Commit Graph

64 Commits

Author SHA1 Message Date
Simon Pilgrim 5d403f6bf8 [X86][SSE] Auto upgrade PADDS/PSUBS intrinsics to SADD_SAT/SSUB_SAT generic intrinsics (llvm)
This auto upgrades the signed SSE saturated math intrinsics to SADD_SAT/SSUB_SAT generic intrinsics.

Clang counterpart: https://reviews.llvm.org/D55890

Differential Revision: https://reviews.llvm.org/D55894

llvm-svn: 349892
2018-12-21 09:04:14 +00:00
Craig Topper 2909a3d9d0 [X86] Fix a bad bitcast in the load form of vXi16 uniform shift patterns for EVEX encoded instructions.
llvm-svn: 344563
2018-10-15 21:51:32 +00:00
Craig Topper 548e8b5b47 [X86] Add test cases showing failure to fold load into vpsrlw when EVEX encoded instructions are used.
There's a bad bitcast being used in the isel patterns for the vXi16 shift instructions.

llvm-svn: 344562
2018-10-15 21:51:29 +00:00
Craig Topper 125c54ba10 [X86] Disable the peephole pass on avx2-intrinsics-x86.ll and avx512bw-intrinsics.ll to ensure any load folding tests are testing isel not load folding tables.
llvm-svn: 344561
2018-10-15 21:51:26 +00:00
Craig Topper da0e544953 [X86] Regenerate avx2-intrinsics-x86.ll to compress the 32 vs 64 bit mode checks.
llvm-svn: 344560
2018-10-15 21:51:22 +00:00
Tomasz Krupa 86a63889f3 [X86] Lowering addus/subus intrinsics to native IR
Summary: This revision improves previous version (rL330322) which has been reverted due to crashes.

This is the patch that lowers x86 intrinsics to native IR
in order to enable optimizations. The patch also includes folding
of previously missing saturation patterns so that IR emits the same
machine instructions as the intrinsics.

Reviewers: craig.topper, spatel, RKSimon

Reviewed By: craig.topper

Subscribers: mike.dvoretsky, DavidKreitzer, sroland, llvm-commits

Differential Revision: https://reviews.llvm.org/D46179

llvm-svn: 339650
2018-08-14 08:00:56 +00:00
Chandler Carruth 16429acacb [x86] Revert r330322 (& r330323): Lowering x86 adds/addus/subs/subus intrinsics
The LLVM commit introduces a crash in LLVM's instruction selection.

I filed http://llvm.org/PR37260 with the test case.

llvm-svn: 330997
2018-04-26 21:46:01 +00:00
Alexander Ivchenko e8fed1546e Lowering x86 adds/addus/subs/subus intrinsics (llvm part)
This is the patch that lowers x86 intrinsics to native IR
in order to enable optimizations. The patch also includes folding
of previously missing saturation patterns so that IR emits the same
machine instructions as the intrinsics.

Patch by tkrupa

Differential Revision: https://reviews.llvm.org/D44785

llvm-svn: 330322
2018-04-19 12:13:30 +00:00
Craig Topper 254ed028a4 [X86] Remove the pmuldq/pmuldq intrinsics and replace with native IR.
This completes the work started in r329604 and r329605 when we changed clang to no longer use the intrinsics.

We lost some InstCombine SimplifyDemandedBit optimizations through this change as we aren't able to fold 'and', bitcast, shuffle very well.

llvm-svn: 329990
2018-04-13 06:07:18 +00:00
Francis Visoiu Mistrih 25528d6de7 [CodeGen] Unify MBB reference format in both MIR and debug output
As part of the unification of the debug format and the MIR format, print
MBB references as '%bb.5'.

The MIR printer prints the IR name of a MBB only for block definitions.

* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g'
* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g'
* find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g'
* grep -nr 'BB#' and fix

Differential Revision: https://reviews.llvm.org/D40422

llvm-svn: 319665
2017-12-04 17:18:51 +00:00
Simon Pilgrim e131cb0bd5 [X86][AVX2] Regenerate AVX2 intrinsics tests on 32 + 64-bit targets
llvm-svn: 316326
2017-10-23 14:19:46 +00:00
Simon Pilgrim 19d535e75b [X86][SSE] Add support for PACKSS/PACKUS constant folding
Pulled out of D38472

llvm-svn: 314776
2017-10-03 09:41:00 +00:00
Simon Pilgrim 65bde8806f [X86][SSE] Add PACKSS/PACKUS constant folding tests
llvm-svn: 314682
2017-10-02 15:43:26 +00:00
Craig Topper a80949feb5 [X86] Add VPERMPD/VPERMQ and VPERMPS/VPERMD to the execution domain fixing table.
llvm-svn: 313610
2017-09-19 04:39:55 +00:00
Craig Topper f264fcc704 [X86] Remove VPERM2F128/VPERM2I128 intrinsics and autoupgrade to native shuffles.
I've moved the test cases from the InstCombine optimizations to the backend to keep the coverage we had there. It covered every possible immediate so I've preserved the resulting shuffle mask for each of those immediates.

llvm-svn: 313450
2017-09-16 07:36:14 +00:00
Craig Topper 9313df747d [X86] Remove slash in front of a CHECK line in a test.
llvm-svn: 313433
2017-09-16 01:43:21 +00:00
Uriel Korach 5d5da5f531 [X86] [PATCH] [intrinsics] Lowering X86 ABS intrinsics to IR. (llvm)
This patch, together with a matching clang patch (https://reviews.llvm.org/D37694), implements the lowering of X86 ABS intrinsics to IR.

differential revision: https://reviews.llvm.org/D37693.

llvm-svn: 313134
2017-09-13 09:02:36 +00:00
Yael Tsafrir 47668b5e03 [X86] Lower _mm[256|512]_[mask[z]]_avg_epu[8|16] intrinsics to native llvm IR
Differential Revision: https://reviews.llvm.org/D37560

llvm-svn: 313013
2017-09-12 07:50:35 +00:00
Gadi Haber 3ddffced43 [X86][SKX][KNL] Updating several CodeGen tests to use the attr flag instead of mcpu flag
NFC.
 Updated 3 Codegen regression tests to use the -mattr flag instead of the -mcpu flags as follows:
 Instead of -mcpu=skx use -mattr=+avx512f,+avx512bw,+avx512vl,+avx512dq
 Instead of -mcpu=knl use -mattr=+avx512f

Reviewers: delena
Revision: https://reviews.llvm.org/D37674
llvm-svn: 312909
2017-09-11 11:26:20 +00:00
Craig Topper fa82efb50a [X86] Add VBLENDPS/VPBLENDD to the execution domain fixing tables.
llvm-svn: 312449
2017-09-03 17:52:23 +00:00
Craig Topper cb0e74975a [AVX-512] Remove patterns that select vmovdqu8/16 for unmasked loads. Prefer vmovdqa64/vmovdqu64 instead.
These were taking priority over the aligned load instructions since there is no vmovda8/16. I don't think there is really a difference between aligned and unaligned on newer cpus so I don't think it matters which instructions we use.

But with this change we reduce the size of the isel table a little and we allow the aligned information to pass through to the evex->vec pass and produce the same output has avx/avx2 in some cases.

I also generally dislike patterns rooted in a bitcast which these were.

Differential Revision: https://reviews.llvm.org/D35977

llvm-svn: 309589
2017-07-31 17:35:44 +00:00
Michael Zuckerman f66840020c Reverting commit 306414 on behalf of @gadi.haber
llvm-svn: 306532
2017-06-28 11:23:31 +00:00
Gadi Haber 13759a7ed6 Updated and extended the information about each instruction in HSW and SNB to include the following data:
•static latency
•number of uOps from which the instructions consists
•all ports used by the instruction

Reviewers: 
 RKSimon 
 zvi  
aymanmus  
m_zuckerman 

Differential Revision: https://reviews.llvm.org/D33897
 

llvm-svn: 306414
2017-06-27 15:05:13 +00:00
Simon Pilgrim 5a22eaa2bf [X86][SSE] Update MOVNTDQA non-temporal loads to generic implementation (LLVM)
MOVNTDQA non-temporal aligned vector loads can be correctly represented using generic builtin loads, allowing us to remove the existing x86 intrinsics.

Clang companion patch: D31766.

Differential Revision: https://reviews.llvm.org/D31767

llvm-svn: 300325
2017-04-14 15:05:35 +00:00
Amjad Aboud 4f97751798 [X86] Generate VZEROUPPER for Skylake-avx512.
VZEROUPPER should not be issued on Knights Landing (KNL), but on Skylake-avx512 it should be.

Differential Revision: https://reviews.llvm.org/D29874

llvm-svn: 296859
2017-03-03 09:03:24 +00:00
Gadi Haber 19c4fc5e62 This is a large patch for X86 AVX-512 of an optimization for reducing code size by encoding EVEX AVX-512 instructions using the shorter VEX encoding when possible.
There are cases of AVX-512 instructions that have two possible encodings. This is the case with instructions that use vector registers with low indexes of 0 - 15 and do not use the zmm registers or the mask k registers.
The EVEX encoding prefix requires 4 bytes whereas the VEX prefix can take only up to 3 bytes. Consequently, using the VEX encoding for these instructions results in a code size reduction of ~2 bytes even though it is compiled with the AVX-512 features enabled.

Reviewers: Craig Topper, Zvi Rackoover, Elena Demikhovsky 
Differential Revision: https://reviews.llvm.org/D27901

llvm-svn: 290663
2016-12-28 10:12:48 +00:00
Craig Topper 8e7498976a [X86] Fix VEX encoded VPMADDUBSW to not be marked commutable.
This was accidentallly broken in r285515 when we started lowering the intrinsic to an ISD node. Should fix PR31241.

llvm-svn: 288578
2016-12-03 05:35:44 +00:00
Craig Topper da73a09fcd [X86] Add test cases demonstrating where we incorrectly commute VEX VPMADDUSBW due to a bug introduced in r285515.
I believe this is the cause of PR31241.

llvm-svn: 288577
2016-12-03 05:35:38 +00:00
Craig Topper a4a51f1afe [AVX-512] Add -show-mc-encoding to legacy vector intrinsic tests so we can see when VEX or EVEX encoded instructions are being emitted. Make sure the tests all have an avx2 command line and an skx command line.
llvm-svn: 286055
2016-11-06 02:03:58 +00:00
Craig Topper 5c913e84df [AVX512] Use VMOVAPSZ128rr/VMOVAPS256rr for VR128X/VR256X physreg moves when VLX is supported.
Ideally we would use VEX encoded moves instead of EVEX if the high 16 registers aren't referenced, but this a good first step.

llvm-svn: 275763
2016-07-18 06:14:34 +00:00
Igor Breger e59165ca63 [AVX512] [AVX512/AVX][Intrinsics] Fix Variable Bit Shift Right Arithmetic intrinsic lowering.
Differential Revision: http://reviews.llvm.org/D20897

llvm-svn: 273138
2016-06-20 07:05:43 +00:00
Craig Topper 8287fd8abd [X86] Remove SSE/AVX unaligned store intrinsics as clang no longer uses them. Auto upgrade to native unaligned store instructions.
llvm-svn: 271236
2016-05-30 23:15:56 +00:00
Simon Pilgrim 9602d678cb [X86][SSE] (Reapplied) Replace (V)PMOVSX and (V)PMOVZX integer extension intrinsics with generic IR (llvm)
This patch removes the llvm intrinsics VPMOVSX and (V)PMOVZX sign/zero extension intrinsics and auto-upgrades to SEXT/ZEXT calls instead. We already did this for SSE41 PMOVSX sometime ago so much of that implementation can be reused.

Reapplied now that the the companion patch (D20684) removes/auto-upgrade the clang intrinsics has been committed.

Differential Revision: http://reviews.llvm.org/D20686

llvm-svn: 271131
2016-05-28 18:03:41 +00:00
Simon Pilgrim 4642a57fbf Revert: r270973 - [X86][SSE] Replace (V)PMOVSX and (V)PMOVZX integer extension intrinsics with generic IR (llvm)
llvm-svn: 270976
2016-05-27 09:02:25 +00:00
Simon Pilgrim c013e5737b [X86][SSE] Replace (V)PMOVSX and (V)PMOVZX integer extension intrinsics with generic IR (llvm)
This patch removes the llvm intrinsics VPMOVSX and (V)PMOVZX sign/zero extension intrinsics and auto-upgrades to SEXT/ZEXT calls instead. We already did this for SSE41 PMOVSX sometime ago so much of that implementation can be reused.

A companion patch (D20684) removes/auto-upgrade the clang intrinsics.

Differential Revision: http://reviews.llvm.org/D20686

llvm-svn: 270973
2016-05-27 08:49:15 +00:00
Craig Topper 25363178bb [X86] Run the AVX/AVX2 intrinsic tests in AVX512VL mode too just to make sure we don't break any older intrinsics.
llvm-svn: 270183
2016-05-20 05:10:32 +00:00
Simon Pilgrim 46e57fd073 [X86][AVX2] Regenerated intrinsics tests
llvm-svn: 262401
2016-03-01 21:38:41 +00:00
Craig Topper ecae476e4c [X86] int_x86_avx2_permps and X86ISD::VPERMV should take an integer vector for its shuffle indices.
llvm-svn: 254269
2015-11-29 22:53:22 +00:00
Ahmed Bougacha 1a498705e4 [X86] Replace avx2 broadcast intrinsics with native IR.
Since r245605, the clang headers don't use these anymore.
r245165 updated some of the tests already; update the others, add
an autoupgrade, remove the intrinsics, and cleanup the definitions.

Differential Revision: http://reviews.llvm.org/D10555

llvm-svn: 245606
2015-08-20 20:36:19 +00:00
Sanjay Patel 4339abe66f [X86, AVX2] Replace inserti128 and extracti128 intrinsics with generic shuffles
This should complete the job started in r231794 and continued in r232045:
We want to replace as much custom x86 shuffling via intrinsics
as possible because pushing the code down the generic shuffle
optimization path allows for better codegen and less complexity
in LLVM.

AVX2 introduced proper integer variants of the hacked integer insert/extract
C intrinsics that were created for this same functionality with AVX1.

This should complete the removal of insert/extract128 intrinsics.

The Clang precursor patch for this change was checked in at r232109.

llvm-svn: 232120
2015-03-12 23:16:18 +00:00
Quentin Colombet f59b2d034c [X86] Fix a regression introduced by r223641.
The permps and permd instructions have their operands swapped compared to the
intrinsic definition. Therefore, they do not fall into the INTR_TYPE_2OP
category.

I did not create a new category for those two, as they are the only one AFAICT
in that case.

<rdar://problem/20108262>

llvm-svn: 232085
2015-03-12 19:34:12 +00:00
Juergen Ributzka 1f7a17661c Remove 'llvm.x86.avx2.vbroadcasti128' intrinsic.
The intrinsic is no longer generated by the front-end. Remove the intrinsic and
auto-upgrade it to a vector shuffle.

Reviewed by Nadav

This is related to rdar://problem/18742778.

llvm-svn: 231182
2015-03-04 00:13:25 +00:00
Craig Topper b324e43aed [X86] Remove AVX2 and SSE2 pslldq and psrldq intrinsics. We can represent them in IR with vector shuffles now. All their uses have been removed from clang in favor of shuffles.
llvm-svn: 229640
2015-02-18 06:24:44 +00:00
Craig Topper 49df44e2e2 [X86] Remove the multiply by 8 that goes into the shift constant for X86ISD::VSHLDQ and X86ISD::VSRLDQ. This simplifies the pattern matching in isel and allows these nodes to become the patterns embedded in the instruction.
llvm-svn: 229431
2015-02-16 20:52:07 +00:00
Chandler Carruth c491f72e7a [x86] Remove some windows line endings that snuck into the tests here.
Folks on Windows, remember to set up your subversion to strip these when
submitting...

llvm-svn: 225593
2015-01-11 01:36:20 +00:00
Simon Pilgrim a798e9ffdf [X86][SSE] pslldq/psrldq shuffle mask decodes
Patch to provide shuffle decodes and asm comments for the sse pslldq/psrldq SSE2/AVX2 byte shift instructions.

Differential Revision: http://reviews.llvm.org/D5598

llvm-svn: 219738
2014-10-14 22:31:34 +00:00
Chandler Carruth 373b2b1728 [x86] Fix a pretty horrible bug and inconsistency in the x86 asm
parsing (and latent bug in the instruction definitions).

This is effectively a revert of r136287 which tried to address
a specific and narrow case of immediate operands failing to be accepted
by x86 instructions with a pretty heavy hammer: it introduced a new kind
of operand that behaved differently. All of that is removed with this
commit, but the test cases are both preserved and enhanced.

The core problem that r136287 and this commit are trying to handle is
that gas accepts both of the following instructions:

  insertps $192, %xmm0, %xmm1
  insertps $-64, %xmm0, %xmm1

These will encode to the same byte sequence, with the immediate
occupying an 8-bit entry. The first form was fixed by r136287 but that
broke the prior handling of the second form! =[ Ironically, we would
still emit the second form in some cases and then be unable to
re-assemble the output.

The reason why the first instruction failed to be handled is because
prior to r136287 the operands ere marked 'i32i8imm' which forces them to
be sign-extenable. Clearly, that won't work for 192 in a single byte.
However, making thim zero-extended or "unsigned" doesn't really address
the core issue either because it breaks negative immediates. The correct
fix is to make these operands 'i8imm' reflecting that they can be either
signed or unsigned but must be 8-bit immediates. This patch backs out
r136287 and then changes those places as well as some others to use
'i8imm' rather than one of the extended variants.

Naturally, this broke something else. The custom DAG nodes had to be
updated to have a much more accurate type constraint of an i8 node, and
a bunch of Pat immediates needed to be specified as i8 values.

The fallout didn't end there though. We also then ceased to be able to
match the instruction-specific intrinsics to the instructions so
modified. Digging, this is because they too used i32 rather than i8 in
their signature. So I've also switched those intrinsics to i8 arguments
in line with the instructions.

In order to make the intrinsic adjustments of course, I also had to add
auto upgrading for the intrinsics.

I suspect that the intrinsic argument types may have led everything down
this rabbit hole. Pretty happy with the result.

llvm-svn: 217310
2014-09-06 10:00:01 +00:00
Quentin Colombet 6f12ae0d5c [X86] Add broadcast instructions to the table used by ExeDepsFix pass.
Adds the different broadcast instructions to the ReplaceableInstrsAVX2 table.
That way the ExeDepsFix pass can take better decisions when AVX2 broadcasts are
across domain (int <-> float).

In particular, prior to this patch we were generating:
  vpbroadcastd  LCPI1_0(%rip), %ymm2
  vpand %ymm2, %ymm0, %ymm0
  vmaxps  %ymm1, %ymm0, %ymm0 ## <- domain change penalty

Now, we generate the following nice sequence where everything is in the float
domain:
  vbroadcastss  LCPI1_0(%rip), %ymm2
  vandps  %ymm2, %ymm0, %ymm0
  vmaxps  %ymm1, %ymm0, %ymm0

<rdar://problem/16354675>

llvm-svn: 204770
2014-03-26 00:10:22 +00:00
Cameron McInally 45dc489403 Fix AVX2 Gather execution domains.
llvm-svn: 204713
2014-03-25 12:36:38 +00:00
Craig Topper f7755df776 Update GATHER instructions to support 2 read-write operands. Patch from myself and Manman Ren.
llvm-svn: 160110
2012-07-12 06:52:41 +00:00