- 31ceea0 Add BMI, BMI2, and LZCNT feature flags to enable adding intrinsics. by Craig Topper · 13 years ago
- 5cbd751 Add last of the AVX2 intrinsics except for gather. by Craig Topper · 13 years ago
- 34a1da4 Add AVX2 permute intrinsics. Also add parentheses on some macro arguments in other intrinsic headers. by Craig Topper · 13 years ago
- ee9b41d Add AVX2 intrinsics for FP vbroadcast, vbroadcasti128, and vpblendd. by Craig Topper · 13 years ago
- 7f16caa Intrinsics for AVX2 unpack instructions. by Craig Topper · 13 years ago
- cbe627b More AVX2 intrinsics for shift, psign, some shuffles, and psadbw. by Craig Topper · 13 years ago
- 28a324a Add AVX2 multiply intrinsics. by Craig Topper · 13 years ago
- 231f793 Add AVX2 intrinsics for max, min, sign extend, and zero extend. by Craig Topper · 13 years ago
- 4a4f25a Add a few more AVX2 intrinsics and fix the type strings on a couple SSE intrinsics. by Craig Topper · 13 years ago
- 318e460 Add AVX2 horizontal add/sub intrinsics. by Craig Topper · 13 years ago
- 4c07c5d Add AVX2 intrinsics for pavg, pblend, and pcmp instructions. Also remove unneeded builtins for SSE pcmp. Change SSE pcmpeqq and pcmpgtq to not use builtins and just use vector == and >. by Craig Topper · 13 years ago
- 735ceaa Add AVX2 intrinsics for and, andn, or, and xor. by Craig Topper · 13 years ago
- 9c2ffd8 More AVX2 intrinsic support including saturating add/sub and palignr. by Craig Topper · 13 years ago
- 925be54 Begin adding AVX2 intrinsics. Necessitated increasing the number of bits used to store builtinID when serializing identifier table. by Craig Topper · 13 years ago
- d7dd775 Fix _mm_permute_ps and _mm256_permute_ps AVX intrinsics to use "I" (ICE) by Chad Rosier · 13 years ago
- c17f88e Revert r146797, which was a partial revert of r146791; It was correct in the by Chad Rosier · 13 years ago
- 1e4faf5 Fix _mm256_extractf128_* AVX intrinsics to use "I" (ICE) markings. Fix by Chad Rosier · 13 years ago
- 1978087 Partial revert of r146791; vpermilps/vpermilpd instructions accepts ymm/mem/imm8. by Chad Rosier · 13 years ago
- b8786c4 Fix _mm256_round_pd, _mm256_round_ps, _mm_permute_pd and _mm256_permute_pd AVX by Chad Rosier · 13 years ago
- b95ddf1 Fix vinsertf128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to by Chad Rosier · 13 years ago
- c5cda11 Fix vperm2f128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to by Chad Rosier · 13 years ago
- 0d57ca1 Fix obvious error in _mm_test_all_zeros. PR11565. Patch by Mathias Gaunard! by Bob Wilson · 13 years ago
- 4b45c11 Fix a blatant typo or cut/paste-o reported by users of this header. by Chandler Carruth · 13 years ago
- 9b7568d Use default visibility in the the symbols declared in unwind.h. This matches by Rafael Espindola · 13 years ago
- d85c1e9 Add a minimal unwind.h that knows how to forward to the system one in systems by Rafael Espindola · 13 years ago
- dd023bc Headers: wmmintrin.h only needs xmmintrin.h. by Daniel Dunbar · 13 years ago
- 82e11cd Install cpuid.h when building with cmake too. by Rafael Espindola · 13 years ago
- 6d387ae Fix comment. by Rafael Espindola · 13 years ago
- 1376ba9 Error on non x86 architectures. by Rafael Espindola · 13 years ago
- 7f16d70 Fix file name in comments. by Rafael Espindola · 13 years ago
- b816276 Add the minimum implementation of cpuid.h. This works on "modern" intel cpus by Rafael Espindola · 13 years ago
- 3472089 Fix some additional x86 intrinsics to use "I" (ICE) markings. Fix *mmintrin.h to take them into account. by Eli Friedman · 13 years ago
- 355130f Misc fixes to pcmp*stri. by Eli Friedman · 13 years ago
- 32bae37 Fix vector macros to correctly check argument types. <rdar://problem/10261670> by Bob Wilson · 13 years ago
- 8052a4f Add _mm_comige_sd to emmintrin.h, since I apparently forgot to do this in r138769. by Eli Friedman · 13 years ago
- 6ee5b93 Clang-side build system infrastructure for multiple tblgens. by Peter Collingbourne · 13 years ago
- 82d0b0a Add support for alignment-specifiers in C1X and C++11, remove by Peter Collingbourne · 13 years ago
- 7c06f6b Tweak *mmintrin.h so that they don't make any bad assumptions about alignment (which probably has little effect in practice, but better to get it right). Make the load in _mm_loadh_pi and _mm_loadl_pi a single LLVM IR instruction to make optimizing easier for CodeGen. by Eli Friedman · 13 years ago
- e02e5e2 Remove WCHAR_MIN and WCHAR_MAX from limits.h. According to posix and c99 by Eric Christopher · 13 years ago
- ef534ce Add missing function _mm_ucomige_sd to emmintrin.h. PR10803. by Eli Friedman · 13 years ago
- 426344d Fix _mm256_shuffle_ps mask! Example, for mask=203, Instead of: by Bruno Cardoso Lopes · 13 years ago
- 725fb0e http://llvm.org/bugs/show_bug.cgi?id=10472 by Howard Hinnant · 13 years ago
- 22de49c Fix typo. by Nick Lewycky · 13 years ago
- 2f5127e Implement a __WCHAR_UNSIGNED__ macro and use it to include WCHAR_MIN and by Sean Hunt · 13 years ago
- 2ac5321 lib/Headers/mm_malloc.h: Use __mingw_aligned_malloc() in _mm_malloc() on mingw. by NAKAMURA Takumi · 13 years ago
- 5254c26 Teach Clang's <float.h> to also include MinGW's <float.h>, which provides additional system definitions, from Ruben Van Boxem by Douglas Gregor · 13 years ago
- 6fe6bac Define va_copy when in C++0x mode; C++0x picked it up from C99. by Douglas Gregor · 13 years ago
- 8e3ec9c Add 'may_alias' attribute. Noticed by Eli. by Bill Wendling · 13 years ago
- eed92a1 Represent the unaligned loads natively. These are converted into a call to the by Bill Wendling · 13 years ago
- 0c96430 LLVM doesn't always optimize away the four loads from this: by Bill Wendling · 13 years ago
- 4d37583 PR9866: Fix the implementation of _mm_loadl_pd and _mm_loadh_pd to not make by Eli Friedman · 13 years ago
- 83a401b PR9849: Fix _mm_setr_pi32 and friends to actually work correctly. They broke with the MMX rewrite a while back. by Eli Friedman · 13 years ago
- 277d1e1 Some small improvements to the builtin (-ffreestanding) stdint.h; in by Eli Friedman · 13 years ago
- 85e59d7 don't use compound literals in MM macros, since they will be instantiated by Chris Lattner · 13 years ago
- 1cfeefd PR9772: Fix the definition of WINT_MIN and WINT_MAX on Linux -ffreestanding. by Eli Friedman · 13 years ago
- 408d5d1 Add mm3dnow.h. by Michael J. Spencer · 14 years ago
- fc8f0e1 fix a bunch of comment typos found by codespell. Patch by by Chris Lattner · 14 years ago
- bae20d0 Remove comment that snuck in there. by Bill Wendling · 14 years ago
- 60cb5e9 Just use a native "load" instead of translating the builtin later. Clang can by Bill Wendling · 14 years ago
- d688bc0 Implement the AVX cmp builtins as macros instead of static inlines. by John McCall · 14 years ago
- 8da6bca Add '#ifndef _PTRDIFF_T' guard around definition of ptrdiff_t. Fixes <rdar://problem/9210154>. by Ted Kremenek · 14 years ago
- f0a6475 lib/Headers/mm_malloc.h: On Windows, we can expect _mm_malloc would be provided as macro by <malloc.h>. by NAKAMURA Takumi · 14 years ago
- be7025e CMake: updated list of installable header files. PR9321. by Oscar Fuentes · 14 years ago
- a3f787c Put targets on folders, if the IDE supports the feature. by Oscar Fuentes · 14 years ago
- c8da1ec New function for tablegenning: clang_tablegen. by Oscar Fuentes · 14 years ago
- 64ce733 Optimized IR for vec_splat by Anton Yartsev · 14 years ago
- 7acb953 Undo part of my previous commit to mm_malloc.h, going back to the use of by Chandler Carruth · 14 years ago
- e19df18 turned pointers into pointers to const in function parameters in all functions/builtins accepting pointers to a const-qualified type according to PIM and "Language Extensions for CBEA" by Anton Yartsev · 14 years ago
- ac21a21 Futher reduce the includes of our builtin headers, and teach limits.h to avoid by Chandler Carruth · 14 years ago
- 105716e Fix CMake installation of arm_neon.h by Douglas Gregor · 14 years ago
- 51f56fc lib/Headers/stddef.h: wint_t should be defined whenever <stddef.h> is included with __need_wint_t. by NAKAMURA Takumi · 14 years ago
- 87a34fd From scratch rewrite of mm_malloc.h. by Eric Christopher · 14 years ago
- 44270d6 support for AltiVec extensions from the Cell architecture by Anton Yartsev · 14 years ago
- d1e6fdb Eliminate CIndexer::getClangPath(), since libclang no longer depends by Douglas Gregor · 14 years ago
- 6999339 the mmx intrinsic for pshufw should map to the IR intrinsic, not by Chris Lattner · 14 years ago
- fcb0b25 __builtin_ia32_psrldqi128 too by Chris Lattner · 14 years ago
- 8a72034 the second argument to __builtin_ia32_pslldqi128 must be an immediate, by Chris Lattner · 14 years ago
- d47e262 Clang part of MMX rewrite (goes with 115243). by Dale Johannesen · 14 years ago
- 593770b Define _Bool, bool, true, and false macros in <stdbool.h> when we're by Douglas Gregor · 14 years ago
- 28cab38 Accidentally committed some temporary changes on my branch when reverting patches. by Bill Wendling · 14 years ago
- 2a674e8 Temporarily revert 114929 114925 114924 114921. It looked like they (or at least by Bill Wendling · 14 years ago
- 3ed3272 formatted everything to fit within 80 columns by Anton Yartsev · 14 years ago
- 6d6370e fix PR7192 by defining wchar_t in a more conventional way. The by Chris Lattner · 14 years ago
- 551f37c fix incorrect MM_HINT_ definitions, PR8011 by Chris Lattner · 14 years ago
- faf9404 Move some type defines from smmintrin.h to emmintrin.h to match where by Eric Christopher · 14 years ago
- b764956 Add x86intrin.h which is generic x86 intrinsics for more than just Intel. Thus by Nick Lewycky · 14 years ago
- 01b57e3 Disallow direct inclusion of avxintrin.h. Users should include immintrin.h instead. This matches GCC's behavior. by Benjamin Kramer · 14 years ago
- 033b7b3 Add immintrin meta header. by Benjamin Kramer · 14 years ago
- 3a70f86 alphabeticalize by Chris Lattner · 14 years ago
- 46c25ef hopefully unbreak the msvc buildbot. by Chris Lattner · 14 years ago
- 0930b6e Fix header comments. by Benjamin Kramer · 14 years ago
- d6b84b9 fix some vector extractions to return properly zero extended values by Chris Lattner · 14 years ago
- a4f235b support for predicates with bool/pixel arguments by Anton Yartsev · 14 years ago
- a2fc0f5 support for the rest of AltiVec functions with bool/pixel arguments and return values (except predicates) by Anton Yartsev · 14 years ago
- f54dbfd support for vec_perm and all dependent functions (vec_mergeh, vec_mergel, vec_pack, vec_sld, vec_splat) with bool/pixel arguments and return values by Anton Yartsev · 14 years ago
- 05e3555 support for vec_add, vec_adds, vec_and, vec_andc with bool arguments by Anton Yartsev · 14 years ago
- a816ec8 first test commit by Anton Yartsev · 14 years ago
- 70141c2 Fix define inserting a comma :) by Bruno Cardoso Lopes · 14 years ago
- 7fc3702 Remove 256-bit cast built-ins and make the AVX intrinsic call llvm __builtin_shufflevector with the appropriate arguments by Bruno Cardoso Lopes · 14 years ago
- f0e96c9 Remove 256-bit unpack built-ins and make the AVX intrinsic call llvm __builtin_shufflevector with the appropriate arguments by Bruno Cardoso Lopes · 14 years ago