| Commit message (Expand) | Author | Age | Files | Lines |
* | Convert vperm2f128 and vperm2i128 intrinsics back to using llvm intrinsics. U... | Craig Topper | 2012-04-17 | 2 | -28/+4 |
* | Change _mm256_permute4x64_epi64 and _mm256_permute4x64_pd to use builtin_shuf... | Craig Topper | 2012-04-15 | 1 | -2/+6 |
* | Fix the signatures for the _mm256_storeu2_* intrinsics. | Chad Rosier | 2012-04-12 | 1 | -3/+3 |
* | Correctly check argument types for some vector macros in smmintrin.h. Put par... | Craig Topper | 2012-03-30 | 2 | -17/+40 |
* | Add _mm_minpos_epu16 to smmintrin.h. Fixes PR12399. | Craig Topper | 2012-03-30 | 1 | -0/+6 |
* | Fix shuffle vector calculation for mm_permute_ps. Fixes PR 12401. | Craig Topper | 2012-03-30 | 1 | -1/+1 |
* | unwind.h fix for -fvisibility=hidden users. This fixes firefox build in a system | Rafael Espindola | 2012-03-29 | 1 | -1/+13 |
* | [avx] Define the _mm256_loadu2_xxx and _mm256_storeu2_xxx intrinsics. | Chad Rosier | 2012-03-20 | 1 | -0/+67 |
* | * tgmath_logb.patch implements the missing logb function (see C99 standard 7.... | Howard Hinnant | 2012-02-23 | 1 | -3/+20 |
* | Allow linux builds to take advantage of libunwind to get unwind.h if | Jeffrey Yasskin | 2012-02-21 | 1 | -3/+13 |
* | Add 3dNOW intrinsic header to x86intrin.h, conditioned on __3dNOW__ to | Chandler Carruth | 2012-02-20 | 1 | -1/+5 |
* | Remove vperm2f* and vperm2i builtins. Same effect can be achieved with builti... | Craig Topper | 2012-02-08 | 2 | -4/+28 |
* | Remove vpermilp* builtins. Same effect can be achieved with builtin_shuffleve... | Craig Topper | 2012-02-08 | 1 | -4/+16 |
* | Add C11 FLT_TRUE_MIN and friends. <rdar://problem/10812837>. | Eli Friedman | 2012-02-07 | 1 | -0/+11 |
* | Comment mystery code. | Nick Lewycky | 2012-02-04 | 1 | -0/+2 |
* | Make _mm_cmpgt_epi8 immute to -funsigned-char. | Nick Lewycky | 2012-02-03 | 1 | -1/+2 |
* | Back out my heinous hack that tricked the module generation mechanism | Douglas Gregor | 2012-02-02 | 1 | -46/+7 |
* | Split compiler builtin module into "stdlib" builtins and "intrinsic" | Douglas Gregor | 2012-01-31 | 1 | -12/+17 |
* | Remove tgmath.h from the module map for now, because it currently causes a | Douglas Gregor | 2012-01-30 | 1 | -4/+1 |
* | Fix typo spotted by Sebastian. Thanks! | Douglas Gregor | 2012-01-30 | 1 | -1/+1 |
* | Cleanup 3dnow builtin handling. Most of them were already handled by LLVM con... | Craig Topper | 2012-01-30 | 1 | -1/+1 |
* | Introduce TargetInfo::hasFeature() to query various feature names in | Douglas Gregor | 2012-01-30 | 1 | -1/+107 |
* | Just disable the compiler-builtins module test on MSVC for now | Douglas Gregor | 2012-01-29 | 1 | -3/+1 |
* | Teach tgmath.h to only include <complex.h> if it's available. | Douglas Gregor | 2012-01-29 | 1 | -1/+3 |
* | Alternate fix to the modules failures that doesn't require us to tweak tgmath.h | Douglas Gregor | 2012-01-29 | 1 | -2/+0 |
* | If there's no math.h, then tgmath.h should just be empty | Douglas Gregor | 2012-01-29 | 1 | -0/+2 |
* | Introduce a module map for (some of) the compiler-supplied | Douglas Gregor | 2012-01-29 | 3 | -2/+52 |
* | Represent 256-bit unaligned loads natively and remove the builtins. Similar c... | Craig Topper | 2012-01-25 | 1 | -3/+12 |
* | On Darwin, use the system's <unwind.h> whenever it is | Douglas Gregor | 2012-01-24 | 1 | -4/+3 |
* | Fix a typo: _MM_FLUSH_ZERO_OFF has the wrong value. rdar://10716672 | Bob Wilson | 2012-01-23 | 1 | -1/+1 |
* | Extend unwind.h with the ARM unwinder interface. | Evgeniy Stepanov | 2012-01-19 | 1 | -0/+35 |
* | Don't depend on undefined macros being 0, there are options for the | Joerg Sonnenberger | 2012-01-03 | 1 | -1/+2 |
* | clang/lib/Headers/CMakeLists.txt: Unbreak cmake build. | NAKAMURA Takumi | 2011-12-30 | 1 | -0/+1 |
* | Add FMA4 intrinsics. | Craig Topper | 2011-12-30 | 2 | -0/+235 |
* | Remove an accidental change from r147370. Would only break if the new fma4 fl... | Craig Topper | 2011-12-30 | 1 | -4/+0 |
* | Add FMA4 feature flag. Intrinsics coming soon. Also make sse4a feature flag i... | Craig Topper | 2011-12-30 | 1 | -1/+5 |
* | Unbreak cmake build after r147340. | Richard Smith | 2011-12-29 | 1 | -0/+1 |
* | Add popcnt feature flag to match gcc. This flag is implied when sse42 is enab... | Craig Topper | 2011-12-29 | 3 | -15/+53 |
* | clang/lib/Headers/CMakeLists.txt: Unbreak cmake build to add bmi2intrin.h sin... | NAKAMURA Takumi | 2011-12-26 | 1 | -0/+1 |
* | Add BMI2 intrinsics. | Craig Topper | 2011-12-26 | 3 | -0/+83 |
* | lib/Headers/CMakeLists.txt: Fix cmake build since r147263, for two missing he... | NAKAMURA Takumi | 2011-12-25 | 1 | -0/+2 |
* | Add the rest of the BMI intrinsics. | Craig Topper | 2011-12-25 | 1 | -0/+60 |
* | Add intrinsics for lzcnt and tzcnt instructions. | Craig Topper | 2011-12-25 | 4 | -0/+126 |
* | Add BMI, BMI2, and LZCNT feature flags to enable adding intrinsics. | Craig Topper | 2011-12-25 | 1 | -1/+1 |
* | Add last of the AVX2 intrinsics except for gather. | Craig Topper | 2011-12-24 | 1 | -4/+121 |
* | Add AVX2 permute intrinsics. Also add parentheses on some macro arguments in ... | Craig Topper | 2011-12-24 | 3 | -21/+95 |
* | Add AVX2 intrinsics for FP vbroadcast, vbroadcasti128, and vpblendd. | Craig Topper | 2011-12-24 | 1 | -0/+40 |
* | Intrinsics for AVX2 unpack instructions. | Craig Topper | 2011-12-24 | 1 | -0/+48 |
* | More AVX2 intrinsics for shift, psign, some shuffles, and psadbw. | Craig Topper | 2011-12-24 | 1 | -0/+170 |
* | Add AVX2 multiply intrinsics. | Craig Topper | 2011-12-23 | 1 | -0/+42 |