Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | ARM: Honor -mfpu= and set __VFP_FP__ and __ARM_NEON__ "correctly". | Daniel Dunbar | 2009-12-21 | 1 | -1/+0 |
| | | | | | | | | - Correctly is in quotes, because we are following what I interpreted as GCC's intent (which diverges from practice, naturally). - Also, fix the arch define for arm1136jf-s. llvm-svn: 91855 | ||||
* | a really old testcase I apparently forgot to 'svn add'. | Chris Lattner | 2009-12-20 | 1 | -0/+33 |
| | | | | llvm-svn: 91800 | ||||
* | ARM: Fix predefines (__ARM_ARCH_..., __REGISTER_PREFIX). | Daniel Dunbar | 2009-12-18 | 1 | -2/+3 |
| | | | | | | | - This should be done leveraging the backend, but I'm a little refactored out. I'll fix it one day, I promise. llvm-svn: 91700 | ||||
* | Update tests to use %clang instead of 'clang', and forcibly disable use of ' | Daniel Dunbar | 2009-12-15 | 8 | -14/+14 |
| | | | | | | | clang ' or ' clang -cc1 ' or ' clang-cc ' in test lines (by substituting them to garbage). llvm-svn: 91460 | ||||
* | Update tests to use %clang_cc1 instead of 'clang-cc' or 'clang -cc1'. | Daniel Dunbar | 2009-12-15 | 112 | -223/+223 |
| | | | | | | | | | - 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 | ||||
* | Make tests use the new clang -cc1 flag. | Fariborz Jahanian | 2009-12-14 | 3 | -3/+3 |
| | | | | llvm-svn: 91303 | ||||
* | this was a couple bugzillas too | Chris Lattner | 2009-12-14 | 1 | -1/+1 |
| | | | | llvm-svn: 91267 | ||||
* | fix rdar://7466570 - Be more bug compatible with GCC when it comes to | Chris Lattner | 2009-12-14 | 1 | -0/+20 |
| | | | | | | | | expanding directives withing macro expansions. This is undefined behavior according to 6.10.3p11, so we might as well be undefined in ways similar to GCC. llvm-svn: 91266 | ||||
* | filecheckize | Chris Lattner | 2009-12-14 | 1 | -5/+4 |
| | | | | llvm-svn: 91265 | ||||
* | Improve test portability; I can't figure out how to get the regexp library to | Daniel Dunbar | 2009-12-09 | 1 | -2/+2 |
| | | | | | | match $ correctly with \r\n, unfortunately. llvm-svn: 90907 | ||||
* | Don't use MS extensions in this test, we expect header include markers. | Daniel Dunbar | 2009-12-08 | 1 | -1/+1 |
| | | | | llvm-svn: 90880 | ||||
* | fix -dM with variadic macros, PR5699 | Chris Lattner | 2009-12-07 | 1 | -0/+9 |
| | | | | llvm-svn: 90735 | ||||
* | rename names for consistency | Chris Lattner | 2009-12-07 | 1 | -11/+10 |
| | | | | llvm-svn: 90734 | ||||
* | filecheckize | Chris Lattner | 2009-12-07 | 1 | -11/+10 |
| | | | | llvm-svn: 90733 | ||||
* | Drop Preprocessor/open-failure test, it breaks running the test suite as root, | Daniel Dunbar | 2009-12-06 | 1 | -11/+0 |
| | | | | | | and I can't figure out how to write it more portably. llvm-svn: 90705 | ||||
* | Unbreak and add test case for r90276, a situation in which getBuffer is ↵ | Daniel Dunbar | 2009-12-06 | 1 | -0/+11 |
| | | | | | | | | expected to fail. Also, update SourceManager.h doxyments for getBuffer() to reflect reality. llvm-svn: 90701 | ||||
* | Use '-FOO' 'BAR' instead of '-FOO=BAR' in tests. | Daniel Dunbar | 2009-11-30 | 1 | -2/+2 |
| | | | | llvm-svn: 90122 | ||||
* | Normalize options to use '-FOO' instead of '--FOO'. | Daniel Dunbar | 2009-11-29 | 1 | -2/+2 |
| | | | | llvm-svn: 90071 | ||||
* | Use '-x' 'foo' instead of '-x=foo'. | Daniel Dunbar | 2009-11-29 | 2 | -10/+10 |
| | | | | llvm-svn: 90069 | ||||
* | Remove unnecessary -fms-extensions=0 from tests (this command line syntax is ↵ | Daniel Dunbar | 2009-11-29 | 3 | -4/+4 |
| | | | | | | going away). llvm-svn: 90066 | ||||
* | clang-cc: Change -fsigned-char=0 to -fno-unsigned-char and pass -pic-level ↵ | Daniel Dunbar | 2009-11-29 | 1 | -4/+4 |
| | | | | | | using separate args. llvm-svn: 90054 | ||||
* | Define __SIG_ATOMIC_WIDTH__ for use in stdint.h. | Ken Dyck | 2009-11-22 | 1 | -0/+11 |
| | | | | llvm-svn: 89597 | ||||
* | Avoid unwanted expansion in macros that paste together INT<n>_C(v) and | Ken Dyck | 2009-11-20 | 1 | -2/+2 |
| | | | | | | UINT<n>_C(v) macros. llvm-svn: 89461 | ||||
* | Avoid unwanted expansion in macros that paste together INT<n>_MIN, INT<n>_MAX, | Ken Dyck | 2009-11-20 | 1 | -15/+15 |
| | | | | | | and UINT<n>_MAX defintions. llvm-svn: 89460 | ||||
* | Avoid unwanted macro expansion in macros that paste together int<n>_t and | Ken Dyck | 2009-11-20 | 1 | -0/+29 |
| | | | | | | uint<n>_t definitions. llvm-svn: 89459 | ||||
* | Define __WCHAR_WIDTH__ for use in stdint.h. | Ken Dyck | 2009-11-19 | 1 | -0/+11 |
| | | | | llvm-svn: 89353 | ||||
* | Parameterize WINT_MIN and WINT_MAX with __WINT_WIDTH__ to support arbitrary | Ken Dyck | 2009-11-19 | 1 | -4/+4 |
| | | | | | | widths. This corrects the values of these definitions for MSP430 and PIC16. llvm-svn: 89350 | ||||
* | Add __WINT_WIDTH__ to paramaterize the limits of WINT_MIN and WINT_MAX in | Ken Dyck | 2009-11-19 | 1 | -0/+11 |
| | | | | | | stdint.h. llvm-svn: 89348 | ||||
* | Add __SIZE_WIDTH__ to eventually replace __SIZE_TYPE__ in stdint.h. | Ken Dyck | 2009-11-19 | 1 | -0/+11 |
| | | | | llvm-svn: 89346 | ||||
* | Restore __INTMAX_TYPE__, __UINTMAX_TYPE__, __PTRDIFF_TYPE__, and | Ken Dyck | 2009-11-19 | 1 | -0/+44 |
| | | | | | | | __INTPTR_TYPE__ as the last is used in the test/CodeGen/const-init.c and all could potentially be in use in the wild. My apologies. llvm-svn: 89345 | ||||
* | Remove __PTRDIFF_TYPE__ as it is no longer needed by stdint.h. It has been | Ken Dyck | 2009-11-19 | 1 | -11/+0 |
| | | | | | | replaced with __PTRDIFF_WIDTH__. llvm-svn: 89344 | ||||
* | Add __PTRDIFF_WIDTH__ macro to eventually replace __PTRDIFF_TYPE__ in stdint.h. | Ken Dyck | 2009-11-19 | 1 | -0/+11 |
| | | | | llvm-svn: 89342 | ||||
* | Remove __INTPTR_TYPE__ as it is no longer needed by stdint.h, which uses | Ken Dyck | 2009-11-19 | 1 | -11/+0 |
| | | | | | | __INTPTR_WIDTH__ instead. llvm-svn: 89340 | ||||
* | Define intptr_t and uintptr_t in terms of their equivalent exact-width types. | Ken Dyck | 2009-11-18 | 1 | -22/+22 |
| | | | | llvm-svn: 89237 | ||||
* | Predefine __INTPTR_WIDTH__ for future use in stdint.h. | Ken Dyck | 2009-11-18 | 1 | -0/+11 |
| | | | | llvm-svn: 89231 | ||||
* | Remove the __INTMAX_TYPE__ and __UINTMAX_TYPE__ built-in macros as they are no | Ken Dyck | 2009-11-18 | 1 | -22/+0 |
| | | | | | | longer used by stdint.h. llvm-svn: 89230 | ||||
* | Define INTMAX_C and UINTMAX_C in terms of the corresponding exact-width | Ken Dyck | 2009-11-18 | 1 | -12/+12 |
| | | | | | | INTn_C and UINTn_C macros. llvm-svn: 89226 | ||||
* | Define INTMAX_MIN, INTMAX_MAX, and UINTMAX_MAX in terms of the limit macros for | Ken Dyck | 2009-11-18 | 1 | -15/+15 |
| | | | | | | their corresponding exact-width type. llvm-svn: 89224 | ||||
* | Define intmax_t and uintmax_t as the [u]intN_t type corresponding to | Ken Dyck | 2009-11-18 | 1 | -22/+22 |
| | | | | | | __INTMAX_WIDTH__. llvm-svn: 89221 | ||||
* | Predefine __INTMAX_WIDTH__ for the future parameterization of INTMAX macros in | Ken Dyck | 2009-11-18 | 1 | -0/+11 |
| | | | | | | stdint.h. llvm-svn: 89203 | ||||
* | Replace (-INT8_C(128)), which uses an illegally out-of-range argument for | Ken Dyck | 2009-11-17 | 1 | -70/+70 |
| | | | | | | | INT8_C, with (-INT8_C(127)-1) in the definition of INT8_MIN. Apply similar changes to the definitions of INT16_MIN and INT24_MIN. llvm-svn: 89120 | ||||
* | Use the INTn_C integer constant macros to generate limit constants with correct | Ken Dyck | 2009-11-17 | 1 | -74/+74 |
| | | | | | | | suffixes. This corrects the suffixes for the limit constants of the 32-bit types on MSP430 and PIC16, and the 64-bit types on PPC64, SystemZ, X86_64. llvm-svn: 89101 | ||||
* | Remove unnecessary parens around the bodies of integer constant macros. C99 | Ken Dyck | 2009-11-17 | 1 | -105/+105 |
| | | | | | | | requires that their arguments be decimal, hex, octal constants---no signs allowed---making the parens unnecessary. llvm-svn: 89095 | ||||
* | Don't #include <stdio.h> when tests don't need it, or use clang instead of ↵ | Daniel Dunbar | 2009-11-17 | 2 | -2/+2 |
| | | | | | | clang-cc when they do. llvm-svn: 89070 | ||||
* | Move -fnext-runtime defaulting to driver (and change clang-cc default to | Daniel Dunbar | 2009-11-17 | 1 | -6/+2 |
| | | | | | | -fnext-runtime), instead of using getDefaultLangOptions. llvm-svn: 89058 | ||||
* | Move char-is-signed defaulting to driver, instead of using | Daniel Dunbar | 2009-11-17 | 1 | -3/+3 |
| | | | | | | getDefaultLangOptions. llvm-svn: 89053 | ||||
* | Parameterize the constant-generating macros in stdint.h with new built-in | Ken Dyck | 2009-11-16 | 2 | -10/+20 |
| | | | | | | | __INTn_C_SUFFIX__ macros that are defined for types with corresponding constant suffixes (i.e. long and long long). llvm-svn: 88914 | ||||
* | Generalize stdint.h for non-8-bit-multiple types, patch by | Chris Lattner | 2009-11-12 | 2 | -36/+36 |
| | | | | | | | | | | Ken Dyck! "This adds definitions for types of 8-bit multiples from 8 to 64 to stdint.h and rationalizes the selection of types for the exact-width definitions in InitPreprocessor.cpp." llvm-svn: 86977 | ||||
* | do not store wchar/char16/char32/intmax width/alignment info | Chris Lattner | 2009-11-12 | 2 | -6/+6 |
| | | | | | | | into TargetInfo, just derive this based on the underlying type. This prevents them from getting out of synch, patch by Ken Dyck! llvm-svn: 86976 | ||||
* | Remove RUN: true lines. | Daniel Dunbar | 2009-11-08 | 5 | -5/+0 |
| | | | | llvm-svn: 86432 |