| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | _mm_xor_ps does a xor not a nxor. The other 'xor' builtins look fine, | Chris Lattner | 2010-01-07 | 1 | -1/+1 |
| | | | | | | | but this one is wrong. Thanks to Tanya for noticing this. llvm-svn: 92881 | ||||
| * | Revert mmx palignr to use an intrinsic, since mmx shuffle patterns are missing. | Nate Begeman | 2009-12-14 | 1 | -1/+1 |
| | | | | | llvm-svn: 91269 | ||||
| * | Support x86's PALIGNR instruction without the use of a palignr intrinsic. | Nate Begeman | 2009-12-14 | 1 | -2/+2 |
| | | | | | llvm-svn: 91264 | ||||
| * | minimal fix for PR5743 | Chris Lattner | 2009-12-10 | 1 | -2/+2 |
| | | | | | llvm-svn: 91032 | ||||
| * | Pick up MB_LEN_MAX as defined by the system <limits.h>, when it's provided there | Douglas Gregor | 2009-12-08 | 1 | -1/+0 |
| | | | | | llvm-svn: 90879 | ||||
| * | Define SIG_ATOMIC_MIN and SIG_ATOMIC_MAX in terms of __SIG_ATOMIC_WIDTH__. | Ken Dyck | 2009-11-22 | 1 | -2/+2 |
| | | | | | llvm-svn: 89598 | ||||
| * | Avoid unwanted expansion in macros that paste together INT<n>_C(v) and | Ken Dyck | 2009-11-20 | 1 | -3/+5 |
| | | | | | | | 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 | -13/+16 |
| | | | | | | | 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 | -4/+7 |
| | | | | | | | uint<n>_t definitions. llvm-svn: 89459 | ||||
| * | Define WCHAR_MIN and WCHAR_MAX in terms of __WCHAR_WIDTH__ for consistency with | Ken Dyck | 2009-11-19 | 1 | -2/+2 |
| | | | | | | | other limit macros. llvm-svn: 89355 | ||||
| * | Parameterize WINT_MIN and WINT_MAX with __WINT_WIDTH__ to support arbitrary | Ken Dyck | 2009-11-19 | 1 | -2/+2 |
| | | | | | | | widths. This corrects the values of these definitions for MSP430 and PIC16. llvm-svn: 89350 | ||||
| * | Construct definition of SIZE_MAX from __SIZE_WIDTH__ to support targets of | Ken Dyck | 2009-11-19 | 1 | -16/+1 |
| | | | | | | | arbitrary widths. llvm-svn: 89347 | ||||
| * | Construct the macro body of PTRDIFF_MAX and PTRDIFF_MIN from __PTRDIFF_WIDTH__. | Ken Dyck | 2009-11-19 | 1 | -6/+2 |
| | | | | | llvm-svn: 89343 | ||||
| * | Construct INTPTR_MIN, INTPTR_MAX, and UINTPTR_MAX from the exact-width limit | Ken Dyck | 2009-11-18 | 1 | -9/+4 |
| | | | | | | | macros corresponding to __INTPTR_WIDTH__. llvm-svn: 89239 | ||||
| * | Define intptr_t and uintptr_t in terms of their equivalent exact-width types. | Ken Dyck | 2009-11-18 | 1 | -4/+5 |
| | | | | | llvm-svn: 89237 | ||||
| * | Define INTMAX_C and UINTMAX_C in terms of the corresponding exact-width | Ken Dyck | 2009-11-18 | 1 | -2/+2 |
| | | | | | | | 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 | -3/+3 |
| | | | | | | | 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 | -2/+4 |
| | | | | | | | __INTMAX_WIDTH__. llvm-svn: 89221 | ||||
| * | Replace (-INT8_C(128)), which uses an illegally out-of-range argument for | Ken Dyck | 2009-11-17 | 1 | -6/+3 |
| | | | | | | | | 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 | -24/+27 |
| | | | | | | | | 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 | -20/+20 |
| | | | | | | | | requires that their arguments be decimal, hex, octal constants---no signs allowed---making the parens unnecessary. llvm-svn: 89095 | ||||
| * | Parameterize the constant-generating macros in stdint.h with new built-in | Ken Dyck | 2009-11-16 | 1 | -8/+0 |
| | | | | | | | | __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 | 1 | -96/+523 |
| | | | | | | | | | | | 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 | ||||
| * | A simple reordering of the definitions in stdint.h and | Chris Lattner | 2009-11-04 | 1 | -75/+83 |
| | | | | | | | introduces no new function changes. Patch by Ken Dyck! llvm-svn: 86062 | ||||
| * | Added __has_include and __has_include_next. | John Thompson | 2009-11-02 | 1 | -1/+2 |
| | | | | | llvm-svn: 85834 | ||||
| * | CMake: Respect LLVM_LIBDIR_SUFFIX for clang-specific headers under | Oscar Fuentes | 2009-10-27 | 1 | -1/+1 |
| | | | | | | | | | ${libdir}/clang Patch by Ingmar Vanhassel! llvm-svn: 85308 | ||||
| * | Make our char vector types not be explicitly signed to match GCC and to fix ↵ | Anders Carlsson | 2009-09-18 | 2 | -2/+2 |
| | | | | | | | compilation with C++ and -fno-lax-vector-conversions llvm-svn: 82254 | ||||
| * | Fix PR4923. | Anders Carlsson | 2009-09-18 | 1 | -2/+14 |
| | | | | | | | Fix error in _mm_set_pd/_mm_setr_pd and add _mm_set_epi64x/_mm_set1_epi64x. Patch by Laurent Morichetti! llvm-svn: 82228 | ||||
| * | Collapse more clang version numbers down into fewer places. | Mike Stump | 2009-09-16 | 1 | -4/+4 |
| | | | | | llvm-svn: 81983 | ||||
| * | Back to 1.1 we go. | Mike Stump | 2009-09-15 | 1 | -2/+2 |
| | | | | | llvm-svn: 81944 | ||||
| * | Remove tabs, and whitespace cleanups. | Mike Stump | 2009-09-09 | 1 | -1/+1 |
| | | | | | llvm-svn: 81346 | ||||
| * | CMake: Improve installation of Clang | Douglas Gregor | 2009-08-23 | 1 | -4/+3 |
| | | | | | | | | | - Install clang-cc into libexec - Install headers into lib/clang/<version>/include - Don't install other clang-based tools (clang-wpa, clang-index, etc.) llvm-svn: 79827 | ||||
| * | Switch some functions from using x86 builtins to using vector | Eli Friedman | 2009-07-22 | 2 | -17/+17 |
| | | | | | | | operations. llvm-svn: 76753 | ||||
| * | Make sure install Clang headers when building clang-cc | Douglas Gregor | 2009-06-25 | 1 | -1/+1 |
| | | | | | llvm-svn: 74163 | ||||
| * | Update Clang to include the InitializeAllTargets and | Douglas Gregor | 2009-06-16 | 1 | -1/+6 |
| | | | | | | | | InitializeAllAsmPrinters LLVM headers. Also includes some minor fixes for the CMake-based build with Xcode. llvm-svn: 73544 | ||||
| * | Following gcc, hide the hack to include the SSE2 intrinsics from | Eli Friedman | 2009-06-11 | 1 | -0/+3 |
| | | | | | | | xmmintrin.h in an ifdef. llvm-svn: 73200 | ||||
| * | Remove a few more vector builtins. | Eli Friedman | 2009-06-07 | 1 | -1/+1 |
| | | | | | llvm-svn: 73022 | ||||
| * | xmmintrin needs to include emmintrin, Darwin system headers seem to depend on it | Daniel Dunbar | 2009-06-07 | 1 | -0/+2 |
| | | | | | | | defining m128[id], at least. llvm-svn: 73021 | ||||
| * | Now that LLVM CodeGen can handle the generic variations a bit better, | Eli Friedman | 2009-06-07 | 1 | -8/+5 |
| | | | | | | | get rid of a few more clang vector builtins. llvm-svn: 73015 | ||||
| * | CMake: Install Clang's headers into the right place in the build tree, for ↵ | Douglas Gregor | 2009-06-07 | 1 | -7/+16 |
| | | | | | | | regression testing llvm-svn: 73014 | ||||
| * | Replace more calls to builtins with generic code. | Eli Friedman | 2009-06-06 | 2 | -8/+27 |
| | | | | | llvm-svn: 72995 | ||||
| * | Fix obvious typo. | Eli Friedman | 2009-06-06 | 1 | -3/+3 |
| | | | | | llvm-svn: 72994 | ||||
| * | Fix some casts to work without -flax-vector-conversions. | Eli Friedman | 2009-06-06 | 2 | -6/+6 |
| | | | | | llvm-svn: 72981 | ||||
| * | Misc fixes to MMX/SSE intrinsics: a few small bug fixes, and getting rid | Eli Friedman | 2009-06-06 | 3 | -46/+67 |
| | | | | | | | of calls to builtins for constructs which can be expressed directly. llvm-svn: 72979 | ||||
| * | Add aliases for a couple of SSE intrinsics. Patch by Ed Schouten. | Eli Friedman | 2009-06-02 | 2 | -0/+4 |
| | | | | | llvm-svn: 72717 | ||||
| * | Add 'cmp' SSE builtins and get rid of a bunch of other builtins. | Anders Carlsson | 2009-05-18 | 2 | -48/+48 |
| | | | | | llvm-svn: 72032 | ||||
| * | Fix for PR3841: follow gcc's example and fall back to the system | Eli Friedman | 2009-05-03 | 1 | -3/+11 |
| | | | | | | | | | stdint.h unless we are freestanding. Any suggestions here are welcome. llvm-svn: 70806 | ||||
| * | Fix tyop in SSSE3 header (6808876). | Anders Carlsson | 2009-04-20 | 1 | -2/+2 |
| | | | | | llvm-svn: 69623 | ||||
| * | glibc plays some weird games with multiple different definitions of | Chris Lattner | 2009-04-18 | 1 | -3/+12 |
| | | | | | | | | | int8_t and games it with strange *_defined macros. Emulate its weirdness for better compatibility with linux etc. Problem pointed out by anders johnson. llvm-svn: 69458 | ||||
| * | fix misspelt attribute. | Chris Lattner | 2009-04-17 | 1 | -2/+2 |
| | | | | | llvm-svn: 69362 | ||||

