SwitchInst::getNumCases() returns unsinged, so using uint64_t to count cases
seems unnecessary.
Also fix a missing CHECK in the test case.
llvm-svn: 224393
SelectionDAG::isConsecutiveLoad() was not detecting consecutive loads
when the first load was offset from a base address.
This patch recognizes that pattern and subtracts the offset before comparing
the second load to see if it is consecutive.
The codegen change in the new test case improves from:
vmovsd 32(%rdi), %xmm0
vmovsd 48(%rdi), %xmm1
vmovhpd 56(%rdi), %xmm1, %xmm1
vmovhpd 40(%rdi), %xmm0, %xmm0
vinsertf128 $1, %xmm1, %ymm0, %ymm0
To:
vmovups 32(%rdi), %ymm0
An existing test case is also improved from:
vmovsd (%rdi), %xmm0
vmovsd 16(%rdi), %xmm1
vmovsd 24(%rdi), %xmm2
vunpcklpd %xmm2, %xmm0, %xmm0 ## xmm0 = xmm0[0],xmm2[0]
vmovhpd 8(%rdi), %xmm1, %xmm3
To:
vmovsd (%rdi), %xmm0
vmovsd 16(%rdi), %xmm1
vmovhpd 24(%rdi), %xmm0, %xmm0
vmovhpd 8(%rdi), %xmm1, %xmm1
This patch fixes PR21771 ( http://llvm.org/bugs/show_bug.cgi?id=21771 ).
Differential Revision: http://reviews.llvm.org/D6642
llvm-svn: 224379
This patch extends the optimization in CodeGenPrepare that moves a sign/zero
extension near a load when the target can combine them. The optimization may
promote any operations between the extension and the load to make that possible.
Although this optimization may be beneficial for all targets, in particular
AArch64, this is enabled for X86 only as I have not benchmarked it for other
targets yet.
** Context **
Most targets feature extended loads, i.e., loads that perform a zero or sign
extension for free. In that context it is interesting to expose such pattern in
CodeGenPrepare so that the instruction selection pass can form such loads.
Sometimes, this pattern is blocked because of instructions between the load and
the extension. When those instructions are promotable to the extended type, we
can expose this pattern.
** Motivating Example **
Let us consider an example:
define void @foo(i8* %addr1, i32* %addr2, i8 %a, i32 %b) {
%ld = load i8* %addr1
%zextld = zext i8 %ld to i32
%ld2 = load i32* %addr2
%add = add nsw i32 %ld2, %zextld
%sextadd = sext i32 %add to i64
%zexta = zext i8 %a to i32
%addza = add nsw i32 %zexta, %zextld
%sextaddza = sext i32 %addza to i64
%addb = add nsw i32 %b, %zextld
%sextaddb = sext i32 %addb to i64
call void @dummy(i64 %sextadd, i64 %sextaddza, i64 %sextaddb)
ret void
}
As it is, this IR generates the following assembly on x86_64:
[...]
movzbl (%rdi), %eax # zero-extended load
movl (%rsi), %es # plain load
addl %eax, %esi # 32-bit add
movslq %esi, %rdi # sign extend the result of add
movzbl %dl, %edx # zero extend the first argument
addl %eax, %edx # 32-bit add
movslq %edx, %rsi # sign extend the result of add
addl %eax, %ecx # 32-bit add
movslq %ecx, %rdx # sign extend the result of add
[...]
The throughput of this sequence is 7.45 cycles on Ivy Bridge according to IACA.
Now, by promoting the additions to form more extended loads we would generate:
[...]
movzbl (%rdi), %eax # zero-extended load
movslq (%rsi), %rdi # sign-extended load
addq %rax, %rdi # 64-bit add
movzbl %dl, %esi # zero extend the first argument
addq %rax, %rsi # 64-bit add
movslq %ecx, %rdx # sign extend the second argument
addq %rax, %rdx # 64-bit add
[...]
The throughput of this sequence is 6.15 cycles on Ivy Bridge according to IACA.
This kind of sequences happen a lot on code using 32-bit indexes on 64-bit
architectures.
Note: The throughput numbers are similar on Sandy Bridge and Haswell.
** Proposed Solution **
To avoid the penalty of all these sign/zero extensions, we merge them in the
loads at the beginning of the chain of computation by promoting all the chain of
computation on the extended type. The promotion is done if and only if we do not
introduce new extensions, i.e., if we do not degrade the code quality.
To achieve this, we extend the existing “move ext to load” optimization with the
promotion mechanism introduced to match larger patterns for addressing mode
(r200947).
The idea of this extension is to perform the following transformation:
ext(promotableInst1(...(promotableInstN(load))))
=>
promotedInst1(...(promotedInstN(ext(load))))
The promotion mechanism in that optimization is enabled by a new TargetLowering
switch, which is off by default. In other words, by default, the optimization
performs the “move ext to load” optimization as it was before this patch.
** Performance **
Configuration: x86_64: Ivy Bridge fixed at 2900MHz running OS X 10.10.
Tested Optimization Levels: O3/Os
Tests: llvm-testsuite + externals.
Results:
- No regression beside noise.
- Improvements:
CINT2006/473.astar: ~2%
Benchmarks/PAQ8p: ~2%
Misc/perlin: ~3%
The results are consistent for both O3 and Os.
<rdar://problem/18310086>
llvm-svn: 224351
This changes subrange calculation to calculate subranges sequentially
instead of in parallel. The code is easier to understand that way and
addresses the code review issues raised about LiveOutData being
hard to understand/needing more comments by removing them :)
llvm-svn: 224313
Debug info marks the first instruction without the FrameSetup flag
as being the end of the function prologue. Any CFI instructions in the
middle of the function prologue would cause debug info to end the prologue
too early and worse, attach the line number of the CFI instruction, which
incidentally is often 0.
llvm-svn: 224294
This changes subrange calculation to calculate subranges sequentially
instead of in parallel. The code is easier to understand that way and
addresses the code review issues raised about LiveOutData being
hard to understand/needing more comments by removing them :)
llvm-svn: 224272
Add in definedness checks for shift operators, null checks when
pointers are assumed by the code to be non-null, and explicit
unreachables.
llvm-svn: 224255
options.
This commit changes the command line arguments (PassInfo::PassArgument) of two
passes, MachineFunctionPrinter and MachineScheduler, to avoid collisions with
command line options that have the same argument strings.
This bug manifests when the PassList construct (defined in opt.cpp) is used
in a tool that links with codegen passes. To reproduce the bug, paste the
following lines into llc.cpp and run llc.
#include "llvm/IR/LegacyPassNameParser.h"
static llvm:🆑:list<const llvm::PassInfo*, bool, llvm::PassNameParser>
PassList(llvm:🆑:desc("Optimizations available:"));
rdar://problem/19212448
llvm-svn: 224186
This reapplies r224118 with a fix for test 'misched-code-difference-with-debug.ll'.
That test was failing on some buildbots because it was x86 specific but it was
missing a target triple.
Added an explicit triple to test misched-code-difference-with-debug.ll.
llvm-svn: 224126
This patch fixes the issue reported as PR21807. There was a minor difference
in the generated code depending on the -g flag.
The cause was that with -g the machine scheduler used a different
scheduling strategy. This decision was based on the number of instructions
in a schedule region and included debug instructions in that count.
This patch fixes the issue in MISched and provides a test.
Patch by Russell Gallop!
llvm-svn: 224118
DW_OP_const <const> doesn't describe a constant value, but a value at a constant address.
The proper way to describe a constant value is DW_OP_constu <const>, DW_OP_stack_value.
Added DW_OP_stack_value to the stack.
Marked incorrect-variable-debugloc1.ll to xfail for PowerPC64, while the the failure (PR21881)
is being investigated.
llvm-svn: 224098
Updating comments to reflect the current state of the world after my recent changes to ownership structure and generally better describe what a GCStrategy is and how it works.
llvm-svn: 224086
Add an option to disable optimization to shrink truncated larger type
loads to smaller type loads. On SI this prevents using scalar load
instructions in some cases, since there are no scalar extloads.
llvm-svn: 224084
Since `MachineInstr` is required to have a trivial destructor, it cannot
remove itself from `LeakDetection`. Remove the calls.
As it happens, this requirement is because `MachineFunction` allocates
all `MachineInstr`s in a custom allocator; when the `MachineFunction` is
destroyed they're dropped of the edge. There's no benefit to detecting
leaks.
llvm-svn: 224061
Previously print+verify passes were added in a very unsystematic way, which is
annoying when debugging as you miss intermediate steps and allows bugs to stay
unnotice when no verification is performed.
To make this change practical I added the possibility to explicitely disable
verification. I used this option on all places where no verification was
performed previously (because alot of places actually don't pass the
MachineVerifier).
In the long term these problems should be fixed properly and verification
enabled after each pass. I'll enable some more verification in subsequent
commits.
This is the 2nd attempt at this after realizing that PassManager::add() may
actually delete the pass.
llvm-svn: 224059
Previously print+verify passes were added in a very unsystematic way, which is
annoying when debugging as you miss intermediate steps and allows bugs to stay
unnotice when no verification is performed.
To make this change practical I added the possibility to explicitely disable
verification. I used this option on all places where no verification was
performed previously (because alot of places actually don't pass the
MachineVerifier).
In the long term these problems should be fixed properly and verification
enabled after each pass. I'll enable some more verification in subsequent
commits.
llvm-svn: 224042
Properly determine whether or not a phi was added by splitting.
Check against the current VNInfo of OrigLI instead of against the
OrigVNI argument.
Patch provided by Jonas Paulsson. Reviewed by Quentin Colombet.
llvm-svn: 224009
The test is failing for llvm-ppc64 because for this platform the location list is not being generated at all (most likely because of the bug in PPC code optimization or generation). I will file a bug agains PPC compiler, but meanwhile, until PPC bug is fixed, I will have to revert my change.
llvm-svn: 224000
This change moves the ownership and access of GCFunctionInfo (the object which describes the safepoints associated with a safepoint under GCRoot) to GCModuleInfo. Previously, this was owned by GCStrategy which was in turned owned by GCModuleInfo. This made GCStrategy module specific which is 'surprising' given it's name and other purposes.
There's a few more changes needed, but we're getting towards the point we can reuse GCStrategy for gc.statepoint as well.
p.s. The style of this code ends up being a mess. I was trying to move code around without otherwise changing much. Once I get the ownership structure rearranged, I will go through and fixup spacing, naming, comments etc.
Differential Revision: http://reviews.llvm.org/D6587
llvm-svn: 223994
DW_OP_const <const> doesn't describe a constant value, but a value at a constant address.
The proper way to describe a constant value is DW_OP_constu <const>, DW_OP_stack_value.
Added DW_OP_stack_value to the stack.
-This line, and those below, will be ignored--
M lib/CodeGen/AsmPrinter/DwarfDebug.cpp
A test/DebugInfo/incorrect-variable-debugloc1.ll
llvm-svn: 223981
We can't mark partially undefined registers, so we have to allow reading
a register in the machine verifier if just parts of a register are
defined.
llvm-svn: 223896
In the subregister liveness tracking case we do not create implicit
reads on partial register writes anymore, still we need to produce a new
SSA value for partial writes so the live segment has to end.
llvm-svn: 223895
Adding the implicit defs/uses to the superregisters is semantically questionable
but was not dangerous before as the register allocator never assigned the same
register to two overlapping LiveIntervals even when the actually live
subregisters do not overlap. With subregister liveness tracking enabled this
does actually happen and leads to subsequent bugs if we don't stop adding
the superregister defs/uses.
llvm-svn: 223892
In the current implementation, GCStrategy is a part of the ownership structure for the gc metadata which describes a Module. It also contains a reference to the module in question. As a result, GCStrategy instances are essentially Module specific.
I plan to transition away from this design. Instead, a GCStrategy will be owned by the LLVMContext. It will be a lightweight policy object which contains no information about the Modules or Functions involved, but can be easily reached given a Function.
The first step in this transition is to remove the direct Module reference from GCStrategy. This also requires removing the single user of this reference, the GCMetadataPrinter hierarchy. In theory, this will allow the lifetime of the printers to be scoped to the LLVMContext as well, but in practice, I'm not actually changing that. (Yet?)
An alternate design would have been to move the direct Module reference into the GCMetadataPrinter and change the keying of the owning maps to explicitly key off both GCStrategy and Module. I'm open to doing it that way instead, but didn't see much value in preserving the per Module association for GCMetadataPrinters.
The next change in this sequence will be to start unwinding the intertwined ownership between GCStrategy, GCModuleInfo, and GCFunctionInfo.
Differential Revision: http://reviews.llvm.org/D6566
llvm-svn: 223859
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
Rewrite the pattern match code to work also with Values instead with
Instructions only. Also remove the no longer need matcher (m_Instruction).
llvm-svn: 223797
This optimization transforms code like:
bb1:
%0 = icmp ne i32 %a, 0
%1 = icmp ne i32 %b, 0
%or.cond = or i1 %0, %1
br i1 %or.cond, label %TrueBB, label %FalseBB
into a multiple branch instructions like:
bb1:
%0 = icmp ne i32 %a, 0
br i1 %0, label %TrueBB, label %bb2
bb2:
%1 = icmp ne i32 %b, 0
br i1 %1, label %TrueBB, label %FalseBB
This optimization is already performed by SelectionDAG, but not by FastISel.
FastISel cannot perform this optimization, because it cannot generate new
MachineBasicBlocks.
Performing this optimization at CodeGenPrepare time makes it available to both -
SelectionDAG and FastISel - and the implementation in SelectiuonDAG could be
removed. There are currenty a few differences in codegen for X86 and PPC, so
this commmit only enables it for FastISel.
Reviewed by Jim Grosbach
This fixes rdar://problem/19034919.
llvm-svn: 223786
The aggressive anti-dep breaker, used by the PowerPC backend during post-RA
scheduling (but is available to all targets), did not handle early-clobber MI
operands (at all). When constructing the list of available registers for the
replacement of some def operand, check the using instructions, and remove
registers assigned to early-clobbered defs from the set.
Fixes PR21452.
llvm-svn: 223727
This fixes an issue with ScheduleDAGInstrs::buildSchedGraph
where stores without an underlying object would not be added
as a predecessor to the current BarrierChain.
llvm-svn: 223717
Introduce the ``llvm.instrprof_increment`` intrinsic and the
``-instrprof`` pass. These provide the infrastructure for writing
counters for profiling, as in clang's ``-fprofile-instr-generate``.
The implementation of the instrprof pass is ported directly out of the
CodeGenPGO classes in clang, and with the followup in clang that rips
that code out to use these new intrinsics this ends up being NFC.
Doing the instrumentation this way opens some doors in terms of
improving the counter performance. For example, this will make it
simple to experiment with alternate lowering strategies, and allows us
to try handling profiling specially in some optimizations if we want
to.
Finally, this drastically simplifies the frontend and puts all of the
lowering logic in one place.
llvm-svn: 223672
This can significantly reduce the size of the switch, allowing for more
efficient lowering.
I also worked with the idea of exploiting unreachable defaults by
omitting the range check for jump tables, but always ended up with a
non-neglible binary size increase. It might be worth looking into some more.
SimplifyCFG currently does this transformation, but I'm working towards changing
that so we can optimize harder based on unreachable defaults.
Differential Revision: http://reviews.llvm.org/D6510
llvm-svn: 223566
Reverting this because, while it fixes the problem in the reduced test case, it
does not fix the problem in the full test case from the bug report.
llvm-svn: 223442
The scheduling dependency graph is built bottom-up within each scheduling
region, and ScheduleDAGInstrs::addPhysRegDeps is called to add output/anti
dependencies, based on physical registers, to the SUs for instructions
based on those that come before them.
In the test case, we start before post-RA scheduling with a block that looks
like this:
...
INLINEASM <...
andc $0,$0,$2
stdcx. $0,0,$3
bne- 1b
> [sideeffect] [mayload] [maystore] [attdialect], $0:[regdef-ec:G8RC], %X6<earlyclobber,def,dead>, $1:[mem], %X3<kill>, $2:[reguse:G8RC], %X5<kill>, $3:[reguse:G8RC], %X3, $4:[mem], %X3, $5:[clobber], %CC<earlyclobber,imp-def,dead>, <<badref>>
...
%X4<def,dead> = ANDIo8 %X4<kill>, 1, %CR0<imp-def,dead>, %CR0GT<imp-def>
...
%R29<def> = ISEL %R3<undef>, %R4<kill>, %CR0GT<kill>
where it is relevant that %CC is an alias to %CR0, and that %CR0GT is a
subregister of %CR0. However, for post-RA scheduling, no dependency was added
to prevent the INLINEASM from being scheduled in between the ANDIo8 and the
ISEL (which communicate via the %CR0GT register).
In ScheduleDAGInstrs::addPhysRegDeps, when called for the %CC operand, we'd
iterate over all of its aliases (which include %CC itself and also %CR0), and
look for previously-encountered defs of those registers. We'd find the ANDIo8,
but decide not to add a dependency between the INLINEASM and the ANDIo8 because
both the INLINEASM's def of %CC is dead, and also the ANDIo8 def of %CR0 is
dead. This ignores, however, that ANDIo8 has a non-dead def of %CR0GT, a
subregister of %CR0, and thus a dependency still must exist.
To fix this problem, when calling registerDefIsDead on the SU with the def, we
also check all subregisters for possible non-dead defs, and add the dependency
if any are found.
Fixes PR21742.
llvm-svn: 223440
no DWARF register number mapping, or if the register was a virtual
register that was never materialized. Previously, we would just emit a
bogus location, after this patch we don't emit a location at all by
doing an early exit.
After my bugfix in r223401 today, this doesn't actually happen on any
target that I tested this with, but it's still preferable to make the
possibility of a failure explicit.
llvm-svn: 223428
According to a previous FIXME comment we now not only look at MBB
successors, but also handle code sinking past them:
x = computation
if () {} else {}
use x
The instruction could be sunk over the whole diamond for the
if/then/else (or loop, etc), allowing it to be sunk into other blocks
after that.
Modified test added in r204522, due to one spill less present.
Minor fixes in comments.
Patch provided by Jonas Paulsson. Reviewed by Hal Finkel.
llvm-svn: 223350
Added instcombine optimizations for BSWAP with AND/OR/XOR ops:
OP( BSWAP(x), BSWAP(y) ) -> BSWAP( OP(x, y) )
OP( BSWAP(x), CONSTANT ) -> BSWAP( OP(x, BSWAP(CONSTANT) ) )
Since its just a one liner, I've also added BSWAP to the DAGCombiner equivalent as well:
fold (OP (bswap x), (bswap y)) -> (bswap (OP x, y))
Refactored bswap-fold tests to use FileCheck instead of just checking that the bswaps had gone.
Differential Revision: http://reviews.llvm.org/D6407
llvm-svn: 223349
I'm recommiting the codegen part of the patch.
The vectorizer part will be send to review again.
Masked Vector Load and Store Intrinsics.
Introduced new target-independent intrinsics in order to support masked vector loads and stores. The loop vectorizer optimizes loops containing conditional memory accesses by generating these intrinsics for existing targets AVX2 and AVX-512. The vectorizer asks the target about availability of masked vector loads and stores.
Added SDNodes for masked operations and lowering patterns for X86 code generator.
Examples:
<16 x i32> @llvm.masked.load.v16i32(i8* %addr, <16 x i32> %passthru, i32 4 /* align */, <16 x i1> %mask)
declare void @llvm.masked.store.v8f64(i8* %addr, <8 x double> %value, i32 4, <8 x i1> %mask)
Scalarizer for other targets (not AVX2/AVX-512) will be done in a separate patch.
http://reviews.llvm.org/D6191
llvm-svn: 223348
Use the MCAsmInfo instead of the DataLayout, and allow
specifying a custom prefix for labels specifically. HSAIL
requires that labels begin with @, but global symbols with &.
llvm-svn: 223323
Prior to this commit, physical registers defined implicitly were considered free
right after their definition, i.e.. like dead definitions. Therefore, their uses
had to immediately follow their definitions, otherwise the related register may
be reused to allocate a virtual register.
This commit fixes this assumption by keeping implicit definitions alive until
they are actually used. The downside is that if the implicit definition was dead
(and not marked at such), we block an otherwise available register. This is
however conservatively correct and makes the fast register allocator much more
robust in particular regarding the scheduling of the instructions.
Fixes PR21700.
llvm-svn: 223317
Patch by Ben Gamari!
This redefines the `prefix` attribute introduced previously and
introduces a `prologue` attribute. There are a two primary usecases
that these attributes aim to serve,
1. Function prologue sigils
2. Function hot-patching: Enable the user to insert `nop` operations
at the beginning of the function which can later be safely replaced
with a call to some instrumentation facility
3. Runtime metadata: Allow a compiler to insert data for use by the
runtime during execution. GHC is one example of a compiler that
needs this functionality for its tables-next-to-code functionality.
Previously `prefix` served cases (1) and (2) quite well by allowing the user
to introduce arbitrary data at the entrypoint but before the function
body. Case (3), however, was poorly handled by this approach as it
required that prefix data was valid executable code.
Here we redefine the notion of prefix data to instead be data which
occurs immediately before the function entrypoint (i.e. the symbol
address). Since prefix data now occurs before the function entrypoint,
there is no need for the data to be valid code.
The previous notion of prefix data now goes under the name "prologue
data" to emphasize its duality with the function epilogue.
The intention here is to handle cases (1) and (2) with prologue data and
case (3) with prefix data.
References
----------
This idea arose out of discussions[1] with Reid Kleckner in response to a
proposal to introduce the notion of symbol offsets to enable handling of
case (3).
[1] http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-May/073235.html
Test Plan: testsuite
Differential Revision: http://reviews.llvm.org/D6454
llvm-svn: 223189
We've long supported readcyclecounter on PPC64, but it is easier there (the
read of the 64-bit time-base register can be accomplished via a single
instruction). This now provides an implementation for PPC32 as well. On PPC32,
the time-base register is still 64 bits, but can only be read 32 bits at a time
via two separate SPRs. The ISA manual explains how to do this properly (it
involves re-reading the upper bits and looping if the counter has wrapped while
being read).
This requires PPC to implement a custom integer splitting legalization for the
READCYCLECOUNTER node, turning it into a target-specific SDAG node, which then
gets turned into a pseudo-instruction, which is then expanded to the necessary
sequence (which has three SPR reads, the comparison and the branch).
Thanks to Paul Hargrove for pointing out to me that this was still unimplemented.
llvm-svn: 223161
This is the third patch in a small series. It contains the CodeGen support for lowering the gc.statepoint intrinsic sequences (223078) to the STATEPOINT pseudo machine instruction (223085). The change also includes the set of helper routines and classes for working with gc.statepoints, gc.relocates, and gc.results since the lowering code uses them.
With this change, gc.statepoints should be functionally complete. The documentation will follow in the fourth change, and there will likely be some cleanup changes, but interested parties can start experimenting now.
I'm not particularly happy with the amount of code or complexity involved with the lowering step, but at least it's fairly well isolated. The statepoint lowering code is split into it's own files and anyone not working on the statepoint support itself should be able to ignore it.
During the lowering process, we currently spill aggressively to stack. This is not entirely ideal (and we have plans to do better), but it's functional, relatively straight forward, and matches closely the implementations of the patchpoint intrinsics. Most of the complexity comes from trying to keep relocated copies of values in the same stack slots across statepoints. Doing so avoids the insertion of pointless load and store instructions to reshuffle the stack. The current implementation isn't as effective as I'd like, but it is functional and 'good enough' for many common use cases.
In the long term, I'd like to figure out how to integrate the statepoint lowering with the register allocator. In principal, we shouldn't need to eagerly spill at all. The register allocator should do any spilling required and the statepoint should simply record that fact. Depending on how challenging that turns out to be, we may invest in a smarter global stack slot assignment mechanism as a stop gap measure.
Reviewed by: atrick, ributzka
llvm-svn: 223137
Go through implicit defs of CSMI and MI, and clear the kill flags on
their uses in all the instructions between CSMI and MI.
We might have made some of the kill flags redundant, consider:
subs ... %NZCV<imp-def> <- CSMI
csinc ... %NZCV<imp-use,kill> <- this kill flag isn't valid anymore
subs ... %NZCV<imp-def> <- MI, to be eliminated
csinc ... %NZCV<imp-use,kill>
Since we eliminated MI, and reused a register imp-def'd by CSMI
(here %NZCV), that register, if it was killed before MI, should have
that kill flag removed, because it's lifetime was extended.
Also, add an exhaustive testcase for the motivating example.
Reviewed by: Juergen Ributzka <juergen@apple.com>
llvm-svn: 223133
This is the second patch in a small series. This patch contains the MachineInstruction and x86-64 backend pieces required to lower Statepoints. It does not include the code to actually generate the STATEPOINT machine instruction and as a result, the entire patch is currently dead code. I will be submitting the SelectionDAG parts within the next 24-48 hours. Since those pieces are by far the most complicated, I wanted to minimize the size of that patch. That patch will include the tests which exercise the functionality in this patch. The entire series can be seen as one combined whole in http://reviews.llvm.org/D5683.
The STATEPOINT psuedo node is generated after all gc values are explicitly spilled to stack slots. The purpose of this node is to wrap an actual call instruction while recording the spill locations of the meta arguments used for garbage collection and other purposes. The STATEPOINT is modeled as modifing all of those locations to prevent backend optimizations from forwarding the value from before the STATEPOINT to after the STATEPOINT. (Doing so would break relocation semantics for collectors which wish to relocate roots.)
The implementation of STATEPOINT is closely modeled on PATCHPOINT. Eventually, much of the code in this patch will be removed. The long term plan is to merge the functionality provided by statepoints and patchpoints. Merging their implementations in the backend is likely to be a good starting point.
Reviewed by: atrick, ributzka
llvm-svn: 223085
The MachineVerifier used to check that there was always exactly one
unconditional branch to a non-landingpad (normal) successor.
If that normal successor to an invoke BB is unreachable, it seems
reasonable to only have one successor, the landing pad.
On targets other than AArch64 (and on AArch64 with a different testcase),
the branch folder turns the branch to the landing pad into a fallthrough.
The MachineVerifier, which relies on AnalyzeBranch, is unable to check
the condition, and doesn't complain. However, it does in this specific
testcase, where the branch to the landing pad remained.
Make the MachineVerifier accept it.
llvm-svn: 223059
This can significantly reduce the size of the switch, allowing for more
efficient lowering.
I also worked with the idea of exploiting unreachable defaults by
omitting the range check for jump tables, but always ended up with a
non-neglible binary size increase. It might be worth looking into some more.
llvm-svn: 223049
This commit fixes a bug in stack protector pass where edge weights were not set
when new basic blocks were added to lists of successor basic blocks.
Differential Revision: http://reviews.llvm.org/D5766
llvm-svn: 222987
This reverts commit r222632 (and follow-up r222636), which caused a host
of LNT failures on an internal bot. I'll respond to the commit on the
list with a reproduction of one of the failures.
Conflicts:
lib/Target/X86/X86TargetTransformInfo.cpp
llvm-svn: 222936
Introduced new target-independent intrinsics in order to support masked vector loads and stores. The loop vectorizer optimizes loops containing conditional memory accesses by generating these intrinsics for existing targets AVX2 and AVX-512. The vectorizer asks the target about availability of masked vector loads and stores.
Added SDNodes for masked operations and lowering patterns for X86 code generator.
Examples:
<16 x i32> @llvm.masked.load.v16i32(i8* %addr, <16 x i32> %passthru, i32 4 /* align */, <16 x i1> %mask)
declare void @llvm.masked.store.v8f64(i8* %addr, <8 x double> %value, i32 4, <8 x i1> %mask)
Scalarizer for other targets (not AVX2/AVX-512) will be done in a separate patch.
http://reviews.llvm.org/D6191
llvm-svn: 222632
Before this patch, the DAGCombiner only tried to convert build_vector dag nodes
into shuffles if all operands were either extract_vector_elt or undef.
This patch improves that logic and teaches the DAGCombiner how to deal with
build_vector dag nodes where one or more operands are zero. A build_vector
dag node with some zero operands is turned into a shuffle only if the resulting
shuffle mask is legal for the target.
llvm-svn: 222536
This patch simplifies the logic that combines a pair of shuffle nodes into
a single shuffle if there is a legal mask. Also added comments to better
describe the algorithm. No functional change intended.
llvm-svn: 222522
E.g., ( a / D; b / D ) -> ( recip = 1.0 / D; a * recip; b * recip)
A hook is added to allow the target to control whether it needs to do such combine.
Reviewed in http://reviews.llvm.org/D6334
llvm-svn: 222510
- Show "Considering..." message after flipping so you actually see the final
destination vreg as destination.
- Add a message on final join, so you can grep for "Success" messages to obtain
a list of which register got merged with which.
llvm-svn: 222382
This patch builds on http://reviews.llvm.org/D5598 to perform byte rotation shuffles (lowerVectorShuffleAsByteRotate) on pre-SSSE3 (palignr) targets - pre-SSSE3 is only enabled on i8 and i16 vector targets where it is a more definite performance gain.
I've also added a separate byte shift shuffle (lowerVectorShuffleAsByteShift) that makes use of the ability of the SLLDQ/SRLDQ instructions to implicitly shift in zero bytes to avoid the need to create a zero register if we had used palignr.
Differential Revision: http://reviews.llvm.org/D5699
llvm-svn: 222340
This is to be consistent with StringSet and ultimately with the standard
library's associative container insert function.
This lead to updating SmallSet::insert to return pair<iterator, bool>,
and then to update SmallPtrSet::insert to return pair<iterator, bool>,
and then to update all the existing users of those functions...
llvm-svn: 222334
Having two ways to do this doesn't seem terribly helpful and
consistently using the insert version (which we already has) seems like
it'll make the code easier to understand to anyone working with standard
data structures. (I also updated many references to the Entry's
key and value to use first() and second instead of getKey{Data,Length,}
and get/setValue - for similar consistency)
Also removes the GetOrCreateValue functions so there's less surface area
to StringMap to fix/improve/change/accommodate move semantics, etc.
llvm-svn: 222319
Usually global variables are in a retain list and instanciated before
any call to constructImportedEntityDIE is made. This isn't true for
forward declarations though.
The testcase for this change is generated by a clang patched to emit
such forward declarations (patch at http://reviews.llvm.org/D6173
which will land soon). The updated testcase tests more than just
global variables, it now tests every type of 'using' clause we
support.
llvm-svn: 222217
use DIScopeRef.
A paired commit at clang will follow to show cases where we will use an
identifer for the context of a global variable.
rdar://18958417
llvm-svn: 222195
Some optimisations in DAGCombiner cause miscompilations for targets that use
TargetLowering::UndefinedBooleanContent, because they assume that the results
of a SELECT_CC node are boolean values, and can be safely ANDed, ORed and
XORed. These optimisations are only valid for targets that use
ZeroOrOneBooleanContent or ZeroOrNegativeOneBooleanContent.
This is a follow-up to D6210/r221693.
llvm-svn: 222123
Indices into the table are stored in each MCRegisterClass instead of a pointer. A new method, getRegClassName, is added to MCRegisterInfo and TargetRegisterInfo to lookup the string in the table.
llvm-svn: 222118
This patch teaches the DAGCombiner how to combine shuffles according to rules:
shuffle(shuffle(A, Undef, M0), B, M1) -> shuffle(B, A, M2)
shuffle(shuffle(A, B, M0), B, M1) -> shuffle(B, A, M2)
shuffle(shuffle(A, B, M0), A, M1) -> shuffle(B, A, M2)
llvm-svn: 222090
Summary:
The current "WinEH" exception handling type is more about Itanium-style
LSDA tables layered on top of the Windows native unwind info format
instead of .eh_frame tables or EHABI unwind info. Use the name
"ItaniumWinEH" to better reflect the hybrid nature of the design.
Also rename isExceptionHandlingDWARF to usesItaniumLSDAForExceptions,
since the LSDA is part of the Itanium C++ ABI document, and not the
DWARF standard.
Reviewers: echristo
Subscribers: llvm-commits, compnerd
Differential Revision: http://reviews.llvm.org/D6279
llvm-svn: 222062
Windows defines NULL to 0, which when used as an argument to a variadic
function, is not a null pointer constant. As a result, Clang's
-Wsentinel fires on this code. Using '0' would be wrong on most 64-bit
platforms, but both MSVC and Clang make it work on Windows. Sidestep the
issue with nullptr.
llvm-svn: 221940
Prior to this patch the TypePromotionHelper was promoting only sign extensions.
Supporting zero extensions changes:
- How constants are extended.
- How sign extensions, zero extensions, and truncate are composed together.
- How the type of the extended operation is recorded. Now we need to know the
kind of the extension as well as its type.
Each change is fairly small, unlike the diff.
Most of the diff are comments/variable renaming to say "extension" instead of
"sign extension".
The performance improvements on the test suite are within the noise.
Related to <rdar://problem/18310086>.
llvm-svn: 221851
The DIE offset in the accel tables is an offset relative to the start
of the debug_info section, but we were encoding the offset to the
start of the containing CU.
llvm-svn: 221837
r221820 fixed a problem (PR21548) where an iPTR was used in TLI legality checks,
which isn't valid and resulted in a failed assertion.
The solution was to lower pointer types into the correct target's VT, by
using TL::getValueType instead of EVT::getEVT.
This commit changes 3 other uses of EVT::getEVT, but without any tests:
- One of these non-lowered EVTs is passed to allowsMisalignedMemoryAccesses,
which goes into target's TL implementation and doesn't cause any problem (yet.)
- Two others are passed to TLI.isOperationLegalOrCustom:
- one only looks at extensions, so doesn't concern pointers.
- one only looks at binary operators, so also isn't a problem.
The latter might some day be exposed to pointers and cause the same assert as
the original PR, because there's a comment hinting at also supporting cast ops.
For consistency, update all of them and be done with it.
llvm-svn: 221827
Instead, we're going to separate metadata from the Value hierarchy. See
PR21532.
This reverts commit r221375.
This reverts commit r221373.
This reverts commit r221359.
This reverts commit r221167.
This reverts commit r221027.
This reverts commit r221024.
This reverts commit r221023.
This reverts commit r220995.
This reverts commit r220994.
llvm-svn: 221711
What would happen before that commit is that the SDDbgValues associated with
a deallocated SDNode would be marked Invalidated, but SDDbgInfo would keep
a map entry keyed by the SDNode pointer pointing to this list of invalidated
SDDbgNodes. As the memory gets reused, the list might get wrongly associated
with another new SDNode. As the SDDbgValues are cloned when they are transfered,
this can lead to an exponential number of SDDbgValues being produced during
DAGCombine like in http://llvm.org/bugs/show_bug.cgi?id=20893
Note that the previous behavior wasn't really buggy as the invalidation made
sure that the SDDbgValues won't be used. This commit can be considered a
memory optimization and as such is really hard to validate in a unit-test.
llvm-svn: 221709
This commit adds a new pass that can inject checks before indirect calls to
make sure that these calls target known locations. It supports three types of
checks and, at compile time, it can take the name of a custom function to call
when an indirect call check fails. The default failure function ignores the
error and continues.
This pass incidentally moves the function JumpInstrTables::transformType from
private to public and makes it static (with a new argument that specifies the
table type to use); this is so that the CFI code can transform function types
at call sites to determine which jump-instruction table to use for the check at
that site.
Also, this removes support for jumptables in ARM, pending further performance
analysis and discussion.
Review: http://reviews.llvm.org/D4167
llvm-svn: 221708
LLVM replaces the SelectionDAG pattern (xor (set_cc cc x y) 1) with
(set_cc !cc x y), which is only correct when the xor has type i1.
Instead, we should check that the constant operand to the xor is all
ones.
llvm-svn: 221693
We already use the llvm namespace. Remove the unnecessary prefix. Use the
StringRef::equals method to compare with C strings rather than instantiating
std::strings.
Addresses late review comments from David Majnemer.
llvm-svn: 221564
This introduces the symbol rewriter. This is an IR->IR transformation that is
implemented as a CodeGenPrepare pass. This allows for the transparent
adjustment of the symbols during compilation.
It provides a clean, simple, elegant solution for symbol inter-positioning. This
technique is often used, such as in the various sanitizers and performance
analysis.
The control of this is via a custom YAML syntax map file that indicates source
to destination mapping, so as to avoid having the compiler to know the exact
details of the source to destination transformations.
llvm-svn: 221548
On 32 bit windows we use label differences and .set does not suppress
rolocations, a combination that was not used before r220256.
This fixes PR21497.
llvm-svn: 221456
Change `NamedMDNode::getOperator()` from returning `MDNode *` to
returning `Value *`. To reduce boilerplate at some call sites, add a
`getOperatorAsMDNode()` for named metadata that's expected to only
return `MDNode` -- for now, that's everything, but debug node named
metadata (such as llvm.dbg.cu and llvm.dbg.sp) will soon change. This
is part of PR21433.
Note that there's a follow-up patch to clang for the API change.
llvm-svn: 221375
This patch improves the folding of vector AND nodes into blend operations for
targets that feature SSE4.1. A vector AND node where one of the operands is
a constant build_vector with elements that are either zero or all-ones can be
converted into a blend.
This allows for example to simplify the following code:
define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) {
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1>
%2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
Before this patch llc (-mcpu=corei7) generated:
andps LCPI1_0(%rip), %xmm0, %xmm0
andps LCPI1_1(%rip), %xmm1, %xmm1
orps %xmm1, %xmm0, %xmm0
retq
With this patch we generate a single 'vpblendw'.
llvm-svn: 221343
Clang -gsplit-dwarf self-host -O0, binary increases by 0.0005%, -O2,
binary increases by 25%.
A large binary inside Google, split-dwarf, -O0, and other internal flags
(GDB index, etc) increases by 1.8%, optimized build is 35%.
The size impact may be somewhat greater in .o files (I haven't measured
that much - since the linked executable -O0 numbers seemed low enough)
due to relocations. These relocations could be removed if we taught the
llvm-symbolizer to handle indexed addressing in the .o file (GDB can't
cope with this just yet, but GDB won't be reading this info anyway).
Also debug_ranges could be shared between .o and .dwo, though ideally
debug_ranges would get a schema that could used index(+offset)
addressing, and move to the .dwo file, then we'd be back to sharing
addresses in the address pool again.
But for now, these sizes seem small enough to go ahead with this.
Verified that no other DW_TAGs are produced into the .o file other than
subprograms and inlined_subroutines.
llvm-svn: 221306
Registers are not all equal. Some are not allocatable (infinite cost),
some have to be preserved but can be used, and some others are just free
to use.
Ensure there is a cost hierarchy reflecting this fact, so that the
allocator will favor scratch registers over callee-saved registers.
llvm-svn: 221293
This patch improves how the different costs (register, interference, spill
and coalescing) relates together. The assumption is now that:
- coalescing (or any other "side effect" of reg alloc) is negative, and
instead of being derived from a spill cost, they use the block
frequency info.
- spill costs are in the [MinSpillCost:+inf( range
- register or interference costs are in [0.0:MinSpillCost( or +inf
The current MinSpillCost is set to 10.0, which is a random value high
enough that the current constraint builders do not need to worry about
when settings costs. It would however be worth adding a normalization
step for register and interference costs as the last step in the
constraint builder chain to ensure they are not greater than SpillMinCost
(unless this has some sense for some architectures). This would work well
with the current builder pipeline, where all costs are tweaked relatively
to each others, but could grow above MinSpillCost if the pipeline is
deep enough.
The current heuristic is tuned to depend rather on the number of uses of
a live interval rather than a density of uses, as used by the greedy
allocator. This heuristic provides a few percent improvement on a number
of benchmarks (eembc, spec, ...) and will definitely need to change once
spill placement is implemented: the current spill placement is really
ineficient, so making the cost proportionnal to the number of use is a
clear win.
llvm-svn: 221292
This is experimental, just barely enough to get things to not
immediately combust.
A note for those who are curious:
Only lld can successfully link the object files, other linkers truncate
the section names making the debug sections illegible to debuggers.
Even with this in mind, we believe we are having trouble with SECREL
relocations.
llvm-svn: 221245
This generalizes the range handling for ranges in both the skeleton and
full unit, laying the foundation for the addition of more ranges (rather
than just the CU's special case) in the skeleton CU with fission+gmlt.
llvm-svn: 221202
So that it may be shared between skeleton/full compile unit, for CU
ranges and other ranges to be added for fission+gmlt.
(at some point we might want some kind of object shared between the
skeleton and full compile units for all those things we only want one of
in that scope, rather than having the full unit always look through to
the skeleton... - alternatively, we might be able to have the skeleton
pointer (or another, separate pointer) point to the skeleton or to the
unit itself in non-fission, so we don't have to special case its
absence)
llvm-svn: 221186
This is one of a few steps to generalize range handling to include the
CU range (thus the CU's range list will be moved into the range list
list, losing track of the base address in the process), which means
generalizing ranges from both the skeleton and full unit under fission.
And... then I can used that generalized support for ranges in
fission+gmlt where there'll be a bunch more ranges in the skeleton.
llvm-svn: 221182
call DAGCombiner. But we ran into a case (on Windows) where the
calling convention causes argument lowering to bail out of fast-isel,
and we end up in CodeGenAndEmitDAG() which does run DAGCombiner.
So, we need to make DAGCombiner check for 'optnone' after all.
Commit includes the test that found this, plus another one that got
missed in the original optnone work.
llvm-svn: 221168
When LLVM emits DWARF call frame information, it currently creates a local,
section-relative symbol in the code section, which is pointed to by a
relocation on the .eh_frame section. However, for C++ we emit some functions in
section groups, and the SysV ABI has some rules to make it easier to remove
these sections
(http://www.sco.com/developers/gabi/latest/ch4.sheader.html#section_group_rules):
A symbol table entry with STB_LOCAL binding that is defined relative to one
of a group's sections, and that is contained in a symbol table section that is
not part of the group, must be discarded if the group members are discarded.
References to this symbol table entry from outside the group are not allowed.
This means that we need to use the function symbol for the relocation, not a
temporary symbol.
There was a comment in the code claiming that the local symbol was used to
avoid creating a relocation, but a relocation must be created anyway as the
code and CFI are in different sections.
llvm-svn: 221150
Currently we only need to emit skeleton strings into the CU header and
we do this by explicitly calling "addLocalString". With gmlt-in-fission,
we'll be emitting a bunch of other strings from other codepaths where
it's not statically known that these strings will be local or not.
Introduce a virtual function to indicate whether this unit is a DWO unit
or not (I'm not sure if we have a good term for this, the
opposite/alternative to 'skeleton' unit) and use that to generalize the
string emission logic so that strings can be correctly emitted in both
the skeleton and dwo unit when in split dwarf mode.
And to demonstrate that this works, switch the existing special callers
of addLocalString in the skeleton builder to addString - and they still
work. Yay.
llvm-svn: 221094
This is a useful distinction/invariant/delination to make because
LineTablesOnly mode is never relevant to type units, so it's clear that
we're not doing weird line-tables-only-with-types by making this API
choice.
It also lays the foundations nicely for adding gmlt-like data to fission
skeleton CUs while limiting the effects to CUs and not TUs.
llvm-svn: 221093
(these will shortly become virtual, with a null implementation in
DwarfUnit (since type units don't have accelerator tables in the current
schema) and the current implementation down in DwarfCompileUnit, moving
the actual maps there too)
llvm-svn: 221082
This would help catch cases where we might otherwise try to reference a
dwo CU label, which would be weird - because without relocations in the
dwo file it's not generally meaningful to talk about the CU offsets
there (or, if it is, we can do so in absolute terms without using a
relocation to compute it).
llvm-svn: 221078
This allows the CU label to be emitted only for compile units, as
they're the only ones that need it (so they can be referenced from
pubnames)
llvm-svn: 221072
This was a compile-unit specific label (unused in type units) and seems
unnecessary anyway when we can more easily directly compute the size of
the compile unit.
llvm-svn: 221067
Type units no longer have skeletons and it's misleading to be able to
query for a type unit's skeleton (it might incorrectly lead one to
conclude that if a unit doesn't have a skeleton it's not in a .dwo
file... ).
llvm-svn: 221055
This is the first big step to allowing gmlt-like inline scope
information in the skeleton CU. While this commit doesn't change the
functionality, it's only a small step to call
"constructAbstractSubprogramDIE" on both the InfoHolder and the
SkeletonHolder (when in use) and that will at least create the abstract
SP dies in that case, though still not creating the other subprograms.
llvm-svn: 221051
Change `Instruction::getMetadata()` to return `Value` as part of
PR21433.
Update most callers to use `Instruction::getMDNode()`, which wraps the
result in a `cast_or_null<MDNode>`.
llvm-svn: 221024
This patch adds an optimization in CodeGenPrepare to move an extractelement
right before a store when the target can combine them.
The optimization may promote any scalar operations to vector operations in the
way to make that possible.
** Context **
Some targets use different register files for both vector and scalar operations.
This means that transitioning from one domain to another may incur copy from one
register file to another. These copies are not coalescable and may be expensive.
For example, according to the scheduling model, on cortex-A8 a vector to GPR
move is 20 cycles.
** Motivating Example **
Let us consider an example:
define void @foo(<2 x i32>* %addr1, i32* %dest) {
%in1 = load <2 x i32>* %addr1, align 8
%extract = extractelement <2 x i32> %in1, i32 1
%out = or i32 %extract, 1
store i32 %out, i32* %dest, align 4
ret void
}
As it is, this IR generates the following assembly on armv7:
vldr d16, [r0] @vector load
vmov.32 r0, d16[1] @ cross-register-file copy: 20 cycles
orr r0, r0, #1 @ scalar bitwise or
str r0, [r1] @ scalar store
bx lr
Whereas we could generate much faster code:
vldr d16, [r0] @ vector load
vorr.i32 d16, #0x1 @ vector bitwise or
vst1.32 {d16[1]}, [r1:32] @ vector extract + store
bx lr
Half of the computation made in the vector is useless, but this allows to get
rid of the expensive cross-register-file copy.
** Proposed Solution **
To avoid this cross-register-copy penalty, we promote the scalar operations to
vector operations. The penalty will be removed if we manage to promote the whole
chain of computation in the vector domain.
Currently, we do that only when the chain of computation ends by a store and the
target is able to combine an extract with a store.
Stores are the most likely candidates, because other instructions produce values
that would need to be promoted and so, extracted as some point[1]. Moreover,
this is customary that targets feature stores that perform a vector extract (see
AArch64 and X86 for instance).
The proposed implementation relies on the TargetTransformInfo to decide whether
or not it is beneficial to promote a chain of computation in the vector domain.
Unfortunately, this interface is rather inaccurate for this level of details and
although this optimization may be beneficial for X86 and AArch64, the inaccuracy
will lead to the optimization being too aggressive.
Basically in TargetTransformInfo, everything that is legal has a cost of 1,
whereas, even if a vector type is legal, usually a vector operation is slightly
more expensive than its scalar counterpart. That will lead to too many
promotions that may not be counter balanced by the saving of the
cross-register-file copy. For instance, on AArch64 this penalty is just 4
cycles.
For now, the optimization is just enabled for ARM prior than v8, since those
processors have a larger penalty on cross-register-file copies, and the scope is
limited to basic blocks. Because of these two factors, we limit the effects of
the inaccuracy. Indeed, I did not want to build up a fancy cost model with block
frequency and everything on top of that.
[1] We can imagine targets that can combine an extractelement with other
instructions than just stores. If we want to go into that direction, the current
interfaces must be augmented and, moreover, I think this becomes a global isel
problem.
Differential Revision: http://reviews.llvm.org/D5921
<rdar://problem/14170854>
llvm-svn: 220978
r212242 introduced a legalizer hook, originally to let AArch64 widen
v1i{32,16,8} rather than scalarize, because the legalizer expected, when
scalarizing the result of a conversion operation, to already have
scalarized the operands. On AArch64, v1i64 is legal, so that commit
ensured operations such as v1i32 = trunc v1i64 wouldn't assert.
It did that by choosing to widen v1 types whenever possible. However,
v1i1 types, for which there's no legal widened type, would still trigger
the assert.
This commit fixes that, by only scalarizing a trunc's result when the
operand has already been scalarized, and introducing an extract_elt
otherwise.
This is similar to r205625.
Fixes PR20777.
llvm-svn: 220937
Earlier this summer I fixed an issue where we were incorrectly combining
multiple loads that had different constraints such alignment, invariance,
temporality, etc. Apparently in one case I made copt paste error and swapped
alignment and invariance.
Tests included.
rdar://18816719
llvm-svn: 220933
sets as keys into a cache of interference matrice values in the Interference
constraint adder.
Creating interference matrices was one of the large remaining time-sinks in
PBQP. Caching them reduces the total compile time (when using PBQP) on the
nightly test suite by ~10%.
llvm-svn: 220688
So that it has access to getOrCreateGlobalVariableDIE. If we ever support
decsribing using directive in C++ classes (thus requiring support in type
units), it will certainly use another mechanism anyway.
Differential Revision: http://reviews.llvm.org/D5975
llvm-svn: 220594
(part of refactoring to allow subprogram emission in both the skeleton
and main units to enable -gmlt-like data to be included in the skeleton
for live inlined backtracing purposes)
llvm-svn: 220578
This is a first step for generating SSE rsqrt instructions for
reciprocal square root calcs when fast-math is allowed.
For now, be conservative and only enable this for AMD btver2
where performance improves significantly - for example, 29%
on llvm/projects/test-suite/SingleSource/Benchmarks/BenchmarkGame/n-body.c
(if we convert the data type to single-precision float).
This patch adds a two constant version of the Newton-Raphson
refinement algorithm to DAGCombiner that can be selected by any target
via a parameter returned by getRsqrtEstimate()..
See PR20900 for more details:
http://llvm.org/bugs/show_bug.cgi?id=20900
Differential Revision: http://reviews.llvm.org/D5658
llvm-svn: 220570
This adds support for legalization of instructions of the form:
[fp_conv] <1 x i1> %op to <1 x double>
where fp_conv is one of fpto[us]i, [us]itofp. This used to assert
because they were simply missing from the vector operand scalarizer.
A similar problem arose in r190830, with trunc instead.
Fixes PR20778.
Differential Revision: http://reviews.llvm.org/D5810
llvm-svn: 220533
x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS
dependency because it was represented by a pair of CopyFromReg(EFLAGS) ->
CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an
implicit-def on the instruction, where the result numbers in the DAG and the
Uses list in TableGen matched up precisely.
The Copy notation seems much more robust, so this patch extends ScheduleDAG
rather than refactoring x86.
Should fix PR20376.
llvm-svn: 220529
While refactoring this code I was confused by both the name I had
introduced (addNonArgumentVariable... but it has all this logic to
handle argument numbering and keep things in order?) and by the
redundancy. Seems when I fixed the misordered inlined argument handling,
I didn't realize it was mostly redundant with the argument ordering code
(which I may've also written, I'm not sure). So let's just rely on the
more general case.
The only oddity in output this produces is that it means when we emit
all the variables for the current function, we don't track when we've
finished the argument variables and are about to start the local
variables and insert DW_AT_unspecified_parameters (for varargs
functions) there. Instead it ends up after the local variables, scopes,
etc. But this isn't invalid and doesn't cause DWARF consumers problems
that I know of... so we'll just go with that because it makes the code
nice & simple.
(though, let's see what the buildbots have to say about this - *crosses
fingers*)
There will be some cleanup commits to follow to remove the now trivial
wrappers, etc.
llvm-svn: 220527
This fixes a bug (introduced by fixing the IR emitted from Clang where
the definition of a static member would be scoped within the class,
rather than within its lexical decl context) where the definition of a
static variable would be placed inside a class.
It also improves source fidelity by scoping static class member
definitions inside the lexical decl context in which tehy are written
(eg: namespace n { class foo { static int i; } int foo::i; } - the
definition of 'i' will be within the namespace 'n' in the DWARF output
now).
Lastly, and the original goal, this reduces debug info size slightly
(and makes debug info easier to read, etc) by placing the definitions of
non-member global variables within their namespace, rather than using a
separate namespace-scoped declaration along with a definition at global
scope.
Based on patches and discussion with Frédéric.
llvm-svn: 220497
Variable handling will be sunk into DwarfFile so that abstract variables
and the like can be shared across multiple CUs (to handle cross-CU
inlining, for example).
llvm-svn: 220453
Use the DwarfDebug in one function that previously took it as a
parameter, and lay the foundation for use this for other operations
coming soon.
llvm-svn: 220452
Now that we're sure the only root (non-abstract) scope is the current
function scope, there's no need for isCurrentFunctionScope, the property
can be tested directly instead.
llvm-svn: 220451
This enables targets to adapt their pass pipeline to the register
allocator in use. For example, with the AArch64 backend, using PBQP
with the cortex-a57, the FPLoadBalancing pass is no longer necessary.
llvm-svn: 220321
Every target we support has support for assembly that looks like
a = b - c
.long a
What is special about MachO is that the above combination suppresses the
production of a relocation.
With this change we avoid producing the intermediary labels when they don't
add any value.
llvm-svn: 220256
Our metadata scheme lazily assigns IDs to string metadata, but we have a mechanism to preassign them as well. Using a preassigned ID is helpful since we get compile time type checking, and avoid some (minimal) string construction and comparison. This change adds enum value for three existing metadata types:
+ MD_nontemporal = 9, // "nontemporal"
+ MD_mem_parallel_loop_access = 10, // "llvm.mem.parallel_loop_access"
+ MD_nonnull = 11 // "nonnull"
I went through an updated various uses as well. I made no attempt to get all uses; I focused on the ones which were easily grepable and easily to translate. For example, there were several items in LoopInfo.cpp I chose not to update.
llvm-svn: 220248
TL;DR: Indexing maps with [] creates missing entries.
The long version:
When selecting lifetime intrinsics, we index the *static* alloca map with the AllocaInst we find for that lifetime. Trouble is, we don't first check to see if this is a dynamic alloca.
On the attached example, this causes a dynamic alloca to create an entry in the static map, and returns 0 (the default) as the frame index for that lifetime. 0 was used for the frame index of the stack protector, which given that it now has a lifetime, is coloured, and merged with other stack slots.
PEI would later trigger an assert because it expects the stack protector to not be dead.
This fix ensures that we only get frame indices for static allocas, ie, those in the map. Dynamic ones are effectively dropped, which is suboptimal, but at least isn't completely broken.
rdar://problem/18672951
llvm-svn: 220099
v2: use dyn_cast
fixup comments
v3: use cast
Reviewed-by: Matt Arsenault <arsenm2@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 220044
This is in preparation for another patch that makes patchpoints invokable.
Reviewers: atrick, ributzka
Reviewed By: ributzka
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5657
llvm-svn: 219967
Summary:
Backends can use setInsertFencesForAtomic to signal to the middle-end that
montonic is the only memory ordering they can accept for
stores/loads/rmws/cmpxchg. The code lowering those accesses with a stronger
ordering to fences + monotonic accesses is currently living in
SelectionDAGBuilder.cpp. In this patch I propose moving this logic out of it
for several reasons:
- There is lots of redundancy to avoid: extremely similar logic already
exists in AtomicExpand.
- The current code in SelectionDAGBuilder does not use any target-hooks, it
does the same transformation for every backend that requires it
- As a result it is plain *unsound*, as it was apparently designed for ARM.
It happens to mostly work for the other targets because they are extremely
conservative, but Power for example had to switch to AtomicExpand to be
able to use lwsync safely (see r218331).
- Because it produces IR-level fences, it cannot be made sound ! This is noted
in the C++11 standard (section 29.3, page 1140):
```
Fences cannot, in general, be used to restore sequential consistency for atomic
operations with weaker ordering semantics.
```
It can also be seen by the following example (called IRIW in the litterature):
```
atomic<int> x = y = 0;
int r1, r2, r3, r4;
Thread 0:
x.store(1);
Thread 1:
y.store(1);
Thread 2:
r1 = x.load();
r2 = y.load();
Thread 3:
r3 = y.load();
r4 = x.load();
```
r1 = r3 = 1 and r2 = r4 = 0 is impossible as long as the accesses are all seq_cst.
But if they are lowered to monotonic accesses, no amount of fences can prevent it..
This patch does three things (I could cut it into parts, but then some of them
would not be tested/testable, please tell me if you would prefer that):
- it provides a default implementation for emitLeadingFence/emitTrailingFence in
terms of IR-level fences, that mimic the original logic of SelectionDAGBuilder.
As we saw above, this is unsound, but the best that can be done without knowing
the targets well (and there is a comment warning about this risk).
- it then switches Mips/Sparc/XCore to use AtomicExpand, relying on this default
implementation (that exactly replicates the logic of SelectionDAGBuilder, so no
functional change)
- it finally erase this logic from SelectionDAGBuilder as it is dead-code.
Ideally, each target would define its own override for emitLeading/TrailingFence
using target-specific fences, but I do not know the Sparc/Mips/XCore memory model
well enough to do this, and they appear to be dealing fine with the ARM-inspired
default expansion for now (probably because they are overly conservative, as
Power was). If anyone wants to compile fences more agressively on these
platforms, the long comment should make it clear why he should first override
emitLeading/TrailingFence.
Test Plan: make check-all, no functional change
Reviewers: jfb, t.p.northover
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D5474
llvm-svn: 219957
Summary:
Fixes a FIXME in MachineSinking. Instead of using the simple heuristics in
isPostDominatedBy, use the real MachinePostDominatorTree and MachineLoopInfo.
The old heuristics caused instructions to sink unnecessarily, and might create
register pressure.
This is the second try of the fix. The first one (D4814) caused a performance
regression due to failing to sink instructions out of loops (PR21115). This
patch fixes PR21115 by sinking an instruction from a deeper loop to a shallower
one regardless of whether the target block post-dominates the source.
Thanks Alexey Volkov for reporting PR21115!
Test Plan:
Added a NVPTX codegen test to verify that our change prevents the backend from
over-sinking. It also shows the unnecessary register pressure caused by
over-sinking.
Added an X86 test to verify we can sink instructions out of loops regardless of
the dominance relationship. This test is reduced from Alexey's test in PR21115.
Updated an affected test in X86.
Also ran SPEC CINT2006 and llvm-test-suite for compilation time and runtime
performance. Results are attached separately in the review thread.
Reviewers: Jiangning, resistor, hfinkel
Reviewed By: hfinkel
Subscribers: hfinkel, bruno, volkalexey, llvm-commits, meheff, eliben, jholewinski
Differential Revision: http://reviews.llvm.org/D5633
llvm-svn: 219773
Peephole optimization that generates a single conditional branch
for csinc-branch sequences like in the examples below. This is
possible when the csinc sets or clears a register based on a condition
code and the branch checks that register. Also the condition
code may not be modified between the csinc and the original branch.
Examples:
1. Convert csinc w9, wzr, wzr, <CC>;tbnz w9, #0, 0x44
to b.<invCC>
2. Convert csinc w9, wzr, wzr, <CC>; tbz w9, #0, 0x44
to b.<CC>
rdar://problem/18506500
llvm-svn: 219742
Let me tell you a tale...
Originally committed in r211723 after discovering a nasty case of weird
scoping due to inlining, this was reverted in r211724 after it fired in
ASan/compiler-rt.
(minor diversion where I accidentally committed/reverted again in
r211871/r211873)
After further testing and fixing bugs in ArgumentPromotion (r211872) and
Inlining (r212065) it was recommitted in r212085. Reverted in r212089
after the sanitizer buildbots still showed problems.
Fixed another bug in ArgumentPromotion (r212128) found by this
assertion.
Recommitted in r212205, reverted in r212226 after it crashed some more
on sanitizer buildbots.
Fix clang some more in r212761.
Recommitted in r212776, reverted in r212793. ASan failures.
Recommitted in r213391, reverted in r213432, trying to reproduce flakey
ASan build failure.
Fixed bugs in r213805 (ArgPromo + DebugInfo), r213952
(LiveDebugVariables strips dbg_value intrinsics in functions not
described by debug info).
Recommitted in r214761, reverted in r214999, flakey failure on Windows
buildbot.
Fixed DeadArgElimination + DebugInfo bug in r219210.
Recommitted in r219215, reverted in r219512, failure on ObjC++ atomic
properties in the test-suite on Darwin.
Fixed ObjC++ atomic properties issue in Clang in r219690.
[This commit is provided 'as is' with no hope that this is the last time
I commit this change either expressed or implied]
llvm-svn: 219702
and TargetRegisterInfo in the peephole optimizer. This
makes it easier to grab subtarget dependent variables off
of the MachineFunction rather than the TargetMachine.
llvm-svn: 219669
Broken parent scope pointers in inlined DIVariables can cause
ensureAbstractVariableIsCreated to insert new abstract scopes, thus
invalidating the iterator in this loop and leading to hard-to-debug
crashes. Useful when manually reducing IR for testcases.
llvm-svn: 219628
Reid Kleckner