414fa671be
This PR contains the support of UMPIRE pooling allocators for host and GPU memory. Configure hypre with --with-umpire, device and uvm allocations and deallocations are done with umpire, whereas host pool is not enabled by default. This PR also includes some other minor changes: Adding .gitignore to the repo Removing all malloc/calloc/realloc/free and regression testing on finding them No longer compile ij.c with C++ compiler. It goes back to a C code now. Introducing HYPRE_USING_GPU, which is equivalent to HYPRE_USING_CUDA || HYPRE_USING_DEVICE_OPENMP Adding a few user-level interfaces: HYPRE_SetMemoryLocation, HYPRE_SetExecutionPolicy, HYPRE_SetGPUMemoryPoolSize and HYPRE_CSRMatrixSetSpGemmUseCusparse Co-authored-by: li50@llnl.gov <liruipengblue@gmail.com> Co-authored-by: Rob Falgout <rfalgout@llnl.gov> Co-authored-by: Ruipeng Li <li50@llnl.gov>
20 lines
961 B
XML
20 lines
961 B
XML
slu_util.c:
|
|
autoconf has been disabled
|
|
automake has been disabled
|
|
autoheader has been disabled
|
|
warning: \[options\] bootstrap class path not set in conjunction with
|
|
1 warning
|
|
warning: warning: feupdateenv is not implemented and will always fail
|
|
ranlib: file: lib.*\(.*\) has no symbols
|
|
/tmp/.*: Assembler messages:
|
|
/tmp/.*: Warning: Additional NOP may be necessary to workaround Itanium processor A/B step errata
|
|
ltdl.c:.*: warning: function declaration isn't a prototype
|
|
ltdl.c:*
|
|
Additional optimization may be attained by recompiling and specifying MAXMEM option with a value greater than 8192.
|
|
WARNING in dReadValues: Infinite loop. Program may not stop.
|
|
WARNING in dReadVector: Infinite loop. Program may not stop.
|
|
icc: command line warning .*: overriding
|
|
WARNING: no debugging flags detected
|
|
The device linker only supports static linking. Any device code placed into a shared library by the qmkshrobj option will be inaccessible.
|
|
tcmalloc: large alloc
|