Since non-pow-2 types are going to get split up into multiple loads anyway,
don't do the [SZ]EXTLOAD combine for those and save us trouble later in
legalization.
llvm-svn: 358458
Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't
be degraded.
This change also improves the IRTranslator so that in most places, but not all,
it creates constants using the MIRBuilder directly instead of first creating a
new destination vreg and then creating a constant. By doing this, the
buildConstant() method can just return the vreg of an existing G_CONSTANT
instead of having to create a COPY from it.
I measured a 0.2% improvement in compile time and a 0.9% improvement in code
size at -O0 ARM64.
Compile time:
Program base cse diff
test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8%
test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7%
test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4%
test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3%
test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2%
test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2%
test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2%
test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1%
test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1%
test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0%
Geomean difference -0.2%
Code size:
Program base cse diff
test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7%
test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2%
test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1%
test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1%
test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9%
test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6%
test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4%
test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0%
test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0%
test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0%
Geomean difference -0.9%
Differential Revision: https://reviews.llvm.org/D60580
llvm-svn: 358369
This enables the simple copy combine that already exists in the CombinerHelper.
However, it exposed a bug in the GISelChangeObserver where it wouldn't clear a
set of MIs to process, and so would end up causing a crash when deleted MIs were
being added to the combiner worklist again.
Differential Revision: https://reviews.llvm.org/D60579
llvm-svn: 358318
This crash was introduced in r358032 as we try to construct an EVT from an MVT
in order to find the register type for the calling conv. Fall back instead of
trying to do this with an invalid MVT coming from i256.
llvm-svn: 358314
If a shufflevector's mask vector has an element with "undef" then the generic
instruction defining that element register is a G_IMPLICT_DEF instead of G_CONSTANT.
This fixes the selector to handle this case, and for now assumes that undef just means
zero. In future we'll optimize this case properly.
llvm-svn: 358312
Loads and store of values with type like <2 x p0> currently don't get imported
because SelectionDAG has no knowledge of pointer types. To leverage the existing
support for vector load/stores, we can bitcast the value to have s64 element
types instead. We do this as a custom legalization.
This patch also adds support for general loads of <2 x s64>, and relaxes some
type conditions on selecting G_BITCAST.
Differential Revision: https://reviews.llvm.org/D60534
llvm-svn: 358221
This patch teach getTestBitOperand to look through ANY_EXTENDs when the extended bits aren't used. The test case changed here is based what D60358 did to test16 in tbz-tbnz.ll. So this patch will avoid that regression.
Differential Revision: https://reviews.llvm.org/D60482
llvm-svn: 358108
Summary: The fp16 scalar version of facge and facgt requires a custom patter matching, as the result type is not the same width of the operands.
Reviewers: olista01, javed.absar, pbarrio
Reviewed By: javed.absar
Subscribers: kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D60212
llvm-svn: 358083
The selection for G_ICMP is unfortunately not currently importable from SDAG
due to the use of custom SDNodes. To support this, this selection method has an
opcode table which has been generated by a script, indexed by various
instruction properties. Ideally in future we will have a GISel native selection
patterns that we can write in tablegen to improve on this.
For selection of some types we also need support for G_ASHR and G_SHL which are
generated as a result of legalization. This patch also adds support for them,
generating the same code as SelectionDAG currently does.
Differential Revision: https://reviews.llvm.org/D60436
llvm-svn: 358035
required to be passed as different register types. E.g. <2 x i16> may need to
be passed as a larger <2 x i32> type, so formal arg lowering needs to be able
truncate it back. Likewise, when dealing with returns of these types, they need
to be widened in the appropriate way back.
Differential Revision: https://reviews.llvm.org/D60425
llvm-svn: 358032
Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.).
This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........
Differential Revision: https://reviews.llvm.org/D60006
llvm-svn: 357765
This revision causes tests to fail under ASAN. Since the cause of the failures
is not clear (could be ASAN, could be a Clang bug, could be a bug in this
revision), the safest course of action seems to be to revert while investigating.
llvm-svn: 357667
Same as G_EXP. Add a test, and update legalizer-info-validation.mir and
f16-instructions.ll.
Differential Revision: https://reviews.llvm.org/D60165
llvm-svn: 357605
There are 3 changes to make this correspond to the same transform in instcombine:
1. Remove the legality check - we can't create anything less legal than we started with.
2. Ease the use restriction, so we only bail out if both operands have >1 use.
3. Ease the use restriction for binops with a repeated operand (eg, mul x, x).
As discussed in D60150, there's a scalarization opportunity that will be made
easier by allowing this transform more generally.
llvm-svn: 357580
This adds partial instruction selection support for llvm.aarch64.stlxr. It also
factors out selection for G_INTRINSIC_W_SIDE_EFFECTS into its own function. The
new function removes the restriction that the intrinsic ID on the
G_INTRINSIC_W_SIDE_EFFECTS be on operand 0.
Also add a test, and add a GISel line to arm64-ldxr-stxr.ll.
Differential Revision: https://reviews.llvm.org/D60100
llvm-svn: 357518
There are various places in LLVM where the definition of StackID is not
properly honoured, for example in PEI where objects with a StackID > 0 are
allocated on the default stack (StackID0). This patch enforces that PEI
only considers allocating objects to StackID 0.
Reviewers: arsenm, thegameg, MatzeB
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D60062
llvm-svn: 357460
The code was previously checking that candidates for sinking had exactly
one use or were a store instruction (which can't have uses). This meant
we could sink call instructions only if they had a use.
That limitation seemed a bit arbitrary, so this patch changes it to
"instruction has zero or one use" which seems more natural and removes
the need to special-case stores.
Differential revision: https://reviews.llvm.org/D59936
llvm-svn: 357452
This improves selection for vector stores into v2s64s. Before we just
scalarized them, but we can just use a STRQui instead.
Differential Revision: https://reviews.llvm.org/D60083
llvm-svn: 357432
This adds support for v2s32 vector inserts, and updates the selection +
regbankselect tests for G_INSERT_VECTOR_ELT.
Differential Revision: https://reviews.llvm.org/D59910
llvm-svn: 357318
In the example below, we would previously emit two range checks, one for cases
1--3 and one for 4--6. This patch makes us exploit the fact that the
fall-through is unreachable and only one range check is necessary.
switch i32 %i, label %default [
i32 1, label %bb1
i32 2, label %bb1
i32 3, label %bb1
i32 4, label %bb2
i32 5, label %bb2
i32 6, label %bb2
]
default: unreachable
llvm-svn: 357252
The artifact combiners push instructions which have been marked for deletion
onto an list for the legalizer to deal with on return. However, for trunc(ext)
combines the combiner routine recursively calls itself. When it does this the
dead instructions list may not be empty, and the other combiners don't expect
to be dealing with essentially invalid MIR (multiple vreg defs etc).
This change fixes it by ensuring that the dead instructions are processed on
entry into tryCombineInstruction.
As a result, this fix exposed a few places in tests where G_TRUNC instructions
were not being deleted even though they were dead.
Differential Revision: https://reviews.llvm.org/D59892
llvm-svn: 357101
Original commit by Ayonam Ray.
This commit adds a regression test for the issue discovered in the
previous commit: that the range check for the jump table can only be
omitted if the fall-through destination of the jump table is
unreachable, which isn't necessarily true just because the default of
the switch is unreachable.
This addresses the missing optimization in PR41242.
> 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.
>
> Differential Revision: https://reviews.llvm.org/D52002
> Reviewers: Hans Wennborg, Eli Freidman, Roman Lebedev
llvm-svn: 357067
Various SelectionDAG non-combine operations (e.g. the getNode smart
constructor and legalization) may leave dangling nodes by applying
optimizations or not fully pruning unused result values. This can
result in nodes that are never added to the worklist and therefore can
not be pruned.
Add a node inserter as the current node deleter to make sure such
nodes have the chance of being pruned.
Many minor changes, mostly positive.
llvm-svn: 356996
This is generally more readable due to the way the assembler aliases
work.
(This causes a lot of test changes, but it's not really as scary as it
looks at first glance; it's just mechanically changing a bunch of checks
for orr to check for mov instead.)
Differential Revision: https://reviews.llvm.org/D59720
llvm-svn: 356954
First half of PR40800, this patch adds DAG undef handling to icmp instructions to match the behaviour in llvm::ConstantFoldCompareInstruction and SimplifyICmpInst, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.).
This involved a lot of tweaking to reduced tests as bugpoint loves to reduce icmp arguments to undef........
Differential Revision: https://reviews.llvm.org/D59363
llvm-svn: 356938
This is the result of discussions on the list about how to deal with intrinsics
which require codegen to disambiguate them via only the integer/fp overloads.
It causes problems for GlobalISel as some of that information is lost during
translation, while with other operations like IR instructions the information is
encoded into the instruction opcode.
This patch changes clang to emit the new faddp intrinsic if the vector operands
to the builtin have FP element types. LLVM IR AutoUpgrade has been taught to
upgrade existing calls to aarch64.neon.addp with fp vector arguments, and
we remove the workarounds introduced for GlobalISel in r355865.
This is a more permanent solution to PR40968.
Differential Revision: https://reviews.llvm.org/D59655
llvm-svn: 356722
The AArch64 test was broken since the result register already had a
set register class, so this test was a no-op. The mapping verify call
would fail because the result size is not the same as the inputs like
in a copy or phi.
The AMDGPU testcases are half broken and introduce illegal VGPR->SGPR
copies which need much more work to handle correctly (same for phis),
but add them as a baseline.
llvm-svn: 356713
Added subtarget features for AArch64 to use TPIDR_EL[1|2|3] as the TLS base
register, rather than the default TPIDR_EL0.
Patch by Philip Derrin!
Differential revision: https://reviews.llvm.org/D54685
llvm-svn: 356657
This adds pattern matching for the insert+shufflevector sequence so we can
generate dup instructions instead of the current TBL sequence.
Differential Revision: https://reviews.llvm.org/D59558
llvm-svn: 356526
The 2nd loop calculates spill costs but reports free registers as cost
0 anyway, so there is little benefit from having a separate early
loop.
Surprisingly this is not NFC, as many register are marked regDisabled
so the first loop often picks up later registers unnecessarily instead
of the first one available in the allocation order...
Patch by Matthias Braun
llvm-svn: 356499
These changes are related to PR37743 and include:
SelectionDAGBuilder::visitSelect handles the unary SelectPatternFlavor::SPF_ABS case to build ABS node.
Delete the redundant recognizer of the integer ABS pattern from the DAGCombiner.
Add promoting the integer ABS node in the LegalizeIntegerType.
Expand-based legalization of integer result for the ABS nodes.
Expand-based legalization of ABS vector operations.
Add some integer abs testcases for different typesizes for Thumb arch
Add the custom ABS expanding and change the SAD pattern recognizer for X86 arch: The i64 result of the ABS is expanded to:
tmp = (SRA, Hi, 31)
Lo = (UADDO tmp, Lo)
Hi = (XOR tmp, (ADDCARRY tmp, hi, Lo:1))
Lo = (XOR tmp, Lo)
The "detectZextAbsDiff" function is changed for the recognition of pattern with the ABS node. Given a ABS node, detect the following pattern:
(ABS (SUB (ZERO_EXTEND a), (ZERO_EXTEND b))).
Change integer abs testcases for codegen with the ABS node support for AArch64.
Indicate that the ABS is legal for the i64 type when the NEON is supported.
Change the integer abs testcases to show changing of codegen.
Add combine and legalization of ABS nodes for Thumb arch.
Extend 'matchSelectPattern' to recognize the ABS patterns with ICMP_SGE condition.
For discussion, see https://bugs.llvm.org/show_bug.cgi?id=37743
Patch by: @ikulagin (Ivan Kulagin)
Differential Revision: https://reviews.llvm.org/D49837
llvm-svn: 356468
It uses the generic AArch64_IMM::expandMOVImm to get the correct
number of instruction used in immediate materialization.
Reviewers: efriedma
Differential Revision: https://reviews.llvm.org/D58461
llvm-svn: 356391
This patch follows some ideas from r352866 to optimize the floating
point materialization even further. It changes isFPImmLegal to
considere up to 2 mov instruction or up to 5 in case subtarget has
fused literals.
The rationale is the cost is the same for mov+fmov vs. adrp+ldr; but
the mov+fmov sequence is always better because of the reduced d-cache
pressure. The timings are still the same if you consider movw+movk+fmov
vs. adrp+ldr will be fused (although one instruction longer).
Reviewers: efriedma
Differential Revision: https://reviews.llvm.org/D58460
llvm-svn: 356390
Fixes https://bugs.llvm.org/show_bug.cgi?id=35094
The Dead register definition pass should leave alone the atomicrmw
instructions on AArch64 (LTE extension). The reason is the following
statement in the Arm ARM:
"The ST<OP> instructions, and LD<OP> instructions where the destination
register is WZR or XZR, are not regarded as doing a read for the purpose
of a DMB LD barrier."
A good example was given in the gcc thread by Will Deacon (linked in the
bugzilla ticket 35094):
P0 (atomic_int* y,atomic_int* x) {
atomic_store_explicit(x,1,memory_order_relaxed);
atomic_thread_fence(memory_order_release);
atomic_store_explicit(y,1,memory_order_relaxed);
}
P1 (atomic_int* y,atomic_int* x) {
atomic_fetch_add_explicit(y,1,memory_order_relaxed); // STADD
atomic_thread_fence(memory_order_acquire);
int r0 = atomic_load_explicit(x,memory_order_relaxed);
}
P2 (atomic_int* y) {
int r1 = atomic_load_explicit(y,memory_order_relaxed);
}
My understanding is that it is forbidden for r0 == 0 and r1 == 2 after
this test has executed. However, if the relaxed add in P1 compiles to
STADD and the subsequent acquire fence is compiled as DMB LD, then we
don't have any ordering guarantees in P1 and the forbidden result could
be observed.
Change-Id: I419f9f9df947716932038e1100c18d10a96408d0
llvm-svn: 356360
Fold (x & ~y) | y and it's four commuted variants to x | y. This pattern
can in particular appear when a vselect c, x, -1 is expanded to
(x & ~c) | (-1 & c) and combined to (x & ~c) | c.
This change has some overlap with D59066, which avoids creating a
vselect of this form in the first place during uaddsat expansion.
Differential Revision: https://reviews.llvm.org/D59174
llvm-svn: 356333
This is a subset of what was proposed in:
D59006
...and may overlap with test changes from:
D59174
...but it seems like a good general optimization to turn selects
into bitwise-logic when possible because we never know exactly
what can happen at this stage of DAG combining depending on how
the target has defined things.
Differential Revision: https://reviews.llvm.org/D59066
llvm-svn: 356332
Switch BIC immediate creation for vector ANDs from custom lowering
to a DAG combine, which gives generic DAG combines a change to
apply first. In particular this avoids (and x, -1) being turned into
a (bic x, 0) instead of being eliminated entirely.
Differential Revision: https://reviews.llvm.org/D59187
llvm-svn: 356299
Since we can't insert s16 gprs as we don't have 16 bit GPR registers, we need to
teach RBS to assign them to the FPR bank so our selector works.
llvm-svn: 356282
This isn't necessary according to the DWARF standard, but it matches the
.eh_frame sections emitted by other tools in practice, and the Android
libunwindstack rejects .eh_frame sections where an FDE refers to a CIE
other than the closest previous CIE. So match the other tools and also
sort accordingly.
I consider this a bug in libunwindstack, but it's easy enough to emit
a compatible .eh_frame section for compatibility with installed
operating systems.
Differential Revision: https://reviews.llvm.org/D58266
llvm-svn: 356216
This adds instruction selection support for G_UADDO on s32s and s64s.
Also
- Add an instruction selection test
- Update the arm64-xaluo.ll test to show that we generate the correct assembly
Differential Revision: https://reviews.llvm.org/D58734
llvm-svn: 356214
This re-uses the previous support for extract vector elt to extract the
subvectors.
Differential Revision: https://reviews.llvm.org/D59390
llvm-svn: 356213
This adds support for inserting elements into packed vectors. It also adds
two tests: one for selection, and one for regbank select.
Unpacked vectors will come in a follow-up.
Differential Revision: https://reviews.llvm.org/D59325
llvm-svn: 356182
This is consistent with what SelectionDAG does and is much easier to
work with than the extract sequence with an artificial wide register.
For the AMDGPU control flow intrinsics, this was producing an s128 for
the i64, i1 tuple return. Any legalization that should apply to a real
s128 value would badly obscure the direct values that need to be seen.
llvm-svn: 356147
Summary:
A number of optimizations are inhibited by single-use TokenFactors not
being merged into the TokenFactor using it. This makes we consider if
we can do the merge immediately.
Most tests changes here are due to the change in visitation causing
minor reorderings and associated reassociation of paired memory
operations.
CodeGen tests with non-reordering changes:
X86/aligned-variadic.ll -- memory-based add folded into stored leaq
value.
X86/constant-combiners.ll -- Optimizes out overlap between stores.
X86/pr40631_deadstore_elision -- folds constant byte store into
preceding quad word constant store.
Reviewers: RKSimon, craig.topper, spatel, efriedma, courbet
Reviewed By: courbet
Subscribers: dylanmckay, sdardis, nemanjai, jvesely, nhaehnle, javed.absar, eraman, hiraditya, kbarton, jrtc27, atanasyan, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59260
llvm-svn: 356068
First step towards PR40800 - I intend to move the float case in a separate future patch.
I had to tweak the (overly reduced) thumb2 test and the x86 widening test change is annoying (no longer rematerializable) but we should address this separately.
Differential Revision: https://reviews.llvm.org/D59244
llvm-svn: 356040
After r355865, we should be able to safely select G_EXTRACT_VECTOR_ELT without
running into any problematic intrinsics.
Also add a fix for lane copies, which don't support index 0.
llvm-svn: 355871
Overloaded intrinsics aren't necessarily safe for instruction selection. One
such intrinsic is aarch64.neon.addp.*.
This is a temporary workaround to ensure that we always fall back on that
intrinsic. Eventually this will be replaced with a proper solution.
https://bugs.llvm.org/show_bug.cgi?id=40968
Differential Revision: https://reviews.llvm.org/D59062
llvm-svn: 355865
Fixes https://bugs.llvm.org/show_bug.cgi?id=36796.
Implement basic legalizations (PromoteIntRes, PromoteIntOp,
ExpandIntRes, ScalarizeVecOp, WidenVecOp) for VECREDUCE opcodes.
There are more legalizations missing (esp float legalizations),
but there's no way to test them right now, so I'm not adding them.
This also includes a few more changes to make this work somewhat
reasonably:
* Add support for expanding VECREDUCE in SDAG. Usually
experimental.vector.reduce is expanded prior to codegen, but if the
target does have native vector reduce, it may of course still be
necessary to expand due to legalization issues. This uses a shuffle
reduction if possible, followed by a naive scalar reduction.
* Allow the result type of integer VECREDUCE to be larger than the
vector element type. For example we need to be able to reduce a v8i8
into an (nominally) i32 result type on AArch64.
* Use the vector operand type rather than the scalar result type to
determine the action, so we can control exactly which vector types are
supported. Also change the legalize vector op code to handle
operations that only have vector operands, but no vector results, as
is the case for VECREDUCE.
* Default VECREDUCE to Expand. On AArch64 (only target using VECREDUCE),
explicitly specify for which vector types the reductions are supported.
This does not handle anything related to VECREDUCE_STRICT_*.
Differential Revision: https://reviews.llvm.org/D58015
llvm-svn: 355860
Summary:
This change change the instrumentation to allow users to view the registers at the point at which tag mismatch occured. Most of the heavy lifting is done in the runtime library, where we save the registers to the stack and emit unwind information. This allows us to reduce the overhead, as very little additional work needs to be done in each __hwasan_check instance.
In this implementation, the fast path of __hwasan_check is unmodified. There are an additional 4 instructions (16B) emitted in the slow path in every __hwasan_check instance. This may increase binary size somewhat, but as most of the work is done in the runtime library, it's manageable.
The failure trace now contains a list of registers at the point of which the failure occured, in a format similar to that of Android's tombstones. It currently has the following format:
Registers where the failure occurred (pc 0x0055555561b4):
x0 0000000000000014 x1 0000007ffffff6c0 x2 1100007ffffff6d0 x3 12000056ffffe025
x4 0000007fff800000 x5 0000000000000014 x6 0000007fff800000 x7 0000000000000001
x8 12000056ffffe020 x9 0200007700000000 x10 0200007700000000 x11 0000000000000000
x12 0000007fffffdde0 x13 0000000000000000 x14 02b65b01f7a97490 x15 0000000000000000
x16 0000007fb77376b8 x17 0000000000000012 x18 0000007fb7ed6000 x19 0000005555556078
x20 0000007ffffff768 x21 0000007ffffff778 x22 0000000000000001 x23 0000000000000000
x24 0000000000000000 x25 0000000000000000 x26 0000000000000000 x27 0000000000000000
x28 0000000000000000 x29 0000007ffffff6f0 x30 00000055555561b4
... and prints after the dump of memory tags around the buggy address.
Every register is saved exactly as it was at the point where the tag mismatch occurs, with the exception of x16/x17. These registers are used in the tag mismatch calculation as scratch registers during __hwasan_check, and cannot be saved without affecting the fast path. As these registers are designated as scratch registers for linking, there should be no important information in them that could aid in debugging.
Reviewers: pcc, eugenis
Reviewed By: pcc, eugenis
Subscribers: srhines, kubamracek, mgorny, javed.absar, krytarowski, kristof.beyls, hiraditya, jdoerfert, llvm-commits, #sanitizers
Tags: #sanitizers, #llvm
Differential Revision: https://reviews.llvm.org/D58857
llvm-svn: 355738
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.
Differential Revision: https://reviews.llvm.org/D52002
Reviewers: Hans Wennborg, Eli Freidman, Roman Lebedev
llvm-svn: 355490
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.
Differential Revision: https://reviews.llvm.org/D52002
Reviewers: Hans Wennborg, Eli Freidman, Roman Lebedev
llvm-svn: 355483
Tests only for integers, not floating point or pointers.
The scalar 8-bit case uses branch instead of CMOV,
because there is no no 8-bit CMOV.
Vector tests are for consistency, since it can be vectorized.
https://bugs.llvm.org/show_bug.cgi?id=40965
llvm-svn: 355436
This adds instruction selection support for G_EXTRACT_VECTOR_ELT for cases
where the index is defined by a G_CONSTANT.
It also factos out the lane copy opcode selection part into its own function,
`getLaneCopyOpcode`. This is used by both `selectUnmergeValues` and
`selectExtractElt`.
Differential Revision: https://reviews.llvm.org/D58469
llvm-svn: 355344
The code to materialize a mask from a constant pool load tried to use a 128 bit
LDR to load a 64 bit constant pool entry, which was 8 byte aligned. This resulted
in a link failure in the NEON tests in the test suite since the LDR address was
unaligned. This change fixes that to instead emit a 64 bit LDR if the entry is
64 bit, before converting back to a 128 bit register for the TBL.
llvm-svn: 355326
This patch enables combining integer bitcasts of integer build vectors when the new scalar type is legal. I've avoided floating point because the implementation bitcasts float to int along the way and we would need to check the intermediate types for legality
Differential Revision: https://reviews.llvm.org/D58884
llvm-svn: 355324
In certain cases, the first non-frame-setup instruction in a function is
a branch. For example, it could be a cbz on an argument. Make sure we
correctly allocate the UnwindHelp, and find an appropriate register to
use to initialize it.
Fixes https://bugs.llvm.org/show_bug.cgi?id=40184
Differential Revision: https://reviews.llvm.org/D58752
llvm-svn: 355136
This extends the existing support for shufflevector to handle cases like
<2 x float>, which we can implement by concating the vectors and using a TBL1.
Differential Revision: https://reviews.llvm.org/D58684
llvm-svn: 355104
Summary:
When promoting the over flow vector for these ops we should use the target's desired setcc result type. This way a v8i32 result type will use a v8i32 overflow vector instead of a v8i16 overflow vector. A v8i16 overflow vector will cause LegalizeDAG/LegalizeVectorOps to have to use v8i32 and truncate to v8i16 in its expansion. By doing this in type legalization instead, we get the truncate into the DAG earlier and give DAG combine more of a chance to optimize it.
We also have to fix unrolling to use the scalar setcc result type for the scalarized operation, and convert it to the required vector element type after the scalar operation. We have to observe the vector boolean contents when doing this conversion. The previous code was just taking the scalar result and putting it in the vector. But for X86 and AArch64 that would have only put a the boolean value in bit 0 of the element and left all other bits in the element 0. We need to ensure all bits in the element are the same. I'm using a select with constants here because that's what setcc unrolling in LegalizeVectorOps used.
Reviewers: spatel, RKSimon, nikic
Reviewed By: nikic
Subscribers: javed.absar, kristof.beyls, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58567
llvm-svn: 354753
There's likely a missed IR canonicalization for at least 1 of these
patterns. Otherwise, we wouldn't have needed the pattern-matching
enhancement in D57516.
Note that -- unlike usubo added with D57789 -- the TLI hook for
this transform defaults to 'on'. So if there's any perf fallout
from this, targets should look at how they're lowering the uaddo
node in SDAG and/or override that hook.
The x86 diffs suggest that there's some missing pattern-matching
for forming inc/dec.
This should fix the remaining known problems in:
https://bugs.llvm.org/show_bug.cgi?id=40486https://bugs.llvm.org/show_bug.cgi?id=31754
llvm-svn: 354746
and greendragon also passes, but some other bots fail for reasons I don't understand.
The only difference I can see between these tests is it's missing an -O0
If this doesn't work I'll revert and continue investigating.
llvm-svn: 354529
This change makes some basic type combinations for G_SHUFFLE_VECTOR legal, and
implements them with a very pessimistic TBL2 instruction in the selector.
For TBL2, support is also needed to generate constant pool entries and load from
them in order to materialize the mask register.
Currently supports <2 x s64> and <4 x s32> result types.
Differential Revision: https://reviews.llvm.org/D58466
llvm-svn: 354521
Second part of https://bugs.llvm.org/show_bug.cgi?id=40442.
This adds an extra UnrollVectorOverflowOp() method to SDAG, because
the general UnrollOverflowOp() method can't deal with multiple results.
Additionally we need to expand UMULO/SMULO during vector op
legalization, as it may result in unrolling, which may need additional
type legalization.
Differential Revision: https://reviews.llvm.org/D57997
llvm-svn: 354513
Summary:
This test was failing in one of our setups because the generated ModuleID
had the full path of the test file and that path contained the string
BL.
Reviewers: t.p.northover, jpaquette, paquette
Reviewed By: paquette
Subscribers: javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58217
llvm-svn: 354497
Legalize/select llvm.ctlz.*
Add select-ctlz to show that we actually select them. Update arm64-clrsb.ll and
arm64-vclz.ll to show that we perform valid transformations in optimized builds,
and document where GISel can improve.
Differential Revision: https://reviews.llvm.org/D58155
llvm-svn: 354299
The Verifier is separate from the MachineVerifier, so move it to a
different directory. Some other verifier tests were scattered in
target codegen tests as well (although I'm sure I missed some). Work
towards using a more consistent naming scheme to make it clearer where
the gaps still are for generic instructions.
llvm-svn: 354138
This is a follow up to D48580 and D48581 which allows reserving
arbitrary general purpose registers with the exception of registers
with special purpose (X8, X16-X18, X29, X30) and registers used by LLVM
(X0, X19). This change also generalizes some of the existing logic to
rely entirely on values generated from tablegen.
Differential Revision: https://reviews.llvm.org/D56305
llvm-svn: 353957
This teaches the IRTranslator to emit G_BSWAP when it runs into
Intrinsic::bswap. This allows us to select G_BSWAP for non-vector types in
AArch64.
Add a select-bswap.mir test, and add global isel checks to a couple existing
tests in test/CodeGen/AArch64.
This doesn't handle every bswap case, since some of these rely on known bits
stuff. This just lets us handle the naive case.
Differential Revision: https://reviews.llvm.org/D58081
llvm-svn: 353861
Add support for
- v4s16 <-> v4s32
- v2s64 <-> v2s32
And update tests that use them to show that we generate the correct
instructions.
Differential Revision: https://reviews.llvm.org/D57832
llvm-svn: 353732
This teaches the legalizer about G_FFLOOR, and lets us select G_FFLOOR in
AArch64.
It updates the existing floating point tests, and adds a select-floor.mir test.
Differential Revision: https://reviews.llvm.org/D57486
llvm-svn: 353722
After the changes introduced in r353586, this instruction doesn't cause any
issues for any backend.
Original review: https://reviews.llvm.org/D57485
llvm-svn: 353720
The sqrt case is faster and we already do this for the case where
the exponent is 0.25. This adds the 0.75 case which is also not
sensitive to signed zeros.
Patch by Whitney Tsang (Whitney)
Differential revision: https://reviews.llvm.org/D57434
llvm-svn: 353557
AArch64 NEON has a bunch of instructions with a "2" suffix that extract
the top half of the source vectors, instead of the bottom half. We have
some DAGCombines to try to take advantage of that. However, they
assumed that any EXTRACT_VECTOR was extracting the high half of the
vector in question.
This issue has apparently existed since the AArch64 backend was merged.
Fixes https://bugs.llvm.org/show_bug.cgi?id=40632 .
Differential Revision: https://reviews.llvm.org/D57862
llvm-svn: 353486
This is part of https://bugs.llvm.org/show_bug.cgi?id=40442.
Vector legalization is implemented for the add/sub overflow opcodes.
UMULO/SMULO are also handled as far as legalization is concerned, but
they don't support vector expansion yet (so no tests for them).
The vector result widening implementation is suboptimal, because it
could result in a legalization loop.
Differential Revision: https://reviews.llvm.org/D57639
llvm-svn: 353464
This is pretty much directly ported from SelectionDAG. Doesn't include
the shift by non-constant but known bits version, since there isn't a
globalisel version of computeKnownBits yet.
This shows a disadvantage of targets not specifically which type
should be used for the shift amount. If type 0 is legalized before
type 1, the operations on the shift amount type use the wider type
(which are also less likely to legalize). This can be avoided by
targets specifying legalization actions on type 1 earlier than for
type 0.
llvm-svn: 353455
ARMv8.1a CASP instructions need the first of the pair to be an even register
(otherwise the encoding is unallocated). We enforced this during assembly, but
not CodeGen before.
llvm-svn: 353308
We can't outline BTI instructions, because they need to be the very first
instruction executed after an indirect call or branch. If we outline them, then
an indirect call might go to the branch to the outlined function, which will
fault.
Differential revision: https://reviews.llvm.org/D57753
llvm-svn: 353190
The fewerElementsVectors implementation for load/stores
handles the scalar reduction case just as well, so drop
the redundant code in narrowScalar. This also introduces
support for narrowing irregular size breakdowns for
scalars.
llvm-svn: 353125
Try to use the underlying source registers.
This enables legalization in more cases where some irregular
operations are widened and others narrowed.
This seems to make the test_combines_2 AArch64 test worse, since the
MERGE_VALUES has multiple uses. Since this should be required for
legalization, a hasOneUse check is probably inappropriate (or maybe
should only be used if the merge is legal?).
llvm-svn: 353121
A number of of tests were using imm operands, not cimm. Since CSE
relies on the exact ConstantInt* pointer used, and implicit
conversions are generally evil, also enforce the bitsize of the types.
llvm-svn: 353113
This reverts commit b05ecba6d687fcb3078509220c67458bf1d77a2e.
Apparently adding floor breaks AMDGPU somehow, so I have to back this out
while I look into it.
llvm-svn: 353065
This reverts commit 8bbd570fd5205a04d88d2e5513a6e4adbd028039.
Apparently adding ffloor breaks AMDGPU somehow, so I need to back this out
while I look into it.
llvm-svn: 353064
This introduces a generic opcode for floating point floor, working towards
selecting @llvm.floor.
Differential Revision: https://reviews.llvm.org/D57484
llvm-svn: 353057
As discussed in D50222, this changes the vector types in tests required for that revision to ones legal for X86.
Patch by @hermord (Dmytro Shynkevych)
Differential Revision: https://reviews.llvm.org/D56372
llvm-svn: 353004
For the scalar case only.
Also move the similar G_MERGE_VALUES handling to a separate function
and cleanup to make them look more similar.
llvm-svn: 352979
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 patch changes isFPImmLegal to return if the value can be enconded
as the immediate operand of a logical instruction besides checking if
for immediate field for fmov.
This optimizes some floating point materization, inclusive values
used on isinf lowering.
Reviewed By: rengolin, efriedma, evandro
Differential Revision: https://reviews.llvm.org/D57044
llvm-svn: 352866
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
This teaches the legalizer to handle G_FEXP in AArch64. As a result, it also
allows us to select G_FEXP.
It...
- Updates the legalizer-info tests
- Adds a test for legalizing exp
- Updates the existing fp tests to show that we can now select G_FEXP
https://reviews.llvm.org/D57483
llvm-svn: 352692
This adds instruction selection support for G_FABS in AArch64. It also updates
the existing basic FP tests, adds a selection test for G_FABS.
https://reviews.llvm.org/D57418
llvm-svn: 352684
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
This teaches GlobalISel to emit a RTLib call for @llvm.log2 when it encounters
it.
It updates the existing floating point tests to show that we don't fall back on
the intrinsic, and select the correct instructions. It also adds a legalizer
test for G_FLOG2.
https://reviews.llvm.org/D57357
llvm-svn: 352673
This teaches the legalizer about G_FSQRT in AArch64. Also adds a legalizer
test for G_FSQRT, a selection test for it, and updates existing floating point
tests.
https://reviews.llvm.org/D57361
llvm-svn: 352671
This introduces a generic instruction for computing the floating point
square root of a value.
Right now, we can't select @llvm.sqrt, so this is working towards fixing that.
llvm-svn: 352668
This currently shows up as a selection fallback since the dest regs were given
GPR banks but the source was a vector FPR reg.
Differential Revision: https://reviews.llvm.org/D57408
llvm-svn: 352545
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
Windows ARM64 has PIC relocation model and uses jump table kind
EK_LabelDifference32. This produces jump table entry as
".word LBB123 - LJTI1_2" which represents the distance between the block
and jump table.
A new relocation type (IMAGE_REL_ARM64_REL32) is needed to do the fixup
correctly if they are in different COFF section.
This change saves the jump table to the same COFF section as the
associated code. An ideal fix could be utilizing IMAGE_REL_ARM64_REL32
relocation type.
Patch by Tom Tan!
Differential Revision: https://reviews.llvm.org/D57277
llvm-svn: 352465
This adds support for legalizing G_FLOG into a RTLib call.
It adds a legalizer test, and updates the existing floating point tests.
https://reviews.llvm.org/D57347
llvm-svn: 352429
This adds instruction selection support for @llvm.log10 in AArch64. It teaches
GISel to lower it to a library call, updates the relevant tests, and adds a
legalizer test for log10.
https://reviews.llvm.org/D57341
llvm-svn: 352418
The 'apple-latest' alias is supposed to provide a CPU that contains the
latest Apple processor model supported by LLVM.
This is supposed to be used by tools like lldb to provide a target that
supports most of the CPU features.
For now, this is mapped to Cyclone.
Differential Revision: https://reviews.llvm.org/D56384
llvm-svn: 352412
This adds ISel support for lifetime markers in opt levels above O0.
It also updates the arm64-irtranslator test, and updates some AArch64 tests that
use them for added coverage.
It also adds a testcase taken from the X86 codegen tests which verified a bug
caused by lifetime markers + stack colouring in the past. This is intended to
make sure that GISel doesn't re-introduce the bug.
(This is basically a straight copy from what SelectionDAG does in
SelectionDAGBuilder.cpp)
https://reviews.llvm.org/D57187
llvm-svn: 352410
This contains all of the legalizer changes from D57197 necessary to select
G_FCOS and G_FSIN. It also updates several existing IR tests in
test/CodeGen/AArch64 that verify that we correctly lower the G_FCOS and G_FSIN
instructions.
https://reviews.llvm.org/D57197
3/3
llvm-svn: 352402
This introduces generic instrutions for floating point sin and cos, G_FCOS and
G_FSIN. It updates the tests, etc.
https://reviews.llvm.org/D57197
1/3
llvm-svn: 352400
This fixes loads like 's1 = load %p (load 1 from %p)' being combined with an
extend into an illegal 's8 = g_extload %p (load 1 from %p)' which doesn't do any
extension, by avoiding touching those < s8 size loads.
This bug was uncovered by a verifier update r351584, which I reverted it to keep
the bots green.
llvm-svn: 352311
The IR enforced limit for the address space is 24-bits, but LLT was
only using 23-bits. Additionally, the argument to the constructor was
truncating to 16-bits.
A similar problem still exists for the number of vector elements. The
IR enforces no limit, so if you try to use a vector with > 65535
elements the IRTranslator asserts in the LLT constructor.
llvm-svn: 352264
https://reviews.llvm.org/D57178
Now add a hook in TargetPassConfig to query if CSE needs to be
enabled. By default this hook returns false only for O0 opt level but
this can be overridden by the target.
As a consequence of the default of enabled for non O0, a few tests
needed to be updated to not use CSE (by passing in -O0) to the run
line.
reviewed by: arsenm
llvm-svn: 352126
This patch adds support for vector @llvm.ceil intrinsics when full 16 bit
floating point support isn't available.
To do this, this patch...
- Implements basic isel for G_UNMERGE_VALUES
- Teaches the legalizer about 16 bit floats
- Teaches AArch64RegisterBankInfo to respect floating point registers on
G_BUILD_VECTOR and G_UNMERGE_VALUES
- Teaches selectCopy about 16-bit floating point vectors
It also adds
- A legalizer test for the 16-bit vector ceil which verifies that we create a
G_UNMERGE_VALUES and G_BUILD_VECTOR when full fp16 isn't supported
- An instruction selection test which makes sure we lower to G_FCEIL when
full fp16 is supported
- A test for selecting G_UNMERGE_VALUES
And also updates arm64-vfloatintrinsics.ll to show that the new ceiling types
work as expected.
https://reviews.llvm.org/D56682
llvm-svn: 352113
As part of speculation hardening, the stack pointer gets masked with the
taint register (X16) before a function call or before a function return.
Since there are no instructions that can directly mask writing to the
stack pointer, the stack pointer must first be transferred to another
register, where it can be masked, before that value is transferred back
to the stack pointer.
Before, that temporary register was always picked to be x17, since the
ABI allows clobbering x17 on any function call, resulting in the
following instruction pattern being inserted before function calls and
returns/tail calls:
mov x17, sp
and x17, x17, x16
mov sp, x17
However, x17 can be live in those locations, for example when the call
is an indirect call, using x17 as the target address (blr x17).
To fix this, this patch looks for an available register just before the
call or terminator instruction and uses that.
In the rare case when no register turns out to be available (this
situation is only encountered twice across the whole test-suite), just
insert a full speculation barrier at the start of the basic block where
this occurs.
Differential Revision: https://reviews.llvm.org/D56717
llvm-svn: 351930
Each hwasan check requires emitting a small piece of code like this:
https://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html#memory-accesses
The problem with this is that these code blocks typically bloat code
size significantly.
An obvious solution is to outline these blocks of code. In fact, this
has already been implemented under the -hwasan-instrument-with-calls
flag. However, as currently implemented this has a number of problems:
- The functions use the same calling convention as regular C functions.
This means that the backend must spill all temporary registers as
required by the platform's C calling convention, even though the
check only needs two registers on the hot path.
- The functions take the address to be checked in a fixed register,
which increases register pressure.
Both of these factors can diminish the code size effect and increase
the performance hit of -hwasan-instrument-with-calls.
The solution that this patch implements is to involve the aarch64
backend in outlining the checks. An intrinsic and pseudo-instruction
are created to represent a hwasan check. The pseudo-instruction
is register allocated like any other instruction, and we allow the
register allocator to select almost any register for the address to
check. A particular combination of (register selection, type of check)
triggers the creation in the backend of a function to handle the check
for specifically that pair. The resulting functions are deduplicated by
the linker. The pseudo-instruction (really the function) is specified
to preserve all registers except for the registers that the AAPCS
specifies may be clobbered by a call.
To measure the code size and performance effect of this change, I
took a number of measurements using Chromium for Android on aarch64,
comparing a browser with inlined checks (the baseline) against a
browser with outlined checks.
Code size: Size of .text decreases from 243897420 to 171619972 bytes,
or a 30% decrease.
Performance: Using Chromium's blink_perf.layout microbenchmarks I
measured a median performance regression of 6.24%.
The fact that a perf/size tradeoff is evident here suggests that
we might want to make the new behaviour conditional on -Os/-Oz.
But for now I've enabled it unconditionally, my reasoning being that
hwasan users typically expect a relatively large perf hit, and ~6%
isn't really adding much. We may want to revisit this decision in
the future, though.
I also tried experimenting with varying the number of registers
selectable by the hwasan check pseudo-instruction (which would result
in fewer variants being created), on the hypothesis that creating
fewer variants of the function would expose another perf/size tradeoff
by reducing icache pressure from the check functions at the cost of
register pressure. Although I did observe a code size increase with
fewer registers, I did not observe a strong correlation between the
number of registers and the performance of the resulting browser on the
microbenchmarks, so I conclude that we might as well use ~all registers
to get the maximum code size improvement. My results are below:
Regs | .text size | Perf hit
-----+------------+---------
~all | 171619972 | 6.24%
16 | 171765192 | 7.03%
8 | 172917788 | 5.82%
4 | 177054016 | 6.89%
Differential Revision: https://reviews.llvm.org/D56954
llvm-svn: 351920
For AMDGPU the shift amount is never 64-bit, and
this needs to use a 32-bit shift.
X86 uses i8, but seemed to be hacking around this before.
llvm-svn: 351882
Not sure this is the best fix, but it saves an instruction for certain
constructs involving variable shifts.
Differential Revision: https://reviews.llvm.org/D55572
llvm-svn: 351768
These are copied from the sibling x86 file. I'm not sure which
of the current outputs (if any) is considered optimal, but
someone more familiar with AArch may want to take a look.
llvm-svn: 351754
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
EXPENSIVE_CHECKS buildbots are failing due to r351404.
Add x1 as live in to the funclet basic block for SEH funclets, as well as
-verify-machineinstrs to the test case that triggered the failure.
llvm-svn: 351472
There are cases where we have multiple epilogues that have the exact same unwind
code sequence. In that case, the epilogues can share the same unwind codes in
the .xdata section. This should get us past the assert "SEH unwind data
splitting not yet implemented" in many cases.
We still need to add support for generating multiple .pdata/.xdata sections for
those functions that need to be split into fragments.
Differential Revision: https://reviews.llvm.org/D56813
llvm-svn: 351421
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
https://reviews.llvm.org/D52803
This patch adds support to continuously CSE instructions during
each of the GISel passes. It consists of a GISelCSEInfo analysis pass
that can be used by the CSEMIRBuilder.
llvm-svn: 351283
compiler identification lines in test-cases.
(Doing so only because it's then easier to search for references which
are actually important and need fixing.)
llvm-svn: 351200
A block ending in an unconditional branch can have two successors if one
is a landing pad. In practice, I think this only has an effect on
Windows because landing pads are never empty for Itanium unwinding.
(Alternatively, I could add a check to
AArch64InstrInfo::canInsertSelect, but this seems more obvious.)
Differential Revision: https://reviews.llvm.org/D56468
llvm-svn: 351142
Otherwise, with D56544, the intrinsic will be expanded to an integer
csel, which is probably not what the user expected. This matches the
general convention of using "v1" types to represent scalar integer
operations in vector registers.
While I'm here, also add some error checking so we don't generate
illegal ABS nodes.
Differential Revision: https://reviews.llvm.org/D56616
llvm-svn: 351141
This feature enables the fusion of some arithmetic and logic instructions
together.
Differential revision: https://reviews.llvm.org/D56572
llvm-svn: 351139
Part of the effort to refactoring frame pointer code generation. We used
to use two function attributes "no-frame-pointer-elim" and
"no-frame-pointer-elim-non-leaf" to represent three kinds of frame
pointer usage: (all) frames use frame pointer, (non-leaf) frames use
frame pointer, (none) frame use frame pointer. This CL makes the idea
explicit by using only one enum function attribute "frame-pointer"
Option "-frame-pointer=" replaces "-disable-fp-elim" for tools such as
llc.
"no-frame-pointer-elim" and "no-frame-pointer-elim-non-leaf" are still
supported for easy migration to "frame-pointer".
tests are mostly updated with
// replace command line args ‘-disable-fp-elim=false’ with ‘-frame-pointer=none’
grep -iIrnl '\-disable-fp-elim=false' * | xargs sed -i '' -e "s/-disable-fp-elim=false/-frame-pointer=none/g"
// replace command line args ‘-disable-fp-elim’ with ‘-frame-pointer=all’
grep -iIrnl '\-disable-fp-elim' * | xargs sed -i '' -e "s/-disable-fp-elim/-frame-pointer=all/g"
Patch by Yuanfang Chen (tabloid.adroit)!
Differential Revision: https://reviews.llvm.org/D56351
llvm-svn: 351049
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:
This patch changes the legalization action for some half-precision floating-
point vector intrinsics (FSIN, FLOG, etc.) from Promote to Expand. These ops
are not supported in hardware for half-precision vectors, but promotion is
not always possible (for v8f16 operands). Changing the action to Expand fixes
an assertion failure in the legalizer when the frontend produces such ops.
In addition, a quick microbenchmark shows that, in the v4f16 case,
expanding introduces fewer spills and is therefore slightly faster than
promoting.
Reviewers: t.p.northover, SjoerdMeijer
Reviewed By: SjoerdMeijer
Subscribers: javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D56296
llvm-svn: 350825
Summary:
D55896 and D56029 add support to emit fixups for :abs_g0: , :abs_g1_s: , etc.
This patch adds the necessary enums and MCExpr needed for lowering these.
Reviewers: rnk, mstorsjo, efriedma
Reviewed By: efriedma
Subscribers: javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D56037
llvm-svn: 350798
If the caller's return type does not have a zeroext attribute but the
callee does a tail call zeroext, we won't consider the tail call during
CodeGenPrepare because the attributes don't match.
However, if the result of the tail call has no uses, it makes sense to
drop the sext/zext attributes.
Differential Revision: https://reviews.llvm.org/D56486
llvm-svn: 350753
This is an initial implementation for Speculative Load Hardening for
AArch64. It builds on top of the recently introduced
AArch64SpeculationHardening pass.
This doesn't implement (yet) some of the optimizations implemented for
the X86SpeculativeLoadHardening pass. I thought introducing the
optimizations incrementally in follow-up patches should make this easier
to review.
Differential Revision: https://reviews.llvm.org/D55929
llvm-svn: 350729
Commit rL347861 introduced an unintentional change in the behaviour when
compiling for AArch64 at -O0 with -global-isel=0. Previously, explicitly
disabling GlobalISel resulted in using FastISel but an updated condition
in the commit changed it to using SelectionDAG. The patch fixes this
condition and slightly better organizes the code that chooses the
instruction selector.
Fixes PR40131.
Differential Revision: https://reviews.llvm.org/D56266
llvm-svn: 350626
We have code to split vector splats (of zero and non-zero) for performance
reasons, but it ignores the fact that a store might be truncating.
Actually, truncating stores are formed for vNi8 and vNi16 types. Since the
truncation is from a legal type, the size of the store is always <= 64-bits and
so they don't actually benefit from being split up anyway, so this patch just
disables that transformation.
llvm-svn: 350620
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
@bextr64_32_b1 is extracted from hotpath of real-world code
(RawSpeed BitStream<>::peekBitsNoFill()) after `clang -O3`.
@bextr64_32_b2/@bextr64_32_b0 is the same pattern,
but with trunc done last, showing how i think it can be handled:
https://rise4fun.com/Alive/K4Bhttps://rise4fun.com/Alive/qC9
It is possible that middle-end should do some of this, too.
https://bugs.llvm.org/show_bug.cgi?id=36419
llvm-svn: 349998
This adds support for widening G_FCEIL in LegalizerHelper and
AArch64LegalizerInfo. More specifically, it teaches the AArch64 legalizer to
widen G_FCEIL from a 16-bit float to a 32-bit float when the subtarget doesn't
support full FP 16.
This also updates AArch64/f16-instructions.ll to show that we perform the
correct transformation.
llvm-svn: 349927
If you don't do this, then if you hit a G_LOAD in getInstrMapping, you'll end
up with GPRs on the G_FCEIL instead of FPRs. This causes a fallback.
Add it to the switch, and add a test verifying that this happens.
llvm-svn: 349822
This code pattern is an unfortunate side effect of the way some types get split
at call lowering. Ideally we'd either not generate it at all or combine it away
in the legalizer artifact combiner.
Until then, add selection support anyway which is a significant proportion of
our current fallbacks on CTMark.
rdar://46491420
llvm-svn: 349712
This adds a G_FCEIL generic instruction and uses it in AArch64. This adds
selection for floating point ceil where it has a supported, dedicated
instruction. Other cases aren't handled here.
It updates the relevant gisel tests and adds a select-ceil test. It also adds a
check to arm64-vcvt.ll which ensures that we don't fall back when we run into
one of the relevant cases.
llvm-svn: 349664
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
Summary: This the initial code change to facilitate managing FMF flags from Instructions to MI wrt Intrinsics in Global Isel. Eventually the GlobalObserver interface will be added as well, where FMF additions can be tracked for the builder and CSE.
Reviewers: aditya_nandakumar, bogner
Reviewed By: bogner
Subscribers: rovka, kristof.beyls, javed.absar
Differential Revision: https://reviews.llvm.org/D55668
llvm-svn: 349514
- Reapply changes intially introduced in r343089
- The archtecture info is no longer loaded whenever a DWARFContext is created
- The runtimes libraries (santiziers) make use of the dwarf context classes but
do not intialise the target info
- The architecture of the object can be obtained without loading the target info
- Adding a method to the dwarf context to get this information and multiplex the
string printing later on
Differential Revision: https://reviews.llvm.org/D55774
llvm-svn: 349472
The pass implements tracking of control flow miss-speculation into a "taint"
register. That taint register can then be used to mask off registers with
sensitive data when executing under miss-speculation, a.k.a. "transient
execution".
This pass is aimed at mitigating against SpectreV1-style vulnarabilities.
At the moment, it implements the tracking of miss-speculation of control
flow into a taint register, but doesn't implement a mechanism yet to then
use that taint register to mask off vulnerable data in registers (something
for a follow-on improvement). Possible strategies to mask out vulnerable
data that can be implemented on top of this are:
- speculative load hardening to automatically mask of data loaded
in registers.
- using intrinsics to mask of data in registers as indicated by the
programmer (see https://lwn.net/Articles/759423/).
For AArch64, the following implementation choices are made.
Some of these are different than the implementation choices made in
the similar pass implemented in X86SpeculativeLoadHardening.cpp, as
the instruction set characteristics result in different trade-offs.
- The speculation hardening is done after register allocation. With a
relative abundance of registers, one register is reserved (X16) to be
the taint register. X16 is expected to not clash with other register
reservation mechanisms with very high probability because:
. The AArch64 ABI doesn't guarantee X16 to be retained across any call.
. The only way to request X16 to be used as a programmer is through
inline assembly. In the rare case a function explicitly demands to
use X16/W16, this pass falls back to hardening against speculation
by inserting a DSB SYS/ISB barrier pair which will prevent control
flow speculation.
- It is easy to insert mask operations at this late stage as we have
mask operations available that don't set flags.
- The taint variable contains all-ones when no miss-speculation is detected,
and contains all-zeros when miss-speculation is detected. Therefore, when
masking, an AND instruction (which only changes the register to be masked,
no other side effects) can easily be inserted anywhere that's needed.
- The tracking of miss-speculation is done by using a data-flow conditional
select instruction (CSEL) to evaluate the flags that were also used to
make conditional branch direction decisions. Speculation of the CSEL
instruction can be limited with a CSDB instruction - so the combination of
CSEL + a later CSDB gives the guarantee that the flags as used in the CSEL
aren't speculated. When conditional branch direction gets miss-speculated,
the semantics of the inserted CSEL instruction is such that the taint
register will contain all zero bits.
One key requirement for this to work is that the conditional branch is
followed by an execution of the CSEL instruction, where the CSEL
instruction needs to use the same flags status as the conditional branch.
This means that the conditional branches must not be implemented as one
of the AArch64 conditional branches that do not use the flags as input
(CB(N)Z and TB(N)Z). This is implemented by ensuring in the instruction
selectors to not produce these instructions when speculation hardening
is enabled. This pass will assert if it does encounter such an instruction.
- On function call boundaries, the miss-speculation state is transferred from
the taint register X16 to be encoded in the SP register as value 0.
Future extensions/improvements could be:
- Implement this functionality using full speculation barriers, akin to the
x86-slh-lfence option. This may be more useful for the intrinsics-based
approach than for the SLH approach to masking.
Note that this pass already inserts the full speculation barriers if the
function for some niche reason makes use of X16/W16.
- no indirect branch misprediction gets protected/instrumented; but this
could be done for some indirect branches, such as switch jump tables.
Differential Revision: https://reviews.llvm.org/D54896
llvm-svn: 349456
The default still is dwarf, but SEH exceptions can now be enabled
optionally for the MinGW target.
Differential Revision: https://reviews.llvm.org/D55748
llvm-svn: 349451
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 Load/Store Optimizer runs before Machine Block Placement. At O3 the
Tail Duplication Threshold is set to 4 instructions and this can create
new opportunities for the Load/Store Optimizer. It seems worthwhile to
run it once again.
llvm-svn: 349338
Summary:
This allows us to register it with the MachineFunction delegate and be
notified automatically about erasure and creation of instructions. However,
we still need explicit notification for modifications such as those caused
by setReg() or replaceRegWith().
There is a catch with this though. The notification for creation is
delivered before any operands can be added. While appropriate for
scheduling combiner work. This is unfortunate for debug output since an
opcode by itself doesn't provide sufficient information on what happened.
As a result, the work list remembers the instructions (when debug output is
requested) and emits a more complete dump later.
Another nit is that the MachineFunction::Delegate provides const pointers
which is inconvenient since we want to use it to schedule future
modification. To resolve this GISelWorkList now has an optional pointer to
the MachineFunction which describes the scope of the work it is permitted
to schedule. If a given MachineInstr* is in this function then it is
permitted to schedule work to be performed on the MachineInstr's. An
alternative to this would be to remove the const from the
MachineFunction::Delegate interface, however delegates are not permitted
to modify the MachineInstr's they receive.
In addition to this, the observer has three interface changes.
* erasedInstr() is now erasingInstr() to indicate it is about to be erased
but still exists at the moment.
* changingInstr() and changedInstr() have been added to report changes
before and after they are made. This allows us to trace the changes
in the debug output.
* As a convenience changingAllUsesOfReg() and
finishedChangingAllUsesOfReg() will report changingInstr() and
changedInstr() for each use of a given register. This is primarily useful
for changes caused by MachineRegisterInfo::replaceRegWith()
With this in place, both combine rules have been updated to report their
changes to the observer.
Finally, make some cosmetic changes to the debug output and make Combiner
and CombinerHelp
Reviewers: aditya_nandakumar, bogner, volkan, rtereshin, javed.absar
Reviewed By: aditya_nandakumar
Subscribers: mgorny, rovka, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D52947
llvm-svn: 349167
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
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
This patch restricts the capability of G_MERGE_VALUES, and uses the new
G_BUILD_VECTOR and G_CONCAT_VECTORS opcodes instead in the appropriate places.
This patch also includes AArch64 support for selecting G_BUILD_VECTOR of <4 x s32>
and <2 x s64> vectors.
Differential Revisions: https://reviews.llvm.org/D53629
llvm-svn: 348788
Record the stack protector index in MachineFrameInfo when translating
Intrinsic::stackprotector similarly as is done by SelectionDAG when
processing the same intrinsic.
Setting this index allows the Prologue/Epilogue Insertion to recognize
that the stack protection is enabled. The pass can then make sure that
the stack protector comes before local variables on the stack and
assigns potentially vulnerable objects first so they are close to the
stack protector slot.
Differential Revision: https://reviews.llvm.org/D55418
llvm-svn: 348761
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
The code emitting AND-subtrees used to check whether any of the operands
was an OR in order to figure out if the result needs to be negated.
However the OR could be hidden in further subtrees and not immediately
visible.
Change the code so that canEmitConjunction() determines whether the
result of the generated subtree needs to be negated. Cleanup emission
logic to use this. I also changed the code a bit to make all negation
decisions early before we actually emit the subtrees.
This fixes http://llvm.org/PR39550
Differential Revision: https://reviews.llvm.org/D54137
llvm-svn: 348444
These opcodes are intended to subsume some of the capability of G_MERGE_VALUES,
as it was too powerful and thus complex to add deal with throughout the GISel
pipeline.
G_BUILD_VECTOR creates a vector value from a sequence of uniformly typed
scalar values. G_BUILD_VECTOR_TRUNC is a special opcode for handling scalar
operands which are larger than the destination vector element type, and
therefore does an implicit truncate.
G_CONCAT_VECTOR creates a vector by concatenating smaller, uniformly typed,
vectors together.
These will be used in a subsequent commit. This commit just adds the initial
infrastructure.
Differential Revision: https://reviews.llvm.org/D53594
llvm-svn: 348430
Mostly NFC, only change is the order of outlined function names.
Loop over the outlined functions instead of walking the candidate list.
This is a bit easier to understand. It's far more natural to create a function,
then replace all of its occurrences with calls than the other way around.
The functions outlined after this do not change, but their names will be
decided by their benefit. E.g, OUTLINED_FUNCTION_0 will now always be the
most beneficial function, rather than the first one seen.
This makes it easier to enforce an ordering on the outlined functions. So,
this also adds a test to make sure that the ordering works as expected.
llvm-svn: 348414
Functions annotated with `__fastcall` or `__attribute__((__fastcall__))`
or `__attribute__((__swiftcall__))` may contain SEH handlers even on
Win64. This matches the behaviour of cl which allows for
`__try`/`__except` inside a `__fastcall` function. This was detected
while trying to self-host clang on Windows ARM64.
llvm-svn: 348337
We previously disabled this in r323371 because of a bug where we selected an
extending load, but didn't delete the old G_LOAD, resulting in two loads being
generated for volatile loads.
Since we now have dedicated G_SEXTLOAD/G_ZEXTLOAD operations, and that the
tablegen patterns should no longer be able to select (ext(load x)) patterns, it
should be safe to re-enable it.
The old test case should still work as expected.
llvm-svn: 348320
The comment was misplaced, and the code didn't do what the comment indicated,
namely ignoring the varargs portion when computing the local stack size of a
funclet in emitEpilogue. This results in incorrect offset computations within
funclets that are contained in vararg functions.
Differential Revision: https://reviews.llvm.org/D55096
llvm-svn: 348222
This moves the stack check logic into a lambda within getOutliningCandidateInfo.
This allows us to be less conservative with stack checks. Whether or not a
stack instruction is safe to outline is dependent on the frame variant and call
variant of the outlined function; only in cases where we modify the stack can
these be unsafe.
So, if we move that logic later, when we're looking at an individual candidate,
we can make better decisions here.
This gives some code size savings as a result.
llvm-svn: 348220
If it's a bigger code size win to drop candidates that require stack fixups
than to demote every candidate to that variant, the outliner should do that.
This happens if the number of bytes taken by calls to functions that don't
require fixups, plus the number of bytes that'd be left is less than the
number of bytes that it'd take to emit a save + restore for all candidates.
Also add tests for each possible new behaviour.
- machine-outliner-compatible-candidates shows that when we have candidates
that don't use the stack, we can use the default call variant along with the
no save/regsave variant.
- machine-outliner-all-stack shows that when it's better to fix up the stack,
we still will demote all candidates to that case
- machine-outliner-drop-stack shows that we can discard candidates that
require stack fixups when it would be beneficial to do so.
llvm-svn: 348168
Amara Emerson