This patch is a fix following the revert of 72ce759
(https://reviews.llvm.org/rG72ce759928e6dfee6a9efa310b966c19722352ba)
and fixes the failure that it caused.
The above patch failed on the Thread Sanitizer buildbot with an out of
memory error. After an investigation, the cause was identified as an
explosion in debug intrinsics while running the Jump Threading pass on
ModuleMap.ll. The above patched prevented debug intrinsics from being
dropped when their Basic Block was deleted due to being "empty". In this
case, one of the functions in ModuleMap.ll had (after many optimization
passes) a very large number of debug intrinsics representing a set of
repeatedly inlined variables. Previously the vast majority of these were
silently dropped during Jump Threading when their blocks were deleted,
but as of the above patch they survived for longer, causing a large
increase in the number of debug intrinsics. These intrinsics were then
repeatedly cloned by the Jump Threading pass as edges were threaded,
multiplying the intrinsic count further. The memory consumed by this
process spiralled out of control, crashing the buildbot that uses TSan
(which has an estimated 5-10x memory overhead compared to non-sanitized
builds).
This patch adds RemoveRedundantDbgInstrs to the Jump Threading pass, in
order to reduce the number of debug intrinsics down to a manageable
amount in cases where many intrinsics for the same variable end up
bunched together contiguously, as in this case.
Differential Revision: https://reviews.llvm.org/D73054
With the fixed implementation of the "remainder" operation in
rG9d0956ebd471, we can now add support to folding calls to it.
Differential Revision: https://reviews.llvm.org/D69777
This causes a crash for the reproducer below
enum { a };
enum b { c, d };
e;
static _Bool g(struct f *h, enum b i) {
i &&j();
return a;
}
static k(char h, enum b i) {
_Bool l = g(e, i);
l;
}
m(h) {
k(h, c);
g(h, d);
}
This reverts commit aadb635e04.
Summary:
Right now the alignment of the lower half of a store is computed as
align/2, which fails for unaligned stores (align = 1), and is overly
pessimitic for, e.g. a 8 byte store aligned to 4 bytes.
Fixes PR44851
Fixes PR44877
Reviewers: gchatelet, spatel, lebedev.ri
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74311
Summary:
Currently, `SCEVExpander::isHighCostExpansionHelper()` has the following logic:
```
if (auto *UDivExpr = dyn_cast<SCEVUDivExpr>(S)) {
// If the divisor is a power of two and the SCEV type fits in a native
// integer (and the LHS not expensive), consider the division cheap
// irrespective of whether it occurs in the user code since it can be
// lowered into a right shift.
if (auto *SC = dyn_cast<SCEVConstant>(UDivExpr->getRHS()))
if (SC->getAPInt().isPowerOf2()) {
if (isHighCostExpansionHelper(UDivExpr->getLHS(), L, At,
BudgetRemaining, TTI, Processed))
return true;
const DataLayout &DL =
L->getHeader()->getParent()->getParent()->getDataLayout();
unsigned Width = cast<IntegerType>(UDivExpr->getType())->getBitWidth();
return DL.isIllegalInteger(Width);
}
```
Since this test does not have a datalayout specified,
`SCEVExpander::isHighCostExpansionHelper()` says that
`[[TMP2:%.*]] = lshr exact i64 [[TMP1]], 5` is high-cost, and didn't perform it.
But future patches will change that logic to solely rely on cost-model,
without any such datalayout checks, so i think it is best to show
that that change is ephemeral, and can already happen without costmodel changes.
Reviewers: reames, fhahn, sanjoy, craig.topper, RKSimon
Reviewed By: RKSimon
Subscribers: javed.absar, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D73717
This patch enables the debug entry values feature.
- Remove the (CC1) experimental -femit-debug-entry-values option
- Enable it for x86, arm and aarch64 targets
- Resolve the test failures
- Leave the llc experimental option for targets that do not
support the CallSiteInfo yet
Differential Revision: https://reviews.llvm.org/D73534
Now with the new functionality that allows creating "defines", it is
possible to reduce this test (I tried to find another ones, but seems others
were already fixed previously).
Differential revision: https://reviews.llvm.org/D74392
Summary:
Consider:
%r = call i32 @llvm.amdgcn.writelane(i32 0, i32 1, i32 2)
This produces a value that is 0 on lane 1, and 2 everywhere else; i.e.,
it is divergent.
Reported-by: Marek Olsak <Marek.Olsak@amd.com>
Reviewers: arsenm, foad, mareko
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74400
Summary:
The method attempts to find loads that can be legally clustered by
looking for loads consuming the same chain glue token.
However, the old code looks at _all_ users of values produced by the
chain node -- including uses of the loaded/returned value of volatile
loads or atomics. This could lead to circular dependencies which then
failed during scheduling.
With this change, we filter out users by getResNo, i.e. by which
SDValue value they use, to ensure that we only look at users of the
chain glue token.
This appears to be a rather old bug, which is perhaps surprising.
However, the test case is actually quite fragile (i.e., it is hidden
by fairly small changes), and the test _must_ use volatile loads for
the bug to manifest.
Reviewers: arsenm, bogner, craig.topper, foad
Subscribers: MatzeB, jvesely, wdng, hiraditya, javed.absar, jfb, kerbowa, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74253
The patch removes unnecessary members of DWARFDebugAddr and further
simplifies the implementation by separating parsing methods of tables
in the DWARFv5 and pre-standard formats.
Differential Revision: https://reviews.llvm.org/D74197
As a preparation for the subsequent patches, this updates the wordings
of some error messages in DWARFDebugAddr.
Differential Revision: https://reviews.llvm.org/D74196
This replaces a collocation "a .debug_addr table" with "an address table"
because the latter sounds more accurate.
Differential Revision: https://reviews.llvm.org/D74407
As there is no header in pre-DWARFv5 address tables, and we fill
the class data members with some artificial values, we should not
dump them as that might be misleading.
Differential Revision: https://reviews.llvm.org/D74195
As addresses in the address tables may have relocations, thus,
the relocations should be resolved to read the correct address.
That is especially important for targets that use RELA relocations
because in that case addends are stored in relocation sections.
Differential Revision: https://reviews.llvm.org/D74404
This reverts commit rGcd5b308b828e, rGcd5b308b828e, rG8cedf0e2994c.
There are issues to be investigated for polly bots and bots turning on
EXPENSIVE_CHECKS.
This was creating a select on true/false values, and then comparing
that later. This produced more work for later combines, which can be
avoided by just using the boolean values. This was copied from the
original DAG expansion, which also has the same problem. This doesn't
have a observable change using SelectionDAG, but since GlobalISel is
missing these optimizations, the final code was noticeably longer.
These have nicer expansions implemented in the DAG. Ideally we would
either directly implement all of these special expansions, or stop
expanding division in the IR.
This is apparently worse than 1-byte alignment. This does not attempt
to decompose 2-byte aligned wide stores, but will stop trying to
produce them.
Also fix bug in LoadStoreVectorizer which was decreasing the alignment
and vectorizing stack accesses. It was assuming a stack object was an
alloca that could have its base alignment changed, which is not true
if the pointer is derived from a function argument.
Since natural fdiv lowering is now more conservative even with
denormals disabled, we get a slower expansion from just a plain
1.0/fdiv. Directly emit the rcp intrinsic when using it to implement
integer division to avoid a pointlessly complex sequence.
https://reviews.llvm.org/D74273
Pad macho section data to pointer size bytes, so that relocation
table and symbol table following section data will be pointer size
aligned.
Patch by pguo.
We aren't doing a good job of optimizing AVX512 outside of this code. So remove the bail out for AVX512 and replace with a FIXME. This at least gets us the AVX2 codegen.
Differential Revision: https://reviews.llvm.org/D74431
Update test scripts were limited because they performed a single action
on the entire file and if that action was controlled by arguments, like
the one introduced in D68819, there was no record of it.
This patch introduces the capability of changing the arguments passed to
the script "on-the-fly" while processing a test file. In addition, an
"on/off" switch was added so that processing can be disabled for parts
of the file where the content is simply copied. The last extension is a
record of the invocation arguments in the auto generated NOTE. These
arguments are also picked up in a subsequent invocation, allowing
updates with special options enabled without user interaction.
To change the arguments the string `UTC_ARGS:` has to be present in a
line, followed by "additional command line arguments". That is
everything that follows `UTC_ARGS:` will be added to a growing list
of "command line arguments" which is reparsed after every update.
Reviewed By: arichardson
Differential Revision: https://reviews.llvm.org/D69701
Instructions marked as FrameSetup do not cause requestLabelAfterInsn to
be called and so no such label is generated. Call instructions which
require call site entries to be generated require this label to be
present in order to calculate the return PC offset/address, but the
check for whether the call instruction is marked as FrameSetup was not
present.
Therefore in the case where a call instruction is marked as FrameSetup,
an assertion failure occurs if a call site entry is to be generated.
This is the case with RISC-V's implementation of save/restore via
library calls.
Differential Revision: https://reviews.llvm.org/D71593
This patch adds the support required for using the __riscv_save and
__riscv_restore libcalls to implement a size-optimization for prologue
and epilogue code, whereby the spill and restore code of callee-saved
registers is implemented by common functions to reduce code duplication.
Logic is also included to ensure that if both this optimization and
shrink wrapping are enabled then the prologue and epilogue code can be
safely inserted into the basic blocks chosen by shrink wrapping.
Differential Revision: https://reviews.llvm.org/D62686
ObjectLinkingLayer was not correctly propagating dependencies through local
symbols within an object. This could cause symbol lookup to return before a
searched-for symbol is ready if the following conditions are met:
(1) The definition of the symbol being searched for transitively depends on a
local symbol within the same object, and that local symbol in turn
transitively depends on an external symbol provided by some other module
in the JIT.
(2) Concurrent compilation is enabled.
(3) Thread scheduling causes the lookup of the searched-for symbol to return
before all transitive dependencies of the looked-up symbol are emitted.
This bug was found by inspection and has not been observed in practice.
A jitlink test case has been added to verify that symbol dependencies are
correctly propagated through local symbol definitions.
Summary:
Part of the changes in D44564 made BasicAA not CFG only due to it using
PhiAnalysisValues which may have values invalidated.
Subsequent patches (rL340613) appear to have addressed this limitation.
BasicAA should not be invalidated by non-CFG-altering passes.
A concrete example is MemCpyOpt which preserves CFG, but we are testing
it invalidates BasicAA.
llvm-dev RFC: https://groups.google.com/forum/#!topic/llvm-dev/eSPXuWnNfzM
Reviewers: john.brawn, sebpop, hfinkel, brzycki
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74353
Based on uops.info these should have 5 cycle latency as they did on Haswell/Broadwell. I have no additional internal information from Intel.
This was also shown as a discrepancy in the spreadsheet that was sent with an early llvm-dev post about llvm-exegesis.
It also matches Agner Fog.
Differential Revision: https://reviews.llvm.org/D74357
This restores commit 748bb5a0f1, along
with a fix for a Chromium test suite build issue (and a new test for
that case).
Differential Revision: https://reviews.llvm.org/D73242
Currently, isTruncateFree() and isZExtFree() callbacks return false
as they are not implemented in BPF backend. This may cause suboptimal
code generation. For example, if the load in the context of zero extension
has more than one use, the pattern zextload{i8,i16,i32} will
not be generated. Rather, the load will be matched first and
then the result is zero extended.
For example, in the test together with this commit, we have
I1: %0 = load i32, i32* %data_end1, align 4, !tbaa !2
I2: %conv = zext i32 %0 to i64
...
I3: %2 = load i32, i32* %data, align 4, !tbaa !7
I4: %conv2 = zext i32 %2 to i64
...
I5: %4 = trunc i64 %sub.ptr.lhs.cast to i32
I6: %conv13 = sub i32 %4, %2
...
The I1 and I2 will match to one zextloadi32 DAG node, where SUBREG_TO_REG is
used to convert a 32bit register to 64bit one. During code generation,
SUBREG_TO_REG is a noop.
The %2 in I3 is used in both I4 and I6. If isTruncateFree() is false,
the current implementation will generate a SLL_ri and SRL_ri
for the zext part during lowering.
This patch implement isTruncateFree() in the BPF backend, so for the
above example, I3 and I4 will generate a zextloadi32 DAG node with
SUBREG_TO_REG is generated during lowering to Machine IR.
isZExtFree() is also implemented as it should help code gen as well.
This patch also enables the change in https://reviews.llvm.org/D73985
since it won't kick in generates MOV_32_64 machine instruction.
Differential Revision: https://reviews.llvm.org/D74101
The changeXXXAfterManifest functions are better suited to deal with
changes so we should prefer them. These functions also recursively
delete dead instructions which is why we see test changes.
When more than one SelectPseudo instruction is handled a new MBB is
returned. This must not be done if that would result in leaving an undhandled
isel pseudo behind in the original MBB.
Fixes https://bugs.llvm.org/show_bug.cgi?id=44849.
Review: Ulrich Weigand
Differential Revision: https://reviews.llvm.org/D74352
This patch removes forcedconstant to simplify things for the
move to ValueLattice, which includes constant ranges, but no
forced constants.
This patch removes forcedconstant and changes ResolvedUndefsIn
to mark instructions with unknown operands as overdefined. This
means we do not do simplifications based on undef directly in SCCP
any longer, but this seems to hardly come up in practice (see stats
below), presumably because InstCombine & others take care
of most of the relevant folds already.
It is still beneficial to keep ResolvedUndefIn, as it allows us delaying
going to overdefined until we propagated all known information.
I also built MultiSource, SPEC2000 and SPEC2006 and compared
sccp.IPNumInstRemoved and sccp.NumInstRemoved. It looks like the impact
is quite low:
Tests: 244
Same hash: 238 (filtered out)
Remaining: 6
Metric: sccp.IPNumInstRemoved
Program base patch diff
test-suite...arks/VersaBench/dbms/dbms.test 4.00 3.00 -25.0%
test-suite...TimberWolfMC/timberwolfmc.test 38.00 34.00 -10.5%
test-suite...006/453.povray/453.povray.test 158.00 155.00 -1.9%
test-suite.../CINT2000/176.gcc/176.gcc.test 668.00 668.00 0.0%
test-suite.../CINT2006/403.gcc/403.gcc.test 1209.00 1209.00 0.0%
test-suite...arks/mafft/pairlocalalign.test 76.00 76.00 0.0%
Tests: 244
Same hash: 238 (filtered out)
Remaining: 6
Metric: sccp.NumInstRemoved
Program base patch diff
test-suite...arks/mafft/pairlocalalign.test 185.00 175.00 -5.4%
test-suite.../CINT2006/403.gcc/403.gcc.test 2059.00 2056.00 -0.1%
test-suite.../CINT2000/176.gcc/176.gcc.test 2358.00 2357.00 -0.0%
test-suite...006/453.povray/453.povray.test 317.00 317.00 0.0%
test-suite...TimberWolfMC/timberwolfmc.test 12.00 12.00 0.0%
Reviewers: davide, efriedma, mssimpso
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D61314
A small IR change in calculating the active lanes resulted in no longer
recognising tail-predication. Now recognise both an 'add' and 'or' in
the expression that calculates the active lanes.
Differential Revision: https://reviews.llvm.org/D74394
ADDI(C.ADDI) may achieve better code size than XORI, since XORI has no C extension.
This patch transforms two patterns and gets almost equivalent results.
Differential Revision: https://reviews.llvm.org/D71774
This reverts commit d0c4d4fe09.
Revert "[DSE,MSSA] Move more passing test cases from todo to simple.ll."
This reverts commit 02266e64bb.
Revert "[DSE,MSSA] Adjust mda-with-dbg-values.ll to MSSA backed DSE."
This reverts commit 74f03e4ff0.
Without PSHUFB we are better using ROTL (expanding to OR(SHL,SRL)) than using the generic v16i8 shuffle lowering - but if we can widen to v8i16 or more then the existing shuffles are still the better option.
New intrinisics are implemented for when we need to port SIMD code from other
arhitectures and only load or store portions of MSA registers.
Following intriniscs are added which only load/store element 0 of a vector:
v4i32 __builtin_msa_ldrq_w (const void *, imm_n2048_2044);
v2i64 __builtin_msa_ldr_d (const void *, imm_n4096_4088);
void __builtin_msa_strq_w (v4i32, void *, imm_n2048_2044);
void __builtin_msa_str_d (v2i64, void *, imm_n4096_4088);
Differential Revision: https://reviews.llvm.org/D73644
LiveDebugVariables uses interval maps to explicitly represent DBG_VALUE
intervals. DBG_VALUEs are filtered into an interval map based on their {
Variable, DIExpression }. The interval map will coalesce adjacent entries that
use the same { Location }. Under this model, DBG_VALUEs which refer to the same
bits of the same variable will be filtered into different interval maps if they
have different DIExpressions which means the original intervals will not be
properly preserved.
This patch fixes the problem by using { Variable, Fragment } to filter the
DBG_VALUEs into maps, and coalesces adjacent entries iff they have the same
{ Location, DIExpression } pair.
The solution is not perfect because we see the similar issues appear when
partially overlapping fragments are encountered, but is far simpler than a
complete solution (i.e. D70121).
Fixes: pr41992, pr43957
Reviewed By: aprantl
Differential Revision: https://reviews.llvm.org/D74053
This adds a test to document --elf-cg-profile option we have.
I am going to refactor this area, and this patch is mostly to
create a base for a follow-up change.
Differential revision: https://reviews.llvm.org/D74115
We need to use vector instructions for these operations. Previously
we handled this with isel patterns that used extra instructions
and copies to handle the the conversions.
Now we use custom lowering to emit the conversions. This allows
them to be pattern matched and optimized on their own. For
example we can now emit vpextrw to store the result if its going
directly to memory.
I've forced the upper elements to VCVTPHS2PS to zero to keep some
code similar. Zeroes will be needed for strictfp. I've added a
DAG combine for (fp16_to_fp (fp_to_fp16 X)) to avoid extra
instructions in between to be closer to the previous codegen.
This is a step towards strictfp support for f16 conversions.
Summary:
There are a few field init values that are concrete but not complete/foldable (e.g. `?`). This allows for using those values as initializers without erroring out.
Example:
```
class A {
string value = ?;
}
class B<A impl> : A {
let value = impl.value; // This currently emits an error.
let value = ?; // This doesn't emit an error.
}
```
Differential Revision: https://reviews.llvm.org/D74360
As discussed in PR41083:
https://bugs.llvm.org/show_bug.cgi?id=41083
...we can assert/crash in EarlyCSE using the current hashing scheme and
instructions with flags.
ValueTracking's matchSelectPattern() may rely on overflow (nsw, etc) or
other flags when detecting patterns such as min/max/abs composed of
compare+select. But the value numbering / hashing mechanism used by
EarlyCSE intersects those flags to allow more CSE.
Several alternatives to solve this are discussed in the bug report.
This patch avoids the issue by doing simple matching of min/max/abs
patterns that never requires instruction flags. We give up some CSE
power because of that, but that is not expected to result in much
actual performance difference because InstCombine will canonicalize
these patterns when possible. It even has this comment for abs/nabs:
/// Canonicalize all these variants to 1 pattern.
/// This makes CSE more likely.
(And this patch adds PhaseOrdering tests to verify that the expected
transforms are still happening in the standard optimization pipelines.
I left this code to use ValueTracking's "flavor" enum values, so we
don't have to change the callers' code. If we decide to go back to
using the ValueTracking call (by changing the hashing algorithm
instead), it should be obvious how to replace this chunk.
Differential Revision: https://reviews.llvm.org/D74285
Summary: The lit feature object-emission was added because Hexagon did not support the integrated assembler, so some tests needed to be turned off with a Hexagon target. Hexagon now supports the integrated assembler, so this feature can be removed.
Reviewers: bcain, kparzysz, jverma, whitequark, JDevlieghere
Reviewed By: JDevlieghere
Subscribers: mehdi_amini, hiraditya, steven_wu, dexonsmith, arphaman, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D73568
This patch:
- enable frame pointer for AIX;
- update some of red zone comments;
- add/update testcases;
Differential Revision: https://reviews.llvm.org/D72454
Test that instcombine and early-cse can cooperate
to reduce sequences of select patterns that are not
composed of the same underlying instructions.
There's a bug in EarlyCSE (PR41083), and we can test
how much a possible fix (D74285) may affect optimization.
We were checking for extra uses of the negated operand even
if we were not going to create it as part of this canonicalization.
This was showing up as a regression when we limit EarlyCSE as
proposed in D74285.
SUMMARY:
The patch is enable to support Mergeable2ByteCString and Mergeable4ByteCString
Reviewers: daltenty
Subscribers: wuzish, nemanjai, hiraditya
Differential Revision: https://reviews.llvm.org/D74164
LoopCacheAnalysis currently assumes the loop will be iterated over in
a forward direction. This patch addresses the issue by using the
absolute value of the stride when iterating backwards.
Note: this patch will treat negative and positive array access the
same, resulting in the same cost being calculated for single and
bi-directional access patterns. This should be improved in a
subsequent patch.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D73064
Each function is with this compiled with the SystemZSubtarget initialized
from the functions attributes.
Review: Ulrich Weigand.
Differential Revision: https://reviews.llvm.org/D74086
Non-AVX512BW targets failed to concatenate 256-bit shifts back to 512-bits (split during 512-bit shuffle lowering as they don't have v32i16/v64i8 types).
This reverts commit b54a8ec1bc.
The commit triggered debug invariance (different output with/without
-g). The patch seems to have exposed a pre-existing invariance problem
in GlobalOpt, which I'll write a bug report for.
As noted on PR44379, we didn't attempt to lower vector shuffles using bit rotations on XOP/AVX512F targets.
This patch lowers to uniform ISD:ROTL nodes - ROTR isn't supported by XOP and they are interchangeable for constant values anyway.
There might be cases where targets without ISD:ROTL support would benefit from this (expanding to SRL+SHL+OR), which I'll investigate in a future patch.
REAPPLIED rGe82e17d4d4ca after reversion at rG39eade73a567 - fixed offset matching in matchShuffleAsBitRotate.
This patch makes the following System Registers Read Only:
- CurrentEL
- ICH_MISR_EL2
- PMBIDR_EL1
- PMSIDR_EL1
as found in:
https://developer.arm.com/docs/ddi0595/e/aarch64-system-registers
Relative line numbers were also added to the tests so we get more
informative error messages on failure.
Change-Id: I963b4f01ca5737b58f9e8e7abe9ca1d99e328758
Add a simplification to fuse a manual vector extract with shifts and
truncate into a bitcast.
Unpacking and packing values into vectors is only optimized with
extractelement instructions, not when manually unpacked using shifts
and truncates.
This patch simplifies shifts and truncates into a bitcast if possible.
Simplify (build_vec (trunc $1)
(trunc (srl $1 width))
(trunc (srl $1 (2 * width))) ...)
to (bitcast $1)
Differential Revision: https://reviews.llvm.org/D73892
The DebugInfo/dwarfdump-invalid-line-table test used a pre-canned binary
generated by a fuzzer to demonstrate a bug fix. Unfortunately, the
binary is rigid and requires hand-editing if we change behaviour, such
as rejecting certain properties within it (as I plan on doing in another
change).
Rather than hand-edit the binary, I have replaced it with two tests. The
first tests the high-level code path from the debug line parser that
produces the same error as this test previously did, and the second is a
set of unit test cases that comprehensively cover the
FormValue::skipValue method, which in turn covers the area that the
original bug fix touched.
Reviewed by: MaskRay, dblaikie
Differential Revision: https://reviews.llvm.org/D74202
This change implements the llvm intrinsic llvm.read_register for
the SystemZ platform which returns the value of the specified
register
(http://llvm.org/docs/LangRef.html#llvm-read-register-and-llvm-write-register-intrinsics).
This implementation returns the value of the stack register, and
can be extended to return the value of other registers. The
implementation for this intrinsic exists on various other platforms
including Power, x86, ARM, etc. but missing on SystemZ.
Reviewers: uweigand
Differential Revision: https://reviews.llvm.org/D73378
As noted on PR44379, we didn't attempt to lower vector shuffles using bit rotations on XOP/AVX512F targets.
This patch lowers to uniform ISD:ROTL nodes - ROTR isn't supported by XOP and they are interchangeable for constant values anyway.
There might be cases where targets without ISD:ROTL support would benefit from this (expanding to SRL+SHL+OR), which I'll investigate in a future patch.
Also, non-AVX512BW targets fail to concatenate 256-bit rotations back to 512-bits (split during shuffle lowering as they don't have v32i16/v64i8 types).
---
Internal shuffle tests indicate theres a bug somewhere that I haven't been able to track down yet.
This patch adds a first version of a MemorySSA based DSE. It is missing
a lot of features, which will get added as follow-ups, to help to keep
the review manageable.
The patch uses the following general approach: given a MemoryDef, walk
upwards to find clobbering MemoryDefs that may be killed by the
starting def. Then check that there are no uses that may read the
location of the original MemoryDef in between both MemoryDefs. A bit
more concretely:
For all MemoryDefs StartDef:
1. Get the next dominating clobbering MemoryDef (DomAccess) by walking upwards.
2. Check that there no reads between DomAccess and the StartDef by checking
all uses starting at DomAccess and walking until we see StartDef.
3. For each found DomDef, check that:
1. There are no barrier instructions between DomDef and StartDef (like
throws or stores with ordering constraints).
2. StartDef is executed whenever DomDef is executed.
3. StartDef completely overwrites DomDef.
4. Erase DomDef from the function and MemorySSA.
The patch uses a very simple approach to guarantee that no throwing
instructions are between 2 stores: We only allow accesses to stack
objects, access that are in the same basic block if the block does not
contain any throwing instructions or accesses in functions that do
not contain any throwing instructions. This will get lifted later.
Besides adding support for the missing cases, there is plenty of additional
potential for improvements as follow-up work, e.g. the way we visit stores
(could be just a traversal of the MemorySSA, rather than collecting them
up-front), using the alias information discovered during walking to optimize
the MemorySSA.
This is loosely based on D40480 by Dave Green.
Reviewers: dmgreen, rnk, efriedma, bryant, asbirlea, Tyker
Reviewed By: asbirlea
Differential Revision: https://reviews.llvm.org/D72700
This copies the DSE tests into a MSSA subdirectory to test the MemorySSA
backed DSE implementation, without disturbing the original tests.
Differential Revision: https://reviews.llvm.org/D72145
Based on D72931
This adds a new feature called A16 which is enabled for gfx10.
gfx9 keeps the R128A16 feature so it can share all the instruction encodings
with gfx7/8.
Differential Revision: https://reviews.llvm.org/D73956
This is a minimal but important advancement over the existing code. A
cast with an operand that is only used in the cast retains the no-alias
property of the operand.
Traversing PHI nodes is natural with the genericValueTraversal but also
a bit tricky. The problem is similar to the ones we have seen in AAAlign
and AADereferenceable, namely that we continue to increase the range in
each iteration. We use a pessimistic approach here to stop the
iterations. Nevertheless, optimistic information can now be propagated
through a PHI node.
The change is performed as stated by the FIXME and the tests are
adjusted. All changes look fine to me and values can be inferred as
undef without it being an error.
Casts can be handled natively by the ConstantRange class. We do limit it
to extends for now as we assume an integer type in different locations.
A TODO and a test case with a FIXME was added to remove that restriction
in the future.
Using sign extend forces the adjacent element to either all zeros
or all ones. But all ones is a NAN. So that doesn't seem like a
great idea.
Trying to work on supporting this with strict FP where NAN would
definitely be bad.
When the FP exists, the FP base CFI directive offset should take the size of variable arguments into account.
Differential Revision: https://reviews.llvm.org/D73862
Vector indexing with a constant index should be folded out in the
legalizer, but this was accidentally falling through. This would
produce the indexing operation with $noreg. Handle this case as a
dynamic index just in case a bug like this happens again in the
future.
We were failing to find constants that were casted. I feel like the
artifact combiner should have folded the constant in the trunc before
the custom lowering, but that doesn't happen.
Reverts part of 6524a7a2b9. Since that
commit, the expansion was ignoring the actual save exec register
produced by the instruction, and looking at other instructions. I do
not understand why it was looking at other instructions, but relying
on this scan was wrong.
Fixes verifier errors after SI_IF is tail duplicated, which should be
correct to do. The results were fed into a phi, which was lowered to
the S_MOV_B64_term instructions.
Fix issue mentioned on rGe82e17d4d4ca - non-AVX512BW targets failed to concatenate 256-bit rotations back to 512-bits (split during shuffle lowering as they don't have v32i16/v64i8 types).
As noted on PR44379, we didn't attempt to lower vector shuffles using bit rotations on XOP/AVX512F targets.
This patch lowers to uniform ISD:ROTL nodes - ROTR isn't supported by XOP and they are interchangeable for constant values anyway.
There might be cases where targets without ISD:ROTL support would benefit from this (expanding to SRL+SHL+OR), which I'll investigate in a future patch.
Also, non-AVX512BW targets fail to concatenate 256-bit rotations back to 512-bits (split during shuffle lowering as they don't have v32i16/v64i8 types).
We have several bug reports that could be characterized as "reducing scalarization",
and this topic was also raised on llvm-dev recently:
http://lists.llvm.org/pipermail/llvm-dev/2020-January/138157.html
...so I'm proposing that we deal with these patterns in a new, lightweight IR vector
pass that runs before/after other vectorization passes.
There are 4 alternate options that I can think of to deal with this kind of problem
(and we've seen various attempts at all of these), but they all have flaws:
InstCombine - can't happen without TTI, but we don't want target-specific
folds there.
SDAG - too late to assist other vectorization passes; TLI is not equipped
for these kind of cost queries; limited to a single basic block.
CGP - too late to assist other vectorization passes; would need to re-implement
basic cleanups like CSE/instcombine.
SLP - doesn't fit with existing transforms; limited to a single basic block.
This initial patch/transform is based on existing code in AggressiveInstCombine:
we walk backwards through the function looking for a pattern match. But we diverge
from that cost-independent IR canonicalization pass by using TTI to decide if the
vector alternative is profitable.
We probably have at least 10 similar bug reports/patterns (binops, constants,
inserts, cheap shuffles, etc) that would fit in this pass as follow-up enhancements.
It's possible that we could iterate on a worklist to fix-point like InstCombine does,
but it's safer to start with a most basic case and evolve from there, so I didn't
try to do anything fancy with this initial implementation.
Differential Revision: https://reviews.llvm.org/D73480
The LoopExtractor created new functions (by definition), which violates
the restrictions of a LoopPass.
The correct implementation of this pass should be as a ModulePass.
Includes reverting rL82990 implications on the LoopExtractor.
Fixes PR3082 and PR8929.
Differential Revision: https://reviews.llvm.org/D69069
Implement protection against the stack clash attack [0] through inline stack
probing.
Probe stack allocation every PAGE_SIZE during frame lowering or dynamic
allocation to make sure the page guard, if any, is touched when touching the
stack, in a similar manner to GCC[1].
This extends the existing `probe-stack' mechanism with a special value `inline-asm'.
Technically the former uses function call before stack allocation while this
patch provides inlined stack probes and chunk allocation.
Only implemented for x86.
[0] https://www.qualys.com/2017/06/19/stack-clash/stack-clash.txt
[1] https://gcc.gnu.org/ml/gcc-patches/2017-07/msg00556.html
This a recommit of 39f50da2a3 with proper LiveIn
declaration, better option handling and more portable testing.
Differential Revision: https://reviews.llvm.org/D68720
Implement protection against the stack clash attack [0] through inline stack
probing.
Probe stack allocation every PAGE_SIZE during frame lowering or dynamic
allocation to make sure the page guard, if any, is touched when touching the
stack, in a similar manner to GCC[1].
This extends the existing `probe-stack' mechanism with a special value `inline-asm'.
Technically the former uses function call before stack allocation while this
patch provides inlined stack probes and chunk allocation.
Only implemented for x86.
[0] https://www.qualys.com/2017/06/19/stack-clash/stack-clash.txt
[1] https://gcc.gnu.org/ml/gcc-patches/2017-07/msg00556.html
This a recommit of 39f50da2a3 with proper LiveIn
declaration, better option handling and more portable testing.
Differential Revision: https://reviews.llvm.org/D68720
In addition to the module pass, this patch introduces a CGSCC pass that
runs the Attributor on a strongly connected component of the call graph
(both old and new PM). The Attributor was always design to be used on a
subset of functions which makes this patch mostly mechanical.
The one change is that we give up `norecurse` deduction in the module
pass in favor of doing it during the CGSCC pass. This makes the
interfaces simpler but can be revisited if needed.
Reviewed By: hfinkel
Differential Revision: https://reviews.llvm.org/D70767
Parallel regions known to be read-only, e.g., after we removed all dead
write accesses, and terminating (`willreturn`) can be removed.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D69954
The OpenMPOpt pass is a CGSCC pass in which OpenMP specific
optimizations can reside.
The OpenMPOpt pass uses the OpenMPKinds.def file to identify runtime
calls and their uses. This allows targeted transformations and eases
their implementation.
This initial patch deduplicates `__kmpc_global_thread_num` and
`omp_get_thread_num` calls. We can also identify arguments that are
equivalent to such a call result and use it instead. Later we can
determine "gtid" arguments based on the use in kernel functions etc.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D69930
Bionic has had `__strlen_chk` for a while. Optimizing that into a
constant is quite profitable, when possible.
Differential Revision: https://reviews.llvm.org/D74079
While D72944 also fixes https://bugs.llvm.org/show_bug.cgi?id=44541,
it does so in a more roundabout manner and there might be other
loopholes to trigger the same issue. This is a more direct fix,
that prevents the transform if the min/max is based on a
non-canonical sub X, 0 instruction.
Differential Revision: https://reviews.llvm.org/D73849
As discussed on D73919, this replaces a few cases where we were
modifying multiple operands of instructions in-place with the
creation of a new instruction, which we generally prefer nowadays.
This tends to be more readable and less prone to worklist management
bugs.
Test changes are only superficial (instruction naming and order).
Fixes https://bugs.llvm.org/show_bug.cgi?id=44835. Skip the transform
if it wouldn't actually do anything (apart from removing and reinserting
the same instructions).
Note that the test case doesn't loop on current master anymore, only
on the LLVM 10 release branch. The issue is already mitigated on master
due to worklist order fixes, but we should fix the root cause there as well.
As a side note, we should probably assert in combineLoadToNewType()
that it does not combine to the same type. Not doing this here, because
this assertion would also be triggered in another place right now.
Differential Revision: https://reviews.llvm.org/D74278
Implement protection against the stack clash attack [0] through inline stack
probing.
Probe stack allocation every PAGE_SIZE during frame lowering or dynamic
allocation to make sure the page guard, if any, is touched when touching the
stack, in a similar manner to GCC[1].
This extends the existing `probe-stack' mechanism with a special value `inline-asm'.
Technically the former uses function call before stack allocation while this
patch provides inlined stack probes and chunk allocation.
Only implemented for x86.
[0] https://www.qualys.com/2017/06/19/stack-clash/stack-clash.txt
[1] https://gcc.gnu.org/ml/gcc-patches/2017-07/msg00556.html
This a recommit of 39f50da2a3 with better option
handling and more portable testing
Differential Revision: https://reviews.llvm.org/D68720
Ayman Musa