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).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149468 91177308-0d34-0410-b5e6-96231b3b80d8
Before 3.0, I'd like to add a mechanism for automatically loading a set of plugins from a config file. API suggestions welcome...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137717 91177308-0d34-0410-b5e6-96231b3b80d8
but it solves a layering violation since things in Support are not supposed to
use things in Transforms.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136726 91177308-0d34-0410-b5e6-96231b3b80d8
to CallGraphSCCPass's instead of passing around a
std::vector<CallGraphNode*>. No functionality change,
but now we have a much tidier interface.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101558 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98099 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98089 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95466 91177308-0d34-0410-b5e6-96231b3b80d8
No functional change except the forgotten test for
InlineLimit.getNumOccurrences() == 0 in the CurrentThreshold2 calculation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@94007 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@80527 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@80215 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@67311 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58450 91177308-0d34-0410-b5e6-96231b3b80d8
Furthermore, double the limit when more than 10% of the callee instructions are vector instructions. Multimedia kernels tend to love inlining.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@48725 91177308-0d34-0410-b5e6-96231b3b80d8
out how to run a collection of passes optimially given their behaviors and
charactaristics.
Convert code to use it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@1507 91177308-0d34-0410-b5e6-96231b3b80d8