5140d1b75e
Update tests in -Asserts mode. These tests really need to be rewritten...
...
llvm-svn: 95658
2010-02-09 08:22:03 +00:00
a04ecfb701
Refine the non-virtual this adjustments for thunks by using the offset
...
to the declaring class from the nearest virtual base class. WIP.
This fixes 40% of all the problems remaining in one of my testcases.
llvm-svn: 94592
2010-01-26 21:35:27 +00:00
77537b136e
Be sure to track the non-virtual part of the vcall offset in complex
...
multiple inheritance cases. WIP.
This fixes 20% of the outstanding problems found by the randomized
tester.
llvm-svn: 94499
2010-01-26 03:42:22 +00:00
90181eb294
Fixup a missing vcall entry. WIP.
...
llvm-svn: 94478
2010-01-26 00:05:04 +00:00
20bac07abb
Adjust testcase for recent AsmPrinter changes, sigh.
...
llvm-svn: 94307
2010-01-23 10:15:32 +00:00
1891698a9b
Fixup the rest of the testcases to grep the .ll file instead of the .s
...
file, and add FIXMEs to the remaining broken tests.
llvm-svn: 94238
2010-01-22 22:37:17 +00:00
3cd08d9df7
Convert more testcases to checking the .ll file instead of the .s file.
...
llvm-svn: 94229
2010-01-22 22:06:55 +00:00
0a2754ed8a
Be sure to select primary bases among the nearly empties in preorder,
...
not just among the direct bases. Before we where missing nearly
empties that were bases of virtual base classes.
llvm-svn: 94208
2010-01-22 20:27:17 +00:00
9eb76d47f2
Ensure we output all non-virtual base vtables. Fixes PR5890.
...
llvm-svn: 94163
2010-01-22 06:45:05 +00:00
5e536d85ad
allow this test to pass, even with the recent .s printer changes.
...
Have I ever mentioned that clang regtests should not be grepping .s files??
llvm-svn: 93998
2010-01-20 07:45:09 +00:00
1af3df854f
Fix a bunch of VTT layout bugs, add simple tests for VTT layout.
...
llvm-svn: 93709
2010-01-18 04:25:18 +00:00
25933d4ecd
Update virt.cpp for changes to the LLVM asm printer (?) This test should really be all LLVM IR...
...
llvm-svn: 93707
2010-01-18 03:58:13 +00:00
5c1e7259f1
Fix Release-Asserts.
...
llvm-svn: 93346
2010-01-13 20:43:31 +00:00
d681a29ac0
Baby steps towards fixing PR5589. If a class needs a vtable pointer, add one.
...
llvm-svn: 91545
2009-12-16 17:27:20 +00:00
8fbe78f6fc
Update tests to use %clang_cc1 instead of 'clang-cc' or 'clang -cc1'.
...
- This is designed to make it obvious that %clang_cc1 is a "test variable"
which is substituted. It is '%clang_cc1' instead of '%clang -cc1' because it
can be useful to redefine what gets run as 'clang -cc1' (for example, to set
a default target).
llvm-svn: 91446
2009-12-15 20:14:24 +00:00
8174f2c23c
Work-in-progess rewrite of thunks: move thunk generation outside of vtable
...
generation, and make sure we generate thunks when the function is defined
rather than when the vtable is defined.
llvm-svn: 90722
2009-12-06 22:01:30 +00:00
a7a1b7e780
Fixup key function calculations.
...
llvm-svn: 89412
2009-11-20 00:02:19 +00:00
2fb78c0250
More VTT and constructor vtable testcases from recent work.
...
llvm-svn: 88710
2009-11-13 22:12:05 +00:00
3693652378
Add more testcase for construction vtables and VTTs.
...
llvm-svn: 88702
2009-11-13 21:55:26 +00:00
464de23b72
Add some more VTT testcases.
...
llvm-svn: 88699
2009-11-13 21:40:38 +00:00
e56213fc1e
Add a testcase for the recent VTT work.
...
llvm-svn: 88681
2009-11-13 19:36:46 +00:00
88fc7d4202
This falls into the category of stupid pet tricks. I hate to do this,
...
but this is necessary to continue work on virtual vtables. We don't
want to penalize virtual table building testcases, just because
complex virtual conversions don't yet work.
llvm-svn: 88676
2009-11-13 18:53:35 +00:00
d7686ef31c
Unify the codepaths used to verify base and member initializers for explicitly
...
and implicitly defined constructors. This has a number of benefits:
1. Less code.
2. Explicit and implicit constructors get the same diagnostics.
3. The AST explicitly contains constructor calls from implicit default
constructors. This allows handing some cases that previously weren't handled
correctly in IRGen without any additional code. Specifically, implicit default
constructors containing calls to constructors with default arguments are now
handled correctly.
llvm-svn: 86500
2009-11-09 01:05:47 +00:00
34546ce43d
Remove RUN: true lines.
...
llvm-svn: 86432
2009-11-08 01:47:25 +00:00
8b57697954
Eliminate &&s in tests.
...
- 'for i in $(find . -type f); do sed -e 's#\(RUN:.*[^ ]\) *&& *$#\1#g' $i | FileUpdate $i; done', for the curious.
llvm-svn: 86430
2009-11-08 01:45:36 +00:00
cd6f9ed906
Refine the non-virtual this adjustment. Optimize out virtual this
...
adjustments of zero.
llvm-svn: 86300
2009-11-06 23:27:42 +00:00
72431bd9ea
Refine the vcall for a function that is defined in a virtual base
...
class that is overridden in a base that isn't morally virtual.
llvm-svn: 86217
2009-11-06 02:38:24 +00:00
aea4b8a0c3
Convert file over to checking the .ll file for codegen. Also, we
...
speed up this file by not doing twice the checking.
llvm-svn: 86205
2009-11-06 00:18:25 +00:00
b8da7a046d
Refine covariant return value adjustments for thunks when null
...
pointers are returned.
llvm-svn: 86120
2009-11-05 06:12:26 +00:00
098da869a7
Testcase for a recent checkin.
...
llvm-svn: 86118
2009-11-05 05:26:28 +00:00
abcffc3b59
Update.
...
llvm-svn: 86117
2009-11-05 05:01:19 +00:00
b73beb36f5
this test has started failing due to an optimizer change. Clang tests
...
should only look at -O0 IR output not -O3 assembly output. XFAIL it for
now.
llvm-svn: 86029
2009-11-04 16:37:13 +00:00
71609a2874
Split out return adjustments in thunks from this adjustment in thunks
...
so the optimizer can tailcall into the return value adjustment thunk.
This improves codesize for complex hierarchies.
llvm-svn: 85988
2009-11-04 00:53:51 +00:00
f6968a5749
vtable testcase for recent work on vcall/vbase offsets.
...
llvm-svn: 85925
2009-11-03 19:28:52 +00:00
4627132ebc
Refine codegen for covariant thunks that return references.
...
llvm-svn: 85916
2009-11-03 19:03:17 +00:00
77738205e6
Refine return value adjustments for thunks.
...
llvm-svn: 85905
2009-11-03 16:59:27 +00:00
75ce573815
Refine vcall/vbase ordering with vtable construction.
...
llvm-svn: 85677
2009-10-31 20:06:59 +00:00
375faa8dd7
Finish off pure virtual function handling.
...
llvm-svn: 85354
2009-10-28 00:35:46 +00:00
84bc8bda49
Testcase for recent checkin. WIP.
...
llvm-svn: 84123
2009-10-14 18:38:01 +00:00
87876a0053
Refine handling for return value conversions with respect to virtual
...
offsets for covariant thunks.
llvm-svn: 83965
2009-10-13 10:55:21 +00:00
e7a2b48572
Fix http://llvm.org/PR5090 .
...
llvm-svn: 83035
2009-09-29 00:50:50 +00:00
11289f4280
Remove tabs, and whitespace cleanups.
...
llvm-svn: 81346
2009-09-09 15:08:12 +00:00
e73d5ca9a8
Refine vcall offsets. Cleanups. WIP.
...
llvm-svn: 81143
2009-09-07 04:27:52 +00:00
843b78412a
Testcase for recent checkin.
...
llvm-svn: 80725
2009-09-01 22:01:25 +00:00
beefdc8948
iGenerate vcalls as we build up the methods. WIP.
...
llvm-svn: 80405
2009-08-28 23:22:54 +00:00
b414ef6f18
Testcase for an almost recent checkin.
...
llvm-svn: 80189
2009-08-27 01:09:45 +00:00
a0d0e6fcb1
Fixup codegen for static dispatch to a virtual function that was
...
almost correct. :-)
llvm-svn: 80181
2009-08-26 23:38:08 +00:00
a5588bf3ac
Implement virtual dispatch. :-) This is self-consistent with clang,
...
but not yet necessarily perfectly consistent with gcc. Also addressed
Doug and John's comments.
llvm-svn: 80137
2009-08-26 20:46:33 +00:00
458055a890
Revert r80064 since it broke the build.
...
llvm-svn: 80066
2009-08-26 03:30:14 +00:00
fbddfdacdc
Implement virtual dispatch. :-) This is self-consistent with clang, but not yet
...
necessarily perfectly consistent with gcc.
llvm-svn: 80064
2009-08-26 01:54:35 +00:00
Daniel Dunbar