The missing line added by this patch ensures that only spilt variable
locations are candidates for being restored from the stack. Otherwise,
register or constant-value information can be interpreted as a spill
location, through a union.
The added regression test replicates a scenario where this occurs: the
stack load from [rsp] causes the register-location DBG_VALUE to be
"restored" to rsi, when it should be left alone. See PR43058 for details.
Un x-fail a test that was suffering from this from a previous patch.
Differential Revision: https://reviews.llvm.org/D66895
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370334 91177308-0d34-0410-b5e6-96231b3b80d8
Masked loads and store fit naturally with MVE, the instructions being easily
predicated. This adds lowering for the simple cases of masked loads and stores.
It does not yet deal with widening/narrowing or pre/post inc.
The llvm masked load intrinsic will accept a "passthru" value, dictating the
values used for the zero masked lanes. In MVE the instructions write 0 to the
zero predicated lanes, so we need to match a passthru that isn't 0 (or undef)
with a select instruction to pull in the correct data after the load.
We also need to do something with unaligned loads/stores. Currently this uses a
similar method used in big endian, using an VLDRB.8 (and potentially a VREV in
BE). This does mean that the predicate mask is converted from, for example, a
v4i1 to a v16i1. The VLDR instructions are defined as using the first bit of
the relevant mask lane, so this could potentially load different results if the
predicate is little odd. As the input is a v4i1 however, I believe this is OK
and all the bits required should be set in the predicate, making the VLDRB.8
load the same data.
Differential Revision: https://reviews.llvm.org/D66534
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370329 91177308-0d34-0410-b5e6-96231b3b80d8
The "join" method in LiveDebugValues does not attempt to join unseen
predecessor blocks if their out-locations aren't yet initialized, instead
the block should be re-visited later to see if any locations have changed
validity. However, because the set of blocks were all being "process"'d
once before "join" saw them, that logic in "join" was actually ignoring
legitimate out-locations on the first pass through. This meant that some
invalidated locations were not removed from the head of loops, allowing
illegal locations to persist.
Fix this by removing the run of "process" before the main join/process loop
in ExtendRanges. Now the unseen predecessors that "join" skips truly are
uninitialized, and we come back to the block at a later time to re-run
"join", see the @baz function added.
This also fixes another fault where stack/register transfers in the entry
block (or any other before-any-loop-block) had their tranfers initially
ignored, and were then never revisited. The MIR test added tests for this
behaviour.
XFail a test that exposes another bug; a fix for this is coming in D66895.
Differential Revision: https://reviews.llvm.org/D66663
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370328 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
We were previously doing it in DAGCombine.
But we also want to do `sub %x, C` -> `add %x, (sub 0, C)` for vectors in DAGCombine.
So if we had `sub %x, -1`, we'll transform it to `add %x, 1`,
which `combineIncDecVector()` will immediately transform back into `sub %x, -1`,
and here we go again...
I've marked this as NFC since not a single test changes,
but since that 'changes' DAGCombine, probably this isn't fully NFC.
Reviewers: RKSimon, craig.topper, spatel
Reviewed By: craig.topper
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62327
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370327 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: This is beneficial when the shuffle is only used once and end up being generated in a few places when some node is combined into a shuffle.
Reviewers: craig.topper, efriedma, RKSimon, lebedev.ri
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66718
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370326 91177308-0d34-0410-b5e6-96231b3b80d8
We had an isel pattern to perform this, but its better to
do it in DAG combine as a simplification. This also fixes the lack
of patterns for AVX512 targets.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370294 91177308-0d34-0410-b5e6-96231b3b80d8
Including a type legalizer fix to make bitcast operand promotion
work correctly when getSoftenedFloat returns f128 instead of i128.
Fixes PR43157
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370293 91177308-0d34-0410-b5e6-96231b3b80d8
SGPR spills aren't really handled after SILowerSGPRSpills. In order to
directly control what happens if the scavenger needs to spill, the
scavenger needs to be used directly. There is an alternative to
spilling in these contexts anyway since the frame register can be
increment and restored.
This does present another possible issue if spilling is needed for the
unused carry out if an add is needed. I think this can be avoided by
using a scalar add (although that clobbers SCC, which happens anyway).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370281 91177308-0d34-0410-b5e6-96231b3b80d8
This is a special case because one node maps to two different G_
instructions, and the operand order is changed.
This mostly enables G_FCMP for AMDPGPU. G_ICMP is still manually
selected for now since it has the SALU and VALU complication to deal
with.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370280 91177308-0d34-0410-b5e6-96231b3b80d8
-debug-only option for llc is only available in debug builds so
"REQUIRES: asserts" is needed in the tes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370279 91177308-0d34-0410-b5e6-96231b3b80d8
The patch fixed the issue that RV64 didn't clear the upper bits
when return complex floating value with lp64 ABI.
float _Complex
complex_add(float _Complex a, float _Complex b)
{
return a + b;
}
RealResult = zero_extend(RealA + RealB)
ImageResult = ImageA + ImageB
Return (RealResult | (ImageResult << 32))
The patch introduces shouldExtendTypeInLibCall target hook to suppress
the AssertZext generation when lowering floating LibCall.
Thanks to Eli's comments from the Bugzilla
https://bugs.llvm.org/show_bug.cgi?id=42820
Differential Revision: https://reviews.llvm.org/D65497
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370275 91177308-0d34-0410-b5e6-96231b3b80d8
If result of 64-bit address loading combines with 32-bit mask, LLVM
tries to optimize the code and remove "redundant" loading of upper
32-bits of the address. It leads to incorrect code on MIPS64 targets.
MIPS backend creates the following chain of commands to load 64-bit
address in the `MipsTargetLowering::getAddrNonPICSym64` method:
```
(add (shl (add (shl (add %highest(sym), %higher(sym)),
16),
%hi(sym)),
16),
%lo(%sym))
```
If the mask presents, LLVM decides to optimize the chain of commands. It
really does not make sense to load upper 32-bits because the 0x0fffffff
mask anyway clears them. After removing redundant commands we get this
chain:
```
(add (shl (%hi(sym), 16), %lo(%sym))
```
There is no patterns matched `(MipsHi (i64 symbol))`. Due a bug in `SYM_32`
predicate definition, backend incorrectly selects a pattern for a 32-bit
symbols and uses the `lui` instruction for loading `%hi(sym)`.
As a result we get incorrect set of instructions with unnecessary 16-bit
left shifting:
```
lui at,0x0
R_MIPS_HI16 foo
dsll at,at,0x10
daddiu at,at,0
R_MIPS_LO16 foo
```
This patch resolves two problems:
- Fix `SYM_32/SYM_64` predicates to prevent selection of patterns dedicated
to 32-bit symbols in case of using N64 ABI.
- Add missed patterns for 64-bit symbols for `%hi/%lo`.
Fix PR42736.
Differential Revision: https://reviews.llvm.org/D66228
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370268 91177308-0d34-0410-b5e6-96231b3b80d8
Reuse the logic for INSERT_SUBREG to also import SUBREG_TO_REG patterns.
- Split `inferSuperRegisterClass` into two functions, one which tries to use
an existing TreePatternNode (`inferSuperRegisterClassForNode`), and one that
doesn't. SUBREG_TO_REG doesn't have a node to leverage, which is the cause
for the split.
- Rename GlobalISelEmitterInsertSubreg.td to GlobalISelEmitterSubreg.td and
update it.
- Update impacted tests in the AArch64 and X86 backends.
This is kind of a hit/miss for code size improvements/regressions. E.g. in
add-ext.ll, we now get some identity copies. This isn't really anything the
importer can handle, since it's caused by a later pass introducing the copy for
the sake of correctness.
Differential Revision: https://reviews.llvm.org/D66769
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370254 91177308-0d34-0410-b5e6-96231b3b80d8
This implements constrained floating point intrinsics for FP to signed and
unsigned integers.
Quoting from D32319:
The purpose of the constrained intrinsics is to force the optimizer to
respect the restrictions that will be necessary to support things like the
STDC FENV_ACCESS ON pragma without interfering with optimizations when
these restrictions are not needed.
Reviewed by: Andrew Kaylor, Craig Topper, Hal Finkel, Cameron McInally, Roman Lebedev, Kit Barton
Approved by: Craig Topper
Differential Revision: http://reviews.llvm.org/D63782
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370228 91177308-0d34-0410-b5e6-96231b3b80d8
This reduces the number of SGPRs due to some concerns about running
out of SGPRs if you make all the SGPRs that aren't reserved available
for the calling convention.
Change-Id: Idb4ca4dc72f5b6808cb524ff7270915a8de5b4c1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370215 91177308-0d34-0410-b5e6-96231b3b80d8
There is no pattern matched `add hi, (MipsLo texternalsym)`. As a result,
loading an address of 32-bit symbol requires two registers and one more
additional instruction:
```
addiu $1, $zero, %lo(foo)
lui $2, %hi(foo)
addu $25, $2, $1
```
This patch adds the missed pattern and enables generation more effective
set of instructions:
```
lui $1, %hi(foo)
addiu $25, $1, %lo(foo)
```
Differential Revision: https://reviews.llvm.org/D66771
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370196 91177308-0d34-0410-b5e6-96231b3b80d8
This adds fp16 VMOVX patterns, using the same patterns as rL362482 with some
adjustments for MVE. It allows us to move fp16 registers without going into and
out of gprs.
VMOVX is able to move the top bits from a fp16 in a fp reg into the bottom bits
of another register, zeroing the rest. This can be used for odd MVE register
lanes. The top bits are not read by fp16 instructions, so no move is required
there if we are dealing with even lanes.
Differential revision: https://reviews.llvm.org/D66793
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370184 91177308-0d34-0410-b5e6-96231b3b80d8
rL369567 reverted a couple of recent changes made to ARMParallelDSP
because of a miscompilation error: PR43073.
The issue stemmed from an underlying bug that was caused by adding
muls into a reduction before it was proved that they could be executed
in parallel with another mul.
Most of the changes here are from the previously reverted commits.
The additional changes have been made area:
1) The Search function now doesn't insert any muls into the Reduction
object. That now happens once the search has successfully finished.
2) For any muls added into the reduction but that weren't paired, we
accumulate their values as an input into the smlad.
Differential Revision: https://reviews.llvm.org/D66660
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370171 91177308-0d34-0410-b5e6-96231b3b80d8
If the result register already had a register class assigned, the
sources may not have been properly constrained.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370150 91177308-0d34-0410-b5e6-96231b3b80d8
This change moves the actual stack pointer manipulation into the legalizer,
available to targets via lower(). The codegen is slightly different because
we're using explicit masks instead of G_PTRMASK, and using G_SUB rather than
adding a negative amount via G_GEP.
Differential Revision: https://reviews.llvm.org/D66678
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370104 91177308-0d34-0410-b5e6-96231b3b80d8
Copied directly from the IR version.
Most of the testcases I've added for this are somewhat problematic
because they really end up testing the yet to be implemented version
for MUL_I24/MUL_U24.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370099 91177308-0d34-0410-b5e6-96231b3b80d8
(-X) * (-Y) + Z --> X * Y + Z
This is a missing optimization that shows up as a potential regression in D66050,
so we should solve it first. We appear to be partly missing this fold in IR as well.
We do handle the simpler case already:
(-X) * (-Y) --> X * Y
And it might be beneficial to make the constraint less conservative (eg, if both
operands are cheap, but not necessarily cheaper), but that causes infinite looping
for the existing fmul transform.
Differential Revision: https://reviews.llvm.org/D66755
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370071 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Adds support for emitting common local global symbols to an XCOFF object file.
Local commons are emitted into the .bss section with a storage class of
C_HIDEXT.
Patch by: daltenty
Reviewers: sfertile, hubert.reinterpretcast
Differential Revision: https://reviews.llvm.org/D66097
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370070 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts commit b3d258fc44b588f06eb35f8e4b9a6d1fc859acec.
@skatkov is reporting crash in D63972#1646303
Contacted @ZhangKang, and revert the commit on behalf of him.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370069 91177308-0d34-0410-b5e6-96231b3b80d8
Inserting a value into Visited has the effect of terminating a search for
predecessors if that node is seen. This is legitimate for the base address, and
acts as a slight performance optimization, but the vector-building node can be
paert of a legitimate cycle so we shouldn't stop searching there.
PR43056.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370036 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This is an alternate approach to D63396
Currently funclets reuse the same stack slots that are used in the
parent function for saving callee-saved xmm registers. If the parent
function modifies a callee-saved xmm register before an excpetion is
thrown, the catch handler will overwrite the original saved value.
This patch allocates space in funclets stack for saving callee-saved xmm
registers and uses RSP instead RBP to access memory.
Signed-off-by: Pengfei Wang <pengfei.wang@intel.com>
Reviewers: rnk, RKSimon, craig.topper, annita.zhang, LuoYuanke, andrew.w.kaylor
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66596
Signed-off-by: Pengfei Wang <pengfei.wang@intel.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370005 91177308-0d34-0410-b5e6-96231b3b80d8
The problem these are supposed to work around can occur before the
intrinsics are lowered into the nodes. Try to directly simplify them
so they are matched before the bit assert operations can be optimized
out.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369994 91177308-0d34-0410-b5e6-96231b3b80d8
The mul24 matching could interfere with SLSR and the other addressing
mode related passes. This probably is not the optimal placement, but
is an intermediate step. This should probably be moved after all the
generic IR passes, particularly LSR. Moving this after LSR seems to
help in some cases, and hurts others.
As-is in this patch, in idiv-licm, it saves 1-2 instructions inside
some of the loop bodies, but increases the number in others. Moving
this later helps these loops. In the new lsr tests in
mul24-pass-ordering, the intrinsic prevents introducing more
instructions in the loop preheader, so moving this later ends up
hurting them. This shouldn't be any worse than before the intrinsics
were introduced in r366094, and LSR should probably be smarter. I
think it's because it doesn't know the and inside the loop will be
folded away.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369991 91177308-0d34-0410-b5e6-96231b3b80d8
Probably better to keep add over sub in early DAG combines.
It might make sense to push this to lowering or delay it all
the way to isel. But this was the simplest change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369981 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Previously we skipped uses within the same BB as a def when rebuilding
SSA after SjLj transformation. For example, before transformation,
```
for.cond:
%0 = phi i32 [ %var, %for.inc ] ...
%var = ...
br label %for.inc
for.inc: ; preds = %for.cond
call i32 @setjmp(...)
br %for.cond
```
In this BB, %var should be defined in all paths from %for.inc to make %0
valid. In the input it was true; %for.inc's only predecessor was
%for.cond. But after SjLj transformation, it is possible that %for.inc
has other predecessors that are reachable without reaching %for.cond.
```
entry.split:
...
br i1 %a, label %bb.1, label %for.inc
for.cond:
%0 = phi i32 [ %var, %for.inc ] ... ; Not valid!
%var = ...
br label %for.inc
for.inc: ; preds = %for.cond, %entry.split
call i32 @setjmp(...)
...
br %for.cond
```
In this case, we can't use %var in the `phi` instruction in %for.cond,
because %var is not defined in all paths through %for.inc (If the
control flow is %entry -> %entry.split -> %for.inc -> %for.cond, %var
has not been defined until we reach the `phi`). But the previous code
excluded users within the same BB, skipping instructions within the same
BB so they are not rewritten properly. User instructions within the same
BB also should be candidates for rewriting if they are _before_ the
original definition.
Fixes PR43097.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66729
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369978 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Combine a test in lower-em-sjlj-longjmp-only.ll into lower-em-sjlj.ll,
because the test command is the same and I don't see any reason it
should be a separate file. Also converted tabs into spaces and fixed
indentations in lower-em-sjlj-sret.ll. (lower-em-sjlj.ll uses a
different test command (llc), so it couldn't be combined)
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66728
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369974 91177308-0d34-0410-b5e6-96231b3b80d8
This teaches the importer to handle INSERT_SUBREG instructions.
We were missing patterns involving INSERT_SUBREG in AArch64. It appears in
AArch64InstrInfo.td 107 times, and 14 times in AArch64InstrFormats.td.
To meaningfully import it, the GlobalISelEmitter needs to know how to infer a
super register class for a given register class.
This patch introduces the following:
- `getSuperRegForSubReg`, a function which finds the largest register class
which supports a value type and subregister index
- `inferSuperRegisterClass`, a function which finds the appropriate super
register class for an INSERT_SUBREG'
- `inferRegClassFromPattern`, a function which allows for some trivial
lookthrough into instructions
- `getRegClassFromLeaf`, a helper function which returns the register class for
a leaf `TreePatternNode`
- Support for subregister index operands in `importExplicitUseRenderer`
It also
- Updates tests in each backend which are impacted by the change
- Adds GlobalISelEmitterSubreg.td to test that we import and skip the expected
patterns
As a result of this patch, INSERT_SUBREG patterns in X86 may use the
LOW32_ADDR_ACCESS_RBP register class instead of GR32. This is correct, since the
register class contains the same registers as GR32 (except with the addition of
RBP). So, this also teaches X86 to handle that register class. This is in line
with X86ISelLowering, which treats this as a GR class.
Differential Revision: https://reviews.llvm.org/D66498
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369973 91177308-0d34-0410-b5e6-96231b3b80d8
ANY_EXTEND_VECTOR_INREG isn't currently marked Legal which prevents SimplifyDemandedBits from turning SIGN/ZERO_EXTEND_VECTOR_INREG into it after op legalization. And even if we did make it Legal, combineExtInVec doesn't do shuffle combining on the VECTOR_INREG nodes until AVX1.
This patch adds a quick hack to combinePMULDQ to directly emit a vector shuffle corresponding to an ANY_EXTEND_VECTOR_INREG operation. This avoids both of those issues without creating any other regressions on our tests. The xop-ifma.ll change here also showed up when I tried to resurrect D56306 and seemed to be the only improvement that patch creates now. This is a more direct way to get the benefit.
Differential Revision: https://reviews.llvm.org/D66436
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369942 91177308-0d34-0410-b5e6-96231b3b80d8
This improves the combine I included in D66504 to handle constants in the upper operands of the concat. If we can constant fold them away we can pull the concat after the bin op. This helps with chains of madd reductions on X86 from loop unrolling. The loop madd reduction pattern creates pmaddwd with half the width of the add that follows it using zeroes to fill the upper bits. If we have two of these added together we can pull the zeroes through the accumulating add and then shrink it.
Differential Revision: https://reviews.llvm.org/D66680
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369937 91177308-0d34-0410-b5e6-96231b3b80d8
Jeremy Morse