maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/flang/test/Semantics/symbol16.f90

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

18 lines
359 B
Fortran
Raw Normal View History

[flang] Port all remaining regression tests to lit We have re-classified a subset of the regression tests as unit tests and now we are porting the remaining ones. Test discovery and running is now performed by lit rather than ctest. The tests continue to use their original scripts with minor modifications. Most of the changes were mechanical and so scripted. A few changes were made by hand. Details Manual: * modfile09-*.f90 tests depend on being run together as some tests have dependencies on modules created by other tests. This will need separating out when porting away from test_modfile.sh, but for now, added modfile09-*.f90 to the Inputs directory and added a single tests modfile09.f90 to hold the run line. * getdefinition03-a.f90 includes a non-test file getdefinition03-b.f90. Manually edited the former to find the latter in Inputs so as to add only one test. * Same pattern for getsymbols03-{a,b}.f90 Auto: * Remaining tests have a lit RUN line added to them based on the type of test they are. * Failing tests also have an XFAIL line added to them. * Generic tests have their pre-existing RUN lines replaced with the word "EXEC" to avoid conflict with the added lit RUN line. Original-commit: flang-compiler/f18@63ec0af9f4c8e736a626d1cd1410f71f4e578aa9 Reviewed-on: https://github.com/flang-compiler/f18/pull/1027 Tree-same-pre-rewrite: false
2020-02-14 22:02:29 +08:00
! RUN: %S/test_symbols.sh %s %flang %t
[flang] Fix bug with statement functions When the name of a statement function was previously declared, we weren't correctly recognizing it as a statement function. E.g. ``` integer :: f, i f(i) = i + 1 ``` `f` was entered in the symbol table with `EntityDetails` and the `parser::Name` on the first line was resolved to that symbol. On the second line we replaced the symbol for `f` in the scope with a subprogram symbol, but that didn't change the symbol in the first `parser::Name`. The fix requires: 1. don't erase the original symbol for `f`, just replace its details 2. when we erase the symbol for `f` in the subprogram scope, don't unresolve it Original-commit: flang-compiler/f18@31212686ea357503840c0562853c6977bfc1ffe5
2019-08-27 06:46:49 +08:00
! Statement functions
!DEF: /p1 MainProgram
program p1
[flang] Improve flag dumping for -funparse-with-symbols Original-commit: flang-compiler/f18@768fb1b36925c1e1ed563562ef01146c2bba4b2b
2019-09-13 14:03:06 +08:00
!DEF: /p1/f (Function) Subprogram INTEGER(4)
[flang] Fix bug with statement functions When the name of a statement function was previously declared, we weren't correctly recognizing it as a statement function. E.g. ``` integer :: f, i f(i) = i + 1 ``` `f` was entered in the symbol table with `EntityDetails` and the `parser::Name` on the first line was resolved to that symbol. On the second line we replaced the symbol for `f` in the scope with a subprogram symbol, but that didn't change the symbol in the first `parser::Name`. The fix requires: 1. don't erase the original symbol for `f`, just replace its details 2. when we erase the symbol for `f` in the subprogram scope, don't unresolve it Original-commit: flang-compiler/f18@31212686ea357503840c0562853c6977bfc1ffe5
2019-08-27 06:46:49 +08:00
!DEF: /p1/i ObjectEntity INTEGER(4)
!DEF: /p1/j ObjectEntity INTEGER(4)
integer f, i, j
!REF: /p1/f
!REF: /p1/i
!DEF: /p1/f/i ObjectEntity INTEGER(4)
f(i) = i + 1
!REF: /p1/j
!REF: /p1/f
j = f(2)
end program