Commit Graph

228 Commits

Author SHA1 Message Date
Asaf Badouh ffeb624483 [X86][AVX512F] add FP arithmetic intrinsics
add/div/mul/sub include rounding versions


Differential Revision: http://reviews.llvm.org/D11354

llvm-svn: 242790
2015-07-21 15:27:28 +00:00
Elena Demikhovsky c563c2c61a AVX-512: Implemented AVX-512 FMA intrinsics and tests.
by Igor Breger

http://reviews.llvm.org/D10797

llvm-svn: 240928
2015-06-29 09:20:57 +00:00
Asaf Badouh 5a26b25471 minor test fix
llvm-svn: 238924
2015-06-03 13:42:46 +00:00
Elena Demikhovsky 23fccde1b1 AVX-512: Changed CC parameter in "cmp" intrinsic
from i8 to i32 according to the Intel Spec

llvm-svn: 236980
2015-05-11 09:03:41 +00:00
Elena Demikhovsky 35dc8c0944 AVX-512: added intrinsics for KNL and SKX
by Asaf Badouh (asaf.badouh@intel.com)

llvm-svn: 235986
2015-04-28 13:28:01 +00:00
Elena Demikhovsky 29da2fba46 AVX-512: added clang intrinsics for logical and, or xor for 512 bits
by Asaf Badouh (asaf.badouh@intel.com)

llvm-svn: 233794
2015-04-01 06:54:16 +00:00
David Blaikie a953f2825b Update Clang tests to handle explicitly typed load changes in LLVM.
llvm-svn: 230795
2015-02-27 21:19:58 +00:00
Craig Topper 53565c60e7 [X86] Add other flavors of AVX512 cmpps/cmppd intrinsics.
llvm-svn: 227773
2015-02-01 22:27:40 +00:00
Craig Topper 67826a5883 [X86] Rename _mm512_valign_epi64/32 intrinsics to _mm512_alignr_epi64/32 to match Intel docs. Make immediate argument to them an ICE. Fix mask size for the alignd version.
llvm-svn: 227713
2015-02-01 07:35:40 +00:00
Craig Topper 2f25a5a875 [X86] Add more of the AVX512 integer comparision intrinsics. This adds 128 and 256 bit vectors of dwords and qwords.
llvm-svn: 227075
2015-01-26 08:11:49 +00:00
Craig Topper 4cac1c2318 [X86] Add AVX512F integer comparision intrinsics to header file.
llvm-svn: 227067
2015-01-25 23:30:07 +00:00
Adam Nemet f893edeaea [AVX512] Add sub-vector FP extracts
Analogous to AVX2, these need to be implemented as macros to properly
propagate the immediate index operand.

Part of <rdar://problem/17688758>

llvm-svn: 226496
2015-01-19 20:12:05 +00:00
Craig Topper f557b09f14 [x86] Mark that the AVX-512 cmpps/cmppd builtins need an ICE for the comparison immediate. This requires converting to a macro in the header file.
llvm-svn: 226421
2015-01-19 01:18:19 +00:00
Adam Nemet c0cff244fc [AVX512] Add intrinsics for masked aligned FP loads and stores
Part of <rdar://problem/17688758>

llvm-svn: 226298
2015-01-16 18:51:50 +00:00
Adam Nemet d47dec4690 Fix typo in r225922.
llvm-svn: 226297
2015-01-16 18:51:46 +00:00
Adam Nemet 63a951eb1c [AVX512] Add FP unpack intrinsics
These are implemented with __builtin_shufflevector just like AVX.

We have some tests on the LLVM side to assert that these shufflevectors do
indeed generate the corresponding unpck instruction.

Part of <rdar://problem/17688758>

llvm-svn: 225922
2015-01-14 01:31:17 +00:00
Robert Khasanov b9f3a911c9 [AVX512] Added VPCMPEQ intrinisics to headers.
Added tests.

Patch by Maxim Blumenthal <maxim.blumenthal@intel.com>

llvm-svn: 219319
2014-10-08 17:18:13 +00:00
Adam Nemet 2278fcbf0c [AVX512] Add FMA intrinsics
Part of <rdar://problem/17688758>

llvm-svn: 215666
2014-08-14 17:17:57 +00:00
Adam Nemet 4abc07cb75 [AVX512] Add intrinsics for FP scalar broadcasts
Similar approach to the set1 intrinsics is used: implement in terms of vector
initializers and then ensure with an LLVM test that a broadcast is generated
at the end.

Part of <rdar://problem/17688758>

llvm-svn: 215486
2014-08-13 00:29:01 +00:00
Adam Nemet 5bf7baa938 [AVX512] Add intrinsic for valignd/q
Note that similar to palingr, we could further optimize these to emit
shufflevector when the shift count is <=64.  This however does not
change the overall design that unlike palignr we would still need the LLVM
intrinsic corresponding to this intruction to handle the >64 cases.  (palignr
uses the psrldq intrinsic in this case.)

llvm-svn: 214891
2014-08-05 17:28:23 +00:00
Adam Nemet da82bcc4dd [AVX512] Add unaligned FP load intrinsics
Part of <rdar://problem/17688758>

llvm-svn: 214380
2014-07-31 04:00:39 +00:00
Adam Nemet 2db1d2fb32 [AVX512] Add intrinsic for knot
Part of <rdar://problem/17688758>

llvm-svn: 214316
2014-07-30 16:51:27 +00:00
Adam Nemet c871ff95f3 [AVX512] Add some of the FP cast intrinsics
Part of <rdar://problem/17688758>

llvm-svn: 214315
2014-07-30 16:51:24 +00:00
Adam Nemet f42e7a274a [AVX512] Add set1 intrinsics
(Dropped the byte and word variants from the patch.  Turns out these are not
part of AVX512F but only AVX512BW/VL.)

Part of <rdar://problem/17688758>

llvm-svn: 214314
2014-07-30 16:51:22 +00:00
Adam Nemet fce1ad0b99 [AVX512] Add non-masking FP store intrinsics
Part of <rdar://problem/17688758>

llvm-svn: 214099
2014-07-28 17:14:45 +00:00
Adam Nemet a3ebe6214b [AVX512] Add FP add/sub/mul intrinsics
Part of <rdar://problem/17688758>

llvm-svn: 214098
2014-07-28 17:14:42 +00:00
Adam Nemet 062ba618f5 [AVX512] Add CHECK-LABELs to test/CodeGen/avx512f-builtins.c
llvm-svn: 214095
2014-07-28 17:14:36 +00:00
Elena Demikhovsky fcc6df310d AVX-512: Added intrinsics to clang.
The set is small, that what I have right now.
Everybody is welcome to add more.

llvm-svn: 213641
2014-07-22 11:31:39 +00:00