If we have:
R = sub X, Y
P = cmp Y, X
...then flipping the operands in the compare instruction can allow using a subtract that sets compare flags.
Motivated by diffs in D58875 - not sure if this changes anything there,
but this seems like a good thing independent of that.
There's a more involved version of this transform already in IR (in instcombine
although that seems misplaced to me) - see "swapMayExposeCSEOpportunities()".
Differential Revision: https://reviews.llvm.org/D63958
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365711 91177308-0d34-0410-b5e6-96231b3b80d8
Since we have distinct types for pointers and scalars, G_INTTOPTRs can sometimes
obstruct attempts to find constant source values. These usually come about when
try to do some kind of null pointer check. Teaching getConstantVRegValWithLookThrough
about this operation allows the CBZ/CBNZ optimization to catch more cases.
This change also improves the case where we can't find a constant source at all.
Previously we would emit a cmp, cset and tbnz for that. Now we try to just emit
a cmp and conditional branch, saving an instruction.
The cumulative code size improvement of this change plus D64354 is 5.5% geomean
on arm64 CTMark -O0.
Differential Revision: https://reviews.llvm.org/D64377
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365690 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: Unsafe does not map well alone for each of these three cases as it is missing NoNan context when accessed directly with clang. I have migrated the fold guards to reflect the expectations of handing nan and zero contexts directly (NoNan, NSZ) and some tests with it. Unsafe does include NSZ, however there is already precedent for using the target option directly to reflect that context.
Reviewers: spatel, wristow, hfinkel, craig.topper, arsenm
Reviewed By: arsenm
Subscribers: michele.scandale, wdng, javed.absar
Differential Revision: https://reviews.llvm.org/D64450
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365679 91177308-0d34-0410-b5e6-96231b3b80d8
Keep the uint64_t type from getZExtValue() to stop truncation/extension overflow warnings in MSVC in subvector index math.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365621 91177308-0d34-0410-b5e6-96231b3b80d8
In SelectionDAG AMDGPU treated these as legal, but this was mostly
because the bitcasts required for FP types were painful. Theoretically
the bitpattern should eventually match to bfi, so don't bother trying
to get the patterns to import.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365583 91177308-0d34-0410-b5e6-96231b3b80d8
Basically the problem is that X86 doesn't set the Fast flag from
allowsMemoryAccess on certain CPUs due to slow unaligned memory
subtarget features. This prevents bitcasts from being folded into
loads and stores. But all vector loads and stores of the same width
are the same cost on X86.
This patch merges the allowsMemoryAccess call into isLoadBitCastBeneficial to allow X86 to skip it.
Differential Revision: https://reviews.llvm.org/D64295
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365549 91177308-0d34-0410-b5e6-96231b3b80d8
If we have an icmp->brcond->br sequence where the brcond just branches to the
next block jumping over the br, while the br takes the false edge, then we can
modify the conditional branch to jump to the br's target while inverting the
condition of the incoming icmp. This means we can eliminate the br as an
unconditional branch to the fallthrough block.
Differential Revision: https://reviews.llvm.org/D64354
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365510 91177308-0d34-0410-b5e6-96231b3b80d8
Keep the uint64_t type from getOffsetFromBase() to stop truncation/extension overflow warnings in MSVC in alignment math.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365504 91177308-0d34-0410-b5e6-96231b3b80d8
Select gprb or fprb when def/use register operand of G_PHI is
used/defined by either:
copy to/from physical register or
instruction with only one mapping available for that use/def operand.
Integer s64 phi is handled with narrowScalar when mapping is applied,
produced artifacts are combined away. Manually set gprb to all register
operands of instructions created during narrowScalar.
Differential Revision: https://reviews.llvm.org/D64351
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365494 91177308-0d34-0410-b5e6-96231b3b80d8
Now that we've dropped VS2015 support (D64326) we can enable the constexpr variables on MSVC builds as VS2017+ correctly handles them
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365477 91177308-0d34-0410-b5e6-96231b3b80d8
In addition, fix the build failure for the 'unused'
variable. The variable was used inside the 'LLVM_DEBUG()'.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365469 91177308-0d34-0410-b5e6-96231b3b80d8
This makes the functions in Loads.h require a type to be specified
independently of the pointer Value so that when pointers have no structure
other than address-space, it can still do its job.
Most callers had an obvious memory operation handy to provide this type, but a
SROA and ArgumentPromotion were doing more complicated analysis. They get
updated to merge the properties of the various instructions they were
considering.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365468 91177308-0d34-0410-b5e6-96231b3b80d8
Dump the DWARF information about call sites and call site parameters into
debug info sections.
The patch also provides an interface for the interpretation of instructions
that could load values of a call site parameters in order to generate DWARF
about the call site parameters.
([13/13] Introduce the debug entry values.)
Co-authored-by: Ananth Sowda <asowda@cisco.com>
Co-authored-by: Nikola Prica <nikola.prica@rt-rk.com>
Co-authored-by: Ivan Baev <ibaev@cisco.com>
Differential Revision: https://reviews.llvm.org/D60716
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365467 91177308-0d34-0410-b5e6-96231b3b80d8
DAGTypeLegalizer and SelectionDAGLegalize has helper
functions wrapping the call to TLI.getSetCCResultType(...).
Use those helpers in more places.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365456 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Make sure we use SETGE instead of SETGT when checking
if the sign bit is zero at SMULFIXSAT expansion.
The faulty expansion occured when doing "expand" of
SMULFIXSAT and the scale was exactly matching the
size of the smaller type. For example doing
i64 Z = SMULFIXSAT X, Y, 32
and expanding X/Y/Z into using two i32 values.
The problem was that we sometimes did not saturate
to min when overflowing.
Here is an example using Q3.4 numbers:
Consider that we are multiplying X and Y.
X = 0x80 (-8.0 as Q3.4)
Y = 0x20 (2.0 as Q3.4)
To avoid loss of precision we do a widening
multiplication, getting a 16 bit result
Z = 0xF000 (-16.0 as Q7.8)
To detect negative overflow we should check if
the five most significant bits in Z are less than -1.
Assume that we name the 4 most significant bits
as HH and the next 4 bits as HL. Then we can do the
check by examining if
(HH < -1) or (HH == -1 && "sign bit in HL is zero").
The fault was that we have been doing the check as
(HH < -1) or (HH == -1 && HL > 0)
instead of
(HH < -1) or (HH == -1 && HL >= 0).
In our example HH is -1 and HL is 0, so the old
code did not trigger saturation and simply truncated
the result to 0x00 (0.0). With the bugfix we instead
detect that we should saturate to min, and the result
will be set to 0x80 (-8.0).
Reviewers: leonardchan, bevinh
Reviewed By: leonardchan
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64331
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365455 91177308-0d34-0410-b5e6-96231b3b80d8
Jordan reports on llvm-commits a performance regression with r364515,
backing the patch out while it's investigated.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365448 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This is exposed by functional testing on PowerPC.
In some pipelined loops, Phi refer to phi did not get value defined by
the Phi, hence getting wrong value later.
As the comment mentioned, we should "use the value defined by the Phi,
unless we're generating the firstepilog and the Phi refers to a Phi
in a different stage.", so Phi refering to same stage Phi should use
the value defined by the Phi here.
Reviewers: bcahoon, hfinkel
Reviewed By: hfinkel
Subscribers: MaskRay, wuzish, nemanjai, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64035
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365428 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This makes it so that IR files using triples without an environment work
out of the box, without normalizing them.
Typically, the MSVC behavior is more desirable. For example, it tends to
enable things like constant merging, use of associative comdats, etc.
Addresses PR42491
Reviewers: compnerd
Subscribers: hiraditya, dexonsmith, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64109
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365387 91177308-0d34-0410-b5e6-96231b3b80d8
This is extremly slow on AMDGPU, which has a lot of physical register
and a lot of register classes.
determineCalleeSaves, via MachineRegisterInfo::isPhysRegUsed already
added all of the super registers to the saved set.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365370 91177308-0d34-0410-b5e6-96231b3b80d8
Don't do this locally, computeKnownBits does this better (and can handle non-constant cases as well).
A next step would be to actually simplify non-constant elements - building on what we already do in SimplifyDemandedVectorElts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365309 91177308-0d34-0410-b5e6-96231b3b80d8
Some out of tree backend require larger vector type. Since maintaining the changes out of tree is difficult due to the many manual changes needed when adding a new type we are adding it even if no backend currently use it.
Differential Revision: https://reviews.llvm.org/D64141
Patch by Thomas Raoux!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365274 91177308-0d34-0410-b5e6-96231b3b80d8
Although removeCopyByCommutingDef deals with full copies, it is still
possible to copy undef lanes and thus, we wouldn't have any a value
number for these lanes.
This fixes PR40215.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365256 91177308-0d34-0410-b5e6-96231b3b80d8
I'm not sure if it's worth it or not to add a hook to disable the pass
for an arbitrary function.
This pass is taking up to 5% of compile time in tiny programs by
iterating through all of the physical registers in every register
class. This pass should be rewritten in terms of regunits. For now,
skip doing anything for entry point functions. The vast majority of
functions in the real world aren't callable, so just not running this
will give the majority of the benefit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365255 91177308-0d34-0410-b5e6-96231b3b80d8
When looking for uses/defs to add kill flags, the iterator was double
incremented, skipping the first instruction in the bundle. The use
register in the first bundle instruction was then incorrectly killed.
The "First" instruction should be the BUNDLE itself as the proper
reverse iterator endpoint.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365216 91177308-0d34-0410-b5e6-96231b3b80d8
Revision r365061 changed a skip of debug instructions for a skip
of meta instructions. This is not safe, as IMPLICIT_DEF is classed
as a meta instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365198 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The uaddo won't be removed and the addcarry will still be
dependent on the uaddo. So we'll just increase the use count
of X and Y and potentially require a COPY.
Reviewers: spatel, RKSimon, deadalnix
Reviewed By: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64190
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365149 91177308-0d34-0410-b5e6-96231b3b80d8
We previously marked all the tests with branch funnels as
`-verify-machineinstrs=0`.
This is an attempt to fix it.
1) `ICALL_BRANCH_FUNNEL` has no defs. Mark it as `let OutOperandList =
(outs)`
2) After that we hit an assert: ``` Assertion failed: (Op.getValueType()
!= MVT::Other && Op.getValueType() != MVT::Glue && "Chain and glue
operands should occur at end of operand list!"), function AddOperand,
file
/Users/francisvm/llvm/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp,
line 461. ```
The chain operand was added at the beginning of the operand list. Move
that to the end.
3) After that we hit another verifier issue in the pseudo expansion
where the registers used in the cmps and jmps are not added to the
livein lists. Add the `EFLAGS` to all the new MBBs that we create.
PR39436
Differential Review: https://reviews.llvm.org/D54155
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365058 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This diff improve the capability of DAGCOmbine to generate linear carries propagation in presence of a diamond pattern. It is now able to match a large variety of different patterns rather than some hardcoded one.
Arguably, the codegen in test cases is not better, but this is to be expected. The goal of this transformation is more about canonicalisation than actual optimisation.
Reviewers: hfinkel, RKSimon, craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D57302
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365051 91177308-0d34-0410-b5e6-96231b3b80d8
When a target intrinsic has been determined to touch memory, we construct a MachineMemOperand during SDAG construction. In this case, we should propagate AAMDNodes metadata to the MachineMemOperand where available.
Differential revision: https://reviews.llvm.org/D64131
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365043 91177308-0d34-0410-b5e6-96231b3b80d8
For Thumb2, we prefer low regs (costPerUse = 0) to allow narrow
encoding. However, current allocation order is like:
R0-R3, R12, LR, R4-R11
As a result, a lot of instructs that use R12/LR will be wide instrs.
This patch changes the allocation order to:
R0-R7, R12, LR, R8-R11
for thumb2 and -Osize.
In most cases, there is no extra push/pop instrs as they will be folded
into existing ones. There might be slight performance impact due to more
stack usage, so we only enable it when opt for min size.
https://reviews.llvm.org/D30324
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365014 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This is the backend part of [[ https://bugs.llvm.org/show_bug.cgi?id=42457 | PR42457 ]].
In middle-end, we'd want to prefer the form with two adds - D63992,
but as this diff shows, not every target will prefer that pattern.
Out of 4 targets for which i added tests all seem to be ok with inc-of-add for scalars,
but only X86 prefer that same pattern for vectors.
Here i'm adding a new TLI hook, always defaulting to the inc-of-add,
but adding AArch64,ARM,PowerPC overrides to prefer inc-of-add only for scalars.
Reviewers: spatel, RKSimon, efriedma, t.p.northover, hfinkel
Reviewed By: efriedma
Subscribers: nemanjai, javed.absar, kristof.beyls, kbarton, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64090
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365010 91177308-0d34-0410-b5e6-96231b3b80d8
Sanjay Patel