Oleksandr "Alex" Zinenko
Oleksandr "Alex" Zinenko
List of modules - codegen: CLooG, ppcg - dependence analyzer: candl, isl - parser: clan, pet - enumerator: isl, polylib, piplib This requires deeper transformation code between OpenScop and isl...
Use new cmake system to enforce C++14 flags, it may randomly add "gnu++11" on top now.
Proceeding with ScheduleTree evolution plan (#553) This PR replaces overloaded comparison operators with two functions, `nodeEquals` and `treeEquals`. The main motivation for this change: after grafting ScheduleTreeElem* onto ScheduleTree in...
cuda::MappedScop: introduce maxPrivateElements mapping option This mapping option controls the maximum number of elements per thread that are promoted into the private memory (hopefully, registers, but we cannot guarantee this...
#543 removed the notion of schedule tree element: now specific, node types inherit directly from `ScheduleTree`, which is simpler and offers more type safety. This refactoring uncovered several technical and...
Similarly to shared memory promotion, we may want to limit the number of elements promoted to registers. In particular, it should be less than the number of available registers of...
With #537, it is possible to promote to shared memory at disjoint subtrees. Tthe `maxSharedMemory` option controls the _total_ amount of shared memory used by _all_ subtrees, whereas the same...
If a tensor reference group is promoted to shared memory at some scope, it may be interesting to promote it to registers at some deeper scope. There are two possibilities:...
Currently, TC makes extensive use of command line flags (provided by gflags) for debugging or configuration purposes. These flags are essentially global variables, and global variables are generally discouraged. In...
#489 introduces more code that needs the mapping to be represented as both a mupa and a `union_set`, depending on the context of use. We now have (almost) duplicate code...