RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-26 06:22:56 +02:00
Code Issues Projects Releases Wiki Activity
125,996 Commits 4 Branches 5 Tags 704 MiB
3e4a1e477a
Commit Graph

367 Commits

Author SHA1 Message Date
Michael Zuckerman
3e4a1e477a [AVX512] adding PRORQ , PRORD , PRORLVQ and PRORLVD Intrinsics 
Differential Revision: http://reviews.llvm.org/D16052

llvm-svn: 257594
 2016-01-13 12:39:33 +00:00
Michael Zuckerman
412db37229 [AVX512] adding PROLQ and PROLD Intrinsics 
Differential Revision: http://reviews.llvm.org/D16048

llvm-svn: 257523
 2016-01-12 21:19:17 +00:00
Igor Breger
46e273fe48 AVX512: VPMOVAPS/PD and VPMOVUPS/PD (load) intrinsic implementation. 
Differential Revision: http://reviews.llvm.org/D16042

llvm-svn: 257463
 2016-01-12 10:02:32 +00:00
Craig Topper
d62ff1659a [AVX-512] Remove another extra space from the Intel syntax asm strings. 
llvm-svn: 257304
 2016-01-11 01:03:40 +00:00
Craig Topper
d9fb66564c [AVX-512] Remove more superfluous spaces from asm strings. 
llvm-svn: 257301
 2016-01-11 00:44:58 +00:00
Craig Topper
e6ae356ee7 [AVX-512] Remove unused Round and Itinerary from the maskable_cmp multiclasses. They weren't used and there were extra spaces in the asm string to prepare for the concatenations of the round string that wasn't ever used. 
llvm-svn: 257300
 2016-01-11 00:44:56 +00:00
Craig Topper
59a087ed05 [AVX-512] Make spacing between comma and {sae} operand consistent in asm strings. 
llvm-svn: 257299
 2016-01-11 00:44:52 +00:00
Craig Topper
9845f978d1 [AVX-512] Remove superfluous spaces from some asm strings. 
llvm-svn: 257150
 2016-01-08 06:09:20 +00:00
Craig Topper
a899645fbc [AVX512] Add hasSideEffects=0 to kunpck instructions since they lack a pattern in their instructions. 
llvm-svn: 256816
 2016-01-05 07:44:08 +00:00
Asaf Badouh
6fcb80c7ac [X86][AVX512] add fp scalar broadcast intrinsics 
Differential Revision: http://reviews.llvm.org/D15790

llvm-svn: 256489
 2015-12-28 08:09:25 +00:00
Craig Topper
228bc66bfc [AVX512] Remove VEX_LIG from vmovd/vmovq instructions. From what I can tell from the Intel docs these instructions require the L-bit to be 0. 
llvm-svn: 256486
 2015-12-28 06:32:47 +00:00
Craig Topper
a315cd0b1d [AVX512] Fix some places that used FR64 instead of FR64X. 
llvm-svn: 256484
 2015-12-28 06:11:45 +00:00
Craig Topper
cf3121d888 [AVX512] Bring vmovq instructions names into alignment with the AVX and SSE names. Add a missing encoding to disassembler and assembler. 
I believe this also fixes a case where a 64-bit memory form that is documented as being unsupported in 32-bit mode was able to be selected there.

llvm-svn: 256483
 2015-12-28 06:11:42 +00:00
Craig Topper
e4e0592ca3 [AVX512] Remove separate instruction and patterns for lowering ctlz_zero_undef. Change the operation for CTLZ_ZERO_UNDEF to Expand so SelectionDAG will convert them to CTLZ before lowering. 
llvm-svn: 256477
 2015-12-27 21:33:50 +00:00
Craig Topper
ce5014e9fe [AVX512] Remove alternate data type versions of VALIGND, VALIGNQ, VMOVSHDUP and VMOVSLDUP. They don't have any tests and I don't think they can be selected. If they are truly needed they should be implemented with patterns against the normal instructions and not separate instructions. 
llvm-svn: 256475
 2015-12-27 19:45:21 +00:00
Igor Breger
a848a96908 AVX512: Change VPMOVB2M DAG lowering , use CVT2MASK node instead TRUNCATE. 
Fix TRUNCATE lowering vector to vector i1, use LSB and not MSB.
Implement VPMOVB/W/D/Q2M intrinsic.

Differential Revision: http://reviews.llvm.org/D15675

llvm-svn: 256470
 2015-12-27 13:56:16 +00:00
Asaf Badouh
f94cbd0492 [X86][AVX512] change broadcast to use maskable pattern 
Differential Revision: http://reviews.llvm.org/D15786

llvm-svn: 256469
 2015-12-27 12:14:34 +00:00
Craig Topper
c79efd26f5 [AVX-512] Remove alernate integer forms for VPERMILPS and VPERMILPD. There no tests for them and I don't see any way to select them anyway. If they are really needed they should be implemented as patterns and not full fledged instructions. 
llvm-svn: 256462
 2015-12-27 06:55:08 +00:00
Igor Breger
305115c35b AVX512BW: Enable packed word shift for 512bit vector. Enable lowering scalar immidiate shift v64i8 .Fix predicate for AVX1/2 shifts. 
Differential Revision: http://reviews.llvm.org/D15713

llvm-svn: 256324
 2015-12-23 08:06:50 +00:00
Asaf Badouh
d891bbfe44 [X86][AVX512] Add rcp14 and rsqrt14 intrinsics 
Differential Revision: http://reviews.llvm.org/D15414

llvm-svn: 256237
 2015-12-22 11:40:04 +00:00
Elena Demikhovsky
61fc55d5da Type legalizer for masked gather and scatter intrinsics. 
Full type legalizer that works with all vectors length - from 2 to 16, (i32, i64, float, double).

This intrinsic, for example
void @llvm.masked.scatter.v2f32(<2 x float>%data , <2 x float*>%ptrs , i32 align , <2 x i1>%mask )
requires type widening for data and type promotion for mask.

Differential Revision: http://reviews.llvm.org/D13633

llvm-svn: 255629
 2015-12-15 08:40:41 +00:00
Matt Arsenault
fad94dae85 Start replacing vector_extract/vector_insert with extractelt/insertelt 
These are redundant pairs of nodes defined for
INSERT_VECTOR_ELEMENT/EXTRACT_VECTOR_ELEMENT.
insertelement/extractelement are slightly closer to the corresponding
C++ node name, and has stricter type checking so prefer it.

Update targets to only use these nodes where it is trivial to do so.
AArch64, ARM, and Mips all have various type errors on simple replacement,
so they will need work to fix.

Example from AArch64:

def : Pat<(sext_inreg (vector_extract (v16i8 V128:$Rn), VectorIndexB:$idx), i8),
          (i32 (SMOVvi8to32 V128:$Rn, VectorIndexB:$idx))>;

Which is trying to do sext_inreg i8, i8.

llvm-svn: 255359
 2015-12-11 19:20:16 +00:00
Elena Demikhovsky
4e301fd23f AVX-512: Fixed masked load / store instruction selection for KNL. 
Patterns were missing for KNL target for <8 x i32>, <8 x float> masked load/store.

This intrinsic comes with all legal types:
<8 x float> @llvm.masked.load.v8f32(<8 x float>* %addr, i32 align, <8 x i1> %mask, <8 x float> %passThru),
but still requires lowering, because VMASKMOVPS, VMASKMOVDQU32 work with 512-bit vectors only.

All data operands should be widened to 512-bit vector.
The mask operand should be widened to v16i1 with zeroes.

Differential Revision: http://reviews.llvm.org/D15265

llvm-svn: 254909
 2015-12-07 13:39:24 +00:00
Igor Breger
2e5da39635 AVX-512: implement kunpck intrinsics. 
Differential Revision: http://reviews.llvm.org/D14821

llvm-svn: 254908
 2015-12-07 13:25:18 +00:00
Asaf Badouh
903869d4c1 [X86][AVX512] add vmovss/sd missing encoding 
Differential Revision: http://reviews.llvm.org/D14701

llvm-svn: 254875
 2015-12-06 13:26:56 +00:00
Asaf Badouh
d6d08d5567 [X86][AVX512] add comi with Sae 
add builtin_ia32_vcomisd and builtin_ia32_vcomisd

Differential Revision: http://reviews.llvm.org/D14331

llvm-svn: 254493
 2015-12-02 08:17:51 +00:00
Elena Demikhovsky
a67f2cd5e4 AVX-512: fixed asm string of vsqrtss 
(vvsqrtss was generated before)

llvm-svn: 254411
 2015-12-01 12:43:46 +00:00
Craig Topper
32bf88a844 [AVX512] The vpermi2 instructions require an integer vector for the index vector. This is reflected correctly in the intrinsics, but was not refelected in the isel patterns. 
For the floating point types, this requires adding a bitcast to the index vector when its passed through to the output.

llvm-svn: 254277
 2015-11-30 00:13:24 +00:00
Igor Breger
31205fdf6a AVX512:Implemented encoding for the vmovq.s instruction. 
Differential Revision: http://reviews.llvm.org/D14810

llvm-svn: 254248
 2015-11-29 07:41:26 +00:00
Craig Topper
c5257f522e [X86] Pair a NoVLX with HasAVX512 to match the others and remove a unique predicate check in the isel tables. NFC 
llvm-svn: 254191
 2015-11-27 05:44:02 +00:00
Craig Topper
c259757ddf [X86] Now that X86VPermt2 is used in all the avx512_perm_t_sizes just hardcode it into the patterns instead of passing as an argument. NFC 
llvm-svn: 254177
 2015-11-26 20:21:29 +00:00
Craig Topper
f284e70884 [X86] Merge X86VPermt2Fp and X86VPermt2Int back together by weakening them just enough. The SDTCisSameSizeAs introduced in r254138 helps here. 
llvm-svn: 254176
 2015-11-26 20:02:01 +00:00
Elena Demikhovsky
f792042843 AVX-512: Fixed a bug in VPERMT2* intrinsic. 
It was wrong order of operands (from intrinsic to DAG node).
I added more strict type specification for instruction selection.

Differential Revision: http://reviews.llvm.org/D14942

llvm-svn: 254059
 2015-11-25 08:17:56 +00:00
Cong Hou
c0bb26286b [X86] Fix several issues related to X86's psadbw instruction. 
This patch fixes the following issues:

1. Fix the return type of X86psadbw: it should not be the same type of inputs.
   For vNi8 inputs the output should be vMi64, where M = N/8.
2. Fix the return type of int_x86_avx512_psad_bw_512 accordingly.
3. Fix the definiton of PSADBW, VPSADBW, and VPSADBWY accordingly.
4. Adjust the return type when building a DAG node of X86ISD::PSADBW type.
5. Update related tests.


Differential revision: http://reviews.llvm.org/D14897

llvm-svn: 254010
 2015-11-24 19:51:26 +00:00
Elena Demikhovsky
678dc46339 AVX-512: Optimized INSERT_SUBVECTOR for i1 vector types 
ISERT_SUBVECTOR for i1 vectors may be done with shifts, when we insert into the lower part, or into the upper part, on into all-zero vector.
CONCAT_VECTORS uses ISERT_SUBVECTOR.

Differential Revision: http://reviews.llvm.org/D14815

llvm-svn: 253819
 2015-11-22 13:57:38 +00:00
Igor Breger
0a68600909 AVX512: Implemented encoding, intrinsics and DAG lowering for VMOVDDUP instructions. 
Differential Revision: http://reviews.llvm.org/D14702

llvm-svn: 253548
 2015-11-19 08:26:56 +00:00
Igor Breger
fb07c48ef1 AVX512: Implemented encoding for the vmovss.s and vmovsd.s instructions. 
Differential Revision: http://reviews.llvm.org/D14771

llvm-svn: 253547
 2015-11-19 07:58:33 +00:00
Igor Breger
8a3c708d1f AVX512: Implemented encoding for the follow instructions. 
vmovapd.s, vmovaps.s, vmovdqa32.s, vmovdqa64.s, vmovdqu16.s, vmovdqu32.s, vmovdqu64.s, vmovdqu8.s, vmovupd.s, vmovups.s

Differential Revision: http://reviews.llvm.org/D14768

llvm-svn: 253546
 2015-11-19 07:43:43 +00:00
Asaf Badouh
e49f73285d [X86][AVX512CD] add mask broadcast intrinsics 
Differential Revision: http://reviews.llvm.org/D14573

llvm-svn: 253450
 2015-11-18 09:42:45 +00:00
Igor Breger
d09bcb79bc AVX512: Implemented encoding for vpextrw.s instruction. 
Differential Revision: http://reviews.llvm.org/D14766

llvm-svn: 253447
 2015-11-18 08:46:16 +00:00
Igor Breger
06ae954df6 AVX512: Implemented encoding and intrinsics for VMOVSHDUP/VMOVSLDUP instructions. 
Differential Revision: http://reviews.llvm.org/D14322

llvm-svn: 253185
 2015-11-16 07:22:00 +00:00
Igor Breger
02e6595c76 Revert r253160. 
It broke layering violation. Reproducible with BUILD_SHARED_LIBS=ON.

llvm-svn: 253163
 2015-11-15 12:19:11 +00:00
Igor Breger
3ec0d86d6a AVX512: Implemented encoding and intrinsics for VMOVSHDUP/VMOVSLDUP instructions. 
Differential Revision: http://reviews.llvm.org/D14322

llvm-svn: 253160
 2015-11-15 07:23:13 +00:00
Igor Breger
bfb07ae48a AVX512 : Implemented encoding and DAG lowering for VMOVHPS/PD and VMOVLPS/PD instructions. 
Differential Revision: http://reviews.llvm.org/D14492

llvm-svn: 252592
 2015-11-10 07:09:07 +00:00
Asaf Badouh
f3f551dd7e revert rev. 252153 due to build failure on ubuntu 
[X86][AVX512] add comi with Sae

llvm-svn: 252154
 2015-11-05 08:55:54 +00:00
Asaf Badouh
c9c8bfa4c4 [X86][AVX512] add comi with Sae 
add builtin_ia32_vcomisd and builtin_ia32_vcomisd

Differential Revision: http://reviews.llvm.org/D14331

llvm-svn: 252153
 2015-11-05 08:45:06 +00:00
Asaf Badouh
e9eadcdf13 [X86][AVX512] small bugfix in VPBROADCASTM 
VPBROADCASTMW2D and VPBROADCASTMB2Q

Differential Revision: http://reviews.llvm.org/D14335

llvm-svn: 252151
 2015-11-05 08:08:21 +00:00
Igor Breger
207c14b67f AVX512: add encoding tests for vmovq/d instructions. 
llvm-svn: 251903
 2015-11-03 07:30:17 +00:00
Igor Breger
dd070c17bb AVX512: Implemented encoding and intrinsics for VBROADCASTI32x2 and VBROADCASTF32x2 instructions. 
Differential Revision: http://reviews.llvm.org/D14216

llvm-svn: 251781
 2015-11-02 07:39:36 +00:00
Elena Demikhovsky
f42814b247 AVX-512: Optimized SIMD truncate operations for AVX512F set. 
Optimized <8 x i32> to <8 x i16>
<4 x i64> to < 4 x i32>
<16 x i16> to <16 x i8>
All these oprtrations use now AVX512F set (KNL). Before this change it was implemented with AVX2 set.


Differential Revision: http://reviews.llvm.org/D14108

llvm-svn: 251764
 2015-11-01 11:45:47 +00:00