Move the (add (umax X, C), -C) --> (usubsat X, C) X86 combine into generic DAGCombiner
First of a number of saturated arithmetic folds that can be moved out of X86-specific code for PR40111.
Differential Revision: https://reviews.llvm.org/D57754
llvm-svn: 353457
I noticed that we are missing this canonicalization in IR:
rL352515
...and then realized that we don't get this right in SDAG either,
so this has to be fixed first regardless of what we choose to do in IR.
The existing fold was limited to scalars and using the wrong predicate
to guard the transform. We have a boolean contents TLI query that can
be used to decide which direction to fold.
This may eventually lead back to the problems/question in:
https://bugs.llvm.org/show_bug.cgi?id=40486
...but it makes no difference to that yet.
Differential Revision: https://reviews.llvm.org/D57401
llvm-svn: 353433
Summary:
If the index isn't constant, this transform inserts a multiply and an add on the index to calculating the base pointer for a scalar load. But we still create a memory operand with an offset of 0 and the size of the scalar access. But the access is really to an unknown offset within the original access size.
This can cause the machine scheduler to incorrectly calculate dependencies between this load and other accesses. In the case we saw, there was a 32 byte vector store that was split into two 16 byte stores, one with offset 0 and one with offset 16. The size of the memory operand for both was 16. The scheduler correctly detected the alias with the offset 0 store, but not the offset 16 store.
This patch discards the pointer info so we don't incorrectly detect aliasing. I wasn't sure if we could keep using the original offset and size without risking some other transform on the load changing the size.
I tried to reduce a test case, but there's still a lot of memory operations needed to get the scheduler to do the bad reordering. So it looked pretty fragile to maintain.
Reviewers: efriedma
Reviewed By: efriedma
Subscribers: arphaman, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D57616
llvm-svn: 353124
Add an intrinsic that takes 2 unsigned integers with the scale of them
provided as the third argument and performs fixed point multiplication on
them.
This is a part of implementing fixed point arithmetic in clang where some of
the more complex operations will be implemented as intrinsics.
Differential Revision: https://reviews.llvm.org/D55625
llvm-svn: 353059
Noticed while investigating PR40483, and fixes the basic test case from the bug - but not a more general case.
We're pretty weak at dealing with ADD/SUB combines compared to the SimplifyAssociativeOrCommutative/SimplifyUsingDistributiveLaws abilities that InstCombine can manage.
llvm-svn: 353044
We already have the getConstantOperandVal helper which returns a uint64_t, but along comes the fuzzer and inserts a i128 -1 constant or something and the whole thing asserts.......
I've updated a few obvious cases, and tried to make use of the const reference where possible, but there's more to do. A number of existing oss-fuzz tickets should be fixed if we start using APInt and perform value clamping where necessary.
llvm-svn: 352961
Summary: This fixes using the correct stack registers for SEH when stack realignment is needed or when variable size objects are present.
Reviewers: rnk, efriedma, ssijaric, TomTan
Reviewed By: rnk, efriedma
Subscribers: javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D57183
llvm-svn: 352923
This cleans up all CallInst creation in LLVM to explicitly pass a
function type rather than deriving it from the pointer's element-type.
Differential Revision: https://reviews.llvm.org/D57170
llvm-svn: 352909
The version of FoldConstantArithmetic() that takes arbitrary nodes
was confusingly naming those nodes as constants when they might
not be; also "Cst" reads like "Cast".
llvm-svn: 352884
This might be the start of tracking all vector element constants generally if we take it to its
logical conclusion, but let's stop here and make sure this is correct/beneficial so far.
The affected tests require a convoluted path before they get simplified currently because we
don't call SimplifyDemandedVectorElts() from binops directly and don't modify the binop operands
directly in SimplifyDemandedVectorElts().
That's why the tests all have a trailing shuffle to induce a chain reaction of transforms. So
something like this is happening:
1. Improve the knowledge of undefs in the binop via a SimplifyDemandedVectorElts() call that
originates from a shuffle.
2. Transfer that undef knowledge back to the shuffle mask user as more undef lanes.
3. Combine the modified shuffle by calling SimplifyDemandedVectorElts() again.
4. Translate the improved shuffle mask as undemanded lanes of build vector constants causing
those to become full undef constants.
5. Simplify the binop now that it has a full undef operand.
As we can see from the unchanged 'and' and 'or' tests, tracking undefs alone isn't a full solution.
We would need to track zero and all-ones constants to improve those opcodes. We'd probably need to
track NaN for FP ops too (assuming we don't have fast-math-flags set).
Differential Revision: https://reviews.llvm.org/D57066
llvm-svn: 352880
For targets where i32 is not a legal type (e.g. 64-bit RISC-V),
LegalizeIntegerTypes must promote the integer operand of ISD::FPOWI. As this
is a signed value, this should be sign-extended.
This patch enables all tests in test/CodeGen/RISCVfloat-intrinsics.ll for
RV64, as prior to this patch that file couldn't be compiled for RV64 due to an
assertion when performing codegen for fpowi.
Differential Revision: https://reviews.llvm.org/D54574
llvm-svn: 352832
This patch fixes pr39098.
For the attached test case, CombineZExtLogicopShiftLoad can optimize it to
t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
t58: i64 = srl t57, Constant:i8<1>
t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64
But later visitANDLike transforms it to
t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
t61: i32 = truncate t57
t63: i32 = srl t61, Constant:i8<1>
t64: i32 = and t63, Constant:i32<524287>
t65: i64 = zero_extend t64
t58: i64 = srl t57, Constant:i8<1>
t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64
And it triggers CombineZExtLogicopShiftLoad again, causes a dead loop.
Both forms should generate same instructions, CombineZExtLogicopShiftLoad generated IR looks cleaner. But it looks more difficult to prevent visitANDLike to do the transform, so I prevent CombineZExtLogicopShiftLoad to do the transform if the ZExt is free.
Differential Revision: https://reviews.llvm.org/D57491
llvm-svn: 352792
While dangling nodes will eventually be pruned when they are
considered, leaving them disables combines requiring single-use.
Reviewers: Carrot, spatel, craig.topper, RKSimon, efriedma
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D57520
llvm-svn: 352784
r zero scale SMULFIX, expand into MUL which produces better code for X86.
For vector arguments, expand into MUL if SMULFIX is provided with a zero scale.
Otherwise, expand into MULH[US] or [US]MUL_LOHI.
Differential Revision: https://reviews.llvm.org/D56987
llvm-svn: 352783
And instead just generate a libcall. My motivating example on ARM was a simple:
shl i64 %A, %B
for which the code bloat is quite significant. For other targets that also
accept __int128/i128 such as AArch64 and X86, it is also beneficial for these
cases to generate a libcall when optimising for minsize. On these 64-bit targets,
the 64-bits shifts are of course unaffected because the SHIFT/SHIFT_PARTS
lowering operation action is not set to custom/expand.
Differential Revision: https://reviews.llvm.org/D57386
llvm-svn: 352736
Summary:
Fixes PR40267, in which the removed assertion was triggering on
perfectly valid IR. As far as I can tell, constant out of bounds
indices should be allowed when splitting extract_vector_elt, since
they will simply be propagated as out of bounds indices in the
resulting split vector and handled appropriately elsewhere.
Reviewers: aheejin
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya
Differential Revision: https://reviews.llvm.org/D57471
llvm-svn: 352702
These can be triggered by mistakenly using a 64-bit mode only intrinsics with a -mtriple=i686. Using report_fatal_error gives a better experience for this mistake in release builds instead of probably crashing.
We already do this for some of the vector type legalization handles.
llvm-svn: 352699
This extends the existing transform for:
add X, 0/1 --> sub X, 0/-1
...to allow the sibling subtraction fold.
This pattern could regress with the proposed change in D57401.
llvm-svn: 352680
Summary:
This switches the EH implementation to the new proposal:
https://github.com/WebAssembly/exception-handling/blob/master/proposals/Exceptions.md
(The previous proposal was
https://github.com/WebAssembly/exception-handling/blob/master/proposals/old/Exceptions.md)
- Instruction changes
- Now we have one single `catch` instruction that returns a except_ref
value
- `throw` now can take variable number of operations
- `rethrow` does not have 'depth' argument anymore
- `br_on_exn` queries an except_ref to see if it matches the tag and
branches to the given label if true.
- `extract_exception` is a pseudo instruction that simulates popping
values from wasm stack. This is to make `br_on_exn`, a very special
instruction, work: `br_on_exn` puts values onto the stack only if it
is taken, and the # of values can vay depending on the tag.
- Now there's only one `catch` per `try`, this patch removes all special
handling for terminate pad with a call to `__clang_call_terminate`.
Before it was the only case there are two catch clauses (a normal
`catch` and `catch_all` per `try`).
- Make `rethrow` act as a terminator like `throw`. This splits BB after
`rethrow` in WasmEHPrepare, and deletes an unnecessary `unreachable`
after `rethrow` in LateEHPrepare.
- Now we stop at all catchpads (because we add wasm `catch` instruction
that catches all exceptions), this creates new
`findWasmUnwindDestinations` function in SelectionDAGBuilder.
- Now we use `br_on_exn` instrution to figure out if an except_ref
matches the current tag or not, LateEHPrepare generates this sequence
for catch pads:
```
catch
block i32
br_on_exn $__cpp_exception
end_block
extract_exception
```
- Branch analysis for `br_on_exn` in WebAssemblyInstrInfo
- Other various misc. changes to switch to the new proposal.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D57134
llvm-svn: 352598
This is the sibling fold for insert-of-insert that was added with D56604.
Now that we have x86 shuffle narrowing (D57156), this change shows improvements for
lots of AVX512 reduction code (not sure that we would ever expect extract-of-extract otherwise).
There's a small regression in some of the partial-permute tests (extracting followed by splat).
That is tracked by PR40500:
https://bugs.llvm.org/show_bug.cgi?id=40500
Differential Revision: https://reviews.llvm.org/D57336
llvm-svn: 352528
This fixes most references to the paths:
llvm.org/svn/
llvm.org/git/
llvm.org/viewvc/
github.com/llvm-mirror/
github.com/llvm-project/
reviews.llvm.org/diffusion/
to instead point to https://github.com/llvm/llvm-project.
This is *not* a trivial substitution, because additionally, all the
checkout instructions had to be migrated to instruct users on how to
use the monorepo layout, setting LLVM_ENABLE_PROJECTS instead of
checking out various projects into various subdirectories.
I've attempted to not change any scripts here, only documentation. The
scripts will have to be addressed separately.
Additionally, I've deleted one document which appeared to be outdated
and unneeded:
lldb/docs/building-with-debug-llvm.txt
Differential Revision: https://reviews.llvm.org/D57330
llvm-svn: 352514
During the lowering of a switch that would result in the generation of a
jump table, a range check is performed before indexing into the jump
table, for the switch value being outside the jump table range and a
conditional branch is inserted to jump to the default block. In case the
default block is unreachable, this conditional jump can be omitted. This
patch implements omitting this conditional branch for unreachable
defaults.
Review ID: D52002
Reviewers: Hans Wennborg, Eli Freidman, Roman Lebedev
llvm-svn: 352484
A FrameIndex should be valid throughout a block regardless of what instructions
get selected in that block -- therefore we shouldn't harness dbg.values that
refer to FrameIndexes to an SDNode. There are numerous codegen reasons why
an SDNode never appears or doesn't become a location that a DBG_VALUE can
refer to. None of them actually affect the variable location.
Therefore, before any other tests to encode dbg_values in a SelectionDAG,
identify FrameIndex operands and encode them unattached to any SDNode.
Differential Revision: https://reviews.llvm.org/D57328
llvm-svn: 352467
This did not cause the buildbot failure it was previously reverted for.
Original commit message:
I'm not sure why we were using SEXTLOAD. EXTLOAD seems more appropriate since we don't care about the upper bits.
This patch changes this and then modifies the X86 post legalization combine to emit a extending shuffle instead of a sign_extend_vector_inreg. Could maybe use an any_extend_vector_inre
On AVX512 targets I think we might be able to use a masked vpmovzx and not have to expand this at all.
llvm-svn: 352433
Followup to D56636, this time handling the UADDSAT case by expanding
uadd.sat(a, b) to umin(a, ~b) + b.
Differential Revision: https://reviews.llvm.org/D56869
llvm-svn: 352409
This patch improves the placement of DBG_VALUEs when by SelectionDAG, which
as documented in PR40427 can go very wrong. At the core of this is
ProcessSourceNode, which assumes the last instruction in a BB is the start
of the last processed IR instruction, which isn't always true.
Instead, use a helper function to call InstrEmitter::EmitNode, that records
before-and-after iterators and determines the first of any new instruction
created during emission. This is passed to ProcessSourceNode, which can
then make more elightened decisions about ordering for DBG_VALUE placement.
Differential revision: https://reviews.llvm.org/D57163
llvm-svn: 352350
Summary:
I'm not sure why we were using SEXTLOAD. EXTLOAD seems more appropriate since we don't care about the upper bits.
This patch changes this and then modifies the X86 post legalization combine to emit a extending shuffle instead of a sign_extend_vector_inreg. Could maybe use an any_extend_vector_inreg, but I just did what we already do in LowerLoad. I think we can actually get rid of this code entirely if we switch to -x86-experimental-vector-widening-legalization.
On AVX512 targets I think we might be able to use a masked vpmovzx and not have to expand this at all.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D57186
llvm-svn: 352255
It should be emitted when any floating-point operations (including
calls) are present in the object, not just when calls to printf/scanf
with floating point args are made.
The difference caused by this is very subtle: in static (/MT) builds,
on x86-32, in a program that uses floating point but doesn't print it,
the default x87 rounding mode may not be set properly upon
initialization.
This commit also removes the walk of the types pointed to by pointer
arguments in calls. (To assist in opaque pointer types migration --
eventually the pointee type won't be available.)
That latter implies that it will no longer consider a call like
`scanf("%f", &floatvar)` as sufficient to emit _fltused on its
own. And without _fltused, `scanf("%f")` will abort with error R6002. This
new behavior is unlikely to bite anyone in practice (you'd have to
read a float, and do nothing with it!), and also, is consistent with
MSVC.
Differential Revision: https://reviews.llvm.org/D56548
llvm-svn: 352076
The current check in CombineToPreIndexedLoadStore is too
conversative, preventing a pre-indexed store when the base pointer
is a predecessor of the value being stored. Instead, we should check
the pointer operand of the store.
Differential Revision: https://reviews.llvm.org/D56719
llvm-svn: 351933
Also add debug prints in the default case of the switches in these routines.
Most if not all of the type legalization handlers already do this so this makes promoting floats consistent
llvm-svn: 351890
vecbo (insertsubv undef, X, Z), (insertsubv undef, Y, Z) --> insertsubv VecC, (vecbo X, Y), Z
This is another step in generic vector narrowing. It's also a step towards more horizontal op
formation specifically for x86 (although we still failed to match those in the affected tests).
The scalarization cases are also not optimal (we should be scalarizing those), but it's still
an improvement to use a narrower vector op when we know part of the result must be constant
because both inputs are undef in some vector lanes.
I think a similar match but checking for a constant operand might help some of the cases in
D51553.
Differential Revision: https://reviews.llvm.org/D56875
llvm-svn: 351825
The regression test is reduced from the example shown in D56281.
This does raise a question as noted in the test file: do we want
to handle this pattern? I don't have a motivating example for
that on x86 yet, but it seems like we could have that pattern
there too, so we could avoid the back-and-forth using a shuffle.
llvm-svn: 351753
to reflect the new license.
We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.
Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.
llvm-svn: 351636
Summary:
This patch makes some changes related to -dag-dump-verbose.
Main use case has been when debugging how SelectionDAG is
dealing with debug info (SDDbgValue nodes).
1) We now print the number of DbgValues that are mapped to each
SDNode.
2) Removed duplicated printing of DebugLoc (nowadays DebugLoc is
printed also when not using -dag-dump-verbose).
3) Renamed SDDbgValue::dump to SDDbgValue::print, and added a
new SDDbgValue::dump that will start a new line after calling
print.
4) SDDbgValue::print now prints "Order", and it also prints
some additional information when kind is CONST/FRAMEIX/VREG.
5) SelectionDAG::dump() now dumps all SDDbgValue nodes after
the list of SDNodes (both "regular" and "ByVal" SDDbgValue:s).
Invalidated nodes are not printed.
6) Prohibit inline printing of SDNode operands that has SDDbgValue
nodes associated to them.
Reviewers: jmorse, aprantl
Reviewed By: aprantl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D56793
llvm-svn: 351581
Similar to D55073. Without this change, the DAG combiner crashes on code
with more than 64k of stores in a single basic block that form parallelizable
chains.
No test case, as it would be very IR file.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D56740
llvm-svn: 351571
Defer inline asm's output fixup work until after we've generated the
inline asm node itself. Remove StoresToEmit, IndirectStoresToEmit, and
RetValRegs in favor of using ConstraintOperands.
llvm-svn: 351558
This functionality is required at multiple places which potentially
create large operand lists, like SelectionDAGBuilder or DAGCombiner.
Differential Revision: https://reviews.llvm.org/D56739
llvm-svn: 351552
Summary:
Use this helper to make sure we use the same value at various places.
This will likely be needed at more places were we currently crash
because we use more operands than possible.
Also makes it easier to change in the future.
Reviewers: RKSimon, craig.topper, efriedma, aemerson
Reviewed By: RKSimon
Subscribers: hiraditya, arsenm, llvm-commits
Differential Revision: https://reviews.llvm.org/D56859
llvm-svn: 351537
We should not pre-scheduled the node has ADJCALLSTACKDOWN parent,
or else, when bottom-up scheduling, ADJCALLSTACKDOWN and
ADJCALLSTACKUP may hold CallResource too long and make other
calls can't be scheduled. If there's no other available node
to schedule, the scheduler will try to rename the register by
creating copy to avoid the conflict which will fail because
CallResource is not a real physical register.
llvm-svn: 351527
Summary:
This patch supports MS SEH extensions __try/__except/__finally. The intrinsics localescape and localrecover are responsible for communicating escaped static allocas from the try block to the handler.
We need to preserve frame pointers for SEH. So we create a new function/property HasLocalEscape.
Reviewers: rnk, compnerd, mstorsjo, TomTan, efriedma, ssijaric
Reviewed By: rnk, efriedma
Subscribers: smeenai, jrmuizel, alex, majnemer, ssijaric, ehsan, dmajor, kristina, javed.absar, kristof.beyls, chrib, llvm-commits
Differential Revision: https://reviews.llvm.org/D53540
llvm-svn: 351370
dbg.value intrinsics can appear in blocks where their operand is not used,
meaning the operand never receives an SDNode, and thus no DBG_VALUE will
be created. Get around this by looking to see whether the operand has already
been allocated a virtual register. This allows dbg.values of Phi node and
Values that are used across basic blocks to successfully be translated into
DBG_VALUEs.
Differential Revision: https://reviews.llvm.org/D56678
llvm-svn: 351358
The value returned by max() is the last valid value, adjust the
comparison accordingly.
The code added in D55073 creates TokenFactors with max() operands.
Reviewers: aemerson, efriedma, RKSimon, craig.topper
Reviewed By: aemerson
Differential Revision: https://reviews.llvm.org/D56738
llvm-svn: 351318
ReduceLoadWidth can trigger using a shifted mask is used and this
requires that the function return a shl node to correct for the
offset. However, the way that this was implemented meant that the
returned result could be an existing node, which would be incorrect.
This fixes the method of inserting the new node and replacing uses.
Differential Revision: https://reviews.llvm.org/D50432
llvm-svn: 351310
The motivating case for this is shown in the first regression test. We are
transferring to scalar and back rather than just zero-extending with 'vpmovzxdq'.
That's a special-case for a more general pattern as shown here. In all tests,
we're avoiding the vector-scalar-vector moves in favor of vector ops.
We aren't producing optimal shuffle code in some cases though, so the patch is
limited to reduce regressions.
Differential Revision: https://reviews.llvm.org/D56281
llvm-svn: 351198
I accidentally triggered this code while doing some experiments and it doesn't look lke it could possibly work.
It calls 'getNOT' on a node that should be a CondCode.
I think to do this right we would need to swap the branch target and the fallthrough target. But that's not easy to do. Or we could create an explicit SetCC and feed that into a new BR_CC?
llvm-svn: 351022
This pattern:
t33: v8i32 = insert_subvector undef:v8i32, t35, Constant:i64<0>
t21: v16i32 = insert_subvector undef:v16i32, t33, Constant:i64<0>
...shows up in PR33758:
https://bugs.llvm.org/show_bug.cgi?id=33758
...although this patch doesn't make any difference to the final result on that yet.
In the affected tests here, it looks like it just makes RA wiggle. But we might
as well squash this to prevent it interfering with other pattern-matching.
Differential Revision:
https://reviews.llvm.org/D56604
llvm-svn: 351008
This patch takes some of the code from D49837 to allow us to enable ISD::ABS support for all SSE vector types.
Differential Revision: https://reviews.llvm.org/D56544
llvm-svn: 350998
Summary:
When legalizing the result of a SELECT_CC node by promoting the
floating-point type, use the promoted-to type rather than the original
type.
Fix PR40273.
Reviewers: efriedma, majnemer
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D56566
llvm-svn: 350951
That is, remove many of the calls to Type::getNumContainedTypes(),
Type::subtypes(), and Type::getContainedType(N).
I'm not intending to remove these accessors -- they are
useful/necessary in some cases. However, removing the pointee type
from pointers would potentially break some uses, and reducing the
number of calls makes it easier to audit.
llvm-svn: 350835
This removes check for single use from general ShrinkDemandedConstant
to the BE because of the AArch64 regression after D56289/rL350475.
After several hours of experiments I did not come up with a testcase
failing on any other targets if check is not performed.
Moreover, direct call to ShrinkDemandedConstant is not really needed
and superceed by SimplifyDemandedBits.
Differential Revision: https://reviews.llvm.org/D56406
llvm-svn: 350684
As we saw in D56057 when we tried to use this function on X86, it's unsafe. It allows the operand node to have multiple users, but doesn't prevent recursing past the first node when it does have multiple users. This can cause other simplifications earlier in the graph without regard to what bits are needed by the other users of the first node. Ideally all we should do to the first node if it has multiple uses is bypass it when its not needed by the user we started from. Doing any other transformation that SimplifyDemandedBits can do like turning ZEXT/SEXT into AEXT would result in an increase in instructions.
Fortunately, we already have a function that can do just that, GetDemandedBits. It will only make transformations that involve bypassing a node.
This patch changes AMDGPU's simplifyI24, to use a combination of GetDemandedBits to handle the multiple use simplifications. And then uses the regular SimplifyDemandedBits on each operand to handle simplifications allowed when the operand only has a single use. Unfortunately, GetDemandedBits simplifies constants more aggressively than SimplifyDemandedBits. This caused the -7 constant in the changed test to be simplified to remove the upper bits. I had to modify computeKnownBits to account for this by ignoring the upper 8 bits of the input.
Differential Revision: https://reviews.llvm.org/D56087
llvm-svn: 350560
The FSHL/FSHR nodes are handled in the expand function, but they need to also be listed in the code that queries for the operation action too.
llvm-svn: 350490
Fixes cvt_f32_ubyte combine. performCvtF32UByteNCombine() could shrink
source node to demanded bits only even if there are other uses.
Differential Revision: https://reviews.llvm.org/D56289
llvm-svn: 350475
This adds support for calculating sign bits of insert_subvector. I based it on the computeKnownBits.
My motivating case is propagating sign bits information across basic blocks on AVX targets where concatenating using insert_subvector is common.
Differential Revision: https://reviews.llvm.org/D56283
llvm-svn: 350432
As noted in PR39973 and D55558:
https://bugs.llvm.org/show_bug.cgi?id=39973
...this is a partial implementation of a fold that we do as an IR canonicalization in instcombine:
// extelt (binop X, Y), Index --> binop (extelt X, Index), (extelt Y, Index)
We want to have this in the DAG too because as we can see in some of the test diffs (reductions),
the pattern may not be visible in IR.
Given that this is already an IR canonicalization, any backend that would prefer a vector op over
a scalar op is expected to already have the reverse transform in DAG lowering (not sure if that's
a realistic expectation though). The transform is limited with a TLI hook because there's an
existing transform in CodeGenPrepare that tries to do the opposite transform.
Differential Revision: https://reviews.llvm.org/D55722
llvm-svn: 350354
Currently we expand the two nodes separately. This gives DAG combiner an opportunity to optimize the expanded sequence taking into account only one set of users. When we expand the other node we'll create the expansion again, but might not be able to optimize it the same way. So the nodes won't CSE and we'll have two similarish sequences in the same basic block. By expanding both nodes at the same time we'll avoid prematurely optimizing the expansion until both the division and remainder have been replaced.
Improves the test case from PR38217. There may be additional opportunities after this.
Differential Revision: https://reviews.llvm.org/D56145
llvm-svn: 350239
By also promoting the input type we get a better idea for what scalar type to use. This can provide better results if the result of the extract is sign extended. What was previously happening is that the extract result would be legalized, sometime later the input of the sign extend would be legalized using the result of the extract. Then later the extract input would be legalized forcing a truncate into the input of the sign extend using a replace all uses. This requires DAG combine to combine out the sext/truncate pair. But sometimes we visited the truncate first and messed things up before the sext could be combined.
By creating the extract with the correct scalar type when we create legalize the result type, the truncate will be added right away. Then when the sign_extend input is legalized it will create an any_extend of the truncate which can be optimized by getNode to maybe remove the truncate. And then a sign_extend_inreg. Now DAG combine doesn't have to worry about getting rid of the extend.
This fixes the regression on X86 in D56156.
Differential Revision: https://reviews.llvm.org/D56176
llvm-svn: 350236
If x has multiple sign bits than it doesn't matter which one we extend from so we can sext from x's msb instead.
The X86 setcc-combine.ll changes are a little weird. It appears we ended up with a (sext_inreg (aext (trunc (extractelt)))) after type legalization. The sext_inreg+aext now gets optimized by this combine to leave (sext (trunc (extractelt))). Then we visit the trunc before we visit the sext. This ends up changing the truncate to an extractvectorelt from a bitcasted vector. I have a follow up patch to fix this.
Differential Revision: https://reviews.llvm.org/D56156
llvm-svn: 350235
default
During the lowering of a switch that would result in the generation of a jump
table, a range check is performed before indexing into the jump table, for the
switch value being outside the jump table range and a conditional branch is
inserted to jump to the default block. In case the default block is
unreachable, this conditional jump can be omitted. This patch implements
omitting this conditional branch for unreachable defaults.
Review Reference: D52002
llvm-svn: 350186
The patch adds a possibility to make library calls on NVPTX.
An important thing about library functions - they must be defined within
the current module. This basically should guarantee that we produce a
valid PTX assembly (without calls to not defined functions). The one who
wants to use the libcalls is probably will have to link against
compiler-rt or any other implementation.
Currently, it's completely impossible to make library calls because of
error LLVM ERROR: Cannot select: i32 = ExternalSymbol '...'. But we can
lower ExternalSymbol to TargetExternalSymbol and verify if the function
definition is available.
Also, there was an issue with a DAG during legalisation. When we expand
instruction into libcall, the inner call-chain isn't being "integrated"
into outer chain. Since the last "data-flow" (call retval load) node is
located in call-chain earlier than CALLSEQ_END node, the latter becomes
a leaf and therefore a dead node (and is being removed quite fast).
Proposed here solution relies on another data-flow pseudo nodes
(ProxyReg) which purpose is only to keep CALLSEQ_END at legalisation and
instruction selection phases - we remove the pseudo instructions before
register scheduling phase.
Patch by Denys Zariaiev!
Differential Revision: https://reviews.llvm.org/D34708
llvm-svn: 350069
This is an alternative to what I attempted in D56057.
GetDemandedBits is a special version of SimplifyDemandedBits that allows simplifications even when the operand has other uses. GetDemandedBits will only do simplifications that allow a node to be bypassed. It won't create new nodes or alter any of the other users.
I had to add support for bypassing SIGN_EXTEND_INREG to GetDemandedBits.
Based on a patch that Simon Pilgrim sent me in email.
Fixes PR40142.
llvm-svn: 350059
More migration so we can disable the implicit int -> LocationSize
conversion.
All of these are either scatter/gather'ed vector instructions, or direct
loads. Hence, they're all precise.
Perhaps if we see way more getTypeStoreSize calls, we can make a
getTypeStoreLocationSize (or similar) as a wrapper that applies this
::precise. Doesn't appear that it's a good idea to make getTypeStoreSize
return a LocationSize itself, however.
llvm-svn: 350042
It's dangerous to knowingly create an illegal vector type
no matter what stage of combining we're in.
This prevents the missed folding/scalarization seen in:
https://bugs.llvm.org/show_bug.cgi?id=40146
llvm-svn: 350034
trunc (add X, C ) --> add (trunc X), C'
If we're throwing away the top bits of an 'add' instruction, do it in the narrow destination type.
This makes the truncate-able opcode list identical to the sibling transform done in IR (in instcombine).
This change used to show regressions for x86, but those are gone after D55494.
This gets us closer to deleting the x86 custom function (combineTruncatedArithmetic)
that does almost the same thing.
Differential Revision: https://reviews.llvm.org/D55866
llvm-svn: 350006
This saves materializing the immediate. The additional forms are less
common (they don't usually show up for bitfield insert/extract), but
they're still relevant.
I had to add a new target hook to prevent DAGCombine from reversing the
transform. That isn't the only possible way to solve the conflict, but
it seems straightforward enough.
Differential Revision: https://reviews.llvm.org/D55630
llvm-svn: 349857
This patch enables funnel shift -> rotate building for all ROTL/ROTR custom/legal operations.
AFAICT X86 was the last target that was missing modulo support (PR38243), but I've tried to CC stakeholders for every target that has ROTL/ROTR custom handling for their final OK.
Differential Revision: https://reviews.llvm.org/D55747
llvm-svn: 349765
Now that SimplifyDemandedBits/SimplifyDemandedVectorElts is simplifying vector elements, we're seeing more constant BUILD_VECTOR containing undefs.
This patch provides opt-in support for UNDEF elements in matchBinaryPredicate, passing NULL instead of the result ConstantSDNode* argument.
I've updated the (or (and X, c1), c2) -> (and (or X, c2), c1|c2) fold to demonstrate its use, which I believe is safe for undef cases.
Differential Revision: https://reviews.llvm.org/D55822
llvm-svn: 349629
Now that SimplifyDemandedBits/SimplifyDemandedVectorElts is simplifying vector elements, we're seeing more constant BUILD_VECTOR containing undefs.
This patch provides opt-in support for UNDEF elements in matchBinaryPredicate, passing NULL instead of the result ConstantSDNode* argument.
Differential Revision: https://reviews.llvm.org/D55822
llvm-svn: 349628
As described on PR40091, we have several places where zext (and zext_vector_inreg) fold an undef input into an undef output. For zero extensions this is incorrect as the output should guarantee to least have the new upper bits set to zero.
SimplifyDemandedVectorElts is the worst offender (and its the most likely to cause new undefs to appear) but DAGCombiner's tryToFoldExtendOfConstant has a similar issue.
Thanks to @dmgreen for catching this.
Differential Revision: https://reviews.llvm.org/D55883
llvm-svn: 349625
Now that SimplifyDemandedBits/SimplifyDemandedVectorElts are simplifying vector elements, we're seeing more constant BUILD_VECTOR containing UNDEFs.
This patch provides opt-in handling of UNDEF elements in matchUnaryPredicate, passing NULL instead of the ConstantSDNode* argument.
I've updated SelectionDAG::simplifyShift to demonstrate its use.
Differential Revision: https://reviews.llvm.org/D55819
llvm-svn: 349616
SelectionDAG currently changes these intrinsics to function calls, but that won't work
for other ISel's. Also we want to eventually support nonlazybind and weak linkage coming
from the front-end which we can't do in SelectionDAG.
llvm-svn: 349552
For opcodes not covered by SimplifyDemandedVectorElts, SimplifyDemandedBits might be able to help now that it supports demanded elts as well.
llvm-svn: 349466
The assertion type is always supposed to be a scalar type. So if the result VT of the assertion is a vector, we need to get the scalar VT before we can compare them.
Similarly for the assert above it.
I don't have a test case because I don't know of any place we violate this today. A coworker found this while trying to use r347287 on the 6.0 branch without also having r336868
llvm-svn: 349390
This is an initial patch to add the necessary support for a DemandedElts argument to SimplifyDemandedBits, more closely matching computeKnownBits and to help improve vector codegen.
I've added only a small amount of the changes necessary to get at least one test to update - a lot more can be done but I'd like to add these methodically with proper test coverage, at the same time the hope is to slowly move some/all of SimplifyDemandedVectorElts into SimplifyDemandedBits as well.
Differential Revision: https://reviews.llvm.org/D55768
llvm-svn: 349374
We keep a few iterators into the basic block we're selecting while
performing FastISel. Usually this is fine, but occasionally code wants
to remove already-emitted instructions. When this happens we have to be
careful to update those iterators so they're not pointint at dangling
memory.
llvm-svn: 349365
The transform performs a bitwise logic op in a wider type followed by
truncate when both inputs are truncated from the same source type:
logic_op (truncate x), (truncate y) --> truncate (logic_op x, y)
There are a bunch of other checks that should prevent doing this when
it might be harmful.
We already do this transform for scalars in this spot. The vector
limitation was shared with a check for the case when the operands are
extended. I'm not sure if that limit is needed either, but that would
be a separate patch.
Differential Revision: https://reviews.llvm.org/D55448
llvm-svn: 349303
Also exposes an issue in DAGCombiner::visitFunnelShift where we were assuming the shift amount had the result type (after legalization it'll have the targets shift amount type).
llvm-svn: 349298
Summary:
If the setcc already has the target desired type we can reach the getSetCC/getSExtOrTrunc after the MatchingVecType check with the exact same types as the nodes we started with. This causes those causes VsetCC to be CSEd to N0 and the getSExtOrTrunc will CSE to N. When we return N, the caller will think that meant we called CombineTo and did our own worklist management. But that's not what happened. This prevents target hooks from being called for the node.
To fix this, I've now returned SDValue if the setcc is already the desired type. But to avoid some regressions in X86 I've had to disable one of the target combines that wasn't being reached before in the case of a (sext (setcc)). If we get vector widening legalization enabled that entire function will be deleted anyway so hopefully this is only for the short term.
Reviewers: RKSimon, spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D55459
llvm-svn: 349137
This isn't quite NFC, but I don't know how to expose
any outward diffs from these changes. Mostly, this
was confusing because it used 'VT' to refer to the
operand type rather the usual type of the input node.
There's also a large block at the end that is dedicated
solely to matching loads, but that wasn't obvious. This
could probably be split up into separate functions to
make it easier to see.
It's still not clear to me when we make certain transforms
because the legality and constant conditions are
intertwined in a way that might be improved.
llvm-svn: 349095
This is a retry of rL349051 (reverted at rL349056). I changed the check for dead-ness from
number of uses to an opcode test for DELETED_NODE based on existing similar code.
Differential Revision: https://reviews.llvm.org/D55655
llvm-svn: 349058
Move existing rotation expansion code into TargetLowering and set it up for vectors as well.
Ideally this would share more of the funnel shift expansion, but we handle the shift amount modulo quite differently at the moment.
Begun removing x86 vector rotate custom lowering to use the expansion.
llvm-svn: 349025
Summary:
All targets either just return false here or properly model `Fast`, so I
don't think there is any reason to prevent CodeGen from doing the right
thing here.
Subscribers: nemanjai, javed.absar, eraman, jsji, llvm-commits
Differential Revision: https://reviews.llvm.org/D55365
llvm-svn: 349016
This patch introduces a generic function to determine whether a given vector type is known to be a splat value for the specified demanded elements, recursing up the DAG looking for BUILD_VECTOR or VECTOR_SHUFFLE splat patterns.
It also keeps track of the elements that are known to be UNDEF - it returns true if all the demanded elements are UNDEF (as this may be useful under some circumstances), so this needs to be handled by the caller.
A wrapper variant is also provided that doesn't take the DemandedElts or UndefElts arguments for cases where we just want to know if the SDValue is a splat or not (with/without UNDEFS).
I had hoped to completely remove the X86 local version of this function, but I'm seeing some regressions in shift/rotate codegen that will take a little longer to fix and I hope to get this in sooner so I can continue work on PR38243 which needs more capable splat detection.
Differential Revision: https://reviews.llvm.org/D55426
llvm-svn: 348953
If either of the operand elements are zero then we know the result element is going to be zero (even if the other element is undef).
Differential Revision: https://reviews.llvm.org/D55558
llvm-svn: 348926
Add an intrinsic that takes 2 signed integers with the scale of them provided
as the third argument and performs fixed point multiplication on them.
This is a part of implementing fixed point arithmetic in clang where some of
the more complex operations will be implemented as intrinsics.
Differential Revision: https://reviews.llvm.org/D54719
llvm-svn: 348912
Summary:
All targets either just return false here or properly model `Fast`, so I
don't think there is any reason to prevent CodeGen from doing the right
thing here.
Subscribers: nemanjai, javed.absar, eraman, jsji, llvm-commits
Differential Revision: https://reviews.llvm.org/D55365
llvm-svn: 348843
If all the demanded elements of the SimplifyDemandedVectorElts are known to be UNDEF, we can simplify to an ISD::UNDEF node.
Zero constant folding will be handled in a future patch - its a little trickier as we often have bitcasted zero values.
Differential Revision: https://reviews.llvm.org/D55511
llvm-svn: 348784
As discussed on D55511, this caused an issue if the inner node deletes a node that the outer node depends upon. As it doesn't affect any lit-tests and I've only been able to expose this with the D55511 change I'm committing this now.
llvm-svn: 348781
This triggers an assert when combining concat_vectors of a bitcast of
merge_values.
With asserts disabled, it fails to select:
fatal error: error in backend: Cannot select: 0x7ff19d000e90: i32 = any_extend 0x7ff19d000ae8
0x7ff19d000ae8: f64,ch = CopyFromReg 0x7ff19d000c20:1, Register:f64 %1
0x7ff19d000b50: f64 = Register %1
In function: d
Differential Revision: https://reviews.llvm.org/D55507
llvm-svn: 348759
Currently, dbg.value's of "nullptr" are dropped when entering a SelectionDAG --
apparently just because of an oversight when recognising Values that are
constant (see PR39787). This patch adds ConstantPointerNull to the list of
constants that can be turned into DBG_VALUEs.
The matter of what bit-value a null pointer constant in LLVM has was raised
in this mailing list thread:
http://lists.llvm.org/pipermail/llvm-dev/2018-December/128234.html
Where it transpires LLVM relies on (IR) null pointers being zero valued,
thus I've baked this assumption into the patch.
Differential Revision: https://reviews.llvm.org/D55227
llvm-svn: 348753
This is a fix for PR39896, where dbg.value's of SDNodes that have been
optimised out do not lead to "DBG_VALUE undef" instructions being created.
Such undef instructions are necessary to terminate earlier variable
ranges, otherwise variable values leak past the point where they're valid.
The "invalidated" flag of SDDbgValue is currently being abused to mean two
things:
* The corresponding SDNode is now invalid
* This SDDbgValue should not be emitted
Of which there are several legitimate combinations of meaning:
* The SDNode has been invalidated and we should emit "DBG_VALUE undef"
* The SDNode has been invalidated but the debug data was salvaged, don't
emit anything for this SDDbgValue
* This SDDbgValue has been emitted
This patch introduces distinct "Emitted" and "Invalidated" fields to the
SDDbgValue class, updates users accordingly, and generates "undef"
DBG_VALUEs for invalidated records. Awkwardly, there are circumstances
where we emit SDDbgValue's twice, specifically DebugInfo/X86/dbg-addr-dse.ll
which I've preserved.
Differential Revision: https://reviews.llvm.org/D55372
llvm-svn: 348751
This is effectively re-committing the changes from:
rL347917 (D54640)
rL348195 (D55126)
...which were effectively reverted here:
rL348604
...because the code had a bug that could induce infinite looping
or eventual out-of-memory compilation.
The bug was that this code did not guard against transforming
opaque constants. More details are in the post-commit mailing
list thread for r347917. A reduced test for that is included
in the x86 bool-math.ll file. (I wasn't able to reduce a PPC
backend test for this, but it was almost the same pattern.)
Original commit message for r347917:
The motivating case for this is shown in:
https://bugs.llvm.org/show_bug.cgi?id=32023
and the corresponding rot16.ll regression tests.
Because x86 scalar shift amounts are i8 values, we can end up with trunc-binop-trunc
sequences that don't get folded in IR.
As the TODO comments suggest, there will be regressions if we extend this (for x86,
we mostly seem to be missing LEA opportunities, but there are likely vector folds
missing too). I think those should be considered existing bugs because this is the
same transform that we do as an IR canonicalization in instcombine. We just need
more tests to make those visible independent of this patch.
llvm-svn: 348706
These nodes should have two results. A real VT and a Glue. But this code would have returned Undef which would only be a single result. But we're in the single result version of getNode so these opcodes should never be seen by this function anyway.
llvm-svn: 348670
As discussed in the post-commit thread of r347917, this
transform is fighting with an existing transform causing
an infinite loop or out-of-memory, so this is effectively
reverting r347917 and its follow-up r348195 while we
investigate the bug.
llvm-svn: 348604
If this is not a valid way to assign an SDLoc, then we get this
wrong all over SDAG.
I don't know enough about the SDAG to explain this. IIUC, theoretically,
debug info is not supposed to affect codegen. But here it has clearly
affected 3 different targets, and the x86 change is an actual improvement.
llvm-svn: 348552
We shouldn't care about the debug location for a node that
we're creating, but attaching the root of the pattern should
be the best effort. (If this is not true, then we are doing
it wrong all over the SDAG).
This is no-functional-change-intended, and there are no
regression test diffs...and that's what I expected. But
there's a similar line above this diff, where those
assumptions apparently do not hold.
llvm-svn: 348550
This was probably organized as it was because bswap is a unary op.
But that's where the similarity to the other opcodes ends. We should
not limit this transform to scalars, and we should not try it if
either input has other uses. This is another step towards trying to
clean this whole function up to prevent it from causing infinite loops
and memory explosions.
Earlier commits in this series:
rL348501
rL348508
rL348518
llvm-svn: 348534
Unlike some of the folds in hoistLogicOpWithSameOpcodeHands()
above this shuffle transform, this has the expected hasOneUse()
checks in place.
llvm-svn: 348523
This patch introduces a new DAGCombiner rule to simplify concat_vectors nodes:
concat_vectors( bitcast (scalar_to_vector %A), UNDEF)
--> bitcast (scalar_to_vector %A)
This patch only partially addresses PR39257. In particular, it is enough to fix
one of the two problematic cases mentioned in PR39257. However, it is not enough
to fix the original test case posted by Craig; that particular case would
probably require a more complicated approach (and knowledge about used bits).
Before this patch, we used to generate the following code for function PR39257
(-mtriple=x86_64 , -mattr=+avx):
vmovsd (%rdi), %xmm0 # xmm0 = mem[0],zero
vxorps %xmm1, %xmm1, %xmm1
vblendps $3, %xmm0, %xmm1, %xmm0 # xmm0 = xmm0[0,1],xmm1[2,3]
vmovaps %ymm0, (%rsi)
vzeroupper
retq
Now we generate this:
vmovsd (%rdi), %xmm0 # xmm0 = mem[0],zero
vmovaps %ymm0, (%rsi)
vzeroupper
retq
As a side note: that VZEROUPPER is completely redundant...
I guess the vzeroupper insertion pass doesn't realize that the definition of
%xmm0 from vmovsd is already zeroing the upper half of %ymm0. Note that on
%-mcpu=btver2, we don't get that vzeroupper because pass vzeroupper insertion
%pass is disabled.
Differential Revision: https://reviews.llvm.org/D55274
llvm-svn: 348522
The PPC test with 2 extra uses seems clearly better by avoiding this transform.
With 1 extra use, we also prevent an extra register move (although that might
be an RA problem). The general rule should be to only make a change here if
it is always profitable. The x86 diffs are all neutral.
llvm-svn: 348518
The AVX512 diffs are neutral, but the bswap test shows a clear overreach in
hoistLogicOpWithSameOpcodeHands(). If we don't check for other uses, we can
increase the instruction count.
This could also fight with transforms trying to go in the opposite direction
and possibly blow up/infinite loop. This might be enough to solve the bug
noted here:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20181203/608593.html
I did not add the hasOneUse() checks to all opcodes because I see a perf
regression for at least one opcode. We may decide that's irrelevant in the
face of potential compiler crashing, but I'll see if I can salvage that first.
llvm-svn: 348508
Because we're potentially peeking through a bitcast in this transform,
we need to use overall bitwidths rather than number of elements to
determine when it's safe to proceed.
Should fix:
https://bugs.llvm.org/show_bug.cgi?id=39893
llvm-svn: 348383
This is an initial patch to add a minimum level of support for funnel shifts to the SelectionDAG and to begin wiring it up to the X86 SHLD/SHRD instructions.
Some partial legalization code has been added to handle the case for 'SlowSHLD' where we want to expand instead and I've added a few DAG combines so we don't get regressions from the existing DAG builder expansion code.
Differential Revision: https://reviews.llvm.org/D54698
llvm-svn: 348353
Fix potential issue with the ISD::INSERT_VECTOR_ELT case tweaking the DemandedElts mask instead of using a local copy - so later uses of the mask use the tweaked version.....
Noticed while investigating adding zero/undef folding to SimplifyDemandedVectorElts and the altered DemandedElts mask was causing mismatches.
llvm-svn: 348348
There's a 64k limit on the number of SDNode operands, and some very large
functions with 64k or more loads can cause crashes due to this limit being hit
when a TokenFactor with this many operands is created. To fix this, create
sub-tokenfactors if we've exceeded the limit.
No test case as it requires a very large function.
rdar://45196621
Differential Revision: https://reviews.llvm.org/D55073
llvm-svn: 348324
PR17686 demonstrates that for some targets FP exceptions can fire in cases where the FP_TO_UINT is expanded using a FP_TO_SINT instruction.
The existing code converts both the inrange and outofrange cases using FP_TO_SINT and then selects the result, this patch changes this for 'strict' cases to pre-select the FP_TO_SINT input and the offset adjustment.
The X87 cases don't need the strict flag but generates much nicer code with it....
Differential Revision: https://reviews.llvm.org/D53794
llvm-svn: 348251
Add support for ISD::*_EXTEND and ISD::*_EXTEND_VECTOR_INREG opcodes.
The extra broadcast in trunc-subvector.ll will be fixed in an upcoming patch.
llvm-svn: 348246
This is the smallest vector enhancement I could find to D54640.
Here, we're allowing narrowing to only legal vector ops because we'll see
regressions without that. All of the test diffs are wins from what I can tell.
With AVX/AVX512, we can shrink ymm/zmm ops to xmm.
x86 vector multiplies are the problem case that we're avoiding due to the
patchwork ISA, and it's not clear to me if we can dance around those
regressions using TLI hooks or if we need preliminary patches to plug those
holes.
Differential Revision: https://reviews.llvm.org/D55126
llvm-svn: 348195
Summary:
Under -x86-experimental-vector-widening-legalization, fp_to_uint/fp_to_sint with a smaller than 128 bit vector type results are custom type legalized by promoting the result to a 128 bit vector by promoting the elements, inserting an assertzext/assertsext, then truncating back to original type. The truncate will be further legalizdd to a pack shuffle. In the case of a v8i8 result type, we'll end up with a v8i16 fp_to_sint. This will need to be further legalized during vector op legalization by promoting to v8i32 and then truncating again. Under avx2 this produces good code with two pack instructions, but Under avx512 this will result in a truncate instruction and a packuswb instruction. But we should be able to get away with a single truncate instruction.
The other option is to promote all the way to vXi32 result type during the first type legalization. But in some experimentation that seemed to require more work to produce good code for other configurations.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D54836
llvm-svn: 348158
This makes the SDAG behavior consistent with the way we do this in IR.
It's possible that we were getting the wrong answer before. For example,
'xor undef, undef --> 0' but 'xor undef, C' --> undef.
But the most practical improvement is likely as shown in the tests here -
for FP, we were overconstraining undef lanes to NaN, and that can prevent
vector simplifications/narrowing (see D51553).
llvm-svn: 348090
This change prevents the crash noted in the post-commit comments
for rL347478 :
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20181119/605166.html
We can't guarantee that an oversized shift amount is folded away,
so we have to check for it.
Note that I committed an incomplete fix for that crash with:
rL347502
But as discussed here:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20181126/605679.html
...we have to try harder.
So I'm not sure how to expose the bug now (and apparently no fuzzers have found
a way yet either).
On the plus side, we have discovered that we're missing real optimizations by
not simplifying nodes sooner, so the earlier fix still has value, and there's
likely more value in extending that so we can simplify more opcodes and simplify
when doing RAUW and/or putting nodes on the combiner worklist.
Differential Revision: https://reviews.llvm.org/D54954
llvm-svn: 348089
D52935 introduced the ability for SimplifyDemandedBits to call SimplifyDemandedVectorElts through BITCASTs if the demanded bit mask entirely covered the sub element.
This patch relaxes this to demanding an element if we need any bit from it.
Differential Revision: https://reviews.llvm.org/D54761
llvm-svn: 348073
Summary:
The VirtReg2Value mapping is crucial for getting consistently
reliable divergence information into the SelectionDAG. This
patch fixes a bunch of issues that lead to incorrect divergence
info and introduces tight assertions to ensure we don't regress:
1. VirtReg2Value is generated lazily; there were some cases where
a lookup was performed before all relevant virtual registers were
created, leading to an out-of-sync mapping. Those cases were:
- Complex code to lower formal arguments that generated CopyFromReg
nodes from live-in registers (fixed by never querying the mapping
for live-in registers).
- Code that generates CopyToReg for formal arguments that are used
outside the entry basic block (fixed by never querying the
mapping for Register nodes, which don't need the divergence info
anyway).
2. For complex values that are lowered to a sequence of registers,
all registers must be reflected in the VirtReg2Value mapping.
I am not adding any new tests, since I'm not actually aware of any
bugs that these problems are causing with trunk as-is. However,
I recently added a test case (in r346423) which fails when D53283 is
applied without this change. Also, the new assertions should provide
most of the effective test coverage.
There is one test change in sdwa-peephole.ll. The underlying issue
is that since the divergence info is now correct, the DAGISel will
select V_OR_B32 directly instead of S_OR_B32. This leads to an extra
COPY which affects the behavior of MachineLICM in a way that ends up
with the S_MOV_B32 with the constant in a different basic block than
the V_OR_B32, which is presumably what defeats the peephole.
Reviewers: alex-t, arsenm, rampitec
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D54340
llvm-svn: 348049
Summary:
If a given liveness arg of STATEPOINT is at a fixed frame index
(e.g. a function argument passed on stack), prefer to use this
fixed location even the address is also in a register. If we use
the register it will generate a spill, which is not necessary
since the fixed frame index can be directly recorded in the stack
map.
Patch by Cherry Zhang <cherryyz@google.com>.
Reviewers: thanm, niravd, reames
Reviewed By: reames
Subscribers: cherryyz, reames, anna, arphaman, llvm-commits
Differential Revision: https://reviews.llvm.org/D53889
llvm-svn: 347998
Summary:
This simplifies writing predicates for pattern fragments that are
automatically re-associated or commuted.
For example, a followup patch adds patterns for fragments of the form
(add (shl $x, $y), $z) to the AMDGPU backend. Such patterns are
automatically commuted to (add $z, (shl $x, $y)), which makes it basically
impossible to refer to $x, $y, and $z generically in the PredicateCode.
With this change, the PredicateCode can refer to $x, $y, and $z simply
as `Operands[i]`.
Test confirmed that there are no changes to any of the generated files
when building all (non-experimental) targets.
Change-Id: I61c00ace7eed42c1d4edc4c5351174b56b77a79c
Reviewers: arsenm, rampitec, RKSimon, craig.topper, hfinkel, uweigand
Subscribers: wdng, tpr, llvm-commits
Differential Revision: https://reviews.llvm.org/D51994
llvm-svn: 347992
For targets where i32 is not a legal type (e.g. 64-bit RISC-V),
LegalizeIntegerTypes must promote the result of ISD::FLT_ROUNDS_.
Differential Revision: https://reviews.llvm.org/D53820
llvm-svn: 347986
For targets where i32 is not a legal type (e.g. 64-bit RISC-V),
LegalizeIntegerTypes must promote the operands of ISD::PREFETCH.
Differential Revision: https://reviews.llvm.org/D53281
llvm-svn: 347980
For targets where i32 is not a legal type (e.g. 64-bit RISC-V),
LegalizeIntegerTypes must promote the operand.
Differential Revision: https://reviews.llvm.org/D53279
llvm-svn: 347978
DAGTypeLegalizer::PromoteSetCCOperands currently prefers to zero-extend
operands when it is able to do so. For some targets this is more expensive
than a sign-extension, which is also a valid choice. Introduce the
isSExtCheaperThanZExt hook and use it in the new SExtOrZExtPromotedInteger
helper. On RISC-V, we prefer sign-extension for FromTy == MVT::i32 and ToTy ==
MVT::i64, as it can be performed using a single instruction.
Differential Revision: https://reviews.llvm.org/D52978
llvm-svn: 347977
The motivating case for this is shown in:
https://bugs.llvm.org/show_bug.cgi?id=32023
and the corresponding rot16.ll regression tests.
Because x86 scalar shift amounts are i8 values, we can end up with trunc-binop-trunc
sequences that don't get folded in IR.
As the TODO comments suggest, there will be regressions if we extend this (for x86,
we mostly seem to be missing LEA opportunities, but there are likely vector folds
missing too). I think those should be considered existing bugs because this is the
same transform that we do as an IR canonicalization in instcombine. We just need
more tests to make those visible independent of this patch.
Differential Revision: https://reviews.llvm.org/D54640
llvm-svn: 347917
I believe we should be legalizing these with the rest of vector binary operations. If any custom lowering is required for these nodes, this will give the DAG combine between LegalizeVectorOps and LegalizeDAG to run on the custom code before constant build_vectors are lowered in LegalizeDAG.
I've moved MULHU/MULHS handling in AArch64 from Lowering to isel. Moving the lowering earlier caused build_vector+extract_subvector simplifications to kick in which made the generated code worse.
Differential Revision: https://reviews.llvm.org/D54276
llvm-svn: 347902
SplitVecOp_TruncateHelper tries to promote the result type while splitting FP_TO_SINT/UINT. It then concatenates the result and introduces a truncate to the original result type. But it does this without inserting the AssertZExt/AssertSExt that the regular result type promotion would insert. Nor does it turn FP_TO_UINT into FP_TO_SINT the way normal result type promotion for these operations does. This is bad on X86 which doesn't support FP_TO_SINT until AVX512.
This patch disables the use of SplitVecOp_TruncateHelper for these operations and just lets normal promotion handle it. I've tweaked a couple things in X86ISelLowering to avoid a few obvious regressions there. I believe all the changes on X86 are improvements. The other targets look neutral.
Differential Revision: https://reviews.llvm.org/D54906
llvm-svn: 347593
We might find a target specific node that needs to be unwrapped after we look through an add/or. Otherwise we get inconsistent results if one pointer is just X86WrapperRIP and the other is (add X86WrapperRIP, C)
Differential Revision: https://reviews.llvm.org/D54818
llvm-svn: 347591
This should likely be adjusted to limit this transform
further, but these diffs should be clear wins.
If we have blendv/conditional move, then we should assume
those are cheap ops. The loads become independent of the
compare, so those can be speculated before we need to use
the values in the blend/mov.
llvm-svn: 347526
rL347502 moved the null sibling, so we should group all of these
together. I'm not sure why these aren't methods of the SDValue
class itself, but that's another patch if that's possible.
llvm-svn: 347523
...and use them to avoid creating obviously undef values as
discussed in the post-commit thread for r347478.
The diffs in vector div/rem show that we were missing real
optimizations by creating bogus shift nodes.
llvm-svn: 347502
This code takes a truncate, fp_to_int, or int_to_fp with a legal result type and an input type that needs to be split and enlarges the elements in the result type before doing the split. Then inserts a follow up truncate or fp_round after concatenating the two halves back together.
But if the input type of the original op is being split on its way to ultimately being scalarized we're just going to end up building a vector from scalars and then truncating or rounding it in the vector register. Seems kind of silly to enlarge the result element type of the operation only to end up with scalar code and then building a vector with large elements only to make the elements smaller again in the vector register. Seems better to just try to get away producing smaller result types in the scalarized code.
The X86 test case that changes is a pretty contrived test case that exists because of a bug we used to have in our AVG matching code. I think the code is better now, but its not realistic anyway.
llvm-svn: 347482
SplitVecOp_TruncateHelper tries to introduce a multilevel truncate to avoid scalarization. But if splitting the result type would still be a legal type we don't need to do that.
The comment block at the top of the function implied that this was already implemented. I looked back through the history and it doesn't look to have ever been checked.
llvm-svn: 347479
We fail to canonicalize IR this way (prefer 'not' ops to arbitrary 'xor'),
but that would not matter without this patch because DAGCombiner was
reversing that transform. I think we need this transform in the backend
regardless of what happens in IR to catch cases where the shift-xor
is formed late from GEP or other ops.
https://rise4fun.com/Alive/NC1
Name: shl
Pre: (-1 << C2) == C1
%shl = shl i8 %x, C2
%r = xor i8 %shl, C1
=>
%not = xor i8 %x, -1
%r = shl i8 %not, C2
Name: shr
Pre: (-1 u>> C2) == C1
%sh = lshr i8 %x, C2
%r = xor i8 %sh, C1
=>
%not = xor i8 %x, -1
%r = lshr i8 %not, C2
https://bugs.llvm.org/show_bug.cgi?id=39657
llvm-svn: 347478
This transform needs to be limited.
We are converting to a constant pool load very early, and we
are turning loads that are independent of the select condition
(and therefore speculatable) into a dependent non-speculatable
load.
We may also be transferring a condition code from an FP register
to integer to create that dependent load.
llvm-svn: 347424
This is another step in vector narrowing - a follow-up to D53784
(and hoping to eventually squash potential regressions seen in
D51553).
The x86 test diffs are wins, but the AArch64 diff is probably not.
That problem already exists independent of this patch (see PR39722), but it
went unnoticed in the previous patch because there were no regression tests
that showed the possibility.
The x86 diff in i64-mem-copy.ll is close. Given the frequency throttling
concerns with using wider vector ops, an extra extract to reduce vector
width is the right trade-off at this level of codegen.
Differential Revision: https://reviews.llvm.org/D54392
llvm-svn: 347356
This uncovered an off-by-one typo in SimplifyDemandedVectorElts's INSERT_SUBVECTOR handling as its bounds check was bailing on safe indices.
llvm-svn: 347313
For bitcast nodes from larger element types, add the ability for SimplifyDemandedVectorElts to call SimplifyDemandedBits by merging the elts mask to a bits mask.
I've raised https://bugs.llvm.org/show_bug.cgi?id=39689 to deal with the few places where SimplifyDemandedBits's lack of vector handling is a problem.
Differential Revision: https://reviews.llvm.org/D54679
llvm-svn: 347301
Summary:
We already support this for scalars, but it was explicitly disabled for vectors. In the updated test cases this allows us to see the upper bits are zero to use less multiply instructions to emulate a 64 bit multiply.
This should help with this ispc issue that a coworker pointed me to https://github.com/ispc/ispc/issues/1362
Reviewers: spatel, efriedma, RKSimon, arsenm
Reviewed By: spatel
Subscribers: wdng, llvm-commits
Differential Revision: https://reviews.llvm.org/D54725
llvm-svn: 347287
Consistently use (!LegalOperations || isOperationLegalOrCustom) for all node pairs.
Differential Revision: https://reviews.llvm.org/D53478
llvm-svn: 347255
As discussed on D53794, for float types with ranges smaller than the destination integer type, then we should be able to just use a regular FP_TO_SINT opcode.
I thought we'd need to provide MSA test cases for very small integer types as well (fp16 -> i8 etc.), but it turns out that promotion will kick in so they're unnecessary.
Differential Revision: https://reviews.llvm.org/D54703
llvm-svn: 347251
Sadly, this duplicates (twice) the logic from InstSimplify. There
might be some way to at least share the DAG versions of the code,
but copying the folds seems to be the standard method to ensure
that we don't miss these folds.
Unlike in IR, we don't run DAGCombiner to fixpoint, so there's no
way to ensure that we do these kinds of simplifications unless the
code is repeated at node creation time and during combines.
There were other tests that would become worthless with this
improvement that I changed as pre-commits:
rL347161
rL347164
rL347165
rL347166
rL347167
I'm not sure how to salvage the remaining tests (diffs in this patch).
So the x86 tests verify that the new code is working as intended.
The AMDGPU test is actually similar to my motivating case: we have
some undef value that has survived to machine IR in an x86 test, and
then it gets folded in some weird way, or we crash if we don't transfer
the undef flag. But we would have been better off never getting to that
point by doing these simplifications.
This will lead back to PR32023 someday...
https://bugs.llvm.org/show_bug.cgi?id=32023
llvm-svn: 347170
For example, on X86 we emit a sign_extend_vector_inreg from LowerLoad and without sse4.1 this node will need further legalization. Previously this sign_extend_vector_inreg was being custom lowered during DAG legalization instead of vector op legalization.
Unfortunately, this doesn't seem to matter for the output of any existing lit tests.
llvm-svn: 347094
Legalizer used to request an ext load from i8 to i1 when promoting
vector element type to i8. Fixed.
Differential Revision: https://reviews.llvm.org/D54440
llvm-svn: 346795
Previously, the extend_vector_inreg opcode required their input register to be the same total width as their output. But this doesn't match up with how the X86 instructions are defined. For X86 the input just needs to be a legal type with at least enough elements to cover the output.
This patch weakens the check on these nodes and allows them to be used as long as they have more input elements than output elements. I haven't changed type legalization behavior so it will still create them with matching input and output sizes.
X86 will custom legalize these nodes by shrinking the input to be a 128 bit vector and once we've done that we treat them as legal operations. We still have one case during type legalization where we must custom handle v64i8 on avx512f targets without avx512bw where v64i8 isn't a legal type. In this case we will custom type legalize to a *extend_vector_inreg with a v16i8 input. After that the input is a legal type so type legalization should ignore the node and doesn't need to know about the relaxed restriction. We are no longer allowed to use the default expansion for these nodes during vector op legalization since the default expansion uses a shuffle which required the widths to match. Custom legalization for all types will prevent us from reaching the default expansion code.
I believe DAG combine works correctly with the released restriction because it doesn't check the number of input elements.
The rest of the patch is changing X86 to use either the vector_inreg nodes or the regular zero_extend/sign_extend nodes. I had to add additional isel patterns to handle any_extend during isel since simplifydemandedbits can create them at any time so we can't legalize to zero_extend before isel. We don't yet create any_extend_vector_inreg in simplifydemandedbits.
Differential Revision: https://reviews.llvm.org/D54346
llvm-svn: 346784
The IEEE-754 Standard makes it clear that fneg(x) and
fsub(-0.0, x) are two different operations. The former is a bitwise
operation, while the latter is an arithmetic operation. This patch
creates a dedicated FNeg IR Instruction to model that behavior.
Differential Revision: https://reviews.llvm.org/D53877
llvm-svn: 346774
It should be ok to create a new build_vector after legal operations so long as it doesn't cause an infinite loop in DAG combiner.
Unfortunately, X86's custom constant folding in combineVSZext is hiding any test changes from this. But I'm trying to get to a point where that X86 specific code isn't necessary at all.
Differential Revision: https://reviews.llvm.org/D54285
llvm-svn: 346728
Summary:
Handle extra output from index loads in cases where we wish to
forward a load value directly from a preceeding store.
Fixes PR39571.
Reviewers: peter.smith, rengolin
Subscribers: javed.absar, hiraditya, arphaman, llvm-commits
Differential Revision: https://reviews.llvm.org/D54265
llvm-svn: 346654
This is a long-awaited follow-up suggested in D33578. Since then, we've picked up even more
opportunities for vector narrowing from changes like D53784, so there are a lot of test diffs.
Apart from 2-3 strange cases, these are all wins.
I've structured this to be no-functional-change-intended for any target except for x86
because I couldn't tell if AArch64, ARM, and AMDGPU would improve or not. All of those
targets have existing regression tests (4, 4, 10 files respectively) that would be
affected. Also, Hexagon overrides the shouldReduceLoadWidth() hook, but doesn't show
any regression test diffs. The trade-off is deciding if an extra vector load is better
than a single wide load + extract_subvector.
For x86, this is almost always better (on paper at least) because we often can fold
loads into subsequent ops and not increase the official instruction count. There's also
some unknown -- but potentially large -- benefit from using narrower vector ops if wide
ops are implemented with multiple uops and/or frequency throttling is avoided.
Differential Revision: https://reviews.llvm.org/D54073
llvm-svn: 346595
It's possible for vector op legalization to generate a shuffle. If that happens we should give a chance for DAG combine to combine that with a build_vector input.
I also fixed a bug in combineShuffleOfScalars that was considering the number of uses on a undef input to a shuffle. We don't care how many times undef is used.
Differential Revision: https://reviews.llvm.org/D54283
llvm-svn: 346530
Previous version used type erasure through a `void* (*)()` pointer,
which triggered gcc warning and implied a lot of reinterpret_cast.
This version should make it harder to hit ourselves in the foot.
Differential revision: https://reviews.llvm.org/D54203
llvm-svn: 346522
The DAGCombiner tries to SimplifySelectCC as follows:
select_cc(x, y, 16, 0, cc) -> shl(zext(set_cc(x, y, cc)), 4)
It can't cope with the situation of reordered operands:
select_cc(x, y, 0, 16, cc)
In that case we just need to swap the operands and invert the Condition Code:
select_cc(x, y, 16, 0, ~cc)
Differential Revision: https://reviews.llvm.org/D53236
llvm-svn: 346484
FindBetterNeighborChains simulateanously improves the chain
dependencies of a chain of related stores avoiding the generation of
extra token factors. For chains longer than the GatherAllAliasDepths,
stores further down in the chain will necessarily fail, a potentially
significant waste and preventing otherwise trivial parallelization.
This patch directly parallelize the chains of stores before improving
each store. This generally improves DAG-level parallelism.
Reviewers: courbet, spatel, RKSimon, bogner, efriedma, craig.topper, rnk
Subscribers: sdardis, javed.absar, hiraditya, jrtc27, atanasyan, llvm-commits
Differential Revision: https://reviews.llvm.org/D53552
llvm-svn: 346432
This adds the llvm-side support for post-inlining evaluation of the
__builtin_constant_p GCC intrinsic.
Also fixed SCCPSolver::visitCallSite to not blow up when seeing a call
to a function where canConstantFoldTo returns true, and one of the
arguments is a struct.
Updated from patch initially by Janusz Sobczak.
Differential Revision: https://reviews.llvm.org/D4276
llvm-svn: 346322
The original code avoided creating a zero vector after type legalization, but if we're after type legalization the type we have is legal. The real hazard we need to avoid is creating a build vector after op legalization. tryFoldToZero takes care of checking for this.
llvm-svn: 346119
These methods were just wrappers around getNode with additional asserts (identical and repeated 3 times). But getNode already has a switch that can be used to hold these asserts that allows them to be shared for all 3 opcodes. This also enables checking on the places that create these nodes without using the wrappers.
The rest of the patch is just changing all callers to use getNode directly.
llvm-svn: 346087
We already have custom lowering for the AVX case in LegalizeVectorOps. So its better to keep the regular extend op around as long as possible.
I had to qualify one place in DAG combine that created illegal vector extending load operations. This change by itself had no effect on any tests which is why its included here.
I've made a few cleanups to the custom lowering. The sign extend code no longer creates an identity shuffle with undef elements. The zero extend code now emits a zero_extend_vector_inreg instead of an unpckl with a zero vector.
For the high half of the custom lowering of zero_extend/any_extend, we're now using an unpckh with a zero vector or undef. Previously we used used a pshufd to move the upper 64-bits to the lower 64-bits and then used a zero_extend_vector_inreg. I think the zero vector should require less execution resources and be smaller code size.
Differential Revision: https://reviews.llvm.org/D54024
llvm-svn: 346043
reduceBuildVecConvertToConvertBuildVec vectorizes int2float in the DAGCombiner, which means that even if the LV/SLP has decided to keep scalar code using the cost models, this will override this.
While there are cases where vectorization is necessary in the DAG (mainly due to legalization artefacts), I don't think this is the case here, we should assume that the vectorizers know what they are doing.
Differential Revision: https://reviews.llvm.org/D53712
llvm-svn: 345964
I'm having trouble creating a test case for the ISD::TRUNCATE part of this that shows any codegen differences. But I was able to test the setcc path which is what the test changes here cover.
llvm-svn: 345908
This patch adds support for expanding vector CTPOP instructions and removes the x86 'bitmath' lowering which replicates the same expansion.
Differential Revision: https://reviews.llvm.org/D53258
llvm-svn: 345869
The test causes a crash because we were trying to extract v4f32 to v3f32, and the
narrowing factor was then 4/3 = 1 producing a bogus narrow type.
This should fix:
https://bugs.llvm.org/show_bug.cgi?id=39511
llvm-svn: 345842
SimplifySetCC could shrink a load without checking for
profitability or legality of such shink with a target.
Added checks to prevent shrinking of aligned scalar loads
in AMDGPU below dword as scalar engine does not support it.
Differential Revision: https://reviews.llvm.org/D53846
llvm-svn: 345778
lowerRangeToAssertZExt currently relies on something like EarlyCSE having
eliminated the constant range [0,1). At -O0 this leads to an assert.
Differential Revision: https://reviews.llvm.org/D53888
llvm-svn: 345770
Summary:
Normalize the offset for endianess before checking
if the store cover the load in ForwardStoreValueToDirectLoad.
Without this we missed out on some optimizations for big
endian targets. If for example having a 4 bytes store followed
by a 1 byte load, loading the least significant byte from the
store, the STCoversLD check would fail (see @test4 in
test/CodeGen/AArch64/load-store-forwarding.ll).
This patch also fixes a problem seen in an out-of-tree target.
The target has i40 as a legal type, it is big endian,
and the StoreSize for i40 is 48 bits. So when normalizing
the offset for endianess we need to take the StoreSize into
account (assuming that padding added when storing into
a larger StoreSize always is added at the most significant
end).
Reviewers: niravd
Reviewed By: niravd
Subscribers: javed.absar, kristof.beyls, llvm-commits, uabelho
Differential Revision: https://reviews.llvm.org/D53776
llvm-svn: 345636
Narrowing vector binops came up in the demanded bits discussion in D52912.
I don't think we're going to be able to do this transform in IR as a canonicalization
because of the risk of creating unsupported widths for vector ops, but we already have
a DAG TLI hook to allow what I was hoping for: isExtractSubvectorCheap(). This is
currently enabled for x86, ARM, and AArch64 (although only x86 has existing regression
test diffs).
This is artificially limited to not look through bitcasts because there are so many
test diffs already, but that's marked with a TODO and is a small follow-up.
Differential Revision: https://reviews.llvm.org/D53784
llvm-svn: 345602
Similar to FoldCONCAT_VECTORS, this patch adds FoldBUILD_VECTOR to simplify cases that can avoid the creation of the BUILD_VECTOR - if all the operands are UNDEF or if the BUILD_VECTOR simplifies to a copy.
This exposed an assumption in some AMDGPU code that getBuildVector was guaranteed to be a BUILD_VECTOR node that I've tried to handle.
Differential Revision: https://reviews.llvm.org/D53760
llvm-svn: 345578
Summary: Previously if we had a bitcast vector output type that needs promotion and a vector input type that needs widening we would just do a stack store and load to handle the conversion. We can do a little better if we can widen the bitcast to a legal vector type the same size as the widened input type. Then we can do the bitcast between this widened type and the widened input type. Afterwards we can extract_subvector back to the original output and any_extend that. Type legalization will then circle back and handle promotion of the extract_subvector and the any_extend will just be removed. This will avoid going through the stack and allows us to remove a custom version of this legalization from X86.
Reviewers: efriedma, RKSimon
Reviewed By: efriedma
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D53229
llvm-svn: 345567
Add an intrinsic that takes 2 integers and perform saturation subtraction on
them.
This is a part of implementing fixed point arithmetic in clang where some of
the more complex operations will be implemented as intrinsics.
Differential Revision: https://reviews.llvm.org/D53783
llvm-svn: 345512
Add vector support to TargetLowering::expandFP_TO_UINT.
This exposes an issue in X86TargetLowering::LowerVSELECT which was assuming that the select mask was the same width as the LHS/RHS ops - as long as the result is a sign splat we can easily sext/trunk this.
llvm-svn: 345473
The DAGTypeLegalizer::getSETCCWidenedResultTy was widening the MaskVT, but the code in convertMask called after getSETCCWidenedResultTy had no idea this widening had occurred. So none of the operands were widened when convertMask created new setccs with the widened VT.
This patch removes the widening and adds some asserts to getNode to validate the types of setccs to prevent issues like this in the future.
Differential Revision: https://reviews.llvm.org/D53743
llvm-svn: 345428
The "dead" markings allow existing target-independent optimizations,
like MachineSink, to trigger more frequently. The CPSR defs would have
eventually been marked dead by LiveVariables, so this only affects
optimizations before regalloc.
The ARMBaseInstrInfo.cpp change is fixing a bug which is only visible
with this change: the transform adds a use to an otherwise dead def
of CPSR. This is covered by existing regression tests.
thumb2-tbh.ll breaks for Thumb1 due to MachineLICM changing the
generated code; I'll fix it in D53452.
Differential Revision: https://reviews.llvm.org/D53453
llvm-svn: 345420
Summary:
This adds support for LSDA (exception table) generation for wasm EH.
Wasm EH mostly follows the structure of Itanium-style exception tables,
with one exception: a call site table entry in wasm EH corresponds to
not a call site but a landing pad.
In wasm EH, the VM is responsible for stack unwinding. After an
exception occurs and the stack is unwound, the control flow is
transferred to wasm 'catch' instruction by the VM, after which the
personality function is called from the compiler-generated code. (Refer
to WasmEHPrepare pass for more information on this part.)
This patch:
- Changes wasm.landingpad.index intrinsic to take a token argument, to
make this 1:1 match with a catchpad instruction
- Stores landingpad index info and catch type info MachineFunction in
before instruction selection
- Lowers wasm.lsda intrinsic to an MCSymbol pointing to the start of an
exception table
- Adds WasmException class with overridden methods for table generation
- Adds support for LSDA section in Wasm object writer
Reviewers: dschuff, sbc100, rnk
Subscribers: mgorny, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D52748
llvm-svn: 345345
Replacing BinaryOperator::isFNeg(...) to avoid regressions when we
separate FNeg from the FSub IR instruction.
Differential Revision: https://reviews.llvm.org/D53650
llvm-svn: 345295
As noticed on D52965, the SINT_TO_FP i64 to f32 legalization code has been dead for years - protected by an assert.
Differential Revision: https://reviews.llvm.org/D53703
llvm-svn: 345290
As suggested on D52965, this patch moves the i64 to f64 UINT_TO_FP expansion code from LegalizeDAG into TargetLowering and makes it available to LegalizeVectorOps as well.
Not only does this help perform X86 lowering as a true vectorization instead of (partially vectorized) scalar conversions, it avoids the HADDPD op from the scalar code which can be slow on most targets.
The AVX512F does have the vcvtusi2sdq scalar operation but we don't unroll to use it as it seems to only help for the v2f64 case - otherwise the unrolling cost will certainly be too high. My feeling is that we should leave it to the vectorizers - and if it generates the vector UINT_TO_FP we should use it.
Differential Revision: https://reviews.llvm.org/D53649
llvm-svn: 345256
Summary:
Changes all uses of minnan/maxnan to minimum/maximum
globally. These names emphasize that the semantic difference between
these operations is more than just NaN-propagation.
Reviewers: arsenm, aheejin, dschuff, javed.absar
Subscribers: jholewinski, sdardis, wdng, sbc100, jgravelle-google, jrtc27, atanasyan, llvm-commits
Differential Revision: https://reviews.llvm.org/D53112
llvm-svn: 345218
Until now, we've only checked whether merging stores would cause a cycle via
the value argument, but the address and indexed offset arguments are also
capable of creating cycles in some situations.
The addresses are all base+offset with notionally the same base, but the base
SDNode may still be different (e.g. via an indexed load in one case, and an
ISD::ADD elsewhere). This allows cycles to creep in if one of these sources
depends on another.
The indexed offset is usually undef (representing a non-indexed store), but on
some architectures (e.g. 32-bit ARM-mode ARM) it can be an arbitrary value,
again allowing dependency cycles to creep in.
llvm-svn: 345200
When implementing memset's today we often see this pattern:
$x0 = MOV 0xXYXYXYXYXYXYXYXY
store $x0, ...
$w1 = MOV 0xXYXYXYXY
store $w1, ...
We first create a 64bit constant in a 64bit register with all bytes the
same and then create a 32bit constant with all bytes the same in a 32bit
register. In many targets we could just access the lower byte of the
64bit register instead.
- Ideally this would be handled by the ConstantHoist pass but it runs
too early when memset isn't expanded yet.
- The memset expansion code already had this optimization implemented,
however SelectionDAG constantfolding would constantfold the
"trunc(bigconstnat)" pattern to "smallconstant".
- This patch makes the memset expansion mark the constant as Opaque and
stop DAGCombiner from constant folding in this situation. (Similar to
how ConstantHoisting marks things as Opaque to avoid folding
ADD/SUB/etc.)
Differential Revision: https://reviews.llvm.org/D53181
llvm-svn: 345102
As suggested on D53258, this patch move the CTPOP expansion code from SelectionDAGLegalize to TargetLowering to allow it to be reused by the VectorLegalizer.
Proper vector support will be added by D53258.
llvm-svn: 345066
As suggested on D53258, this patch shares common CTLZ expansion code between VectorLegalizer and SelectionDAGLegalize by putting it in TargetLowering.
Extension to D53474
llvm-svn: 345060
Vector types are not possible here because this code only starts
matching from the scalar bool value of a conditional branch, but
this is another step towards completely removing the fake binop
queries for not/neg/fneg.
llvm-svn: 345041
As suggested on D53258, this patch demonstrates sharing common CTTZ expansion code between VectorLegalizer and SelectionDAGLegalize by putting it in TargetLowering.
I intend to move CTLZ and (scalar) CTPOP over as well and then update D53258 accordingly.
Differential Revision: https://reviews.llvm.org/D53474
llvm-svn: 345039
Add an intrinsic that takes 2 integers and perform unsigned saturation
addition on them.
This is a part of implementing fixed point arithmetic in clang where some of
the more complex operations will be implemented as intrinsics.
Differential Revision: https://reviews.llvm.org/D53340
llvm-svn: 344971
I've included a fix to DAGCombiner::ForwardStoreValueToDirectLoad that I believe will prevent the previous miscompile.
Original commit message:
Theoretically this was done to simplify the amount of isel patterns that were needed. But it also meant a substantial number of our isel patterns have to match an explicit bitcast. By making the vXi32/vXi16/vXi8 types legal for loads, DAG combiner should be able to change the load type to rem
I had to add some additional plain load instruction patterns and a few other special cases, but overall the isel table has reduced in size by ~12000 bytes. So it looks like this promotion was hurting us more than helping.
I still have one crash in vector-trunc.ll that I'm hoping @RKSimon can help with. It seems to relate to using getTargetConstantFromNode on a load that was shrunk due to an extract_subvector combine after the constant pool entry was created. So we end up decoding more mask elements than the lo
I'm hoping this patch will simplify the number of patterns needed to remove the and/or/xor promotion.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits, RKSimon
Differential Revision: https://reviews.llvm.org/D53306
llvm-svn: 344965
Introduce new versions that follow the IEEE semantics
to help with legalization that may need quieted inputs.
There are some regressions from inserting unnecessary
canonicalizes when these are matched from fast math
fcmp + select which should be fixed in a future commit.
llvm-svn: 344914
This is a late backend subset of the IR transform added with:
D52439
We can confirm that the conversion to a 'trunc' is correct by running:
$ opt -instcombine -data-layout="e"
(assuming the IR transforms are correct; change "e" to "E" for big-endian)
As discussed in PR39016:
https://bugs.llvm.org/show_bug.cgi?id=39016
...the pattern may emerge during legalization, so that's we are waiting for an
insertelement to become a scalar_to_vector in the pattern matching here.
The DAG allows for fun variations that are not possible in IR. Result types for
extracts and scalar_to_vector don't necessarily match input types, so that means
we have to be a bit more careful in the transform (see code comments).
The tests show that we don't handle cases that require a shift (as we did in the
IR version). I've left that as a potential follow-up because I'm not sure if
that's a real concern at this late stage.
Differential Revision: https://reviews.llvm.org/D53201
llvm-svn: 344872
Add an intrinsic that takes 2 integers and perform saturation addition on them.
This is a part of implementing fixed point arithmetic in clang where some of
the more complex operations will be implemented as intrinsics.
Differential Revision: https://reviews.llvm.org/D53053
llvm-svn: 344629
Summary:
This adds support for LSDA (exception table) generation for wasm EH.
Wasm EH mostly follows the structure of Itanium-style exception tables,
with one exception: a call site table entry in wasm EH corresponds to
not a call site but a landing pad.
In wasm EH, the VM is responsible for stack unwinding. After an
exception occurs and the stack is unwound, the control flow is
transferred to wasm 'catch' instruction by the VM, after which the
personality function is called from the compiler-generated code. (Refer
to WasmEHPrepare pass for more information on this part.)
This patch:
- Changes wasm.landingpad.index intrinsic to take a token argument, to
make this 1:1 match with a catchpad instruction
- Stores landingpad index info and catch type info MachineFunction in
before instruction selection
- Lowers wasm.lsda intrinsic to an MCSymbol pointing to the start of an
exception table
- Adds WasmException class with overridden methods for table generation
- Adds support for LSDA section in Wasm object writer
Reviewers: dschuff, sbc100, rnk
Subscribers: mgorny, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D52748
llvm-svn: 344575
This is intended to make the backend on par with functionality that was
added to the IR version of SimplifyDemandedVectorElts in:
rL343727
...and the original motivation is that we need to improve demanded-vector-elements
in several ways to avoid problems that would be exposed in D51553.
Differential Revision: https://reviews.llvm.org/D52912
llvm-svn: 344541
by `getTerminator()` calls instead be declared as `Instruction`.
This is the biggest remaining chunk of the usage of `getTerminator()`
that insists on the narrow type and so is an easy batch of updates.
Several files saw more extensive updates where this would cascade to
requiring API updates within the file to use `Instruction` instead of
`TerminatorInst`. All of these were trivial in nature (pervasively using
`Instruction` instead just worked).
llvm-svn: 344502
The final stage of CTPOP expansion (v = (v * 0x01010101...) >> (Len - 8)) is completely pointless for the byte (Len = 8) case as it reduces to (v = (v * 0x01...) >> 0), but annoyingly this doesn't always get optimized away.
Found while investigating generic vector CTPOP expansion (PR32655).
llvm-svn: 344477
The CTPOP case has been changed from VT.getSizeInBits to VT.getScalarSizeInBits - but this fits in with future work for vector support (PR32655) and doesn't affect any current (scalar) uses.
llvm-svn: 344461
Summary:
getShiftAmountTy for X86 returns MVT::i8. If a BSWAP or BITREVERSE is created that requires promotion and the difference between the original VT and the promoted VT is more than 255 then we won't able to create the constant.
This patch adds a check to replace the result from getShiftAmountTy to MVT::i32 if the difference won't fit. This should get legalized later when the shift is ultimately expanded since its clearly an illegal type that we're only promoting to make it a power of 2 bit width. Alternatively we could base the decision completely on the largest shift amount the promoted VT could use.
Vectors should be immune here because getShiftAmountTy always returns the incoming VT for vectors. Only the scalar shift amount can be changed by the targets.
Reviewers: eli.friedman, RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D53232
llvm-svn: 344460
There is one remnant - AVX1 custom splitting of 256-bit vectors - which is due to a regression where the X86ISD::ANDNP is still performed as a YMM.
I've also tightened the CTLZ or CTPOP lowering in SelectionDAGLegalize::ExpandBitCount to require a legal CTLZ - it doesn't affect existing users and fixes an issue with AVX512 codegen.
llvm-svn: 344457
Summary:
These new intrinsics have the semantics of the `minimum` and `maximum`
operations specified by the latest draft of IEEE 754-2018. Unlike
llvm.minnum and llvm.maxnum, these new intrinsics propagate NaNs and
always treat -0.0 as less than 0.0. `minimum` and `maximum` lower
directly to the existing `fminnan` and `fmaxnan` ISel DAG nodes. It is
safe to reuse these DAG nodes because before this patch were only
emitted in situations where there were known to be no NaN arguments or
where NaN propagation was correct and there were known to be no zero
arguments. I know of only four backends that lower fminnan and
fmaxnan: WebAssembly, ARM, AArch64, and SystemZ, and each of these
lowers fminnan and fmaxnan to instructions that are compatible with
the IEEE 754-2018 semantics.
Reviewers: aheejin, dschuff, sunfish, javed.absar
Subscribers: kristof.beyls, dexonsmith, kristina, llvm-commits
Differential Revision: https://reviews.llvm.org/D52764
llvm-svn: 344437
This is more consistent with what we usually do and matches some code X86 custom emits in some cases that I think I can cleanup.
The MIPS test change just looks to be an instruction ordering change.
llvm-svn: 344422
This saves a conversion to extracts and build_vector. We already do this when both the result and the input need to be widened to the same type.
This changed the sse-intrinsics-fast-isel test because we don't lower (insert_vector_elt (scalar_to_vector X), Y, 1) well. We turn it into (vector_shuffle (scalar_to_vector X), (scalar_to_vector Y), <0, 4, 2, 3>) losing track of the fact that the upper elts could be undef.
We should probably find a way to prevent the scalarization of the <2 x f32> load on these tests.
llvm-svn: 344404
If the input type is widened as well, but we still were forced to unroll, we shouldn't be considering the widened input element count. We should only create as many scalar operations as the original type called for.
This will be important for an upcoming patch.
llvm-svn: 344403
Generalize SelectionDAGLegalize's CTLZ expansion to handle vectors - lets VectorLegalizer::ExpandCTLZ to just pass the expansion on instead of repeating the same codegen.
llvm-svn: 344349
I want to add another pattern here that includes scalar_to_vector,
so this makes that patch smaller. I was hoping to remove the
hasOneUse() check because it shouldn't be necessary for common
codegen, but an AMDGPU test has a comment suggesting that the
extra check makes things better on one of those targets.
llvm-svn: 344320
Summary:
Extend analysis forwarding loads from preceeding stores to work with
extended loads and truncated stores to the same address so long as the
load is fully subsumed by the store.
Hexagon's swp-epilog-phis.ll and swp-memrefs-epilog1.ll test are
deleted as they've no longer seem to be relevant.
Reviewers: RKSimon, rnk, kparzysz, javed.absar
Subscribers: sdardis, nemanjai, hiraditya, atanasyan, llvm-commits
Differential Revision: https://reviews.llvm.org/D49200
llvm-svn: 344142
Similar to what already happens in the DAGCombiner wrappers, this patch adds the root nodes back onto the worklist if the DCI wrappers' SimplifyDemandedBits/SimplifyDemandedVectorElts were successful.
Differential Revision: https://reviews.llvm.org/D53026
llvm-svn: 344132
We already do the following combines:
(bitcast int (and (bitcast fp X to int), 0x7fff...) to fp) -> fabs X
(bitcast int (xor (bitcast fp X to int), 0x8000...) to fp) -> fneg X
When the target has "bit preserving fp logic". This patch just extends it
to also combine:
(bitcast int (or (bitcast fp X to int), 0x8000...) to fp) -> fneg (fabs X)
As some targets have fnabs and even those that don't can efficiently lower
both the fabs and the fneg.
Differential revision: https://reviews.llvm.org/D44548
llvm-svn: 344093
r126518 introduced a a type parameter to the getShiftAmountTy target hook. It
produces the type of the shift (RHSTy), parameterised by the type of the value
being shifted (LHSTy). SelectionDAGBuilder::visitShift passed RHSTy rather
than LHSTy and this patch corrects this. The change is a no-op because in LLVM
IR the LHS and RHS types for a shift must be equal anyway.
llvm-svn: 343955
This is where we legalize gather and masked load so this is consistent.
Since these ops are always on vectors I've chosen to go with LegalizeDAG since that's what we do for other vector only ops like BUILD_VECTOR, VECTOR_SHUFFLE, etc. The ScalarizeMaskedMemIntrinsic pass should take care of scalarizing these before SelectionDAG so hopefully we don't need to worry about illegally typed scalar ops being emitted in the legalizing. If we did we would need to do this in LegalizeVectorOps so we could get the second type legalization that runs between LegalizeVectorOps and LegalizeDAG.
llvm-svn: 343947
This change is proposed as a part of D44548, but we
need this independently to avoid regressions from improved
undef propagation in SimplifyDemandedVectorElts().
llvm-svn: 343940
rL343913 was using SimplifyDemandedBits's original demanded mask instead of the adjusted 'NewMask' that accounts for multiple uses of the op (those variable names really need improving....).
Annoyingly many of the test changes (back to pre-rL343913 state) are actually safe - but only because their multiple uses are all by PMULDQ/PMULUDQ.
Thanks to Jan Vesely (@jvesely) for bisecting the bug.
llvm-svn: 343935
It was always returning the chain which seems to be the result number of the SDValue in the lit tests we have. But I don't know if that's guaranteed.
llvm-svn: 343933
This patch enables SimplifyDemandedBits to call SimplifyDemandedVectorElts in cases where the demanded bits mask covers entire elements of a bitcasted source vector.
There are a couple of cases here where simplification at a deeper level (such as through bitcasts) prevents further simplification - CommitTargetLoweringOpt only adds immediate uses/users back to the worklist when we might want to combine the original caller again to see what else it can simplify.
As well as that I had to disable handling of bool vector until SimplifyDemandedVectorElts better supports some of their opcodes (SETCC, shifts etc.).
Fixes PR39178
Differential Revision: https://reviews.llvm.org/D52935
llvm-svn: 343913
And use that to transform fsub with zero constant operands.
The integer part isn't used yet, but it is proposed for use in
D44548, so adding both enhancements here makes that
patch simpler.
llvm-svn: 343865
Previously we replaced the chain use ourself and return the data result. LegalizeVectorOps then detected that we'd done this and assumed the chain had already been handled.
This commit instead returns a MERGE_VALUES node with two results joined from nodes. This allows LegalizeVectorOps to do all the replacements for us without any special casing. The MERGE_VALUES will be removed by DAG combine.
llvm-svn: 343817
This fixes a case of bad index calculation when merging mismatching
vector types. This changes the existing code to just use the existing
extract_{subvector|element} and a bitcast (instead of bitcast first and
then newly created extract_xxx) so we don't need to adjust any indices
in the first place.
rdar://44584718
Differential Revision: https://reviews.llvm.org/D52681
llvm-svn: 343493
The SINT_TO_FP<->UINT_TO_FP combines for non-negative integers should only occur for legal ops once LegalOperations = true
No test case to hand, noticed when investigating PR38226 + PR38970
llvm-svn: 343405
Adding NonNull as attributes to returned pointers has the unfortunate side
effect of disabling tail calls. This patch ignores the NonNull attribute when
we decide whether to tail merge, in the same way that we ignore the NoAlias
attribute, as it has no affect on the call sequence.
Differential Revision: https://reviews.llvm.org/D52238
llvm-svn: 343091
VerifyDAGDiverence costs compilation time, avoid running it in non-debug
builds.
Differential Revision: https://reviews.llvm.org/D52454
llvm-svn: 343086
Summary:
We have `llvm::addLandingPadInfo` and `MachineFunction::addLandingPad`,
both of which add landing pad information to populate `LandingPadInfo`
but are called from different locations, which was confusing. This patch
unifies them with one `MachineFunction::addLandingPad` function, which
now has functionlities of both functions.
Reviewers: rnk
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D52428
llvm-svn: 343018
This is the final (I hope!) problem pattern mentioned in PR37749:
https://bugs.llvm.org/show_bug.cgi?id=37749
We are trying to avoid an AVX1 sinkhole caused by having 256-bit bitwise logic ops but no other 256-bit integer ops.
We've already solved the simple logic ops, but 'andn' is an x86 special. I looked at alternative solutions like
extending the generic DAG combine or trying to wait until the ANDNP node is created, but those are bigger patches
that can over-reach. Ie, splitting to 128-bit does not look like a win in most cases with >1 256-bit op.
The pattern matching is cluttered with bitcasts because of our i64 element canonicalization. For the affected test,
we have this vector-type-legalized sequence:
t29: v8i32 = concat_vectors t27, t28
t30: v4i64 = bitcast t29
t18: v8i32 = BUILD_VECTOR Constant:i32<-1>, Constant:i32<-1>, ...
t31: v4i64 = bitcast t18
t32: v4i64 = xor t30, t31
t9: v8i32 = BUILD_VECTOR Constant:i32<255>, Constant:i32<255>, ...
t34: v4i64 = bitcast t9
t35: v4i64 = and t32, t34
t36: v8i32 = bitcast t35
t37: v4i32 = extract_subvector t36, Constant:i64<0>
t38: v4i32 = extract_subvector t36, Constant:i64<4>
Differential Revision: https://reviews.llvm.org/D52318
llvm-svn: 343008
DAGCombine will try to fold two loads that feed a SELECT or SELECT_CC
after the select, resulting in a select of an address and a single
load after.
If either of the loads depend on the other, this is not legal as it
could introduce cycles. However, it only checked this if the opcode
was a SELECT, and not for a SELECT_CC.
Unfortunately, the only reproducer I have for this is for our
downstream target. I've tried getting it to trigger on an upstream one
but haven't been successful.
Patch thanks to Bevin Hansson.
llvm-svn: 342980
This is a preliminary step towards solving PR14613:
https://bugs.llvm.org/show_bug.cgi?id=14613
If we have an 'add' instruction that sets flags, we can use that to eliminate an
explicit compare instruction or some other instruction (cmn) that sets flags for
use in the later select.
As shown in the unchanged tests that use 'icmp ugt %x, %a', we're effectively
reversing an IR icmp canonicalization that replaces a variable operand with a
constant:
https://rise4fun.com/Alive/V1Q
But we're not using 'uaddo' in those cases via DAG transforms. This happens in
CGP after D8889 without checking target lowering to see if the op is supported.
So AArch already shows 'uaddo' codegen for the i8/i16/i32/i64 test variants with
"using_cmp_sum" in the title. That's the pattern that CGP matches as an unsigned
saturated add and converts to uaddo without checking target capabilities.
This patch is gated by isOperationLegalOrCustom(ISD::UADDO, VT), so we see only
see AArch diffs for i32/i64 in the tests with "using_cmp_notval" in the title
(unlike x86 which sees improvements for all sizes because all sizes are 'custom').
But the AArch code (like x86) looks better when translated to 'uaddo' in all cases.
So someone that is involved with AArch may want to set i8/i16 to 'custom' for UADDO,
so this patch will fire on those tests.
Another possibility given the existing behavior: we could remove the legal-or-custom
check altogether because we're assuming that a UADDO sequence is canonical/optimal
before we ever reach here. But that seems like a bug to me. If the target doesn't
have an add-with-flags op, then it's not likely that we'll get optimal DAG combining
using a UADDO node. This is similar justification for why we don't canonicalize IR to
the overflow math intrinsic sibling (llvm.uadd.with.overflow) for UADDO in the first
place.
Differential Revision: https://reviews.llvm.org/D51929
llvm-svn: 342886
This code handled SCALAR_TO_VECTOR being returned by the recursion, but the code that used to return SCALAR_TO_VECTOR was removed in 2015.
llvm-svn: 342856
This comment was misleading about why we were restricting to before legalize types. The reason given would only apply to before legalize ops. But there is a before legalize types reason that should also be listed.
llvm-svn: 342851
This is an alternative to https://reviews.llvm.org/D37896. We can't decompose
multiplies generically without a target hook to tell us when it's profitable.
ARM and AArch64 may be able to remove some existing code that overlaps with
this transform.
This extends D52195 and may resolve PR34474:
https://bugs.llvm.org/show_bug.cgi?id=34474
(still an open question about transforming legal vector multiplies, but we
could open another bug report for those)
llvm-svn: 342844
x86 had 2 versions of peekThroughBitcast. DAGCombiner had 1. Plus, it had a 1-off implementation for the one-use variant.
Move the x86 versions of the code to SelectionDAG, so we don't have different copies of the code.
No functional change intended.
I'm putting this next to isBitwiseNot() because I am planning to use it in there. Another option is next to the
helpers in the ISD namespace (eg, ISD::isConstantSplatVector()). But if there's no good reason for those to be
there, I'd prefer to pull other helpers over to SelectionDAG in follow-up steps.
Differential Revision: https://reviews.llvm.org/D52285
llvm-svn: 342669
The test diff in not-and-simplify.ll is from a use in SimplifyDemandedBits,
and the test diff in add.ll is from a DAGCombiner transform.
llvm-svn: 342594
Summary: This patch adds a GlobalIsel copy utility into MI for flags and updates the instruction emitter for the SDAG path. Some tests show new behavior and I added one for GlobalIsel which mirrors an SDAG test for handling nsw/nuw.
Reviewers: spatel, wristow, arsenm
Reviewed By: arsenm
Subscribers: wdng
Differential Revision: https://reviews.llvm.org/D52006
llvm-svn: 342576
This is an alternative to D37896. I don't see a way to decompose multiplies
generically without a target hook to tell us when it's profitable.
ARM and AArch64 may be able to remove some duplicate code that overlaps with
this transform.
As a first step, we're only getting the most clear wins on the vector examples
requested in PR34474:
https://bugs.llvm.org/show_bug.cgi?id=34474
As noted in the code comment, it's likely that the x86 constraints are tighter
than necessary, but it may not always be a win to replace a pmullw/pmulld.
Differential Revision: https://reviews.llvm.org/D52195
llvm-svn: 342554
- Instead of having both `SUnit::dump(ScheduleDAG*)` and
`ScheduleDAG::dumpNode(ScheduleDAG*)`, just keep the latter around.
- Add `ScheduleDAG::dump()` and avoid code duplication in several
places. Implement it for different ScheduleDAG variants.
- Add `ScheduleDAG::dumpNodeName()` in favor of the `SUnit::print()`
functions. They were only ever used for debug dumping and putting the
function into ScheduleDAG is consistent with the `dumpNode()` change.
llvm-svn: 342520
This is a follow-up suggested in D51630 and originally proposed as an IR transform in D49040.
Copying the motivational statement by @evandro from that patch:
"This transformation helps some benchmarks in SPEC CPU2000 and CPU2006, such as 188.ammp,
447.dealII, 453.povray, and especially 300.twolf, as well as some proprietary benchmarks.
Otherwise, no regressions on x86-64 or A64."
I'm proposing to add only the minimum support for a DAG node here. Since we don't have an
LLVM IR intrinsic for cbrt, and there are no other DAG ways to create a FCBRT node yet, I
don't think we need to worry about DAG builder, legalization, a strict variant, etc. We
should be able to expand as needed when adding more functionality/transforms. For reference,
these are transform suggestions currently listed in SimplifyLibCalls.cpp:
// * cbrt(expN(X)) -> expN(x/3)
// * cbrt(sqrt(x)) -> pow(x,1/6)
// * cbrt(cbrt(x)) -> pow(x,1/9)
Also, given that we bail out on long double for now, there should not be any logical
differences between platforms (unless there's some platform out there that has pow()
but not cbrt()).
Differential Revision: https://reviews.llvm.org/D51753
llvm-svn: 342348
This patch fixes the debug info handling for SelectionDAG legalization
of DAG nodes with two results. When an replaced SDNode has more than
one result, transferDbgValues was always copying the SDDbgValue from
the first result and attaching them to all members. In reality
SelectionDAG::ReplaceAllUsesWith() is given an array of SDNodes
(though the type signature doesn't make this obvious (cf. the call
site code in ReplaceNode()).
rdar://problem/44162227
Differential Revision: https://reviews.llvm.org/D52112
llvm-svn: 342264
I suspect this became unecessary when the CSE of mgather was fixed in r338080. It may still be possible to hit this if we widen the element type of a gather outside of type legalization and the promote the mask of a separate gather node so they become the same. But that seems pretty unlikely.
llvm-svn: 342022
This already worked if only one register piece was used,
but didn't if a type was split into multiple, unequal
sized pieces.
Fixes not splitting 3i16/v3f16 into two registers for
AMDGPU.
This will also allow fixing the ABI for 16-bit vectors
in a future commit so that it's the same for all subtargets.
llvm-svn: 341801
This is the DAG equivalent of D51433.
If we know we're not using all vector lanes, use that knowledge to potentially simplify a vselect condition.
The reduction/horizontal tests show that we are eliminating AVX1 operations on the upper half of 256-bit
vectors because we don't need those anyway.
I'm not sure what the pr34592 test is showing. That's run with -O0; is SimplifyDemandedVectorElts supposed
to be running there?
Differential Revision: https://reviews.llvm.org/D51696
llvm-svn: 341762
Add support for bitcasts from float type to an integer type of the same element bitwidth.
There maybe cases where we need to support different widths (e.g. as SSE __m128i is treated as v2i64) - but I haven't seen cases of this in the wild yet.
llvm-svn: 341652
This was proposed as an IR transform in D49306, but it was not clearly justifiable as a canonicalization.
Here, we only do the transform when the target tells us that sqrt can be lowered with inline code.
This is the basic case. Some potential enhancements are in the TODO comments:
1. Generalize the transform for other exponents (allow more than 2 sqrt calcs if that's really cheaper).
2. If we have less fast-math-flags, generate code to avoid -0.0 and/or INF.
3. Allow the transform when optimizing/minimizing size (might require a target hook to get that right).
Note that by default, x86 converts single-precision sqrt calcs into sqrt reciprocal estimate with
refinement. That codegen is controlled by CPU attributes and can be manually overridden. We have plenty
of test coverage for that already, so I didn't bother to include extra testing for that here. AArch uses
its full-precision ops in all cases (not sure if that's the intended behavior or not, but that should
also be covered by existing tests).
Differential Revision: https://reviews.llvm.org/D51630
llvm-svn: 341481
Summary:
A follow-up for D49266 / rL337166 + D49497 / rL338044.
This is still the same pattern to check for the [lack of]
signed truncation, but in this case the constants and the predicate
are negated.
https://rise4fun.com/Alive/BDVhttps://rise4fun.com/Alive/n7Z
Reviewers: spatel, craig.topper, RKSimon, javed.absar, efriedma, dmgreen
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D51532
llvm-svn: 341287
Summary:
This is patch 1 of the new DivergenceAnalysis (https://reviews.llvm.org/D50433).
The purpose of this patch is to free up the name DivergenceAnalysis for the new generic
implementation. The generic implementation class will be shared by specialized
divergence analysis classes.
Patch by: Simon Moll
Reviewed By: nhaehnle
Subscribers: jvesely, jholewinski, arsenm, nhaehnle, mgorny, jfb, llvm-commits
Differential Revision: https://reviews.llvm.org/D50434
Change-Id: Ie8146b11be2c50d5312f30e11c7a3036a15b48cb
llvm-svn: 341071
If an ABI-like value is used in a different block,
the type split used is not necessarily the same as
the call's ABI. The value is used through an intermediate
copy virtual registers from the other block. This
resulted in copies with inconsistent sizes later.
Fixes regressions since r338197 when AMDGPU started
splitting vector types for calls.
llvm-svn: 341018
Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp
Reviewers: RKSimon, spatel, efriedma
Reviewed By: efriedma
Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits
Differential Revision: https://reviews.llvm.org/D51337
llvm-svn: 340891
Summary:
I'm not sure if this patch is correct or if it needs more qualifying somehow. Bitcast shouldn't change the size of the load so it should be ok? We already do something similar for stores. We'll change the type of a volatile store if the resulting store is Legal or Custom. I'm not sure we should be allowing Custom there...
I was playing around with converting X86 atomic loads/stores(except seq_cst) into regular volatile loads and stores during lowering. This would allow some special RMW isel patterns in X86InstrCompiler.td to be removed. But there's some floating point patterns in there that didn't work because we don't fold (f64 (bitconvert (i64 volatile load))) or (f32 (bitconvert (i32 volatile load))).
Reviewers: efriedma, atanasyan, arsenm
Reviewed By: efriedma
Subscribers: jvesely, arsenm, sdardis, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, arichardson, jrtc27, atanasyan, jfb, llvm-commits
Differential Revision: https://reviews.llvm.org/D50491
llvm-svn: 340797
I noticed this along with the patterns in D51125, but when the index is variable,
we don't convert insertelement into a build_vector.
For x86, that means these get expanded at legalization time into the loading/spilling
code that we see in the tests. I think it's always better to avoid going to memory on
these, and we get the optimal 'broadcast' if it's available.
I suspect other targets may want to look at enabling the hook. AArch64 and AMDGPU have
regression tests that would be affected (although I did not check what would happen in
those cases). In the most basic cases shown here, AArch64 would probably do much
better with a splat.
Differential Revision: https://reviews.llvm.org/D51186
llvm-svn: 340705
This is a bit awkward in a handful of places where we didn't even have
an instruction and now we have to see if we can build one. But on the
whole, this seems like a win and at worst a reasonable cost for removing
`TerminatorInst`.
All of this is part of the removal of `TerminatorInst` from the
`Instruction` type hierarchy.
llvm-svn: 340701
Summary:
Previously the value being stored is the last operand in SDNode. This causes the type legalizer to visit the mask operand before the value operand. The type legalizer was more complicated because of this since we want the type of the value to drive the decisions.
This patch moves the value to be the first operand so we visit it first during type legalization. It also simplifies the type legalization code accordingly.
X86 is currently the only in tree target that uses this SDNode. Not sure if there are any users out of tree.
Reviewers: RKSimon, delena, hfinkel, eli.friedman
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D50402
llvm-svn: 340689
Previously we allowed the store to be Custom. But without knowing for sure that the Custom handling won't split the store, we shouldn't convert a volatile store. We also probably shouldn't be creating a store the requires custom handling after LegalizeOps. This could lead to an infinite loop if the custom handling was to insert a bitcast. Though I guess isStoreBitCastBeneficial could be used to block such a loop.
The test changes here are due to the volatile part of this. The stores in the test are all volatile and i32 stores are marked custom, So we are no longer converting them
This is related to D50491 where I was trying to allow some bitcasting of volatile loads
Differential Revision: https://reviews.llvm.org/D50578
llvm-svn: 340626
Having the KnownBits as an output parameter is kind of awkward to use
and a holdover from when it was two separate APInts. Instead, just
return a KnownBits object.
I'm leaving the existing interface in place for now, since updating
the callers all at once would be thousands of lines of diff.
llvm-svn: 340594
This solves the motivating case from:
https://bugs.llvm.org/show_bug.cgi?id=38527
If we are legalizing an FP vector op that maps to 1 of the LLVM intrinsics that mimic libm calls,
but we're going to end up with scalar libcalls for that vector type anyway, then we should unroll
the vector op into scalars before widening. This avoids libcalls because we've lost the knowledge
that some of the scalar elements are undef.
Differential Revision: https://reviews.llvm.org/D50791
llvm-svn: 340469
The inline sequence is very long (about 70 bytes on Thumb1), so it's
not really a good idea to inline it, especially when optimizing for
size.
Differential Revision: https://reviews.llvm.org/D47917
llvm-svn: 340458
Summary:
Catchpads and cleanuppads are not funclet entries; they are only EH
scope entries. We already dont't set `isEHFuncletEntry` for catchpads.
This patch does the same thing for cleanuppads.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D50654
llvm-svn: 340330
During combining, ReduceLoadWdith is used to combine AND nodes that
mask loads into narrow loads. This patch allows the mask to be a
shifted constant. This results in a narrow load which is then left
shifted to compensate for the new offset.
Differential Revision: https://reviews.llvm.org/D50432
llvm-svn: 340261
This reduces most of the sdiv stages (the MULHS, shifts etc.) to just zero/identity values and use the numerator scale factor to multiply by +1/-1.
llvm-svn: 340260
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.
Handle the case where the sign bit extends to only part of the small elements.
llvm-svn: 340169
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.
The next step would be to support cases where the large elements aren't all sign bits, and determine the small element equivalent based on the demanded elements.
llvm-svn: 340143
Summary:
I believe this restores the behavior we had before r339147.
Fixes PR38622.
Reviewers: RKSimon, chandlerc, spatel
Reviewed By: chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D50936
llvm-svn: 340120
Add support for cases where only some c1+c2 results exceed the max bitshift, clamping accordingly.
Differential Revision: https://reviews.llvm.org/D35722
llvm-svn: 340010
When nodes are reassociated the vector-reduction flag gets lost.
The test case is here is what would happen if you had a sum of absolute differences loop that started with a non-zero but contant sum and that loop was unrolled. The vectorizer will generate a constant vector for the initial value. And DAGCombiner reassociate tries to move it down the addition tree erasing the vector-reduction flag. Interestingly this moves constants the opposite direction of the reassociate IR pass.
I've chosen to just punt on the reassociate, but I suppose we could maybe preserve the flag if both nodes have it set.
Differential Revision: https://reviews.llvm.org/D50827
llvm-svn: 339946
a generically extensible collection of extra info attached to
a `MachineInstr`.
The primary change here is cleaning up the APIs used for setting and
manipulating the `MachineMemOperand` pointer arrays so chat we can
change how they are allocated.
Then we introduce an extra info object that using the trailing object
pattern to attach some number of MMOs but also other extra info. The
design of this is specifically so that this extra info has a fixed
necessary cost (the header tracking what extra info is included) and
everything else can be tail allocated. This pattern works especially
well with a `BumpPtrAllocator` which we use here.
I've also added the basic scaffolding for putting interesting pointers
into this, namely pre- and post-instruction symbols. These aren't used
anywhere yet, they're just there to ensure I've actually gotten the data
structure types correct. I'll flesh out support for these in
a subsequent patch (MIR dumping, parsing, the works).
Finally, I've included an optimization where we store any single pointer
inline in the `MachineInstr` to avoid the allocation overhead. This is
expected to be the overwhelmingly most common case and so should avoid
any memory usage growth due to slightly less clever / dense allocation
when dealing with >1 MMO. This did require several ergonomic
improvements to the `PointerSumType` to reasonably support the various
usage models.
This also has a side effect of freeing up 8 bits within the
`MachineInstr` which could be repurposed for something else.
The suggested direction here came largely from Hal Finkel. I hope it was
worth it. ;] It does hopefully clear a path for subsequent extensions
w/o nearly as much leg work. Lots of thanks to Reid and Justin for
careful reviews and ideas about how to do all of this.
Differential Revision: https://reviews.llvm.org/D50701
llvm-svn: 339940
There is no way in the universe, that doing a full-width division in
software will be faster than doing overflowing multiplication in
software in the first place, especially given that this same full-width
multiplication needs to be done anyway.
This patch replaces the previous implementation with a direct lowering
into an overflowing multiplication algorithm based on half-width
operations.
Correctness of the algorithm was verified by exhaustively checking the
output of this algorithm for overflowing multiplication of 16 bit
integers against an obviously correct widening multiplication. Baring
any oversights introduced by porting the algorithm to DAG, confidence in
correctness of this algorithm is extremely high.
Following table shows the change in both t = runtime and s = space. The
change is expressed as a multiplier of original, so anything under 1 is
“better” and anything above 1 is worse.
+-------+-----------+-----------+-------------+-------------+
| Arch | u64*u64 t | u64*u64 s | u128*u128 t | u128*u128 s |
+-------+-----------+-----------+-------------+-------------+
| X64 | - | - | ~0.5 | ~0.64 |
| i686 | ~0.5 | ~0.6666 | ~0.05 | ~0.9 |
| armv7 | - | ~0.75 | - | ~1.4 |
+-------+-----------+-----------+-------------+-------------+
Performance numbers have been collected by running overflowing
multiplication in a loop under `perf` on two x86_64 (one Intel Haswell,
other AMD Ryzen) based machines. Size numbers have been collected by
looking at the size of function containing an overflowing multiply in
a loop.
All in all, it can be seen that both performance and size has improved
except in the case of armv7 where code size has regressed for 128-bit
multiply. u128*u128 overflowing multiply on 32-bit platforms seem to
benefit from this change a lot, taking only 5% of the time compared to
original algorithm to calculate the same thing.
The final benefit of this change is that LLVM is now capable of lowering
the overflowing unsigned multiply for integers of any bit-width as long
as the target is capable of lowering regular multiplication for the same
bit-width. Previously, 128-bit overflowing multiply was the widest
possible.
Patch by Simonas Kazlauskas!
Differential Revision: https://reviews.llvm.org/D50310
llvm-svn: 339922
This patch refactors the existing TargetLowering::BuildSDIV base implementation to support non-uniform constant vector denominators.
This is the last patch necessary to close PR36545
Differential Revision: https://reviews.llvm.org/D50765
llvm-svn: 339908
This patch refactors the existing BuildExactSDIV implementation to support non-uniform constant vector denominators.
Differential Revision: https://reviews.llvm.org/D50392
llvm-svn: 339756
`MachineMemOperand` pointers attached to `MachineSDNodes` and instead
have the `SelectionDAG` fully manage the memory for this array.
Prior to this change, the memory management was deeply confusing here --
The way the MI was built relied on the `SelectionDAG` allocating memory
for these arrays of pointers using the `MachineFunction`'s allocator so
that the raw pointer to the array could be blindly copied into an
eventual `MachineInstr`. This creates a hard coupling between how
`MachineInstr`s allocate their array of `MachineMemOperand` pointers and
how the `MachineSDNode` does.
This change is motivated in large part by a change I am making to how
`MachineFunction` allocates these pointers, but it seems like a layering
improvement as well.
This would run the risk of increasing allocations overall, but I've
implemented an optimization that should avoid that by storing a single
`MachineMemOperand` pointer directly instead of allocating anything.
This is expected to be a net win because the vast majority of uses of
these only need a single pointer.
As a side-effect, this makes the API for updating a `MachineSDNode` and
a `MachineInstr` reasonably different which seems nice to avoid
unexpected coupling of these two layers. We can map between them, but we
shouldn't be *surprised* at where that occurs. =]
Differential Revision: https://reviews.llvm.org/D50680
llvm-svn: 339740
Intentionally excluding nodes from the DAGCombine worklist is likely to
lead to weird optimizations and infinite loops, so it's generally a bad
idea.
To avoid the infinite loops, fix DAGCombine to use the
isDesirableToCommuteWithShift target hook before performing the
transforms in question, and implement the target hook in the ARM backend
disable the transforms in question.
Fixes https://bugs.llvm.org/show_bug.cgi?id=38530 . (I don't have a
reduced testcase for that bug. But we should have sufficient test
coverage for PerformSHLSimplify given that we're not playing weird
tricks with the worklist. I can try to bugpoint it if necessary,
though.)
Differential Revision: https://reviews.llvm.org/D50667
llvm-svn: 339734
Fix SelectionDAG::computeKnownBits asserting when handling EXTRACT_SUBVECTOR
when zero extending the demanded elements mask if it is already as long as the
source vector.
Differential Revision: https://reviews.llvm.org/D49574
llvm-svn: 339600
This is another variation of PR38533. In this case, the result type of the bitcast is legal and 16-bits wide, but not a scalar integer. So we need to emit the convert to i16 and then bitcast it to the true result type. This new bitcast will be further type legalized if necessary.
llvm-svn: 339536
Previously if the result type was a vector, we emitted a FP_TO_FP16 with a vector result type which isn't valid.
This is basically the opposite case of the root cause of PR38533.
llvm-svn: 339535
We were checking for all bits being Known by checking Known.Zero|Known.One, but if all the bits are known then the value should be a Constant and we can just check for that instead.
llvm-svn: 339509
Similar to rL337966 - if the DAGCombiner's rotate matching was
working as expected, I don't think we'd see any test diffs here.
AArch only goes right, and PPC only goes left.
x86 has both, so no diffs there.
Differential Revision: https://reviews.llvm.org/D50091
llvm-svn: 339359
Summary: This change provides a common optimization path for both Unsafe and FMF driven optimization for this fsub fold adding reassociation, as it the flag that most closely represents the translation
Reviewers: spatel, wristow, arsenm
Reviewed By: spatel
Subscribers: wdng
Differential Revision: https://reviews.llvm.org/D50195
llvm-svn: 339357
Simon Pilgrim