This is essentially a ground up re-think of the SROA pass in LLVM. It
was initially inspired by a few problems with the existing pass:
- It is subject to the bane of my existence in optimizations: arbitrary
thresholds.
- It is overly conservative about which constructs can be split and
promoted.
- The vector value replacement aspect is separated from the splitting
logic, missing many opportunities where splitting and vector value
formation can work together.
- The splitting is entirely based around the underlying type of the
alloca, despite this type often having little to do with the reality
of how that memory is used. This is especially prevelant with unions
and base classes where we tail-pack derived members.
- When splitting fails (often due to the thresholds), the vector value
replacement (again because it is separate) can kick in for
preposterous cases where we simply should have split the value. This
results in forming i1024 and i2048 integer "bit vectors" that
tremendously slow down subsequnet IR optimizations (due to large
APInts) and impede the backend's lowering.
The new design takes an approach that fundamentally is not susceptible
to many of these problems. It is the result of a discusison between
myself and Duncan Sands over IRC about how to premptively avoid these
types of problems and how to do SROA in a more principled way. Since
then, it has evolved and grown, but this remains an important aspect: it
fixes real world problems with the SROA process today.
First, the transform of SROA actually has little to do with replacement.
It has more to do with splitting. The goal is to take an aggregate
alloca and form a composition of scalar allocas which can replace it and
will be most suitable to the eventual replacement by scalar SSA values.
The actual replacement is performed by mem2reg (and in the future
SSAUpdater).
The splitting is divided into four phases. The first phase is an
analysis of the uses of the alloca. This phase recursively walks uses,
building up a dense datastructure representing the ranges of the
alloca's memory actually used and checking for uses which inhibit any
aspects of the transform such as the escape of a pointer.
Once we have a mapping of the ranges of the alloca used by individual
operations, we compute a partitioning of the used ranges. Some uses are
inherently splittable (such as memcpy and memset), while scalar uses are
not splittable. The goal is to build a partitioning that has the minimum
number of splits while placing each unsplittable use in its own
partition. Overlapping unsplittable uses belong to the same partition.
This is the target split of the aggregate alloca, and it maximizes the
number of scalar accesses which become accesses to their own alloca and
candidates for promotion.
Third, we re-walk the uses of the alloca and assign each specific memory
access to all the partitions touched so that we have dense use-lists for
each partition.
Finally, we build a new, smaller alloca for each partition and rewrite
each use of that partition to use the new alloca. During this phase the
pass will also work very hard to transform uses of an alloca into a form
suitable for promotion, including forming vector operations, speculating
loads throguh PHI nodes and selects, etc.
After splitting is complete, each newly refined alloca that is
a candidate for promotion to a scalar SSA value is run through mem2reg.
There are lots of reasonably detailed comments in the source code about
the design and algorithms, and I'm going to be trying to improve them in
subsequent commits to ensure this is well documented, as the new pass is
in many ways more complex than the old one.
Some of this is still a WIP, but the current state is reasonbly stable.
It has passed bootstrap, the nightly test suite, and Duncan has run it
successfully through the ACATS and DragonEgg test suites. That said, it
remains behind a default-off flag until the last few pieces are in
place, and full testing can be done.
Specific areas I'm looking at next:
- Improved comments and some code cleanup from reviews.
- SSAUpdater and enabling this pass inside the CGSCC pass manager.
- Some datastructure tuning and compile-time measurements.
- More aggressive FCA splitting and vector formation.
Many thanks to Duncan Sands for the thorough final review, as well as
Benjamin Kramer for lots of review during the process of writing this
pass, and Daniel Berlin for reviewing the data structures and algorithms
and general theory of the pass. Also, several other people on IRC, over
lunch tables, etc for lots of feedback and advice.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163883 91177308-0d34-0410-b5e6-96231b3b80d8
* wrap code blocks in \code ... \endcode;
* refer to parameter names in paragraphs correctly (\arg is not what most
people want -- it starts a new paragraph).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163790 91177308-0d34-0410-b5e6-96231b3b80d8
pointers-to-strong-pointers may be in play. These can lead to retains and
releases happening in unstructured ways, foiling the optimizer. This fixes
rdar://12150909.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163180 91177308-0d34-0410-b5e6-96231b3b80d8
- CodeGenPrepare pass for identifying div/rem ops
- Backend specifies the type mapping using addBypassSlowDivType
- Enabled only for Intel Atom with O2 32-bit -> 8-bit
- Replace IDIV with instructions which test its value and use DIVB if the value
is positive and less than 256.
- In the case when the quotient and remainder of a divide are used a DIV
and a REM instruction will be present in the IR. In the non-Atom case
they are both lowered to IDIVs and CSE removes the redundant IDIV instruction,
using the quotient and remainder from the first IDIV. However,
due to this optimization CSE is not able to eliminate redundant
IDIV instructions because they are located in different basic blocks.
This is overcome by calculating both the quotient (DIV) and remainder (REM)
in each basic block that is inserted by the optimization and reusing the result
values when a subsequent DIV or REM instruction uses the same operands.
- Test cases check for the presents of the optimization when calculating
either the quotient, remainder, or both.
Patch by Tyler Nowicki!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163150 91177308-0d34-0410-b5e6-96231b3b80d8
Scan the body of the loop and find instructions that may trap.
Use this information when deciding if it is safe to hoist or sink instructions.
Notice that we can optimize the search of instructions that may throw in the case of nested loops.
rdar://11518836
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163132 91177308-0d34-0410-b5e6-96231b3b80d8
For example, the ARM target does not have efficient ISel handling for vector
selects with scalar conditions. This patch adds a TLI hook which allows the
different targets to report which selects are supported well and which selects
should be converted to CF duting codegen prepare.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163093 91177308-0d34-0410-b5e6-96231b3b80d8
We update until we hit a fixpoint. This is probably slow but also
slightly simplifies the code. It should also fix the occasional
invalid domtrees observed when building with expensive checking.
I couldn't find a case where this had a measurable slowdown, but
if someone finds a pathological case where it does we may have
to find a cleverer way of updating dominators here.
Thanks to Duncan for the test case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163091 91177308-0d34-0410-b5e6-96231b3b80d8
The old PHI updating code in loop-rotate was replaced with SSAUpdater a while
ago, it has no problems with comples PHIs. What had to be fixed is detecting
whether a loop was already rotated and updating dominators when multiple exits
were present.
This change increases overall code size a bit, mostly due to additional loop
unrolling opportunities. Passes test-suite and selfhost with -verify-dom-info.
Fixes PR7447.
Thanks to Andy for the input on the domtree updating code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162912 91177308-0d34-0410-b5e6-96231b3b80d8
This disables malloc-specific optimization when -fno-builtin (or -ffreestanding)
is specified. This has been a problem for a long time but became more severe
with the recent memory builtin improvements.
Since the memory builtin functions are used everywhere, this required passing
TLI in many places. This means that functions that now have an optional TLI
argument, like RecursivelyDeleteTriviallyDeadFunctions, won't remove dead
mallocs anymore if the TLI argument is missing. I've updated most passes to do
the right thing.
Fixes PR13694 and probably others.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162841 91177308-0d34-0410-b5e6-96231b3b80d8
No intended behavior change. This was introduced in r162023. With the fixed
algorithm a Release build of ARMInstPrinter.cpp goes from 16s to 10s on a
2011 MBP.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162559 91177308-0d34-0410-b5e6-96231b3b80d8
optimizations are guarded by the -enable-double-float-shrink LLVM option.
Last bit of PR13574. Patch by Weiming Zhao <weimingz@codeaurora.org>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162368 91177308-0d34-0410-b5e6-96231b3b80d8
This optimization is really just replacing allocas wholesale with
globals, there is no scalarization.
The underlying motivation for this patch is to simplify the SROA pass
and focus it on splitting and promoting allocas.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162271 91177308-0d34-0410-b5e6-96231b3b80d8
where some fact lake a=b dominates a use in a phi, but doesn't dominate the
basic block itself.
This feature could also be implemented by splitting critical edges, but at least
with the current algorithm reasoning about the dominance directly is faster.
The time for running "opt -O2" in the testcase in pr10584 is 1.003 times slower
and on gcc as a single file it is 1.0007 times faster.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162023 91177308-0d34-0410-b5e6-96231b3b80d8
and allow some optimizations to turn conditional branches into unconditional.
This commit adds a simple control-flow optimization which merges two consecutive
basic blocks which are connected by a single edge. This allows the codegen to
operate on larger basic blocks.
rdar://11973998
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161852 91177308-0d34-0410-b5e6-96231b3b80d8
multiple scalar promotions on a single loop. This also has the effect of
preserving the order of stores sunk out of loops, which is aesthetically
pleasing, and it happens to fix the testcase in PR13542, though it doesn't
fix the underlying problem.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161459 91177308-0d34-0410-b5e6-96231b3b80d8
GetBestDestForJumpOnUndef() assumes there is at least 1 successor, which isn't
true if the block ends in an indirect branch with no successors. Fix this by
bailing out earlier in this case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160546 91177308-0d34-0410-b5e6-96231b3b80d8
