amrex::PArena Class Reference

This arena uses CUDA stream-ordered memory allocator if available. If not, use The_Arena(). More...

#include <AMReX_PArena.H>

Inheritance diagram for amrex::PArena:

Public Member Functions
	PArena (Long release_threshold)
	PArena (const PArena &rhs)=delete
	PArena (PArena &&rhs)=delete
PArena &	operator= (const PArena &rhs)=delete
PArena &	operator= (PArena &&rhs)=delete
	~PArena () override
void *	alloc (std::size_t nbytes) final
void	free (void *p) final
	A pure virtual function for deleting the arena pointed to by pt. More...
bool	isDeviceAccessible () const final
bool	isHostAccessible () const final
bool	isManaged () const final
bool	isDevice () const final
bool	isPinned () const final
bool	isStreamOrderedArena () const final
	Is this CUDA stream ordered memory allocator? More...
Public Member Functions inherited from amrex::Arena
virtual	~Arena ()=default
	Arena () noexcept=default
	Arena (const Arena &rhs)=delete
	Arena (Arena &&rhs)=delete
Arena &	operator= (const Arena &rhs)=delete
Arena &	operator= (Arena &&rhs)=delete
virtual std::pair< void *, std::size_t >	alloc_in_place (void *, std::size_t, std::size_t szmax)
virtual void *	shrink_in_place (void *, std::size_t sz)
virtual std::size_t	freeUnused ()
	Free unused memory back to the system. Return value is the amount memory freed. More...
virtual bool	hasFreeDeviceMemory (std::size_t sz)
	Does the device have enough free memory for allocating this much memory? For CPU builds, this always return true. This is not a const function because it may attempt to release memory back to the system. More...
void	registerForProfiling (const std::string &memory_name)
	Add this Arena to the list of Arenas that are profiled by TinyProfiler. More...
const ArenaInfo &	arenaInfo () const
	Return the ArenaInfo object for querying. More...

Additional Inherited Members
Static Public Member Functions inherited from amrex::Arena
static std::size_t	align (std::size_t sz)
	Given a minimum required arena size of sz bytes, this returns the next largest arena size that will align to align_size bytes. More...
static void	Initialize ()
static void	PrintUsage ()
static void	PrintUsageToFiles (std::string const &filename, std::string const &message)
static void	Finalize ()
Static Public Attributes inherited from amrex::Arena
static const std::size_t	align_size = 16
Protected Member Functions inherited from amrex::Arena
virtual std::size_t	freeUnused_protected ()
void *	allocate_system (std::size_t nbytes)
void	deallocate_system (void *p, std::size_t nbytes)
Protected Attributes inherited from amrex::Arena
ArenaInfo	arena_info
struct amrex::Arena::ArenaProfiler	m_profiler

Detailed Description

This arena uses CUDA stream-ordered memory allocator if available. If not, use The_Arena().

Constructor & Destructor Documentation

PArena() [1/3]

amrex::PArena::PArena

(

Long

release_threshold

)

PArena() [2/3]

amrex::PArena::PArena ( const PArena &  rhs )

delete

PArena() [3/3]

amrex::PArena::PArena ( PArena &&  rhs )

delete

~PArena()

amrex::PArena::~PArena ( )

override

Member Function Documentation

alloc()

void * amrex::PArena::alloc ( std::size_t  sz )

finalvirtual

Allocate a dynamic memory arena

Parameters

sz	size of the memory request

Returns

a pointer to the allocated memory

Implements amrex::Arena.

free()

void amrex::PArena::free ( void *  pt )

finalvirtual

A pure virtual function for deleting the arena pointed to by pt.

Implements amrex::Arena.

isDevice()

bool amrex::PArena::isDevice ( ) const

finalvirtual

Reimplemented from amrex::Arena.

isDeviceAccessible()

bool amrex::PArena::isDeviceAccessible ( ) const

finalvirtual

Reimplemented from amrex::Arena.

isHostAccessible()

bool amrex::PArena::isHostAccessible ( ) const

finalvirtual

Reimplemented from amrex::Arena.

isManaged()

bool amrex::PArena::isManaged ( ) const

finalvirtual

Reimplemented from amrex::Arena.

isPinned()

bool amrex::PArena::isPinned ( ) const

finalvirtual

Reimplemented from amrex::Arena.

isStreamOrderedArena()

bool amrex::PArena::isStreamOrderedArena ( ) const

inlinefinalvirtual

Is this CUDA stream ordered memory allocator?

Reimplemented from amrex::Arena.

operator=() [1/2]

PArena& amrex::PArena::operator= ( const PArena &  rhs )

delete

operator=() [2/2]

PArena& amrex::PArena::operator= ( PArena &&  rhs )

delete

---

The documentation for this class was generated from the following files:

• /home/runner/work/amrex/amrex/Src/Base/AMReX_PArena.H
• /home/runner/work/amrex/amrex/Src/Base/AMReX_PArena.cpp