diff options
| author | Pavel Labath <labath@google.com> | 2018-02-19 17:23:13 +0000 |
|---|---|---|
| committer | Pavel Labath <labath@google.com> | 2018-02-19 17:23:13 +0000 |
| commit | 37a35d339501f911fbd0aa388a5ab5fd5d37da00 (patch) | |
| tree | 3142c42df470a7655806d1039452968dbe945029 /llvm/lib/CodeGen/SelectionDAG | |
| parent | 419bdab7595ff213c326f40683b1dca78c5fff03 (diff) | |
| download | bcm5719-llvm-37a35d339501f911fbd0aa388a5ab5fd5d37da00.tar.gz bcm5719-llvm-37a35d339501f911fbd0aa388a5ab5fd5d37da00.zip | |
Two more dosep-paralellization fallout fixes
The first issue is about the flaky test rerun logic. This was grouping
tests by subdir and passing them into walk_and_invoke in the incorrect
form. This part can be just deleted as its not needed anymore.
The second problem (which I noticed while investigating the first one)
was that the "-p" switch was not working in multiprocessing mode. This
happened because we were returning None from process_file instead of a
tuple full of empty values for tests that did not match the -p regex.
Both of these would be caught earlier if python was a more strongly
typed language. :/
llvm-svn: 325519
Diffstat (limited to 'llvm/lib/CodeGen/SelectionDAG')
0 files changed, 0 insertions, 0 deletions
