name(value="operator =")
public __nv_bfloat162 put(@ByRef(value=true)
                                                              __nv_bfloat162 src)

\ingroup CUDA_MATH__BFLOAT16_MISC Move assignment operator, available for \p C++11 and later dialects

put

@ByRef
 @Name(value="operator =")
public __nv_bfloat162 put(@Const @ByRef
                                                              __nv_bfloat162_raw h2r)

\ingroup CUDA_MATH__BFLOAT16_MISC Assignment operator from \p __nv_bfloat162_raw

as__nv_bfloat162_raw

@ByVal
 @Name(value="operator __nv_bfloat162_raw")
public __nv_bfloat162_raw as__nv_bfloat162_raw()

\ingroup CUDA_MATH__BFLOAT16_MISC Conversion operator to \p __nv_bfloat162_raw