Commits · 03eece728f55b1823645b0196a859241ff9845f2 · Roger Ferrer / llvm-epi · GitLab

Jun 05, 2018
- Reimplement the bittest intrinsic family as builtins with inline asm · 1d9c249d
  Reid Kleckner authored Jun 05, 2018
  1d9c249d
Jun 04, 2018
- Revert r333791 "Cap "voluntary" vector alignment at 16 for all Darwin platforms." · 89fbd551
  Reid Kleckner authored Jun 04, 2018
  89fbd551
- [X86] Avoid passing _mm_undefined* to builtin_shufflevector if we are able to... · 95ed88a1
  Craig Topper authored Jun 04, 2018
  95ed88a1
- [X86] Fix a couple places that were using macro arguments twice when of the... · ae5f0a8a
  Craig Topper authored Jun 04, 2018
  ae5f0a8a
- [X86] Remove superfluous escaped new lines from intrinsic files. · 1359a46c
  Craig Topper authored Jun 03, 2018
  1359a46c
- [X86] Explicitly make the arguments to __slwpcb intrinsic 'void'. · b41c6b85
  Craig Topper authored Jun 03, 2018
  b41c6b85
Jun 03, 2018
- [X86] Replace __builtin_ia32_vbroadcastf128_pd256 and... · 6fb26f93
  Craig Topper authored Jun 03, 2018
  6fb26f93
Jun 01, 2018
- Cap "voluntary" vector alignment at 16 for all Darwin platforms. · 280c6560
  John McCall authored Jun 01, 2018
  280c6560
- [X86] Rewrite avx512vbmi unmasked and maskz macro intrinsics to be wrappers... · d521d16b
  Craig Topper authored Jun 01, 2018
  d521d16b
- [X86] Remove leftover semicolons at end of macros · cad7a5f1
  Martin Storsjö authored Jun 01, 2018
  cad7a5f1
May 31, 2018
- [X86] Make 512-bit unmasked load/store builtins more like their 128/256-bit equivalents. · a6dd2faa
  Craig Topper authored May 31, 2018
  a6dd2faa
- [X86] Fix wrong intrinsic semantic. · f811de48
  Tim Shen authored May 31, 2018
  f811de48
- [X86] Fix some places where macro arguments to intrinsics weren't cast to... · cbf3929b
  Craig Topper authored May 31, 2018
  cbf3929b
- [X86] Remove __extension__ from macro intrinsics when its not needed. · c6338679
  Craig Topper authored May 31, 2018
  c6338679
- [X86] Use C style comments in intrinsic headers for overall consistency. · 73d1d403
  Craig Topper authored May 30, 2018
  73d1d403
May 30, 2018
- [X86] Add __extension__ to a bunch of places in our intrinsic headers that... · 63ec0ea7
  Craig Topper authored May 30, 2018
  63ec0ea7
- [X86] Simplify the implementation of _mm_sqrt_ss, _mm_rcp_ss, and _mm_rsqrt_ss. · c5ec55e9
  Craig Topper authored May 30, 2018
  c5ec55e9
- [X86] Reduce the number of setzero intrinsics to just the set defined by the... · dff5b311
  Craig Topper authored May 30, 2018
  dff5b311
- [X86] Remove 'return' from a bunch of intrinsics that return void and use a... · 819f2a20
  Craig Topper authored May 30, 2018
  819f2a20
- [X86] Lowering FMA intrinsics to native IR (Clang part) · 70d8d510
  Gabor Buella authored May 30, 2018
  70d8d510
- Add missing curly from r333509 · 64fcb049
  Hans Wennborg authored May 30, 2018
  64fcb049
- [X86] Remove masking from the AVX512VNNI builtins. Use a select in IR instead. · f6e79c6d
  Craig Topper authored May 30, 2018
  f6e79c6d
- [X86] Fix the names of a bunch of icelake intrinsics. · 3d9305f2
  Craig Topper authored May 30, 2018
  3d9305f2
May 29, 2018
- [X86] Merge the 3 different flavors of masked vpermi2var/vpermt2var builtins... · 68a272d5
  Craig Topper authored May 29, 2018
  68a272d5
May 26, 2018
- Revert r333347 "[X86] Rewrite the max and min reduction intrinsics to make... · f99532fa
  Craig Topper authored May 26, 2018
  f99532fa
- [X86] Remove mask from avx512ifma builtins. Use a select instruction instead. · 387b1423
  Craig Topper authored May 26, 2018
  387b1423
- [X86] Rewrite the max and min reduction intrinsics to make better use of other... · e091523c
  Craig Topper authored May 26, 2018
  e091523c
May 25, 2018
- [x86] invpcid intrinsic · 078bb99a
  Gabor Buella authored May 25, 2018
  078bb99a
May 24, 2018
- [X86] Fix a bad cast in _mm512_mask_abs_epi32 and _mm512_maskz_abs_epi32. · 26df8c48
  Craig Topper authored May 24, 2018
  26df8c48
May 23, 2018
- [X86] Move the include of clzerointrin.h from immintrin.h back to x86intrin.h. · 3e7d8dfa
  Craig Topper authored May 23, 2018
  3e7d8dfa
- [modules] Mark __wmmintrin_pclmul.h/__wmmintrin_aes.h as textual · 83bdfe5e
  Raphael Isemann authored May 23, 2018
  83bdfe5e
- [X86] Move all Intel defined intrinsic includes into immintrin.h · 664af9bc
  Craig Topper authored May 23, 2018
  664af9bc
- [DOXYGEN] Formatting changes for better intrinsics documentation rendering · 9b412153
  Ekaterina Romanova authored May 23, 2018
  9b412153
- [X86] Undef the vector reduction helper macros when we're done with them. · 9bed2e69
  Craig Topper authored May 23, 2018
  9bed2e69
- [X86] In the floating point max reduction intrinsics, negate infinity before feeding it to set1. · 39e0347e
  Craig Topper authored May 23, 2018
  39e0347e
- [X86] Remove mask argument from more builtins that are handled completely in... · f2043b08
  Craig Topper authored May 23, 2018
  f2043b08
- [X86] As mentioned in post-commit feedback in D47174, move the 128 bit f16c... · 25caca72
  Craig Topper authored May 22, 2018
  25caca72
May 22, 2018
- [X86] Remove mask argument from some builtins that are handled completely in... · 8e3689c0
  Craig Topper authored May 22, 2018
  8e3689c0
- [X86] Another attempt at fixing the intrinsic module map for rr333014. · 99be40c3
  Craig Topper authored May 22, 2018
  99be40c3
- [X86] Add two missing #endif directives to immintrin.h that should have been in r333014. · 1fceff99
  Craig Topper authored May 22, 2018
  1fceff99