Summary:
Recognize wide compares where the wide operand is a splat of a scalar
value in the appropriate range and convert to the immediate variant of
the instruction.
Patch by Graham Hunter
Reviewers: sdesmalen, efriedma, dancgr, rovka, rengolin
Reviewed By: efriedma
Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, psnobl,
llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71009
Summary:
This fixes PR44135.
The special case when we promote a bitcast from a vector to an int
needs special handling when we are on a big-endian target.
Prior to this fix, for the added vec_to_int we see the following in the
SelectionDAG printouts
Type-legalized selection DAG: %bb.1 'foo:bb.1'
SelectionDAG has 9 nodes:
t0: ch = EntryToken
t2: v8i16,ch = CopyFromReg t0, Register:v8i16 %0
t17: v4i32 = bitcast t2
t23: i32 = extract_vector_elt t17, Constant:i32<3>
t8: ch,glue = CopyToReg t0, Register:i32 $r0, t23
t9: ch = ARMISD::RET_FLAG t8, Register:i32 $r0, t8:1
and I think here the extract_vector_elt is wrong and extracts the value
from the wrong index.
The program program should return the 32 bits made up of the elements at
index 4 and 5 in the vec6 array, but with
t23: i32 = extract_vector_elt t17, Constant:i32<3>
as far as I can tell, we will extract values that originally didn't even
exist in the vec6 vectore.
If we would instead extract the element at index 2 we would get the wanted
values.
With this fix we insert a right shift after the bitcast in
DAGTypeLegalizer::PromoteIntRes_BITCAST which then gives us
Type-legalized selection DAG: %bb.1 'vec_to_int:bb.1'
SelectionDAG has 9 nodes:
t0: ch = EntryToken
t2: v8i16,ch = CopyFromReg t0, Register:v8i16 %0
t23: v4i32 = bitcast t2
t27: i32 = extract_vector_elt t23, Constant:i32<2>
t8: ch,glue = CopyToReg t0, Register:i32 $r0, t27
t9: ch = ARMISD::RET_FLAG t8, Register:i32 $r0, t8:1
So now we get
t27: i32 = extract_vector_elt t23, Constant:i32<2>
which is what we want.
Similarly, the new int_to_vec testcase exposes a bug where we cast the other
direction. Then we instead need to add a left shift before the bitcast on
big-endian targets for the bits in the input integer to end up at the exptected
place in the vector.
Reviewers: bogner, spatel, craig.topper, t.p.northover, dmgreen, efriedma, SjoerdMeijer, samparker
Reviewed By: efriedma
Subscribers: eli.friedman, bjope, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70942
Summary:
The new OpenMPConstants.h is a location for all OpenMP related constants
(and helpers) to live.
This patch moves the directives there (the enum OpenMPDirectiveKind) and
rewires Clang to use the new location.
Initially part of D69785.
Reviewers: kiranchandramohan, ABataev, RaviNarayanaswamy, gtbercea, grokos, sdmitriev, JonChesterfield, hfinkel, fghanim
Subscribers: jholewinski, ppenzin, penzn, llvm-commits, cfe-commits, jfb, guansong, bollu, hiraditya, mgorny
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D69853
extern variable usage in BPF is different from traditional
pure user space application. Recent discussion in linux bpf
mailing list has two use cases where debug info types are
required to use extern variables:
- extern types are required to have a suitable interface
in libbpf (bpf loader) to provide kernel config parameters
to bpf programs.
https://lore.kernel.org/bpf/CAEf4BzYCNo5GeVGMhp3fhysQ=_axAf=23PtwaZs-yAyafmXC9g@mail.gmail.com/T/#t
- extern types are required so kernel bpf verifier can
verify program which uses external functions more precisely.
This will make later link with actual external function no
need to reverify.
https://lore.kernel.org/bpf/87eez4odqp.fsf@toke.dk/T/#m8d5c3e87ffe7f2764e02d722cb0d8cbc136880ed
This patch added bpf support to consume such info into BTF,
which can then be used by bpf loader. Function processFuncPrototypes()
only adds extern function definitions into BTF. The functions
with actual definition have been added to BTF in some other places.
Differential Revision: https://reviews.llvm.org/D70697
Making some changes to MIRVRegNamerUtils.cpp to use some more modern c++
features as well as some changes to generally make the code more concise
and more understandable.
I make this an NFCi because in one case I drop the whole
"if (!MO->isDef()) MO->setIsKill(false);" thing that was added in the
original implementation, generally because I don't think this is really
semantically sound. I also changed up the implementation of
VRegRenamer::createVirtualRegisterWithLowerName somewhat because I am
now lower-casing the name unconditionally because I confirmed that that
was in fact aditya_nandakumar@apple.com's intent.
In all other cases, behavior should not be changed.
Differential Revision: https://reviews.llvm.org/D71182
D34393 added MCCodePadder as an infrastructure for padding code with
NOP instructions. It lacked tests and was not being worked on since
then.
Intel has now worked on an assembler patch to mitigate performance loss
after applying microcode update for the Jump Conditional Code Erratum.
https://www.intel.com/content/www/us/en/support/articles/000055650/processors.html
This new patch shares similarity with MCCodePadder, but has a concrete
use case in mind and is being actively developed. The infrastructure it
introduces can potentially be used for general performance improvement
via alignment. Delete the unused MCCodePadder so that people can develop
the new feature from a clean state.
Reviewed By: jyknight, skan
Differential Revision: https://reviews.llvm.org/D71106
As discussed in https://reviews.llvm.org/D69998, we miss to create some dependency edges
if chained more than 2 instructions. Adding an assertion here if someone want to chain
more than 2 instructions.
Differential Revision: https://reviews.llvm.org/D71180
Don't try to fold away shuffles which can't be folded. Fix creation of
shufflevector constant expressions.
Differential Revision: https://reviews.llvm.org/D71147
The generated sequence with whilelo is unintuitive, but it's the best
I could come up with given the limited number of SVE instructions that
interact with scalar registers. The other sequence I was considering
was something like dup+cmpne, but an extra scalar instruction seems
better than an extra vector instruction.
Differential Revision: https://reviews.llvm.org/D71160
Summary:
Following on from rG884351547da2, this patch cleans up the logic for `xxpermdi`
peephole optimizations by converting two layers of nested `if`s to early breaks
and simplifying the logic.
Reviewers: hfinkel, nemanjai, jsji, lkail, #powerpc, steven.zhang
Reviewed By: #powerpc, steven.zhang
Subscribers: wuzish, steven.zhang, hiraditya, kbarton, shchenz, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71170
Patch by vddvss (Colin Samples).
Summary:
Same as D60846 and D69571 but with a fix for the problem encountered
after them. Both times it was a missing context adjustment in the
handling of PHI nodes.
The reproducers created from the bugs that caused the old commits to be
reverted are included.
Reviewers: nikic, nlopes, mkazantsev, spatel, dlrobertson, uabelho, hakzsam, hans
Subscribers: hiraditya, bollu, asbirlea, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71181
Summary:
Split off of D67120.
Add the profile guided size optimization instrumentation / queries in the code
gen or target passes. This doesn't enable the size optimizations in those passes
yet as they are currently disabled in shouldOptimizeForSize (for non-IR pass
queries).
A second try after reverted D71072.
Reviewers: davidxl
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71149
Summary:
This is found during https://reviews.llvm.org/D70758
All the other record forms are having suffix o at the end.
ANDIo8 and ANDISo8 are the only two that put o before 8.
This patch rename them to be consistent with others.
Reviewers: #powerpc, hfinkel, nemanjai, lei, steven.zhang, echristo, jhibbits, joerg
Reviewed By: jhibbits
Subscribers: wuzish, hiraditya, kbarton, shchenz, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70928
Refactor FinishCall to be more easily understandable as a precursor to
implementing indirect calls for AIX. The refactor tries to group similar
code together at the cost of some code duplication. The high level
overview of the refactor:
- Adds a number of helper functions for things like:
* Determining if a call is indirect.
* What the Opcode for a call is.
* Transforming the callee for a direct function call.
* Extracting the Chain operand from a CallSeqStart node.
* Building the operands of the call.
- Adds helpers for building the indirect call DAG nodes
(excluding the call instruction itself which is created in
`FinishCall`).
- Removes PrepareCall, which has been subsumed by the
helpers.
- Rename 'InFlag' to 'Glue'.
- FinishCall has been refactored to:
1) Set TOC pointer usage on the DAG for the TOC based
subtargets.
2) Calculate if a call is indirect.
3) Determine the Opcode to use for the call
instruction.
4) Transform the Callee for direct calls, or build
the DAG nodes for indirect calls.
5) Buildup the call operands.
6) Emit the call instruction.
7) If needed, emit the callSeqEnd Node and
finish lowering by calling `LowerCallResult`
Differential Revision: https://reviews.llvm.org/D70126
I rewrote the isel tablegen for MVE immediate shifts, and accidentally
removed the `let Predicates=[HasMVEInt]` that was wrapping the old
version, which seems to have allowed those rules to cause trouble on
non-MVE targets. That's what I get for only re-running the MVE tests.
Summary:
This adds the family of `vshlq_n` and `vshrq_n` ACLE intrinsics, which
shift every lane of a vector left or right by a compile-time
immediate. They mostly work by expanding to the IR `shl`, `lshr` and
`ashr` operations, with their second operand being a vector splat of
the immediate.
There's a fiddly special case, though. ACLE specifies that the
immediate in `vshrq_n` can take values up to //and including// the bit
size of the vector lane. But LLVM IR thinks that shifting right by the
full size of the lane is UB, and feels free to replace the `lshr` with
an `undef` half way through the optimization pipeline. Hence, to keep
this legal in source code, I have to detect it at codegen time.
Logical (unsigned) right shifts by the element size are handled by
simply emitting the zero vector; arithmetic ones are converted into a
shift of one bit less, which will always give the same output.
In order to do that check, I also had to enhance the tablegen
MveEmitter so that it can cope with converting a builtin function's
operand into a bare integer to pass to a code-generating subfunction.
Previously the only bare integers it knew how to handle were flags
generated from within `arm_mve.td`.
Reviewers: dmgreen, miyuki, MarkMurrayARM, ostannard
Reviewed By: MarkMurrayARM
Subscribers: kristof.beyls, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71065
The cycle values in modulo scheduling results can be negative.
The result of ModuloSchedule::getCycle() must be received as an int type.
Patch by Masaki Arai!
Differential Revision: https://reviews.llvm.org/D71122
CodeGenPrepare::placeDebugValues moves variable location intrinsics to be
immediately after the Value they refer to. This makes tracking of locations
very easy; but it changes the order in which assignments appear to the
debugger, from the source programs order to the order in which the
optimised program computes values. This then leads to PR43986 and PR38754,
where variable locations that were in a conditional block are made
unconditional, which is highly misleading.
This patch adjusts placeDbgValues to only re-order variable location
intrinsics if they use a Value before it is defined, significantly reducing
the damage that it does. This is still not 100% safe, but the rest of
CodeGenPrepare needs polishing to correctly update debug info when
optimisations are performed to fully fix this.
This will probably break downstream debuginfo tests -- if the
instruction-stream position of variable location changes isn't the focus of
the test, an easy fix should be to manually apply placeDbgValues' behaviour
to the failing tests, moving dbg.value intrinsics next to SSA variable
definitions thus:
%foo = inst1
%bar = ...
%baz = ...
void call @llvm.dbg.value(metadata i32 %foo, ...
to
%foo = inst1
void call @llvm.dbg.value(metadata i32 %foo, ...
%bar = ...
%baz = ...
This should return your test to exercising whatever it was testing before.
Differential Revision: https://reviews.llvm.org/D58453
Summary:
This patch adds intrinsics for the following MVE instructions:
* VCADD, VHCADD
* VCMUL
* VCMLA
Each of the above 3 groups has a corresponding new LLVM IR intrinsic.
Reviewers: simon_tatham, MarkMurrayARM, ostannard, dmgreen
Reviewed By: MarkMurrayARM
Subscribers: merge_guards_bot, kristof.beyls, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D71190
With the extra optimisations we have done, these should now be fine to
enable by default. Which is what this patch does.
Differential Revision: https://reviews.llvm.org/D70968
This attempts to teach the cost model in Arm that code such as:
%s = shl i32 %a, 3
%a = and i32 %s, %b
Can under Arm or Thumb2 become:
and r0, r1, r2, lsl #3
So the cost of the shift can essentially be free. To do this without
trying to artificially adjust the cost of the "and" instruction, it
needs to get the users of the shl and check if they are a type of
instruction that the shift can be folded into. And so it needs to have
access to the actual instruction in getArithmeticInstrCost, which if
available is added as an extra parameter much like getCastInstrCost.
We otherwise limit it to shifts with a single user, which should
hopefully handle most of the cases. The list of instruction that the
shift can be folded into include ADC, ADD, AND, BIC, CMP, EOR, MVN, ORR,
ORN, RSB, SBC and SUB. This translates to Add, Sub, And, Or, Xor and
ICmp.
Differential Revision: https://reviews.llvm.org/D70966
This adds some extra cost model tests for shifts, and does some minor
adjustments to some Neon code to make it clear as to what it applies to.
Both NFC.
Summary:
Currently the describeLoadedValue() hook is assumed to describe the
value of the instruction's first explicit define. The hook will not be
called for instructions with more than one explicit define.
This commit adds a register parameter to the describeLoadedValue() hook,
and invokes the hook for all registers in the worklist.
This will allow us to for example describe instructions which produce
more than two parameters' values; e.g. Hexagon's various combine
instructions.
This also fixes situations in our downstream target where we may pass
smaller parameters in the high part of a register. If such a parameter's
value is produced by a larger copy instruction, we can't describe the
call site value using the super-register, and we instead need to know
which sub-register that should be used.
This also allows us to handle cases like this:
$ebx = [...]
$rdi = MOVSX64rr32 $ebx
$esi = MOV32rr $edi
CALL64pcrel32 @call
The hook will first be invoked for the MOV32rr instruction, which will
say that @call's second parameter (passed in $esi) is described by $edi.
As $edi is not preserved it will be added to the worklist. When we get
to the MOVSX64rr32 instruction, we need to describe two values; the
sign-extended value of $ebx -> $rdi for the first parameter, and $ebx ->
$edi for the second parameter, which is now possible.
This commit modifies the dbgcall-site-lea-interpretation.mir test case.
In the test case, the values of some 32-bit parameters were produced
with LEA64r. Perhaps we can in general cases handle such by emitting
expressions that AND out the lower 32-bits, but I have not been able to
land in a case where a LEA64r is used for a 32-bit parameter instead of
LEA64_32 from C code.
I have not found a case where it would be useful to describe parameters
using implicit defines, so in this patch the hook is still only invoked
for explicit defines of forwarding registers.
Reviewers: djtodoro, NikolaPrica, aprantl, vsk
Reviewed By: djtodoro, vsk
Subscribers: ormris, hiraditya, llvm-commits
Tags: #debug-info, #llvm
Differential Revision: https://reviews.llvm.org/D70431
Currently the describeLoadedValue() hook is assumed to describe the
value of the instruction's first explicit define. The hook will not be
called for instructions with more than one explicit define.
This commit adds a register parameter to the describeLoadedValue() hook,
and invokes the hook for all registers in the worklist.
This will allow us to for example describe instructions which produce
more than two parameters' values; e.g. Hexagon's various combine
instructions.
This also fixes a case in our downstream target where we may pass
smaller parameters in the high part of a register. If such a parameter's
value is produced by a larger copy instruction, we can't describe the
call site value using the super-register, and we instead need to know
which sub-register that should be used.
This also allows us to handle cases like this:
$ebx = [...]
$rdi = MOVSX64rr32 $ebx
$esi = MOV32rr $edi
CALL64pcrel32 @call
The hook will first be invoked for the MOV32rr instruction, which will
say that @call's second parameter (passed in $esi) is described by $edi.
As $edi is not preserved it will be added to the worklist. When we get
to the MOVSX64rr32 instruction, we need to describe two values; the
sign-extended value of $ebx -> $rdi for the first parameter, and $ebx ->
$edi for the second parameter, which is now possible.
This commit modifies the dbgcall-site-lea-interpretation.mir test case.
In the test case, the values of some 32-bit parameters were produced
with LEA64r. Perhaps we can in general cases handle such by emitting
expressions that AND out the lower 32-bits, but I have not been able to
land in a case where a LEA64r is used for a 32-bit parameter instead of
LEA64_32 from C code.
I have not found a case where it would be useful to describe parameters
using implicit defines, so in this patch the hook is still only invoked
for explicit defines of forwarding registers.
This caused "Too many bits for uint64_t" asserts when building Chromium. See
https://crbug.com/1031978#c2 for a reproducer. I'll follow up on the
llvm-commits thread with a creduced version.
> ARMCodeGenPrepare has already been generalized and renamed to
> TypePromotion. We've had it enabled and tested downstream for a
> while, so enable it by default.
>
> Differential Revision: https://reviews.llvm.org/D70998
This is another transform suggested in PR44153:
https://bugs.llvm.org/show_bug.cgi?id=44153
The backend for some targets already manages to get
this if it converts copysign to bitwise logic.
MVE doesn't have the range of shuffle instructions available in Neon. We
also cannot use the trick of cutting a difficult vector shuffle in half
to simplify things. Instead we need to be more careful about how we
lower shuffles.
This patch adds an extra combine that attempts to find "whole lane"
vmovs when lowering shuffles of smaller types. This helps us make some
shuffles a lot simpler, generating single lane movs for the parts that
can make use of it, falling back to the original shuffle for the rest.
Differential Revision: https://reviews.llvm.org/D69509
Alas, using half the available vector registers in a single instruction
is just too much for the register allocator to handle. The mve-vldst4.ll
test here fails when these instructions are enabled at present. This
patch disables the generation of VLD4 and VST4 by adding a
mve-max-interleave-factor option, which we currently default to 2.
Differential Revision: https://reviews.llvm.org/D71109
Currently we fail to pick the right insertion point when
PreviousLastPart of a first-order-recurrence is a PHI node not in the
LoopVectorBody. This can happen when PreviousLastPart is produce in a
predicated block. In that case, we should pick the insertion point in
the BB the PHI is in.
Fixes PR44020.
Reviewers: hsaito, fhahn, Ayal, dorit
Reviewed By: Ayal
Differential Revision: https://reviews.llvm.org/D71071
My patch 9db13b5a7d seems to have
caused some build bots to fail due to warnings that appear only
when using -Wcovered-switch-default.
This patch is an attempt to fix this by trying to avoid both the warning
"default label in switch which covers all enumeration values"
for the inner switch statements and at the same time the warning
"this statement may fall through"
for the outer switch statement in getVectorComparison
(SystemZISelLowering.cpp).
Generate types for global variables with "weak" attribute.
Keep allocation scope the same for both weak and non-weak
globals as ELF symbol table can determine whether a global
symbol is weak or not.
Differential Revision: https://reviews.llvm.org/D71162
AssumptionCache can be null in SimplifyCFGOptions. However, FoldCondBranchOnPHI() was not properly handling that when passing a null AssumptionCache to simplifyCFG.
Patch by Rodrigo Caetano Rocha <rcor.cs@gmail.com>
Reviewers: fhahn, lebedev.ri, spatel
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D69963
This adds support for constrained floating-point comparison intrinsics.
Specifically, we add:
declare <ty2>
@llvm.experimental.constrained.fcmp(<type> <op1>, <type> <op2>,
metadata <condition code>,
metadata <exception behavior>)
declare <ty2>
@llvm.experimental.constrained.fcmps(<type> <op1>, <type> <op2>,
metadata <condition code>,
metadata <exception behavior>)
The first variant implements an IEEE "quiet" comparison (i.e. we only
get an invalid FP exception if either argument is a SNaN), while the
second variant implements an IEEE "signaling" comparison (i.e. we get
an invalid FP exception if either argument is any NaN).
The condition code is implemented as a metadata string. The same set
of predicates as for the fcmp instruction is supported (except for the
"true" and "false" predicates).
These new intrinsics are mapped by SelectionDAG codegen onto two new
ISD opcodes, ISD::STRICT_FSETCC and ISD::STRICT_FSETCCS, again
representing quiet vs. signaling comparison operations. Otherwise
those nodes look like SETCC nodes, with an additional chain argument
and result as usual for strict FP nodes. The patch includes support
for the common legalization operations for those nodes.
The patch also includes full SystemZ back-end support for the new
ISD nodes, mapping them to all available SystemZ instruction to
fully implement strict semantics (scalar and vector).
Differential Revision: https://reviews.llvm.org/D69281
The file is intended to gather various VPlan transformations, not only
CFG related transforms. Actually, the only transformation there is not
CFG related.
Reviewers: Ayal, gilr, hsaito, rengolin
Reviewed By: gilr
Differential Revision: https://reviews.llvm.org/D70732
Summary:
This patch fixes an issue where the PPC MI peephole optimization pass incorrectly remove a vector swap.
Specifically, the pass can combine a splat/swap to a splat/copy. It uses `TargetRegisterInfo::lookThruCopyLike` to determine that the operands to the splat are the same. However, the current logic only compares the operands based on register numbers. In the case where the splat operands are ultimately feed from the same physical register, the pass can incorrectly remove a swap if the feed register for one of the operands has been clobbered.
This patch adds a check to ensure that the registers feeding are both virtual registers or the operands to the splat or swap are both the same register.
Here is an example in pseudo-MIR of what happens in the test cased added in this patch:
Before PPC MI peephole optimization:
```
%arg = XVADDDP %0, %1
$f1 = COPY %arg.sub_64
call double rint(double)
%res.first = COPY $f1
%vec.res.first = SUBREG_TO_REG 1, %res.first, %subreg.sub_64
%arg.swapped = XXPERMDI %arg, %arg, 2
$f1 = COPY %arg.swapped.sub_64
call double rint(double)
%res.second = COPY $f1
%vec.res.second = SUBREG_TO_REG 1, %res.second, %subreg.sub_64
%vec.res.splat = XXPERMDI %vec.res.first, %vec.res.second, 0
%vec.res = XXPERMDI %vec.res.splat, %vec.res.splat, 2
; %vec.res == [ %vec.res.second[0], %vec.res.first[0] ]
```
After optimization:
```
; ...
%vec.res.splat = XXPERMDI %vec.res.first, %vec.res.second, 0
; lookThruCopyLike(%vec.res.first) == lookThruCopyLike(%vec.res.second) == $f1
; so the pass replaces the swap with a copy:
%vec.res = COPY %vec.res.splat
; %vec.res == [ %vec.res.first[0], %vec.res.second[0] ]
```
As best as I can tell, this has occurred since r288152, which added support for lowering certain vector operations to direct moves in the form of a splat.
Committed for vddvss (Colin Samples). Thanks Colin for the patch!
Differential Revision: https://reviews.llvm.org/D69497
Before this change, the *InstPrinter.cpp files of each target where some
of the slowest objects to compile in all of LLVM. See this snippet produced by
ClangBuildAnalyzer:
https://reviews.llvm.org/P8171$96
Search for "InstPrinter", and see that it shows up in a few places.
Tablegen was emitting a large switch containing a sequence of operand checks,
each of which created many conditions and many BBs. Register allocation and
jump threading both did not scale well with such a large repetitive sequence of
basic blocks.
So, this change essentially turns those control flow structures into
data. The previous structure looked like:
switch (Opc) {
case TGT::ADD:
// check alias 1
if (MI->getOperandCount() == N && // check num opnds
MI->getOperand(0).isReg() && // check opnd 0
...
MI->getOperand(1).isImm() && // check opnd 1
AsmString = "foo";
break;
}
// check alias 2
if (...)
...
return false;
The new structure looks like:
OpToPatterns: Sorted table of opcodes mapping to pattern indices.
\->
Patterns: List of patterns. Previous table points to subrange of
patterns to match.
\->
Conds: The if conditions above encoded as a kind and 32-bit value.
See MCInstPrinter.cpp for the details of how the new data structures are
interpreted.
Here are some before and after metrics.
Time to compile AArch64InstPrinter.cpp:
0m29.062s vs. 0m2.203s
size of the obj:
3.9M vs. 676K
size of clang.exe:
97M vs. 96M
I have not benchmarked disassembly performance, but typically
disassemblers are bottlenecked on IO and string processing, not alias
matching, so I'm not sure it's interesting enough to be worth doing.
Reviewers: RKSimon, andreadb, xbolva00, craig.topper
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D70650
The xor'ing behaviour is only used for msvc/crt environments, when we're targeting
macho the guard load code doesn't know about the xor in the epilog. Disable xor'ing
when targeting win32-macho to be consistent.
Differential Revision: https://reviews.llvm.org/D71095
D53794 introduced code to perform the FP_TO_UINT expansion via FP_TO_SINT in a way that would never expose floating-point exceptions in the intermediate steps. Unfortunately, I just noticed there is still a way this can happen. As discussed in D53794, the compiler now generates this sequence:
// Sel = Src < 0x8000000000000000
// Val = select Sel, Src, Src - 0x8000000000000000
// Ofs = select Sel, 0, 0x8000000000000000
// Result = fp_to_sint(Val) ^ Ofs
The problem is with the Src - 0x8000000000000000 expression. As I mentioned in the original review, that expression can never overflow or underflow if the original value is in range for FP_TO_UINT. But I missed that we can get an Inexact exception in the case where Src is a very small positive value. (In this case the result of the sub is ignored, but that doesn't help.)
Instead, I'd suggest to use the following sequence:
// Sel = Src < 0x8000000000000000
// FltOfs = select Sel, 0, 0x8000000000000000
// IntOfs = select Sel, 0, 0x8000000000000000
// Result = fp_to_sint(Val - FltOfs) ^ IntOfs
In the case where the value is already in range of FP_TO_SINT, we now simply compute Val - 0, which now definitely cannot trap (unless Val is a NaN in which case we'd want to trap anyway).
In the case where the value is not in range of FP_TO_SINT, but still in range of FP_TO_UINT, the sub can never be inexact, as Val is between 2^(n-1) and (2^n)-1, i.e. always has the 2^(n-1) bit set, and the sub is always simply clearing that bit.
There is a slight complication in the case where Val is a constant, so we know at compile time whether Sel is true or false. In that scenario, the old code would automatically optimize the sub away, while this no longer happens with the new code. Instead, I've added extra code to check for this case and then just fall back to FP_TO_SINT directly. (This seems to catch even slightly more cases.)
Original version of the patch by Ulrich Weigand. X86 changes added by Craig Topper
Differential Revision: https://reviews.llvm.org/D67105
Summary:
musttail calls should not require allocating extra stack for arguments.
Updates to arguments passed in memory should happen in place before the
epilogue.
This bug was mostly a missed optimization, unless inalloca was used and
store to push conversion fired.
If a reserved call frame was used for an inalloca musttail call, the
call setup and teardown instructions would be deleted, and SP
adjustments would be inserted in the prologue and epilogue. You can see
these are removed from several test cases in this change.
In the case where the stack frame was not reserved, i.e. call frame
optimization fires and turns argument stores into pushes, then the
imbalanced call frame setup instructions created for inalloca calls
become a problem. They remain in the instruction stream, resulting in a
call setup that allocates zero bytes (expected for inalloca), and a call
teardown that deallocates the inalloca pack. This deallocation was
unbalanced, leading to subsequent crashes.
Reviewers: hans
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71097
Summary:
Sample profile loader of AutoFDO tries to replay previous inlining using context sensitive profile. The replay only repeats inlining if the call site block is hot. As a result it punts inlining of small functions, some of which can be beneficial for size, and will still be inlined by CSGCC inliner later. The oscillation between sample profile loader's inlining and regular CGSSC inlining cause unnecessary loss of context-sensitive profile. It doesn't have much impact for inline decision itself, but it negatively affects post-inline profile quality as CGSCC inliner have to scale counts which is not as accurate as the original context sensitive profile, and bad post-inline profile can misguide code layout.
This change added regular Inline Cost calculation for sample profile loader, so we can inline small functions upfront under switch -sample-profile-inline-size. In addition -sample-profile-cold-inline-threshold is added so we can tune the separate size threshold - currently the default is chosen to be the same as regular inliner's cold call-site threshold.
Reviewers: wmi, davidxl
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70750
GCC says:
.../llvm/lib/DebugInfo/GSYM/FunctionInfo.cpp:195:12:
error: ‘InfoType’ is not a class, namespace, or enumeration
case InfoType::EndOfList:
^
Presumably, GCC thinks InfoType is a variable here. Work around it by
using the name IT as is done above.
This is a follow-up to D70607 where we made any
extract element on SLM more costly than default. But that is
pessimistic for extract from element 0 because that corresponds
to x86 movd/movq instructions. These generally have >1 cycle
latency, but they are probably implemented as single uop
instructions.
Note that no vectorization tests are affected by this change.
Also, no targets besides SLM are affected because those are
falling through to the default cost of 1 anyway. But this will
become visible/important if we add more specializations via cost
tables.
Differential Revision: https://reviews.llvm.org/D71023
Summary:
Split off of D67120.
Add the profile guided size optimization instrumentation / queries in the code
gen or target passes. This doesn't enable the size optimizations in those passes
yet as they are currently disabled in shouldOptimizeForSize (for non-IR pass
queries).
Reviewers: davidxl
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71072
Current tail duplication integrated in bb layout is designed to increase the fallthrough from a BB's predecessor to its successor, but we have observed cases that duplication doesn't increase fallthrough, or it brings too much size overhead.
To overcome these two issues in function canTailDuplicateUnplacedPreds I add two checks:
make sure there is at least one duplication in current work set.
the number of duplication should not exceed the number of successors.
The modification in hasBetterLayoutPredecessor fixes a bug that potential predecessor must be at the bottom of a chain.
Differential Revision: https://reviews.llvm.org/D64376
SUMMARY:
if the size of Csect is zero, the Csect do not need write any data into sections
for example, the TOC Csect has zero size, it do not need invoke a
Asm.writeSectionData(W.OS, Csect.MCCsect, Layout);
Reviewers: daltenty
Subscribers: rupprecht, seiyai,hiraditya
Differential Revision: https://reviews.llvm.org/D71120
Summary:
The immediate forms of the MVE VQSHL instruction have MC names like
`MVE_VSLIimms8` and `MVE_VSLIimmu32`. Those names are confusing,
because VSLI is a completely different shift instruction with no
semantic relation to VQSHL. But it just happens to be defined
immediately before VQSHL in `ARMInstrMVE.td`, so this looks like a
copy-paste error. Renamed the ids to match the instruction name.
Reviewers: ostannard, dmgreen, MarkMurrayARM, miyuki
Reviewed By: miyuki
Subscribers: kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71114
Summary:
When trying to calculate the offsets for the jump table entries
we fail to take into account the block alignment, which could be
greater than 4 bytes. This led to cases where the jump table
offset was too big to fit in a byte.
Reviewers: t.p.northover, sdesmalen, ostannard
Reviewed By: ostannard
Subscribers: ostannard, kristof.beyls, hiraditya, llvm-commits
Committed on behalf of David Sherwood (david-arm)
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70533
InnerLoopVectorizer's code called during VPlan execution still relies on
original IR's def-use relations to decide which vector code to generate,
limiting VPlan transformations ability to modify def-use relations and still
have ILV generate the vector code.
This commit moves GEP operand queries controlling how GEPs are widened to a
dedicated recipe and extracts GEP widening code to its own ILV method taking
those recorded decisions as arguments. This reduces ingredient def-use usage by
ILV as a step towards full VPlan-based def-use relations.
Differential revision: https://reviews.llvm.org/D69067
One of CodeGenPrepare's optimizations is to duplicate address calculations
into basic blocks, so that as much information as possible can be folded
into memory addressing operands. This is great -- but the dbg.value
variable location intrinsics are not updated in the same way. This can lead
to dbg.values referring to address computations in other blocks that will
never be encoded into the DAG, while duplicate address computations are
performed locally that could be used by the dbg.value. Some of these (such
as non-constant-offset GEPs) can't be salvaged past.
Fix this by, whenever we duplicate an address computation into a block,
looking for dbg.value users of the original memory address in the same
block, and redirecting those to the local computation.
Differential Revision: https://reviews.llvm.org/D58403
Summary:
Adds intrinsics for the following:
* cmphs, cmphi
* cmpge, cmpgt
* cmpeq, cmpne
* cmplt, cmple
* cmplo, cmpls
Includes a minor change to `TLI.getMemValueType` that fixes a crash due to the
scalable flag being dropped.
Reviewers: sdesmalen, efriedma, rengolin, rovka, dancgr, huntergr
Reviewed By: efriedma
Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, psnobl, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70889
This patch implements the following changes:
1) SelectionDAGBuilder::visitConstrainedFPIntrinsic currently treats
each constrained intrinsic like a global barrier (e.g. a function call)
and fully serializes all pending chains. This is actually not required;
it is allowed for constrained intrinsics to be reordered w.r.t one
another or (nonvolatile) memory accesses. The MI-level scheduler already
allows for that flexibility, so it makes sense to allow it at the DAG
level as well.
This patch therefore changes the way chains for constrained intrisincs
are created, and handles them basically like load operations are handled.
This has the effect that constrained intrinsics are no longer serialized
against one another or (nonvolatile) loads. They are still serialized
against stores, but that seems hard to change with the current DAG chain
setup, and it also doesn't seem to be a big problem preventing DAG
2) The OPC_CheckFoldableChainNode check requires that each of the
intermediate nodes in a multi-node pattern match only has a single use.
This check tends to fail if those intermediate nodes are strict operations
as those have a chain output that typically indeed has another use.
However, we don't really need to consider chains here at all, since they
will all be rewritten anyway by UpdateChains later. Other parts of the
matcher therefore already ignore chains, but this hasOneUse check doesn't.
This patch replaces hasOneUse by a custom test that verifies there is no
more than one use of any non-chain output value.
In theory, this change could affect code unrelated to strict FP nodes,
but at least on SystemZ I could not find any single instance of that
happening
3) The SystemZ back-end currently does not allow matching multiply-and-
extend operations (32x32 -> 64bit or 64x64 -> 128bit FP multiply) for
strict FP operations. This was not possible in the past due to the
problems described under 1) and 2) above.
With those issues fixed, it is now possible to fully support those
instructions in strict mode as well, and this patch does so.
Differential Revision: https://reviews.llvm.org/D70913
That refactoring moves NonRelocatableStringpool into common CodeGen folder.
So that NonRelocatableStringpool could be used not only inside dsymutil.
Differential Revision: https://reviews.llvm.org/D71068
In general ValueHandleBase::ValueIsRAUWd shouldn't be called when not
all uses of the value were actually replaced, though, currently
formLCSSAForInstructions calls it when it inserts LCSSA-phis.
Calls of ValueHandleBase::ValueIsRAUWd were added to LCSSA specifically
to update/invalidate SCEV. In the best case these calls duplicate some
of the work already done by SE->forgetValue, though in case when SCEV of
the value is SCEVUnknown, SCEV replaces the underlying value of
SCEVUnknown with the new value (i.e. acts like LCSSA-phi actually fully
replaces the value it is created for), which leads to SCEV being
corrupted because LCSSA-phi rarely dominates all uses of its inputs.
Fixes bug https://bugs.llvm.org/show_bug.cgi?id=44058.
Reviewers: fhahn, efriedma, reames, sanjoy.google
Reviewed By: fhahn
Subscribers: hiraditya, javed.absar, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70593
This is for the case where -gmlt -gsplit-dwarf -fsplit-dwarf-inlining
are used together in some but not all units during LTO (or, in the
reduced case, even without LTO) - ensuring that no split dwarf is used
(because split-dwarf-inlining puts the same data in the .o file, so
there's no need to duplicate it into the .dwo file)
We shouldn't assume that the returned result can be used to get
the other result.
This is prep-work for strict FP where we will also need to pass
the chain result along in more cases.
Summary:
Lookup functions are designed to not fully decode a FunctionInfo, LineTable or InlineInfo, they decode only what is needed into a LookupResult object. This allows lookups to avoid costly memory allocations and avoid parsing large amounts of information one a suitable match is found.
LookupResult objects contain the address that was looked up, the concrete function address range, the name of the concrete function, and a list of source locations. One for each inline function, and one for the concrete function. This allows one address to turn into multiple frames and improves the signal you get when symbolicating addresses in GSYM files.
Reviewers: labath, aprantl
Subscribers: mgorny, hiraditya, llvm-commits, lldb-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70993
Summary:
Add an option to allow the attribute propagation on the index to be
disabled, to allow a workaround for issues (such as that fixed by
D70977).
Also move the setting of the WithAttributePropagation flag on the index
into propagateAttributes(), and remove some old stale code that predated
this flag and cleared the maybe read/write only bits when we need to
disable the propagation (previously only when importing disabled, now
also when the new option disables it).
Reviewers: evgeny777, steven_wu
Subscribers: mehdi_amini, inglorion, hiraditya, dexonsmith, arphaman, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70984
* Context *
During register coalescing, we use rematerialization when coalescing is not
possible. That means we may rematerialize a super register when only a smaller
register is actually used.
E.g.,
0B v1 = ldimm 0xFF
1B v2 = COPY v1.low8bits
2B = v2
=>
0B v1 = ldimm 0xFF
1B v2 = ldimm 0xFF
2B = v2.low8bits
Where xB are the slot indexes.
Here v2 grew from a 8-bit register to a 16-bit register.
When that happens and subregister liveness is enabled, we create subranges for
the newly created value.
E.g., before remat, the live range of v2 looked like:
main range: [1r, 2r)
(Reads v2 is defined at index 1 slot register and used before the slot register
of index 2)
After remat, it should look like:
main range: [1r, 2r)
low 8 bits: [1r, 2r)
high 8 bits: [1r, 1d) <-- dead def
I.e., the unsused lanes of v2 should be marked as dead definition.
* The Problem *
Prior to this patch, the live-ranges from the previous exampel, would have the
full live-range for all subranges:
main range: [1r, 2r)
low 8 bits: [1r, 2r)
high 8 bits: [1r, 2r) <-- too long
* The Fix *
Technically, the code that this patch changes is not wrong:
When we create the subranges for the newly rematerialized value, we create only
one subrange for the whole bit mask.
In other words, at this point v2 live-range looks like this:
main range: [1r, 2r)
low & high: [1r, 2r)
Then, it gets wrong when we call LiveInterval::refineSubRanges on low 8 bits:
main range: [1r, 2r)
low 8 bits: [1r, 2r)
high 8 bits: [1r, 2r) <-- too long
Ideally, we would like LiveInterval::refineSubRanges to be able to do the right
thing and mark the dead lanes as such. However, this is not possible, because by
the time we update / refine the live ranges, the IR hasn't been updated yet,
therefore we actually don't have enough information to do the right thing.
Another option to fix the problem would have been to call
LiveIntervals::shrinkToUses after the IR is updated. This is not desirable as
this may have a noticeable impact on compile time.
Instead, what this patch does is when we create the subranges for the
rematerialized value, we explicitly create one subrange for the lanes that were
used before rematerialization and one for the lanes that were not used. The used
one inherits the live range of the main range and the unused one is just created
empty. The existing rematerialization code then detects that the unused one are
not live and it correctly sets dead def intervals for them.
https://llvm.org/PR41372
Summary:
AutoFDO's sample profile loader processes function in arbitrary source code order, so if I change the order of two functions in source code, the inline decision can change. This also prevented the use of context-sensitive profile to do specialization while inlining. This commit enforces SCC top-down order for sample profile loader. With this change, we can now do specialization, as illustrated by the added test case:
Say if we have A->B->C and D->B->C call path, we want to inline C into B when root inliner is B, but not when root inliner is A or D, this is not possible without enforcing top-down order. E.g. Once C is inlined into B, A and D can only choose to inline (B->C) as a whole or nothing, but what we want is only inline B into A and D, not its recursive callee C. If we process functions in top-down order, this is no longer a problem, which is what this commit is doing.
This change is guarded with a new switch "-sample-profile-top-down-load" for tuning, and it depends on D70653. Eventually, top-down can be the default order for sample profile loader.
Reviewers: wmi, davidxl
Subscribers: hiraditya, llvm-commits, tejohnson
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70655
Summary:
When sample profile loader decides not to inline a previously inlined call-site, we adjust the profile of outlined function simply by scaling up its profile counts by call-site count. This means the context-sensitive profile of that inlined instance will be thrown away. This commit try to keep context-sensitive profile for such cases:
- Instead of scaling outlined function's profile, we now properly merge the FunctionSamples of inlined instance into outlined function, including all recursively inlined profile.
- Instead of adjusting the profile for negative inline decision at the end of the sample profile loader pass, we do the profile merge right after processing each function. This change paired with top-down ordering of annotation/inline-replay (a separate diff) will make sure we recursively merge profile back before the profile is used for annotation and inline replay.
A new switch -sample-profile-merge-inlinee is added to enable the new profile merge for tuning. It should be the default behavior eventually.
Reviewers: wmi, davidxl
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70653
The loclists_table_base was being overwritten for each CU even though
only one loclists contribution is made so everything but the last CU
would have a label that was never defined and fail to assemble.
Summary: Previously we only handled the case where the csect hadn't been set up yet, so we'd hit an assert later on.
Reviewers: jasonliu, DiggerLin, stevewan
Reviewed By: jasonliu
Subscribers: hubert.reinterpretcast, wuzish, nemanjai, hiraditya, kbarton, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71032
Summary:
Emit a value debug intrinsic (with OP_deref) when an alloca address is
passed to a function call after going through a bitcast.
This generates an FP or SP-relative location for the local variable in
the following case:
int x;
use((void *)&x;
Reviewers: aprantl, vsk, pcc
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70752
Summary:
Previously, it was not possible to skip running the localizer pass
conditionally. This patch adds an input function to the pass which
decides if the pass should run on the given MachineFunction or not.
No test case as there is no upstream target needs this functionality.
Reviewers: qcolombet
Reviewed By: qcolombet
Subscribers: rovka, hiraditya, Petar.Avramovic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71038
Summary:
This reverts commit c3b06d0c39.
Reason for revert: Caused miscompiles when inserting assume for undef.
Also adds a test to prevent similar breakage in future.
Fixes PR44154.
Reviewers: rnk, jdoerfert, efriedma, xbolva00
Reviewed By: rnk
Subscribers: thakis, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70933
Summary:
D68408 proposes to greatly improve our negation sinking abilities.
But in current canonicalization, we produce `sub A, zext(B)`,
which we will consider non-canonical and try to sink that negation,
undoing the existing canonicalization.
So unless we explicitly stop producing previous canonicalization,
we will have two conflicting folds, and will end up endlessly looping.
This inverts canonicalization, and adds back the obvious fold
that we'd miss:
* `sub [nsw] Op0, sext/zext (bool Y) -> add [nsw] Op0, zext/sext (bool Y)`
https://rise4fun.com/Alive/xx4
* `sext(bool) + C -> bool ? C - 1 : C`
https://rise4fun.com/Alive/fBl
It is obvious that `@ossfuzz_9880()` / `@lshr_out_of_range()`/`@ashr_out_of_range()`
(oss-fuzz 4871) are no longer folded as much, though those aren't really worrying.
Reviewers: spatel, efriedma, t.p.northover, hfinkel
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71064
Summary:
When MUL is the first operand to SUB, we can't use MLS because the accumulator
should be negated. Emit a NEG of the accumulator and an MLA instead, similar to
what we do for FMUL / FSUB fusing.
Reviewers: dmgreen, SjoerdMeijer, fhahn, Gerolf, mstorsjo, asbirlea
Reviewed By: asbirlea
Subscribers: kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71067
Cullen Rhodes