| Commit message (Expand) | Author | Age |
... | |
* | Add AVX2 horizontal add/sub intrinsics. | Craig Topper | 2011-12-21 |
* | Add AVX2 intrinsics for pavg, pblend, and pcmp instructions. Also remove unne... | Craig Topper | 2011-12-20 |
* | More AVX2 intrinsic support including saturating add/sub and palignr. | Craig Topper | 2011-12-19 |
* | Begin adding AVX2 intrinsics. Necessitated increasing the number of bits used... | Craig Topper | 2011-12-19 |
* | Fix _mm_permute_ps and _mm256_permute_ps AVX intrinsics to use "I" (ICE) | Chad Rosier | 2011-12-17 |
* | Revert r146797, which was a partial revert of r146791; It was correct in the | Chad Rosier | 2011-12-17 |
* | Fix _mm256_extractf128_* AVX intrinsics to use "I" (ICE) markings. Fix | Chad Rosier | 2011-12-17 |
* | Partial revert of r146791; vpermilps/vpermilpd instructions accepts ymm/mem/i... | Chad Rosier | 2011-12-17 |
* | Fix _mm256_round_pd, _mm256_round_ps, _mm_permute_pd and _mm256_permute_pd AVX | Chad Rosier | 2011-12-17 |
* | Fix vinsertf128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to | Chad Rosier | 2011-12-16 |
* | Fix vperm2f128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to | Chad Rosier | 2011-12-16 |
* | Fix some additional x86 intrinsics to use "I" (ICE) markings. Fix *mmintrin.... | Eli Friedman | 2011-11-10 |
* | Add "I" (ICE) annotations onto a few more x86 intrinsics. | Eli Friedman | 2011-11-09 |
* | Misc fixes to pcmp*stri. | Eli Friedman | 2011-11-08 |
* | Reorganize builtins to separate out builtins which require MMX registers. No... | Eli Friedman | 2011-07-02 |
* | Remove the 'unaligned load' builtins now that they're no longer used in the *... | Bill Wendling | 2011-05-13 |
* | LLVM doesn't always optimize away the four loads from this: | Bill Wendling | 2011-05-12 |
* | Remove __builtin_ia32_loadup[sd] since clang can represent the actions natively. | Bill Wendling | 2011-04-20 |
* | Add 3DNow! Intrinsics. | Michael J. Spencer | 2011-04-15 |
* | include/clang/Basic/BuiltinsX86.def: __builtin_ia32_crc32**() should be defin... | NAKAMURA Takumi | 2011-03-09 |
* | Change to match 115473. | Chris Lattner | 2010-10-03 |
* | the mmx intrinsic for pshufw should map to the IR intrinsic, not | Chris Lattner | 2010-10-02 |
* | Various builtins a require an integer constant. Not providing | Chris Lattner | 2010-10-01 |
* | Add a comment explaining why the MMX builtins are segregated and what we plan on | Bill Wendling | 2010-09-21 |
* | The builtins __builtin_ia32_paddq and __builtin_ia32_psubq were missing. | Bill Wendling | 2010-09-20 |
* | Remove FIXME. The type is correct. | Bill Wendling | 2010-09-17 |
* | Add a couple of FIXMEs. The types of palignr are different here than in GCC. | Bill Wendling | 2010-09-02 |
* | Reorder the MMX builtins to be in their own ostracized group. | Bill Wendling | 2010-09-02 |
* | Add some MMX builtins to correspond with the intrinsics now accepted by | Bill Wendling | 2010-09-01 |
* | Remove rsqrtps_nr256 and sqrtps_nr256 builtins, at least until we need them | Bruno Cardoso Lopes | 2010-08-11 |
* | Remove 256-bit cast built-ins and make the AVX intrinsic call llvm __builtin_... | Bruno Cardoso Lopes | 2010-08-11 |
* | Remove 256-bit unpack built-ins and make the AVX intrinsic call llvm __builti... | Bruno Cardoso Lopes | 2010-08-11 |
* | Remove 256-bit shuffle built-ins and make the AVX intrinsic call llvm __built... | Bruno Cardoso Lopes | 2010-08-11 |
* | Make replicate intrinsics use shufflevector instead of dup builtins, also rem... | Bruno Cardoso Lopes | 2010-08-10 |
* | Use i32 instead of i8 for AVX dot product intrinsic | Bruno Cardoso Lopes | 2010-08-10 |
* | Consider the last argument of vblend builtin to be i32 instead of i8 | Bruno Cardoso Lopes | 2010-08-10 |
* | We don't want to support built-ins which aren't needed by the intrinsics. Rem... | Bruno Cardoso Lopes | 2010-08-05 |
* | Add more AVX 256-bit intrinsics and test cases for them | Bruno Cardoso Lopes | 2010-08-04 |
* | Support x86 AVX 256-bit instructions built-ins. Right now support all of them... | Bruno Cardoso Lopes | 2010-08-03 |
* | APIs that take different sized arguments than the instruction | Eric Christopher | 2010-07-27 |
* | Rewrite handling of 64-bit palignr intrinsics to be vector shuffles. | Eric Christopher | 2010-04-15 |
* | First start at wmmintrin.h file with Intel AES-NI instructions. | Eric Christopher | 2010-04-01 |
* | Add sse4.2 header and builtin support. | Eric Christopher | 2010-03-20 |
* | Add remaining sse4.1 intrinsics and builtins. | Eric Christopher | 2010-03-15 |
* | Add SSE4 packed integer comparisons and corresponding intrinsics. | Eric Christopher | 2010-03-12 |
* | Add in movntdqa intrinsic for load hint. | Eric Christopher | 2010-03-07 |
* | Add in dot product intrinsics for dpps and dppd. | Eric Christopher | 2010-03-07 |
* | Fix __builtin_ia32_roundss and __builtin_ia32_roundsd definitions. | Eric Christopher | 2010-03-04 |
* | The codegen for these builtins was removed long ago, but their definitions re... | Tanya Lattner | 2010-01-16 |
* | Revert mmx palignr to use an intrinsic, since mmx shuffle patterns are missing. | Nate Begeman | 2009-12-14 |