maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
129,400 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

28 Commits

Author SHA1 Message Date
Craig Topper 26e74e50b6 Convert vperm2f128 and vperm2i128 intrinsics back to using llvm intrinsics. Unfortunately, these instructions have behavior that can't be modeled with shuffle vector. 
llvm-svn: 154906
 2012-04-17 05:16:56 +00:00
Chad Rosier 2c5154224b Fix the signatures for the _mm256_storeu2_* intrinsics. 
PR12532

llvm-svn: 154591
 2012-04-12 16:29:08 +00:00
Craig Topper 678a53c350 Fix shuffle vector calculation for mm_permute_ps. Fixes PR 12401. 
llvm-svn: 153724
 2012-03-30 05:09:18 +00:00
Chad Rosier f8df4f4e3b [avx] Define the _mm256_loadu2_xxx and _mm256_storeu2_xxx intrinsics. 
From the Intel Optimization Reference Manual, Section 11.6.2.  When data cannot
be aligned or alignment is not known, 16-byte memory accesses may provide better
performance.
rdar://11076953

llvm-svn: 153091
 2012-03-20 16:40:00 +00:00
Craig Topper e5ea3b0239 Remove vperm2f* and vperm2i builtins. Same effect can be achieved with builtin_shufflevector. 
llvm-svn: 150064
 2012-02-08 07:33:36 +00:00
Craig Topper fec9f8edb7 Remove vpermilp* builtins. Same effect can be achieved with builtin_shufflevector. 
llvm-svn: 150056
 2012-02-08 05:16:54 +00:00
Craig Topper 9e9301a83a Represent 256-bit unaligned loads natively and remove the builtins. Similar change was made for 128-bit versions a while back. 
llvm-svn: 148919
 2012-01-25 04:26:17 +00:00
Craig Topper 9f00948a82 Add AVX2 permute intrinsics. Also add parentheses on some macro arguments in other intrinsic headers. 
llvm-svn: 147241
 2011-12-24 07:55:14 +00:00
Chad Rosier 7caca84ce4 Fix _mm_permute_ps and _mm256_permute_ps AVX intrinsics to use "I" (ICE) 
markings.  Fix avxintrin.h to take them into account.
Part of rdar://10595450

llvm-svn: 146810
 2011-12-17 01:51:05 +00:00
Chad Rosier 93375d5fa5 Revert r146797, which was a partial revert of r146791; It was correct in the 
first place.  The permutevar_* (note the *var*) intrinsics use ymm/mem.

llvm-svn: 146807
 2011-12-17 01:39:56 +00:00
Chad Rosier 0adfe7aa2f Fix _mm256_extractf128_* AVX intrinsics to use "I" (ICE) markings. Fix 
avxintrin.h to take them into account.
Part of rdar://10595450

llvm-svn: 146804
 2011-12-17 01:22:27 +00:00
Chad Rosier 3648646b2b Partial revert of r146791; vpermilps/vpermilpd instructions accepts ymm/mem/imm8. 
llvm-svn: 146797
 2011-12-17 00:50:42 +00:00
Chad Rosier 060d03be1c Fix _mm256_round_pd, _mm256_round_ps, _mm_permute_pd and _mm256_permute_pd AVX 
intrinsics to use "I" (ICE) markings.  Fix avxintrin.h to take them into 
account.
Part of rdar://10595450

llvm-svn: 146791
 2011-12-17 00:15:26 +00:00
Chad Rosier 33d22d8def Fix vinsertf128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to 
take them into account.
rdar://10590282

llvm-svn: 146758
 2011-12-16 21:40:31 +00:00
Chad Rosier 9138fea25e Fix vperm2f128_* AVX intrinsics to use "I" (ICE) markings. Fix avxintrin.h to 
take them into account.
rdar://10576962

llvm-svn: 146757
 2011-12-16 21:07:34 +00:00
Eli Friedman f16beb3942 Fix some additional x86 intrinsics to use "I" (ICE) markings. Fix *mmintrin.h to take them into account. 
<rdar://problem/10341145>

llvm-svn: 144246
 2011-11-10 00:11:13 +00:00
Bob Wilson c9b97cc1da Fix vector macros to correctly check argument types. <rdar://problem/10261670> 
llvm-svn: 143792
 2011-11-05 06:08:06 +00:00
Bruno Cardoso Lopes 7a98a7e681 Fix _mm256_shuffle_ps mask! Example, for mask=203, Instead of: 
<i32 3, i32 2, i32 8, i32 11, i32 3, i32 6, i32 12, i32 15>
generate:
  <i32 3, i32 2, i32 8, i32 11, i32 7, i32 6, i32 12, i32 15>

llvm-svn: 138411
 2011-08-23 23:29:45 +00:00
John McCall 91a528841b Implement the AVX cmp builtins as macros instead of static inlines. 
Patch by Syoyo Fujita!  Reviewed by Chris Lattner!  Checked in by me!

llvm-svn: 128984
 2011-04-06 03:37:51 +00:00
Benjamin Kramer 6f35f3cd80 Disallow direct inclusion of avxintrin.h. Users should include immintrin.h instead. This matches GCC's behavior. 
llvm-svn: 111692
 2010-08-20 23:00:03 +00:00
Bruno Cardoso Lopes 8c333153e0 Fix define inserting a comma :) 
llvm-svn: 110839
 2010-08-11 18:45:43 +00:00
Bruno Cardoso Lopes 65954ffc69 Remove 256-bit cast built-ins and make the AVX intrinsic call llvm __builtin_shufflevector with the appropriate arguments 
llvm-svn: 110771
 2010-08-11 02:14:38 +00:00
Bruno Cardoso Lopes a4f1930b75 Remove 256-bit unpack built-ins and make the AVX intrinsic call llvm __builtin_shufflevector with the appropriate arguments 
llvm-svn: 110768
 2010-08-11 01:43:24 +00:00
Bruno Cardoso Lopes e712a135b7 Remove 256-bit shuffle built-ins and make the AVX intrinsic call llvm __builtin_shufflevector with the appropriate arguments 
llvm-svn: 110766
 2010-08-11 01:17:34 +00:00
Bruno Cardoso Lopes 3d3fc1d075 Make replicate intrinsics use shufflevector instead of dup builtins, also remove the dup builtins 
llvm-svn: 110646
 2010-08-10 02:23:54 +00:00
Bruno Cardoso Lopes 3d19889ca8 Fix AVX 256-bit intrinsics headers by using the right cast type while dealing with logical ops 
llvm-svn: 110389
 2010-08-05 23:04:58 +00:00
Bruno Cardoso Lopes fc2320fd73 Logical AVX instrinsics can be matched directly, no need to use builtins here. 
llvm-svn: 110271
 2010-08-04 22:56:42 +00:00
Bruno Cardoso Lopes 7c4b513a3f Add AVX intrinsics header 
llvm-svn: 110253
 2010-08-04 22:03:36 +00:00