One-dimensional and small fixed-size containers used throughout AMReX. More...

Classes
class	amrex::GpuArray< T, N >
	Fixed-size array that can be used on GPU. More...

class	amrex::PODVector< T, Allocator >
	Dynamically allocated vector for trivially copyable data. More...

class	amrex::GpuTuple< Ts >
	GPU-compatible tuple. More...

Typedefs
template<class T , std::size_t N>
using	amrex::Array = std::array< T, N >

template<class T >
using	amrex::Gpu::DeviceVector = PODVector< T, ArenaAllocator< T > >
	A PODVector that uses the standard memory Arena. Note that the memory might or might not be managed depending on the amrex.the_arena_is_managed ParmParse parameter.

template<class T >
using	amrex::Gpu::NonManagedDeviceVector = PODVector< T, DeviceArenaAllocator< T > >
	A PODVector that uses the non-managed device memory arena.

template<class T >
using	amrex::Gpu::ManagedVector = PODVector< T, ManagedArenaAllocator< T > >
	A PODVector that uses the managed memory arena.

template<class T >
using	amrex::Gpu::PinnedVector = PODVector< T, PinnedArenaAllocator< T > >
	A PODVector that uses the pinned memory arena.

template<class T >
using	amrex::Gpu::AsyncVector = PODVector< T, AsyncArenaAllocator< T > >
	A PODVector that uses the async memory arena. Maybe useful for temporary vectors inside MFIters that are accessed on the device.

template<class T >
using	amrex::Gpu::HostVector = PinnedVector< T >
	A PODVector that uses pinned host memory. Same as PinnedVector. For a vector class that uses std::allocator by default, see amrex::Vector.

template<class T >
using	amrex::Gpu::ManagedDeviceVector = PODVector< T, ManagedArenaAllocator< T > >
	This is identical to ManagedVector<T>. The ManagedDeviceVector form is deprecated and will be removed in a future release.

Detailed Description

One-dimensional and small fixed-size containers used throughout AMReX.

Central types include:

Typedef Documentation

◆ Array

template<class T , std::size_t N>

using amrex::Array = typedef std::array<T,N>

◆ AsyncVector

template<class T >

using amrex::Gpu::AsyncVector = typedef PODVector<T, AsyncArenaAllocator<T> >

A PODVector that uses the async memory arena. Maybe useful for temporary vectors inside MFIters that are accessed on the device.

◆ DeviceVector

template<class T >

using amrex::Gpu::DeviceVector = typedef PODVector<T, ArenaAllocator<T> >

A PODVector that uses the standard memory Arena. Note that the memory might or might not be managed depending on the amrex.the_arena_is_managed ParmParse parameter.