CGSCC pass manager. This should insulate the inlining decisions from the
vectorization decisions, however it may have both compile time and code
size problems so it is just an experimental option right now.
Adding this based on a discussion with Arnold and it seems at least
worth having this flag for us to both run some experiments to see if
this strategy is workable. It may solve some of the regressions seen
with the loop vectorizer.
llvm-svn: 184698
This commit completely removes what is left of the simplify-libcalls
pass. All of the functionality has now been migrated to the instcombine
and functionattrs passes. The following C API functions are now NOPs:
1. LLVMAddSimplifyLibCallsPass
2. LLVMPassManagerBuilderSetDisableSimplifyLibCalls
llvm-svn: 184459
interfaces. These methods were used in the old inline cost system where
there was a persistent cache that had to be updated, invalidated, and
cleared. We're now doing more direct computations that don't require
this intricate dance. Even if we resume some level of caching, it would
almost certainly have a simpler and more narrow interface than this.
llvm-svn: 153813
on a per-callsite walk of the called function's instructions, in
breadth-first order over the potentially reachable set of basic blocks.
This is a major shift in how inline cost analysis works to improve the
accuracy and rationality of inlining decisions. A brief outline of the
algorithm this moves to:
- Build a simplification mapping based on the callsite arguments to the
function arguments.
- Push the entry block onto a worklist of potentially-live basic blocks.
- Pop the first block off of the *front* of the worklist (for
breadth-first ordering) and walk its instructions using a custom
InstVisitor.
- For each instruction's operands, re-map them based on the
simplification mappings available for the given callsite.
- Compute any simplification possible of the instruction after
re-mapping, and store that back int othe simplification mapping.
- Compute any bonuses, costs, or other impacts of the instruction on the
cost metric.
- When the terminator is reached, replace any conditional value in the
terminator with any simplifications from the mapping we have, and add
any successors which are not proven to be dead from these
simplifications to the worklist.
- Pop the next block off of the front of the worklist, and repeat.
- As soon as the cost of inlining exceeds the threshold for the
callsite, stop analyzing the function in order to bound cost.
The primary goal of this algorithm is to perfectly handle dead code
paths. We do not want any code in trivially dead code paths to impact
inlining decisions. The previous metric was *extremely* flawed here, and
would always subtract the average cost of two successors of
a conditional branch when it was proven to become an unconditional
branch at the callsite. There was no handling of wildly different costs
between the two successors, which would cause inlining when the path
actually taken was too large, and no inlining when the path actually
taken was trivially simple. There was also no handling of the code
*path*, only the immediate successors. These problems vanish completely
now. See the added regression tests for the shiny new features -- we
skip recursive function calls, SROA-killing instructions, and high cost
complex CFG structures when dead at the callsite being analyzed.
Switching to this algorithm required refactoring the inline cost
interface to accept the actual threshold rather than simply returning
a single cost. The resulting interface is pretty bad, and I'm planning
to do lots of interface cleanup after this patch.
Several other refactorings fell out of this, but I've tried to minimize
them for this patch. =/ There is still more cleanup that can be done
here. Please point out anything that you see in review.
I've worked really hard to try to mirror at least the spirit of all of
the previous heuristics in the new model. It's not clear that they are
all correct any more, but I wanted to minimize the change in this single
patch, it's already a bit ridiculous. One heuristic that is *not* yet
mirrored is to allow inlining of functions with a dynamic alloca *if*
the caller has a dynamic alloca. I will add this back, but I think the
most reasonable way requires changes to the inliner itself rather than
just the cost metric, and so I've deferred this for a subsequent patch.
The test case is XFAIL-ed until then.
As mentioned in the review mail, this seems to make Clang run about 1%
to 2% faster in -O0, but makes its binary size grow by just under 4%.
I've looked into the 4% growth, and it can be fixed, but requires
changes to other parts of the inliner.
llvm-svn: 153812
directly query the function information which this set was representing.
This simplifies the interface of the inline cost analysis, and makes the
always-inline pass significantly more efficient.
Previously, always-inline would first make a single set of every
function in the module *except* those marked with the always-inline
attribute. It would then query this set at every call site to see if the
function was a member of the set, and if so, refuse to inline it. This
is quite wasteful. Instead, simply check the function attribute directly
when looking at the callsite.
The normal inliner also had similar redundancy. It added every function
in the module with the noinline attribute to its set to ignore, even
though inside the cost analysis function we *already tested* the
noinline attribute and produced the same result.
The only tricky part of removing this is that we have to be able to
correctly remove only the functions inlined by the always-inline pass
when finalizing, which requires a bit of a hack. Still, much less of
a hack than the set of all non-always-inline functions was. While I was
touching this function, I switched a heavy-weight set to a vector with
sort+unique. The algorithm already had a two-phase insert and removal
pattern, we were just needlessly paying the uniquing cost on every
insert.
This probably speeds up some compiles by a small amount (-O0 compiles
with lots of always-inline, so potentially heavy libc++ users), but I've
not tried to measure it.
I believe there is no functional change here, but yell if you spot one.
None are intended.
Finally, the direction this is going in is to greatly simplify the
inline cost query interface so that we can replace its implementation
with a much more clever one. Along the way, all the APIs get simplified,
so it seems incrementally good.
llvm-svn: 152903
are optimization hints, but at -O0 we're not optimizing. This becomes a problem
when the alwaysinline attribute is abused.
rdar://10921594
llvm-svn: 151429
This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure.
Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser).
llvm-svn: 149468
to CallGraphSCCPass's instead of passing around a
std::vector<CallGraphNode*>. No functionality change,
but now we have a much tidier interface.
llvm-svn: 101558
The Caller cost info would be reset everytime a callee was inlined. If the
caller has lots of calls and there is some mutual recursion going on, the
caller cost info could be calculated many times.
This patch reduces inliner runtime from 240s to 0.5s for a function with 20000
small function calls.
This is a more conservative version of r98089 that doesn't break the clang
test CodeGenCXX/temp-order.cpp. That test relies on rather extreme inlining
for constant folding.
llvm-svn: 98099
The Caller cost info would be reset everytime a callee was inlined. If the
caller has lots of calls and there is some mutual recursion going on, the
caller cost info could be calculated many times.
This patch reduces inliner runtime from 240s to 0.5s for a function with 20000
small function calls.
llvm-svn: 98089
This time it's for real! I am going to hook this up in the frontends as well.
The inliner has some experimental heuristics for dealing with the inline hint.
When given a -respect-inlinehint option, functions marked with the inline
keyword are given a threshold just above the default for -O3.
We need some experiments to determine if that is the right thing to do.
llvm-svn: 95466
argpromotion and structretpromote. Basically, when replacing
a function, they used the 'changeFunction' api which changes
the entry in the function map (and steals/reuses the callgraph
node).
This has some interesting effects: first, the problem is that it doesn't
update the "callee" edges in any callees of the function in the call graph.
Second, this covers for a major problem in all the CGSCC pass stuff, which
is that it is completely broken when functions are deleted if they *don't*
reuse a CGN. (there is a cute little fixme about this though :).
This patch changes the protocol that CGSCC passes must obey: now the CGSCC
pass manager copies the SCC and preincrements its iterator to avoid passes
invalidating it. This allows CGSCC passes to mutate the current SCC. However
multiple passes may be run on that SCC, so if passes do this, they are now
required to *update* the SCC to be current when they return.
Other less interesting parts of this patch are that it makes passes update
the CG more directly, eliminates changeFunction, and requires clients of
replaceCallSite to specify the new callee CGN if they are changing it.
llvm-svn: 80527
calls into a function and if the calls bring in arrays, try to merge
them together to reduce stack size. For example, in the testcase
we'd previously end up with 4 allocas, now we end up with 2 allocas.
As described in the comments, this is not really the ideal solution
to this problem, but it is surprisingly effective. For example, on
176.gcc, we end up eliminating 67 arrays at "gccas" time and another
24 at "llvm-ld" time.
One piece of concern that I didn't look into: at -O0 -g with
forced inlining this will almost certainly result in worse debug
info. I think this is acceptable though given that this is a case
of "debugging optimized code", and we don't want debug info to
prevent the optimizer from doing things anyway.
llvm-svn: 80215
the inliner; prevents nondeterministic behavior
when the same address is reallocated.
Don't build call graph nodes for debug intrinsic calls;
they're useless, and there were typically a lot of them.
llvm-svn: 67311
function.
- This explicitly models the costs for functions which should
"always" or "never" be inlined. This fixes bugs where such costs
were not previously respected.
llvm-svn: 58450
Furthermore, double the limit when more than 10% of the callee instructions are vector instructions. Multimedia kernels tend to love inlining.
llvm-svn: 48725
