This adds a new scalar pass that reads a file with samples generated
by 'perf' during runtime. The samples read from the profile are
incorporated and emmited as IR metadata reflecting that profile.
The profile file is assumed to have been generated by an external
profile source. The profile information is converted into IR metadata,
which is later used by the analysis routines to estimate block
frequencies, edge weights and other related data.
External profile information files have no fixed format, each profiler
is free to define its own. This includes both the on-disk representation
of the profile and the kind of profile information stored in the file.
A common kind of profile is based on sampling (e.g., perf), which
essentially counts how many times each line of the program has been
executed during the run.
The SampleProfileLoader pass is organized as a scalar transformation.
On startup, it reads the file given in -sample-profile-file to
determine what kind of profile it contains. This file is assumed to
contain profile information for the whole application. The profile
data in the file is read and incorporated into the internal state of
the corresponding profiler.
To facilitate testing, I've organized the profilers to support two file
formats: text and native. The native format is whatever on-disk
representation the profiler wants to support, I think this will mostly
be bitcode files, but it could be anything the profiler wants to
support. To do this, every profiler must implement the
SampleProfile::loadNative() function.
The text format is mostly meant for debugging. Records are separated by
newlines, but each profiler is free to interpret records as it sees fit.
Profilers must implement the SampleProfile::loadText() function.
Finally, the pass will call SampleProfile::emitAnnotations() for each
function in the current translation unit. This function needs to
translate the loaded profile into IR metadata, which the analyzer will
later be able to use.
This patch implements the first steps towards the above design. I've
implemented a sample-based flat profiler. The format of the profile is
fairly simplistic. Each sampled function contains a list of relative
line locations (from the start of the function) together with a count
representing how many samples were collected at that line during
execution. I generate this profile using perf and a separate converter
tool.
Currently, I have only implemented a text format for these profiles. I
am interested in initial feedback to the whole approach before I send
the other parts of the implementation for review.
This patch implements:
- The SampleProfileLoader pass.
- The base ExternalProfile class with the core interface.
- A SampleProfile sub-class using the above interface. The profiler
generates branch weight metadata on every branch instructions that
matches the profiles.
- A text loader class to assist the implementation of
SampleProfile::loadText().
- Basic unit tests for the pass.
Additionally, the patch uses profile information to compute branch
weights based on instruction samples.
This patch converts instruction samples into branch weights. It
does a fairly simplistic conversion:
Given a multi-way branch instruction, it calculates the weight of
each branch based on the maximum sample count gathered from each
target basic block.
Note that this assignment of branch weights is somewhat lossy and can be
misleading. If a basic block has more than one incoming branch, all the
incoming branches will get the same weight. In reality, it may be that
only one of them is the most heavily taken branch.
I will adjust this assignment in subsequent patches.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194566 91177308-0d34-0410-b5e6-96231b3b80d8
specifically about the .space directive. This allows us to force large
blocks of code to appear in test cases for things like constant islands
without having to make giant test cases to force things like long
branches to take effect.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194555 91177308-0d34-0410-b5e6-96231b3b80d8
This patch reapplies r193676 with an additional fix for the Hexagon backend. The
SystemZ backend has already been fixed by r194148.
The Type Legalizer recognizes that VSELECT needs to be split, because the type
is to wide for the given target. The same does not always apply to SETCC,
because less space is required to encode the result of a comparison. As a result
VSELECT is split and SETCC is unrolled into scalar comparisons.
This commit fixes the issue by checking for VSELECT-SETCC patterns in the DAG
Combiner. If a matching pattern is found, then the result mask of SETCC is
promoted to the expected vector mask type for the given target. Now the type
legalizer will split both VSELECT and SETCC.
This allows the following X86 DAG Combine code to sucessfully detect the MIN/MAX
pattern. This fixes PR16695, PR17002, and <rdar://problem/14594431>.
Reviewed by Nadav
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194542 91177308-0d34-0410-b5e6-96231b3b80d8
more smarts in it. This is where most of the interesting logic that used
to live in the implicit-scheduling-hackery of the old pass manager will
live.
Like the previous commits, note that this is a very early prototype!
I expect substantial changes before this is ready to use.
The core of the design is the following:
- We have an AnalysisManager which can be used across a series of
passes over a module.
- The code setting up a pass pipeline registers the analyses available
with the manager.
- Individual transform passes can check than an analysis manager
provides the analyses they require in order to fail-fast.
- There is *no* implicit registration or scheduling.
- Analysis passes are different from other passes: they produce an
analysis result that is cached and made available via the analysis
manager.
- Cached results are invalidated automatically by the pass managers.
- When a transform pass requests an analysis result, either the analysis
is run to produce the result or a cached result is provided.
There are a few aspects of this design that I *know* will change in
subsequent commits:
- Currently there is no "preservation" system, that needs to be added.
- All of the analysis management should move up to the analysis library.
- The analysis management needs to support at least SCC passes. Maybe
loop passes. Living in the analysis library will facilitate this.
- Need support for analyses which are *both* module and function passes.
- Need support for pro-actively running module analyses to have cached
results within a function pass manager.
- Need a clear design for "immutable" passes.
- Need support for requesting cached results when available and not
re-running the pass even if that would be necessary.
- Need more thorough testing of all of this infrastructure.
There are other aspects that I view as open questions I'm hoping to
resolve as I iterate a bit on the infrastructure, and especially as
I start writing actual passes against this.
- Should we have separate management layers for function, module, and
SCC analyses? I think "yes", but I'm not yet ready to switch the code.
Adding SCC support will likely resolve this definitively.
- How should the 'require' functionality work? Should *that* be the only
way to request results to ensure that passes always require things?
- How should preservation work?
- Probably some other things I'm forgetting. =]
Look forward to more patches in shorter order now that this is in place.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194538 91177308-0d34-0410-b5e6-96231b3b80d8
Add user-supplied C runtime and compiler-rt library functions to
llvm.compiler.used to protect them from premature optimization by
passes like -globalopt and -ipsccp. Calls to (seemingly unused)
runtime library functions can be added by -instcombine and instruction
lowering.
Patch by Duncan Exon Smith, thanks!
Fixes <rdar://problem/14740087>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194514 91177308-0d34-0410-b5e6-96231b3b80d8
The system LDM and STM instructions can't usually writeback to the base
register. The one exception is when an LDM is actually an exception-return
(i.e. contains PC in the register list).
(There's already a test that "ldm sp!, {r0-r3, pc}^" works, which is why there
is no positive test).
rdar://problem/15223374
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194512 91177308-0d34-0410-b5e6-96231b3b80d8
Constant merge can merge a constant with implicit alignment with one that has
explicit alignment. Before this change it was assuming that the explicit
alignment was higher than the implicit one, causing the result to be under
aligned in some cases.
Fixes pr17815.
Patch by Chris Smowton!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194506 91177308-0d34-0410-b5e6-96231b3b80d8
copy in MC layer. Added the MC layer tests. Fixed triple setting in test cases.
Patch by Ana Pazos <apazos@codeaurora.org>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194501 91177308-0d34-0410-b5e6-96231b3b80d8
We already know how to fold a reload from a frameindex without
analyzing the load instruction. Generalize this to handle any
frameindex load. This streamlines the logic for rematerializing loads
from stack arguments. As a side effect, it allows stackmaps to record
a stack argument location without spilling it.
Verified no effect on codegen for llvm test-suite.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194497 91177308-0d34-0410-b5e6-96231b3b80d8
Like GCC, this re-uses the 'f' constraint and a new 'w' print-modifier:
asm ("ldi.w %w0, 1", "=f"(result));
Unlike GCC, the 'w' print-modifer is not _required_ to produce the intended
output. This is a consequence of differences in the internal handling of
the registers in each compiler. To be source-compatible between the
compilers, users must use the 'w' print-modifier.
MSA registers (including control registers) are supported in clobber lists.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194476 91177308-0d34-0410-b5e6-96231b3b80d8
ATOMIC_FENCE is lowered to a compiler barrier which is codegen only. There
is no need to emit an instructions since the XCore provides sequential
consistency.
Original patch by Richard Osborne
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194464 91177308-0d34-0410-b5e6-96231b3b80d8
Print the range of registers used with a single letter prefix.
This better matches what the shader compiler produces and
is overall less obnoxious than concatenating all of the
subregister names together.
Instead of SGPR0, it will print s0. Instead of SGPR0_SGPR1,
it will print s[0:1] and so on.
There doesn't appear to be a straightforward way
to get the actual register info in the InstPrinter,
so this parses the generated name to print with the
new syntax.
The required test changes are pretty nasty, and register
matching regexes are now worse. Since there isn't a way to
add to a variable in FileCheck, some of the tests now don't
check the exact number of registers used, but I don't think that
will be a real problem.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194443 91177308-0d34-0410-b5e6-96231b3b80d8
This has no material effect at this time since we don't have a direct
object emitter for mips16 and the assembler can't tell them apart. I
place a comment "16 bit inst" for those so that I can tell them apart in the
output. The constant island pass has only been minimally changed to allow
this. More complete branch work is forthcoming but this is the first
step.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194442 91177308-0d34-0410-b5e6-96231b3b80d8
The parsing method still returns llvm::error_code for consistency with
other parsing methods. Minor cleanup, no functionality change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194437 91177308-0d34-0410-b5e6-96231b3b80d8
X86AsmPrinter::EmitInstruction, rather than X86MCInstLower::Lower.
The aim is to improve the reusability of the X86MCInstLower class by making it
more function-like. The X86::MORESTACK_RET_RESTORE_R10 pseudo broke the
function model by emitting an extra instruction to the MCStreamer attached to
the AsmPrinter.
The patch should have no impact on generated code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194431 91177308-0d34-0410-b5e6-96231b3b80d8
Fixes <rdar://15432754> [JS] Assertion: "Folded a def to a non-store!"
The primary purpose of anyregcc is to prevent a patchpoint's call
arguments and return value from being spilled. They must be available
in a register, although the calling convention does not pin the
register. It's up to the front end to avoid using this convention for
calls with more arguments than allocatable registers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194428 91177308-0d34-0410-b5e6-96231b3b80d8
The symptom is that an assertion is triggered. The assertion was added by
me to detect the situation when value is propagated from dead blocks.
(We can certainly get rid of assertion; it is safe to do so, because propagating
value from dead block to alive join node is certainly ok.)
The root cause of this bug is : edge-splitting is conducted on the fly,
the edge being split could be a dead edge, therefore the block that
split the critial edge needs to be flagged "dead" as well.
There are 3 ways to fix this bug:
1) Get rid of the assertion as I mentioned eariler
2) When an dead edge is split, flag the inserted block "dead".
3) proactively split the critical edges connecting dead and live blocks when
new dead blocks are revealed.
This fix go for 3) with additional 2 LOC.
Testing case was added by Rafael the other day.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194424 91177308-0d34-0410-b5e6-96231b3b80d8
This will enable the PBQP register allocator to provide its own normalizing function.
No functionnal change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194417 91177308-0d34-0410-b5e6-96231b3b80d8
