HypreParVector, HypreParMatrix, and HypreSmoother with GPU backends.
Add 2 versions of a new method: Vector::MakeRef -- one that takes
a Vector and an offset and another that takes a Vector, an offset
and a new size.
Add some simple debugging tools:
* Add a new output "trace" stream: mfem::trc. By default, the output
of mfem::trc goes to std::cout; the new function mfem::OpenTraceFile()
can be used to redirect the output of mfem::trc to a file called
'mfem-trace-<pid>' where <pid> is the process id. Note that this
function can be called from a debugger.
* In class Vector, add a new method Vector::PrintTrace() that prints a
Vector to the mfem::trc stream -- this method can be called from a
debugger, unlike Vector::Print with mfem::trc as argument (at least
in gdb this did not work).
* In class Memory<T>, add 2 new methods: PrintFlags() and
CompareHostAndDevice() which are explicitly instantiated for T=int
and T=double, so that they can be called inside a debugger for
these two types.
* The parameter of Vector::UseDevice(bool) no longer has a default value. All
the calls to UseDevice() in operator.cpp bilinearform_ext.cpp gridfunc.?pp and
linearform.?pp have been replaced with UseDevice(true).
* Added shortcuts for the device flags of the Memory objects inside the Vector
and Array classes:
bool Array::UseDevice()
bool Vector::UseDevice()
* The internal device flag in Memory::FlagMask is now called USE_DEVICE (it was
previously called EXEC_FLAG). The accessor function for this flag have been
renamed:
bool Memory::GetExecFlag() -> bool Memory::UseDevice()
void Memory::SetExecFlag(bool) -> void Memory::UseDevice(bool)
* Further renamed:
Memory::SyncWith -> Memory::Sync
Memory::SyncAliasToBase -> Memory::SyncAlias
Memory::SyncAliasToBase_ -> Memory::SyncAlias_
* Replaced FIXME with TODO in general/mem_manager.cpp
Modify the Device class to require the creation of an object in
order to use backends other then Backend::CPU. At destriction,
this object will call the Destroy() method of the MemoryManager to
deallocate any remaining registered device pointers.
In class Device, remove the method Disable() and make the method
Enable() private.
Use a global Array<double> as the buffer used by the cuda functions
for minimum and dot product.
camierjs