This reverts commit bb9333c350.
This exposes another existing bug that causes an infinite loop as shown in
D110170
...so reverting while I look at another fix.
It caused compiler crashes, see comment on the code review for repro.
> This is basically D108837 but for jump threading. Free instructions
> should be ignored for the threading decision. JumpThreading already
> skips some free instructions (like pointer bitcasts), but does not
> skip various free intrinsics -- in fact, it currently gives them a
> fairly large cost of 2.
>
> Differential Revision: https://reviews.llvm.org/D110290
This reverts commit 1e3c6fc7cb.
There are several places in the code that are currently broken where
we assume an Instruction is always a member of a BasicBlock that
lives in a Function. This is a problem specifically when
attempting to get the vscale_range attribute. This patch adds checks
that an Instruction's parent also has a parent!
I've added a test for a function-less @llvm.vscale intrinsic call here:
unittests/Analysis/ValueTrackingTest.cpp
In repairIntervalsInRange, if the new instructions refer to subregs but
the old instructions did not, make sure any existing live interval for
the superreg is updated to have subranges. Also skip repairing any range
that we have recalculated from scratch, partly for efficiency but also
to avoids some cases that repairOldRegInRange can't handle.
The existing test/CodeGen/AMDGPU/twoaddr-regsequence.mir provides some
test coverage for this change: when TwoAddressInstructionPass converts
REG_SEQUENCE into subreg copies, the live intervals will now get
subranges and MachineVerifier will verify that the subranges are
correct. Unfortunately MachineVerifier does not complain if the
subranges are not present, so the test also passed before this patch.
This patch also fixes ~800 of the ~1500 failures in the whole CodeGen
lit test suite when -early-live-intervals is forced on.
Differential Revision: https://reviews.llvm.org/D110328
The fix applied in D23303 "LiveIntervalAnalysis: fix a crash in repairOldRegInRange"
was over-zealous. It would bail out when the end of the range to be
repaired was in the middle of the first segment of the live range of
Reg, which was always the case when the range contained a single def of
Reg.
This patch fixes it as suggested by Matthias Braun in post-commit review
on the original patch, and tests it by adding -early-live-intervals to
a selection of existing lit tests that now pass.
(Note that D23303 was originally applied to fix a crash in
SILoadStoreOptimizer, but that is now moot since D23814 updated
SILoadStoreOptimizer to run before scheduling so it no longer has to
update live intervals.)
Differential Revision: https://reviews.llvm.org/D110238
Unrevert with some changes to the tests:
- Add -verify-machineinstrs to check for remaining problems in live
interval support in TwoAddressInstructionPass.
- Drop test/CodeGen/AMDGPU/extract-load-i1.ll since it suffers from
some of those remaining problems.
When moving an entire basic block BB before InsertPoint, currently
we check for all instructions whether the operands dominates
InsertPoint, however, this can be improved such that even an
operand does not dominate InsertPoint, as long as it appears as
a previous instruction in the same BB, it is safe to move.
Reviewed By: Whitney
Differential Revision: https://reviews.llvm.org/D110378
Add the tail policy argument to LLVM IR intrinsics. There are two policies for tail elements. Tail agnostic means users do not care about the values in the tail elements and tail undisturbed means the values in the tail elements need to be kept after the operation. In order to let users control the tail policy, we add an additional argument at the end of the argument list.
For unmasked operations, we have no maskedoff and the tail policy is always tail agnostic. If users want to keep tail elements under unmasked operations, they could use all one mask in the masked operations to do it. So, we only add the additional argument for masked operations for most cases. There are exceptions listed below.
In this patch, we do not handle the following cases to reduce the complexity of the patch. There could be two separate patches for them.
* Use dest argument to control tail policy
vmerge.vvm/vmerge.vxm/vmerge.vim (add _t builtins with additional dest argument)
vfmerge.vfm (add _t builtins with additional dest argument)
vmv.v.v (add _t builtins with additional dest argument)
vmv.v.x (add _t builtins with additional dest argument)
vmv.v.i (add _t builtins with additional dest argument)
vfmv.v.f (add _t builtins with additional dest argument)
vadc.vvm/vadc.vxm/vadc.vim (add _t builtins with additional dest argument)
vsbc.vvm/vsbc.vxm (add _t builtins with additional dest argument)
* Always has tail argument for masked/unmasked intrinsics
Vector Single-Width Integer Multiply-Add Instructions (add _t and _mt builtins)
Vector Widening Integer Multiply-Add Instructions (add _t and _mt builtins)
Vector Single-Width Floating-Point Fused Multiply-Add Instructions (add _t and _mt builtins)
Vector Widening Floating-Point Fused Multiply-Add Instructions (add _t and _mt builtins)
Vector Reduction Operations (add _t and _mt builtins)
Vector Slideup Instructions (add _t and _mt builtins)
Vector Slidedown Instructions (add _t and _mt builtins)
Discussion: https://github.com/riscv/rvv-intrinsic-doc/pull/101
Differential Revision: https://reviews.llvm.org/D105092
Testing on a SLM box suggests these can run on either port, but the throughput is 4cy on either (inc MMX versions). Confirmed with Intel AoM / Agner / InstLatX64.
There are several places in the code that are currently broken as
they assume an Instruction always has a parent Function when
attempting to get the vscale_range attribute. This patch adds checks
that an Instruction has a parent.
I've added a test for a parentless @llvm.vscale intrinsic call here:
unittests/Analysis/ValueTrackingTest.cpp
Differential Revision: https://reviews.llvm.org/D110158
The type legalizer has by default no method of doing this bitcast other than
storing and reloading the value from stack.
This patch implements a custom lowering of this operation using extractions
of subregs (z13 and earlier using FP128 register pairs), or of vector
elements (with 'vector enhancements 1' using VR128 FP registers).
Review: Ulrich Weigand
Differential Revision: https://reviews.llvm.org/D110346
It was assuming that GPR extends could only have destination sizes of 32 or 64
bits, but for AArch64 we allow < 32 bits even without matching size physregs.
Removing the 'ess' suffix improves the ergonomics without sacrificing clarity.
Since this class is likely to be used more frequently in the future it's worth
some short term pain to fix this now.
EPCGenericDylibManager provides an interface for loading dylibs and looking up
symbols in the executor, implemented using EPC-calls to functions in the
executor.
SimpleExecutorDylibManager is an executor-side service that provides the
functions used by EPCGenericDylibManager.
SimpleRemoteEPC is updated to use an EPCGenericDylibManager instance to
implement the ExecutorProcessControl loadDylib and lookup methods. In a future
commit these methods will be removed, and clients updated to use
EPCGenericDylibManagers directly.
We don't allow an initializer for LDS variables
and there is an early abort during instruction
selection. This patch legalizes them by ignoring
the init values. During assembly emission, proper
error reporting already exists for such instances.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D109901
In ThinLTO for locals we normally compute the GUID from the name after
prepending the source path to get a unique global id. SamplePGO indirect
call profiles contain the target GUID without this uniquification,
however (unless compiling with -funique-internal-linkage-names).
Therefore, the index contains the original GUID of the local symbols
(without module path prepended to uniquify), in order to correctly
handle the call edges added for these indirect call profile targets
with SamplePGO.
We were emitting these to the combined index when writing it out as
bitcode, which is unnecessary and causes overhead when writing out the
indexes for distributed backends. The only use of the original GUID name
is in the thin link. Suppress it in that case. This reduced the thin
link time for a large distributed build by about 7%, and the aggregate
size of the serialized indexes by over 2%.
Continue to print it when writing out the full index, since that is just
used for debugging and testing.
Update a distributed thinlto index test to contain a local and ensure
that we don't get a COMBINED_ORIGINAL_NAME record.
Differential Revision: https://reviews.llvm.org/D110296
This should have been included with ExecutorBootstrapService in 78b083dbb7,
but was accidentally left out. It give services a chance to release any
resources that they have acquired.
On targets that do not support AGPR to AGPR copying directly, try to find the
defining accvgpr_write and propagate its source vgpr register to the copies
before register allocation so the source vgpr register does not get clobbered.
The postrapseudos pass also attempt to propagate the defining accvgpr_write but
if the register to propagate is clobbered, it will give up and create new
temporary vgpr registers instead.
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D108830
Turn (and (shl x, c2), c1) -> (slli (srli x, c3-c2), c3) if c1 is a
shifted mask with no leading zeros and c3 trailing zeros where c3
is greater than c2.
We should use IMAGE_REL_I386_SECREL in the i386 section of this file.
IMAGE_REL_I386_SECREL and IMAGE_REL_AMD64_SECREL have the same
numeric value 0xB, so this doesn't change behavior.
Two typos, one unsused include and some leftovers from the TargetProcessControl -> ExecutorProcessControl renaming
Reviewed By: xgupta
Differential Revision: https://reviews.llvm.org/D110260
Turn (and (shr x, c2), c1) -> (slli (srli x, c2+c3), c3) if c1 is a
shifted mask with c2 leading zeros and c3 trailing zeros.
When the leading zeros is C2+32 we can use SRLIW in place of SRLI.
This function can be adapted to solve bugs like PR51245,
but it could require differentiating the combiner timing
between the existing and new transforms.
That macro was being defined but not used anywhere in libc++, so it
must be safe to remove it.
As a fly-by fix, also remove mentions of this macro in other places
in LLVM, to make sure they were not depending on the value defined in
libc++.
Differential Revision: https://reviews.llvm.org/D110289
This is basically D108837 but for jump threading. Free instructions
should be ignored for the threading decision. JumpThreading already
skips some free instructions (like pointer bitcasts), but does not
skip various free intrinsics -- in fact, it currently gives them a
fairly large cost of 2.
Differential Revision: https://reviews.llvm.org/D110290
While both GlobalAlias and GlobalIFunc are GlobalIndirectSymbol, their
`getIndirectSymbol()` usage is quite different (GlobalIFunc's resolver
is an entity different from GlobalIFunc itself).
As discussed on https://lists.llvm.org/pipermail/llvm-dev/2020-September/144904.html
("[IR] Modelling of GlobalIFunc"), the name `getBaseObject` is confusing when
used with GlobalIFunc.
To resolve the confusion:
* Move GloalIndirectSymol::getBaseObject to GlobalAlias:: (GlobalIFunc should use `getResolver` instead)
* Change GlobalValue::getBaseObject not to inspect GlobalIFunc. Note: the function has 7 references.
* Add GlobalIFunc::getResolverFunction to peel off potential ConstantExpr indirection
(`strlen` in `test/LTO/Resolution/X86/ifunc.ll`)
Note: GlobalIFunc::getResolver (like GlobalAlias::getAliasee which does not peel
off ConstantExpr indirection) is kept to be used by ValueEnumerator.
Reviewed By: ibookstein
Differential Revision: https://reviews.llvm.org/D109792
The fix applied in D23303 "LiveIntervalAnalysis: fix a crash in repairOldRegInRange"
was over-zealous. It would bail out when the end of the range to be
repaired was in the middle of the first segment of the live range of
Reg, which was always the case when the range contained a single def of
Reg.
This patch fixes it as suggested by Matthias Braun in post-commit review
on the original patch, and tests it by adding -early-live-intervals to
a selection of existing lit tests that now pass.
(Note that D23303 was originally applied to fix a crash in
SILoadStoreOptimizer, but that is now moot since D23814 updated
SILoadStoreOptimizer to run before scheduling so it no longer has to
update live intervals.)
Differential Revision: https://reviews.llvm.org/D110238
The pass amdgpu-propagate-attributes ("Early/Late propagate attributes
from kernels to functions") is currently run also for shaders, where
it does nothing. Modify the check so the pass only processes functions
for kernels.
Differential Revision: https://reviews.llvm.org/D109961
Only the most recent cpus support really 1cy 64-bit multiplies, and the X64 cost table represents a realistic worst case. The 1cy value was also discouraging vectorization when most vXi64 PMULDQ expansions aren't actually slower than scalarization.
Noticed while investigating PR51436.
At the moment, DSE only considers whether a pointer may be captured at
all in a function. This leads to cases where we fail to remove stores to
local objects because we do not check if they escape before potential
read-clobbers or after.
Doing context-sensitive escape queries in isReadClobber has been removed
a while ago in d1a1cce5b1 to save compile-time. See PR50220 for more
context.
This patch introduces a new capture tracker, which keeps track of the
'earliest' capture. An instruction A is considered earlier than instruction
B, if A dominates B. If 2 escapes do not dominate each other, the
terminator of the common dominator is chosen. If not all uses cannot be
analyzed, the earliest escape is set to the first instruction in the
function entry block.
If the query instruction dominates the earliest escape and is not in a
cycle, then pointer does not escape before the query instruction.
This patch uses this information when checking if a load of a loaded
underlying object may alias a write to a stack object. If the stack
object does not escape before the load, they do not alias.
I will share a follow-up patch to also use the information for call
instructions to fix PR50220.
In terms of compile-time, the impact is low in general,
NewPM-O3: +0.05%
NewPM-ReleaseThinLTO: +0.05%
NewPM-ReleaseLTO-g: +0.03
with the largest change being tramp3d-v4 (+0.30%)
http://llvm-compile-time-tracker.com/compare.php?from=1a3b3301d7aa9ab25a8bdf045c77298b087e3930&to=bc6c6899cae757c3480f4ad4874a76fc1eafb0be&stat=instructions
Compared to always computing the capture information on demand, we get
the following benefits from the caching:
NewPM-O3: -0.03%
NewPM-ReleaseThinLTO: -0.08%
NewPM-ReleaseLTO-g: -0.04%
The biggest speedup is tramp3d-v4 (-0.21%).
http://llvm-compile-time-tracker.com/compare.php?from=0b0c99177d1511469c633282ef67f20c851f58b1&to=bc6c6899cae757c3480f4ad4874a76fc1eafb0be&stat=instructions
Overall there is a small, but noticeable benefit from caching. I am not
entirely sure if the speedups warrant the extra complexity of caching.
The way the caching works also means that we might miss a few cases, as
it is less precise. Also, there may be a better way to cache things.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D109844
The NFC commit e5692a564a changed the logic for
DomTreeUpdates to use the range [succ_begin, succ_begin) when
looking for SuccsOfPredBB rather than using [succ_begin, succ_end).
As the commit was NFC this is identified as a typo (it has been
discussed briefly in phabricator).
The typo was found when inspecting the code, so I've got no idea if
changing back to the old range has any significant impact (such as
solving any PR:s or causing some new problems). But at least this
restores the code to the originally indented behavior.
This patch adds codegen support for lowering the vector-predicated
reduction intrinsics to RVV instructions. The process is similar to that
of the other reduction intrinsics, save for the fact that every VP
reduction has a start value. We reuse the existing custom "VL" nodes,
adding extra patterns where required to handle non-true masks.
To support these nodes, the `RISCVISD::VECREDUCE_*_VL` nodes have been
given an explicit "merge" operand. This is to faciliate the VP
reductions, where we must be careful to ensure that even if no operation
is performed (when VL=0) we still produce the start value. The RVV
reductions don't update the destination register under these conditions,
so we tie the splatted start value to the output register.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D107657
This simplifies the API and addresses a FIXME in
TwoAddressInstructionPass::convertInstTo3Addr.
Differential Revision: https://reviews.llvm.org/D110229
Bisecting and reducing opt pipelines that includes the
ModuleInlinerWrapperPass has turned out to be a bit problematic.
This is far from perfect (it still lacks information about inline
advisor params etc.), but it should give some kind of hint to what
the wrapped pipeline looks like when using -print-pipeline-passes.
Reviewed By: aeubanks, mtrofin
Differential Revision: https://reviews.llvm.org/D109878
This patch is to support transform something like
_mm512_add_ph(acc, _mm512_fmadd_pch(a, b, _mm512_setzero_ph()))
to _mm512_fmadd_pch(a, b, acc).
Differential Revision: https://reviews.llvm.org/D109953
This patch fixes a problem when the AAKernelInfo state was invalidated,
e.g., due to `optnone` for a kernel, but not all parts indicated the
invalidation properly. We further eliminate most full state
invalidations as they should never be necessary.
Differential Revision: https://reviews.llvm.org/D109468
This is a follow-up of D110029, which uses bitset to indicate execution mode. This patches makes the changes in the function call.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D110279
Neither of these passes modify the CFG, allowing us to preserve DomTree
and LoopInfo across them by using setPreservesCFG.
Differential Revision: https://reviews.llvm.org/D110161
The return type of strlen is size_t, not just any integer.
This is a partial fix for an example based on:
https://llvm.org/PR50836
There's another bug here because we can still crash
processing a real strlen or something that looks like it.
The pass uses different cost kinds to estimate "old" and "interleaved" costs:
default cost kind for all targets override `getInterleavedMemoryOpCost()` is
`TCK_SizeAndLatency`. Although at the moment estimated `TCK_Latency` costs are
equal to `TCK_SizeAndLatency`, (so the change is NFC) it may change in future.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D110100
When determining whether to fold branches to a common destination by
merging two blocks, SimplifyCFG will count the number of instructions to
be moved into the first basic block. However, there's no reason to count
free instructions like bitcasts and other similar instructions.
This resolves missed branch foldings with -fstrict-vtable-pointers in
llvm-test-suite's lambda benchmark.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D108837
We can use riscv_vse intrinsic instead of riscv_vse_mask. The code here
is based on similar code for handling masked.scatter and vp.scatter.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D110206
Currenlty PseudoProbeInserter is a pass conditioned on a target switch. It works well with a single clang invocation. It doesn't work so well when the backend is called separately (i.e, through the linker or llc), where user has always to pass -pseudo-probe-for-profiling explictly. I'm making the pass a default pass that requires no command line arg to trigger, but will be actually run depending on whether the CU comes with `llvm.pseudo_probe_desc` metadata.
Reviewed By: wenlei
Differential Revision: https://reviews.llvm.org/D110209
Note that MIRCanonicalizerID is declared in
llvm/include/llvm/CodeGen/Passes.h, which MIRCanonicalizerPass.cpp
includes.
Identified with readability-redundant-declaration.
Avoid relying on the default cost kinds in TTI calls (we already do this in other places in SLP) - noticed while trying to see how much work it'd be to extend D110242 and remove all remaining uses of default CostKind arguments.
This patch is for fixing potential shufflevector-related bugs like D93818.
As D93818, this patch change shufflevector's default placeholder to poison.
To reduce risk, it was divided into several patches, and this patch is for InstCombineVectorOps.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D110230
The execution mode of a kernel is stored in a global variable, whose value means:
- 0 - SPMD mode
- 1 - indicates generic mode
- 2 - SPMD mode execution with generic mode semantics
We are going to add support for SIMD execution mode. It will be come with another
execution mode, such as SIMD-generic mode. As a result, this value-based indicator
is not flexible.
This patch changes to bitset based solution to encode execution mode. Each
position is:
[0] - generic mode
[1] - SPMD mode
[2] - SIMD mode (will be added later)
In this way, `0x1` is generic mode, `0x2` is SPMD mode, and `0x3` is SPMD mode
execution with generic mode semantics. In the future after we add the support for
SIMD mode, `0b1xx` will be in SIMD mode.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D110029
This patch is for fixing potential shufflevector-related bugs like D93818.
As D93818, this patch change shufflevector's default placeholder to poison.
To reduce risk, it was divided into several patches, and this patch is for InstCombineCompares and InstructionCombining.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D110227
Based off a discussion on D110100, we should be avoiding default CostKinds whenever possible.
This initial patch removes them from the 'inner' target implementation callbacks - these should only be used by the main TTI calls, so this should guarantee that we don't cause changes in CostKind by missing it in an inner call. This exposed a few missing arguments in getGEPCost and reduction cost calls that I've cleaned up.
Differential Revision: https://reviews.llvm.org/D110242
This patch is for fixing potential shufflevector-related bugs like D93818.
As D93818, this patch change shufflevector's default placeholder to poison.
To reduce risk, it was divided into several patches, and this patch is for InstCombineCasts.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D110226
Summary:
The thread ID function was reintroduced in D110195, but could
potentially be removed by the optimizer. Make the function noinline to
preserve the call sites and add it to the externalization RAII so its
definition is not removed by the attributor.
This code seems untested and is likely obsolete, because this case
should already be handled by the code that legalizes the result type
of EXTRACT_SUBVECTOR.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D110061
Like normal atomicrmw operations, at -O0 the simple register-allocator can
insert spills into the LL/SC loop if it's expanded and visible when regalloc
runs. This can cause the operation to never succeed by repeatedly clearing the
monitor. Instead expand to a cmpxchg, which has a pseudo-instruction for -O0.
This is required to codegen something like:
<vscale x 8 x i16> @llvm.experimental.vector.insert(<vscale x 8 x i16> %vec,
<vscale x 2 x i16> %subvec,
i64 %idx)
where the output vector is legal, but the input vector needs promoting.
It implements this by performing the whole operation on the promoted type,
and then truncating the result.
Reviewed By: david-arm, craig.topper
Differential Revision: https://reviews.llvm.org/D110059
IR with matrix intrinsics is likely to also contain large vector
operations, which can benefit from early simplifications.
This is the last step in a series of changes to improve code-gen for
code using matrix subscript operators with the C/C++ matrix extension in
CLang, like
using matrix_t = double __attribute__((matrix_type(15, 15)));
void foo(unsigned i, matrix_t &A, matrix_t &B) {
for (unsigned j = 0; j < 4; ++j)
for (unsigned k = 0; k < i; k++)
B[k][j] -= A[k][j] * B[i][j];
}
https://clang.godbolt.org/z/6dKxK1Ed7
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D102496
This reverts commit 2f6b07316f.
This caused several bots to hit an infinite loop at stage 2,
so it needs to be reverted while figuring out how to fix that.
This allows VMOVL in tail predicated loops so long as the the vector
size the VMOVL is extending into is less than or equal to the size of
the VCTP in the tail predicated loop. These cases represent a
sign-extend-inreg (or zero-extend-inreg), which needn't block tail
predication as in https://godbolt.org/z/hdTsEbx8Y.
For this a vecsize has been added to the TSFlag bits of MVE
instructions, which stores the size of the elements that the MVE
instruction operates on. In the case of multiple size (such as a
MVE_VMOVLs8bh that extends from i8 to i16, the largest size was be
chosen). The sizes are encoded as 00 = i8, 01 = i16, 10 = i32 and 11 =
i64, which often (but not always) comes from the instruction encoding
directly. A unit test was added, and although only a subset of the
vecsizes are currently used, the rest should be useful for other cases.
Differential Revision: https://reviews.llvm.org/D109706
The folding rule (select C, (gep Ptr, Idx), Ptr) -> (gep Ptr, (select C,
Idx, 0)) creates a malformed SELECT IR if C is a vector while Idx is scalar.
SELECT VecC, ScalarIdx, 0
We could splat Idx to a vector but it defeats the purpose of
optimisation. Don't apply the folding rule in this case.
This fixes a regression from commit d561b6fbdb.
Most of the code wasn't yet scalable safe, although most of the
code conceptually just works for scalable vectors. This change
makes the algorithm work on ElementCount, where appropriate,
and leaves the fixed-width only code to use `getFixedNumElements`.
Reviewed By: david-arm
Differential Revision: https://reviews.llvm.org/D110058
This patch updates VectorCombine to use a worklist to allow iterative
simplifications where a combine enables other combines.
Suggested in D100302.
The main use case at the moment is foldSingleElementStore and
scalarizeLoadExtract working together to improve scalarization.
Note that we now also do not run SimplifyInstructionsInBlock on the
whole function if there have been changes. This means we fail to
remove/simplify instructions not related to any of the vector combines.
IMO this is fine, as simplifying the whole function seems more like a
workaround for not tracking the changed instructions.
Compile-time impact looks neutral:
NewPM-O3: +0.02%
NewPM-ReleaseThinLTO: -0.00%
NewPM-ReleaseLTO-g: -0.02%
http://llvm-compile-time-tracker.com/compare.php?from=52832cd917af00e2b9c6a9d1476ba79754dcabff&to=e66520a4637290550a945d528e3e59573485dd40&stat=instructions
Reviewed By: spatel, lebedev.ri
Differential Revision: https://reviews.llvm.org/D110171
Use of output modifiers forces VOP3 encoding for a VOP2 mac/fmac
instruction, so we might as well convert it to the more flexible VOP3-
only mad/fma form.
With this change, the only way we should emit VOP3-encoded mac/fmac is
if regalloc chooses registers that require the VOP3 encoding, e.g. sgprs
for both src0 and src1. In all other cases the mac/fmac should either be
converted to mad/fma or shrunk to VOP2 encoding.
Differential Revision: https://reviews.llvm.org/D110156
InstCombine's worklist can be re-used by other passes like
VectorCombine. Move it to llvm/Transform/Utils and rename it to
InstructionWorklist.
Reviewed By: lebedev.ri
Differential Revision: https://reviews.llvm.org/D110181
Add an overload to pass the flat workgroup range in separately. This
will allow the attributor to use the assumed value for
amdgpu-flat-workgroup-sizes when inferring amdgpu-waves-per-eu.
This is a follow-up of D105872. Now we are able to prepare for update
form with non-const increment.
Reviewed By: jsji
Differential Revision: https://reviews.llvm.org/D106032
Add a new LLVM switch `-profile-sample-block-accurate` to trust zero block counts for branches. Currently we leave out such zero counts when annotating branch weight metadata, which would lead to weights being considered as unknown.
Differential Revision: https://reviews.llvm.org/D110117
And always print it.
This makes some LLVM diagnostics match up better with Clang's diagnostics.
Updated some AMDGPU uses of DiagnosticInfoResourceLimit and now we print
better diagnostics for those.
Reviewed By: dblaikie
Differential Revision: https://reviews.llvm.org/D110204
This change adds the ASan intrinsic to the list whihc are setting hasCopyImplyingStackAdjustment.
Reviewed By: eugenis
Differential Revision: https://reviews.llvm.org/D110012
This time with the right bug number.
When we rewrite the setcc we replace set old setcc output register
with the new CondReg. But since CondReg can be shared by other
replacements, we don't know if the kill flags for the old register
are valid for CondReg. So be conservative and remove them.
The test case has a SETCCr and a SETCCm on the same condition so
they end up sharing the same CondReg. The SETCCr had one use with
a kill flag. This kill flag isn't valid after the replacement because
CondReg needs a live range extending to the later SETCCm replacment.
Fixes PR51903.
Currently, the dead functions information getting from optimizations remarks does not contain debug location, but knowing where these dead functions locate could be useful for debugging or for detecting dead code.
Cause in `LTO::addRegularLTO()` we use `BitcodeModule::getLazyModule()` to read the bitcode module, when we pass Function F to `ore::NV()`, F is not materialized, so `F->getSubprogram()` returns nullptr, and there is no debug location information of dead functions in optimizations remarks.
This patch call `F->materialize()` before we pass Function F to `ore::NV()`, then debug location information will be emitted for dead functions in optimization remarks.
Reviewed By: tejohnson
Differential Revision: https://reviews.llvm.org/D109737
When we rewrite the setcc we replace set old setcc output register
with the new CondReg. But since CondReg can be shared by other
replacements, we don't know if the kill flags for the old register
are valid for CondReg. So be conservative and remove them.
The test case has a SETCCr and a SETCCm on the same condition so
they end up sharing the same CondReg. The SETCCr had one use with
a kill flag. This kill flag isn't valid after the replacement because
CondReg needs a live range extending to the later SETCCm replacment.
Fixes PR51908.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D110046
This comment references behavior that was removed in
ccae43a247, which is a commit from 5 years
ago. It seems safe to assume that that behavior won't be coming back
soon. If it does, we can readd this part of the comment :)
A logic incompleteness may lead MemorySSA to be too conservative
in its results. Specifically, when dealing with a call of kind
`call i32 bitcast (i1 (i1)* @test to i32 (i32)*)(i32 %1)`, where
the function `test` is declared with readonly attribute, the
bitcast is not looked through, obscuring function attributes. Hence,
some methods of CallBase (e.g., doesNotReadMemory) could provide
suboptimal results.
Differential Revision: https://reviews.llvm.org/D109888
MergeICmps will currently sort (by offset) all comparisons in a chain,
including those that do not get merged. This is problematic in two ways:
* We may end up moving the original first block into the middle of
the chain, in which case the "extra work" instructions will also
be in the middle of the chain, resulting in invalid IR
(reported in https://reviews.llvm.org/D108782#3005583).
* Reordering branches is generally not legal, because it may
introduce branch on poison, which is UB (PR51845). The merging
done by MergeICmps is legal as long as we assume that memcmp()
works on frozen memory, but the reordering of unmerged comparisons
is definitely incorrect (without inserting freeze instructions),
so we should avoid it.
There are easier ways to fix the first issue, but I figured it was
worthwhile to do this properly to also fix the second one. What we
now do is to restore the original relative order of (potentially
merged) comparisons.
I took the liberty of dropping the MERGEICMPS_DOT_ON functionality,
because it would be more awkward to implement now (as the before and
after representation is different) and it doesn't seem terribly
useful nowadays.
Differential Revision: https://reviews.llvm.org/D110024
Normally, given that the DA results are kept consistent over the selection DAG, uniform comparisons get selected to S_CMP_* but divergent to V_CMP_*. Sometimes, for the sake of efficiency, SSA subgraphs may be converted to VALU to avoid repeatedly copying data back and forth. Hence we have to be able to sustain the correctness passing the i1 from VALU to SALU context and vice versa.
VALU operations only process the active lanes of the VGPR and ignore inactive ones.
Active lanes correspond to 1 bit in the EXEC mask register.
SALU represents i1 as just one bit but VALU as 64bits: 0/1 and 0/(0xffffffffffffffff & EXEC) respectively.
SALU uses one-bit conditional flag SCC but VALU - VCC that is a pair of 32-bit SGPRs
To expose SCC to the VALU context we need to convert the one-bit boolean value to the appropriate 64bit.
To return back to the SALU context we need to do the opposite.
To correctly convert 64bit VALU boolean to either 0 or 1 we need to filter out the bits corresponding to the inactive lanes.
Reviewed By: piotr
Differential Revision: https://reviews.llvm.org/D109900
When adding alias.scope and noalias metadata to a memcpy function,
the alias.scope and noalias metadata from the operands are merged.
The rule for merging alias.scope is to take the intersection of
the domains and the union of the scopes within those domains.
The rule for merging noalias is to take the intersection.
The bug is that AMDGPULowerModuleLDS was using concatenation for
both alias.scope and noalias. For example, when f1 and f2 are added
to the LDS structure and there is a memcpy(f2, f1, sizeof(f1)).
Then, concatenation creates noalias metadata for the memcpy that
includes both {f1, f2}. That means that the memcpy is assumed
not to alias a prior load of f2, which enables the optimizer to
remove a load of f2 that occurs after mempcy.
The function MDNode::getmostGenericAliasScope defines the semantics
for alias.scope. There is a function, combineMetadata in Local.cpp,
that uses intersect for noalias.
Differential Revision: https://reviews.llvm.org/D110049
This patch adds a prefixed load pattern involving v2f32 fpext v2f64, where we
are dealing with a value with an offset that fits into a 34-bit signed immediate.
A reduced test case is also added to patch that tests the pattern, in which the
pattern is tested in the big endian CHECKs of the newly added test.
Differential Revision: https://reviews.llvm.org/D109887
This patch fixes the crash found by PR51614:
whenever doing tail folding, interleave groups must be considered under mask.
Another fix D108900 follows for targets that support masked loads and stores:
when *deciding* to vectorize with masked interleave groups, check if the access
is reverse - which is currently not supported; rather than (only) asserting when
computing cost and generating code.
Differential Revision: https://reviews.llvm.org/D108891
This requires a minor change to CodeGenPrepare to ensure that
shouldSinkOperands will be called for And.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D110106
We already have pow(x, y) * pow(x, z) -> pow(x, y + z) transformation, but we are missing same transformation for powi (power is integer).
Requires reassoc.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D109954
isValidAssumeForContext can provide better results with access to the
dominator tree in some cases. This patch adjusts computeConstantRange to
allow passing through a dominator tree.
The use VectorCombine is updated to pass through the DT to enable
additional scalarization.
Note that similar APIs like computeKnownBits already accept optional dominator
tree arguments.
Reviewed By: lebedev.ri
Differential Revision: https://reviews.llvm.org/D110175
When using instructions which have a MetadataAsValue argument
(e.g. some target-specific intrinsics) MD canonicalization strips
internal MDNodes with a single ConstantAsMetadata child. That
prevented IRTranslator from the proper translation of such a calls.
Optimize (add (mul x, c0), c1) -> (ADDI (MUL (ADDI, c1/c0), c0), c1%c0),
if c1/c0 and c1%c0 are simm12, while c1 is not.
Optimize (add (mul x, c0), c1) -> (MUL (ADDI, c1/c0), c0),
if c1%c0 is zero, and c1/c0 is simm12 while c1 is not.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D108607
This patch allows sinking an instruction which can have multiple uses in a
single user. We were previously over-restrictive by looking for exactly one use,
rather than one user.
Also added an API for retrieving a unique undroppable user.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D109700
One of the two inputs of the Shufflevector is often a placeholder.
Previously, there were cases where the placeholder was undef, and there were cases where it was poison.
I added these constructors to create a placeholder consistently.
Changing to use the newly added constructor will be written in a separate patch.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D110146
SystemZ adds the EXRL target instructions in the end of each file. This must
be done before debug info emission since that may end the text section, and
therefore this is now done in emitConstantPools() (instead of in
emitEndOfAsmFile).
Review: Ulrich Weigand
Differential Revision: https://reviews.llvm.org/D109513
FMA_W_CHAIN is used when lowering fdiv f32. Prefer to select it to fmac
if there are no source modifiers, just like we do for other mad/mac and
fma/fmac cases.
Differential Revision: https://reviews.llvm.org/D110074
v_fmac with source modifiers forces VOP3 encoding, but it is strictly
better to use the VOP3-only v_fma instead, because $dst and $src2 are
not tied so it gives the register allocator more freedom and avoids a
copy in some cases.
This is the same strategy we already use for v_mad vs v_mac and
v_fma_legacy vs v_fmac_legacy.
Differential Revision: https://reviews.llvm.org/D110070
Add generic helper function that matches constant splat. It has option to
match constant splat with undef (some elements can be undef but not all).
Add util function and matcher for G_FCONSTANT splat.
Differential Revision: https://reviews.llvm.org/D104410
The logic in howManyLessThans is fishy. It first checks invariance of
RHS, and then uses OrigRHS as argument for isLoopEntryGuardedByCond, which
is, strictly saying, a different thing. We are seeing a very rare intermittent
failure of availability checks, and it looks like this precondition is
sometimes broken. Before we can figure out what's going on, adding asserts
that all involved values that may possibly to to isLoopEntryGuardedByCond
are available at loop entry.
If either of these asserts fails (OrigRHS is the most likely suspect), it
means that the logic here is flawed.
This fixes PR51730, a heap-use-after-free bug in
replaceConditionalBranchesOnConstant().
With the attached reproducer we were left with a function looking
something like this after replaceAndRecursivelySimplify():
[...]
cont2.i:
br i1 %.not1.i, label %handler.type_mismatch3.i, label %cont4.i
handler.type_mismatch3.i:
%3 = phi i1 [ %2, %cont2.thread.i ], [ false, %cont2.i ]
unreachable
cont4.i:
unreachable
[...]
with both the branch instruction and PHI node being in the worklist. As
a result of replacing the branch instruction with an unconditional
branch, the PHI node in %handler.type_mismatch3.i would be removed. This
then resulted in a heap-use-after-free bug due to accessing that removed
PHI node in the next worklist iteration.
This is solved by using a value handle worklist. I am a unsure if this
is the most idiomatic solution. Another solution could have been to
produce a worklist just containing the interesting branch instructions,
but I thought that it perhaps was a bit cleaner to keep all worklist
filtering in the loop that does the rewrites.
Reviewed By: lebedev.ri
Differential Revision: https://reviews.llvm.org/D109221
First (and biggest) change is to use "Killing/Dead" in place of "Later/Earlier" base for names in DSE. For example, [Maybe]DeadLoc - is a location killed by KillingI instruction. I believe such names are more descriptive and easy to understand than current ones.
Second, there are inconsistencies in naming where different names are used for the same thing. Fixed that too.
Third, reordered parameters of isPartialOverwrite, tryToMergePartialOverlappingStores, isOverwrite to make them consistent between each other. This greatly reduces potential mistakes.
Reviewed By: fhahn
Differential Revision: https://reviews.llvm.org/D106947
For artifacts excluding G_TRUNC/G_SEXT, which have IR counterparts, we don't
seem to have debug users of defs. However, in the legalizer we're always calling
MachineInstr::eraseFromParentAndMarkDBGValuesForRemoval() which is expensive.
In some rare cases, this contributes significantly to unreasonably long compile
times when we have lots of artifact combiner activity.
To verify this, I added asserts to that function when it actually replaced a debug
use operand with undef for these artifacts. On CTMark with both -O0 and -Os and
debug info enabled, I didn't see a single case where it triggered.
In my measurements I saw around a 0.5% geomean compile-time improvement on -g -O0
for AArch64 with this change.
Differential Revision: https://reviews.llvm.org/D109750
The implication logic for two values that are both negative or non-negative
says that it doesn't matter whether their predicate is signed and unsigned,
but only flips unsigned into signed for further inference. This patch adds
support for flipping a signed predicate into unsigned as well.
Differential Revision: https://reviews.llvm.org/D109959
Reviewed By: nikic
In llvm, for non-alu32 mode, the stack alignment is 64bit so only one
64bit spill per 64bit slot. For alu32 mode, the stack alignment
is 32bit, so it is possible to have two 32bit spills per
64bit slot.
Currently, bpf kernel verifier does not preserve register states
for 32bit spills. That is, one 32bit register may hold a constant
value or a bounded range before spill. After reload from the
stack, the information is lost and sometimes this may cause
verifier failure. For 64bit register spill, the verifier
indeed tries to preserve the register state for reloading.
The current verifier can be modestly changed to handle one
32bit spill per 64bit stack slot with state-preserving reload.
Handling two 32bit spills per 64bit stack slot will require
substantial changes.
This patch changes stack alignment for alu32 to be 64bit.
This way, for any 64bit slot in alu32 mode, only one
32bit or 64bit register values can be saved. Together
with previous-mentioned verifier enhancement, 32bit
spill can be handled with state preserving.
Note that llvm stack slot coallescing
seems only doing adjacent packing which may leave some holes
in the stack. For example,
stack slot 8 <== 8 bytes
stack slot 4 <== 8 bytes with 4 byte hole
stack slot 8 <== 8 bytes
stack slot 4 <== 4 bytes
Differential Revision: https://reviews.llvm.org/D109073
When following a case of a switch instruction is guaranteed to lead to
UB, we can safely break these edges and redirect those cases into a newly
created unreachable block. As result, CFG will become simpler and we can
remove some of Phi inputs to make further analyzes easier.
Patch by Dmitry Bakunevich!
Differential Revision: https://reviews.llvm.org/D109428
Reviewed By: lebedev.ri
For x86 Darwin, we have a stack checking feature which re-uses some of this
machinery around stack probing on Windows. Renaming this to be more appropriate
for a generic feature.
Differential Revision: https://reviews.llvm.org/D109993
Sanjay Patel