The root cause of reverting was fixed - PR33514.
Summary:
The patch makes instruction count the highest priority for
LSR solution for X86 (previously registers had highest priority).
Reviewers: qcolombet
Differential Revision: http://reviews.llvm.org/D30562
From: Evgeny Stupachenko <evstupac@gmail.com>
<evgeny.v.stupachenko@intel.com>
llvm-svn: 310289
Summary:
All instructions with the DPP modifier may not write to certain lanes of
the output if bound_ctrl=1 is set or any bits in bank_mask or row_mask
aren't set, so the destination register may be both defined and modified.
The right way to handle this is to add a constraint that the destination
register is the same as one of the inputs. We could tie the destination
to the first source, but that would be too restrictive for some use-cases
where we want the destination to be some other value before the
instruction executes. Instead, add a fake "old" source and tie it to the
destination. Effectively, the "old" source defines what value unwritten
lanes will get. We'll expose this functionality to users with a new
intrinsic later.
Also, we want to use DPP instructions for computing derivatives, which
means we need to set WQM for them. We also need to enable the entire
wavefront when using DPP intrinsics to implement nonuniform subgroup
reductions, since otherwise we'll get incorrect results in some cases.
To accomodate this, add a new operand to all DPP instructions which will
be interpreted by the SI WQM pass. This will be exposed with a new
intrinsic later. We'll also add support for Whole Wavefront Mode later.
I also fixed llvm.amdgcn.mov.dpp to overwrite the source and fixed up
the test. However, I could also keep the old behavior (where lanes that
aren't written are undefined) if people want it.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34716
llvm-svn: 310283
X86SubVBroadcast is for memory subvector broadcasts, but we must test that it handles all cases without the load as well just in case.
This was noticed while I was triaging the test cases from PR34041.
llvm-svn: 310268
Try to avoid mutually exclusive features. Don't use
a real default GPU, and use a fake "generic". The goal
is to make it easier to see which set of features are
incompatible between feature strings.
Most of the test changes are due to random scheduling changes
from not having a default fullspeed model.
llvm-svn: 310258
Relanding after case to insert explicit truncation as necessary.
Allow SCALAR_TO_VECTOR of EXTRACT_VECTOR_ELT to reduce to
EXTRACT_SUBVECTOR of vector shuffle when output is smaller. Marginally
improves vector shuffle computations.
Reviewers: efriedma, RKSimon, spatel
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D35566
llvm-svn: 310256
This patch expands the support of lowerInterleavedStore to 16x8i stride 4.
LLVM creates suboptimal shuffle code-gen for AVX2. In overall, this patch is a specific fix for the pattern (Strid=4 VF=16) and we plan to include more patterns in the future.
The patch goal is to optimize the following sequence:
At the end of the computation, we have ymm2, ymm0, ymm12 and ymm3 holding
each 16 chars:
c0, c1, , c16
m0, m1, , m16
y0, y1, , y16
k0, k1, ., k16
And these need to be transposed/interleaved and stored like so:
c0 m0 y0 k0 c1 m1 y1 k1 c2 m2 y2 k2 c3 m3 y3 k3 ....
Differential Revision: https://reviews.llvm.org/D35829
llvm-svn: 310252
The NewNodesMustHaveLegalTypes flag is set to false at the beginning of CodeGenAndEmitDAG, and set to true after legalizing types.
But before calling CodeGenAndEmitDAG we build the DAG for the basic block.
So for the first basic block NewNodesMustHaveLegalTypes would be 'false' during the SDAG building, and for all other basic blocks it would be 'true'.
This patch sets the flag to false before SDAG building each basic block.
Differential Revision:
https://reviews.llvm.org/D33435
llvm-svn: 310239
We can convert any select-of-constants to math ops:
http://rise4fun.com/Alive/d7d
For this patch, I'm enhancing an existing x86 transform that uses fake multiplies
(they always become shl/lea) to avoid cmov or branching. The current code misses
cases where we have a negative constant and a positive constant, so this is just
trying to plug that hole.
The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start
with a select in IR, create a select DAG node, convert it into a sext, convert it
back into a select, and then lower it to sext machine code.
Some notes about the test diffs:
1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR.
2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. I
think we could avoid the push/pop in some cases if we used 'movzbl %al' instead of an xor on
a different reg? That's a post-DAG problem though.
3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if
that's a regression, but I think those would always be nearly equivalent.
4. pr22338.ll and sext-i1.ll - These tests have undef operands, so I don't think we actually care about these diffs.
5. sbb.ll - This shows a win for what I think is a common case: choose -1 or 0.
6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again.
7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops.
Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass.
Differential Revision: https://reviews.llvm.org/D35340
llvm-svn: 310208
Test with/without the sandybridge (default) model for SSE2, SSE3 and AVX targets.
pre-SSE3 the issue is the order of the fpsw and fpcw load/stores (with SSE3 trunc-store FIST instructions avoid the sw/cw manipulations).
llvm-svn: 310198
Summary:
On older processors this instruction encoding is treated as a NOP.
MSVC doesn't disable intrinsics based on features the way clang/gcc does. Because the PAUSE instruction encoding doesn't crash older processors, some software out there uses these intrinsics without checking for SSE2.
This change also seems to also be consistent with gcc behavior.
Fixes PR34079
Reviewers: RKSimon, zvi
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36361
llvm-svn: 310190
Add memory synchronization semantics to LSE Atomics.
The memory semantics feature will be added in a subsequent patch.
In this patch, several corrections were added to the existing LSE Atomics
implementation, based on the ARM Errata D11904 from 05/12/2017.
Patch by: steleman
Differential Revision: https://reviews.llvm.org/D35319
llvm-svn: 310167
Summary:
Direct calls to dllimport functions are very common Windows. We should
add them to the -O0 fast path.
Reviewers: rafael
Subscribers: llvm-commits, hiraditya
Differential Revision: https://reviews.llvm.org/D36197
llvm-svn: 310152
This adds support for the main 128-bit atomic operations,
using the SystemZ instructions LPQ, STPQ, and CDSG.
Generating these instructions is a bit more complex than usual
since the i128 type is not legal for the back-end. Therefore,
we have to hook the LowerOperationWrapper and ReplaceNodeResults
TargetLowering callbacks.
llvm-svn: 310094
We currently emit a serialization operation (bcr 14, 0) before every
atomic load and after every atomic store. This is overly conservative.
The SystemZ architecture actually does not require any serialization
for atomic loads, and a serialization after an atomic store only if
we need to enforce sequential consistency. This is what other compilers
for the platform implement as well.
llvm-svn: 310093
Summary:
This intrinsic lets us set inactive lanes to an identity value when
implementing wavefront reductions. In combination with Whole Wavefront
Mode, it lets inactive lanes be skipped over as required by GLSL/Vulkan.
Lowering the intrinsic needs to happen post-RA so that RA knows that the
destination isn't completely overwritten due to the EXEC shenanigans, so
we need another pseudo-instruction to represent the un-lowered
intrinsic.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34719
llvm-svn: 310088
Summary:
Whole Wavefront Wode (WWM) is similar to WQM, except that all of the
lanes are always enabled, regardless of control flow. This is required
for implementing wavefront reductions in non-uniform control flow, where
we need to use the inactive lanes to propagate intermediate results, so
they need to be enabled. We need to propagate WWM to uses (unless
they're explicitly marked as exact) so that they also propagate
intermediate results correctly. We do the analysis and exec mask munging
during the WQM pass, since there are interactions with WQM for things
that require both WQM and WWM. For simplicity, WWM is entirely
block-local -- blocks are never WWM on entry or exit of a block, and WWM
is not propagated to the block level. This means that computations
involving WWM cannot involve control flow, but we only ever plan to use
WWM for a few limited purposes (none of which involve control flow)
anyways.
Shaders can ask for WWM using the @llvm.amdgcn.wwm intrinsic. There
isn't yet a way to turn WWM off -- that will be added in a future
change.
Finally, it turns out that turning on inactive lanes causes a number of
problems with register allocation. While the best long-term solution
seems like teaching LLVM's register allocator about predication, for now
we need to add some hacks to prevent ourselves from getting into trouble
due to constraints that aren't currently expressed in LLVM. For the gory
details, see the comments at the top of SIFixWWMLiveness.cpp.
Reviewers: arsenm, nhaehnle, tpr
Subscribers: kzhuravl, wdng, mgorny, yaxunl, dstuttard, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D35524
llvm-svn: 310087
Summary:
Previously, we assumed that certain types of instructions needed WQM in
pixel shaders, particularly DS instructions and image sampling
instructions. This was ok because with OpenGL, the assumption was
correct. But we want to start using DPP instructions for derivatives as
well as other things, so the assumption that we can infer whether to use
WQM based on the instruction won't continue to hold. This intrinsic lets
frontends like Mesa indicate what things need WQM based on their
knowledge of the API, rather than second-guessing them in the backend.
We need to keep around the old method of enabling WQM, but eventually we
should remove it once Mesa catches up. For now, this will let us use DPP
instructions for computing derivatives correctly.
Reviewers: arsenm, tpr, nhaehnle
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D35167
llvm-svn: 310085
If all the operands of a BUILD_VECTOR extract elements from same vector then split the vector efficiently based on the maximum vector access index.
Committed on behalf of @jbhateja (Jatin Bhateja)
Differential Revision: https://reviews.llvm.org/D35788
llvm-svn: 310058
Author: milena.vujosevic.janicic
The patch extends size reduction pass for MicroMIPS.
The following instructions are examined and transformed, if possible:
ADDIU instruction is transformed into 16-bit instruction ADDIUSP
ADDIU instruction is transformed into 16-bit instruction ADDIUR1SP
Usage of u_int64_t replaced by uint64_t to avoid issues because of which previous patch version was reverted:
Differential Revision: https://reviews.llvm.org/D34511
llvm-svn: 310044
In case if SI_KILL is in between of the SI_IF and SI_END_CF we need
to preserve the bits actually flipped by if rather then restoring
the original mask.
Differential Revision: https://reviews.llvm.org/D36299
llvm-svn: 310031
Summary:
Following the docs, we need at least 5 wait states between an EXEC write
and an instruction that uses DPP.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D34849
llvm-svn: 310013
Summary: Move test/CodeGen/AArch64/reg-bank-128bit.mir to test/CodeGen/AArch64/GlobalISel/reg-bank-128bit.mir so that the test is executed only when global-isel is enabled. lit.local.cfg under test/CodeGen/AArch64/GlobalISel checks if 'global-isel' is in the available_features while the same file under test/CodeGen/AArch64 doesn't.
Reviewers: qcolombet, davide
Reviewed By: davide
Subscribers: davide, aemerson, javed.absar, igorb, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D36282
llvm-svn: 309985
When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present).
Committed on behalf of @jbhateja (Jatin Bhateja)
Differential Revision: https://reviews.llvm.org/D36271
llvm-svn: 309963
Summary:
If a PHI has at lease one VGPR operand, we have to fix the PHI
in SIFixSGPRCopies.
Reviewer:
Matt
Differential Revision:
http://reviews.llvm.org/D34727
llvm-svn: 309959
rL306209 taught SelectionDAG how to add the dereferenceable flag when
expanding memcpy and memmove. The fix however contained a nit where
the offset + size was constructed as an APInt of PointerSize rather
than PointerSizeInBits.
This lead to isDereferenceableAndAlignedPointer() get truncated values or
values which would be sign extended within that function leading to
incorrect results.
Thanks to Alex Crichton for reporting the issue!
This resolves PR33978.
Reviewers: inouehrs
Differential Revision: https://reviews.llvm.org/D36236
llvm-svn: 309930
Add support in the instruction selector for G_GLOBAL_VALUE for ELF and
MachO for the static relocation model. We don't handle Windows yet
because that's Thumb-only, and we don't handle Thumb in general at the
moment.
Support for PIC, ROPI, RWPI and TLS will be added in subsequent commits.
Differential Revision: https://reviews.llvm.org/D35883
llvm-svn: 309927
This patch:
- makes nodes ISD::ADDCARRY and ISD::SUBCARRY legal for i32
- lowering is done by first converting the boolean value into the carry flag
using (_, C) <- (ARMISD::ADDC R, -1) and converted back to an integer value
using (R, _) <- (ARMISD::ADDE 0, 0, C). An ARMISD::ADDE between the two
operations does the actual addition.
- for subtraction, given that ISD::SUBCARRY second result is actually a
borrow, we need to invert the value of the second operand and result before
and after using ARMISD::SUBE. We need to invert the carry result of
ARMISD::SUBE to preserve the semantics.
- given that the generic combiner may lower ISD::ADDCARRY and
ISD::SUBCARRY into ISD::UADDO and ISD::USUBO we need to update their lowering
as well otherwise i64 operations now would require branches. This implies
updating the corresponding test for unsigned.
- add new combiner to remove the redundant conversions from/to carry flags
to/from boolean values (ARMISD::ADDC (ARMISD::ADDE 0, 0, C), -1) -> C
Differential Revision: https://reviews.llvm.org/D35192
llvm-svn: 309923
IMHO it is an antipattern to have a enum value that is Default.
At any given piece of code it is not clear if we have to handle
Default or if has already been mapped to a concrete value. In this
case in particular, only the target can do the mapping and it is nice
to make sure it is always done.
This deletes the two default enum values of CodeModel and uses an
explicit Optional<CodeModel> when it is possible that it is
unspecified.
llvm-svn: 309911
Power 9 has instructions to do absolute difference (VABSDUB, VABSDUH, VABSDUW)
for byte, halfword and word. We should take advantage of these.
Differential Revision: https://reviews.llvm.org/D34684
llvm-svn: 309876
