Summary: visitSwitchInst should not take INT_MAX when Cost is negative. Instead of INT_MAX , we also use a valid upperbound cost when overflow occurs in Cost.
Reviewers: hans, echristo, dmgreen
Reviewed By: dmgreen
Subscribers: mcrosier, javed.absar, llvm-commits, eraman
Differential Revision: https://reviews.llvm.org/D34436
llvm-svn: 306118
Summary:
This is to enable the new switch inline cost heuristic (r301649) by removing the
old heuristic as well as the flag itself.
In my experiment for LLVM test suite and spec2000/2006, +17.82% performance and
8% code size reduce was observed in spec2000/vertex with O3 LTO in AArch64.
No significant code size / performance regression was found in O3/O2/Os. No
significant complain was reported from the llvm-dev thread.
Reviewers: hans, chandlerc, eraman, haicheng, mcrosier, bmakam, eastig, ddibyend, echristo
Reviewed By: echristo
Subscribers: javed.absar, kristof.beyls, echristo, aemerson, rengolin, mehdi_amini
Differential Revision: https://reviews.llvm.org/D32653
llvm-svn: 304594
Update threshold based on callee's hotness only when BFI is not available.
Otherwise use only callsite's hotness. This makes it easier to reason about
hotness related threshold updates.
Differential revision: https://reviews.llvm.org/D33157
llvm-svn: 303210
I ran the test-suite (including SPEC 2006) in PGO mode comparing cold
thresholds of 225 and 45. Here are some stats on the text size:
Out of 904 tests that ran, 197 see a change in text size. The average
text size reduction (of all the 904 binaries) is 1.07%. Of the 197
binaries, 19 see a text size increase, as high as 18%, but most of them
are small single source benchmarks. There are 3 multisource benchmarks
with a >0.5% size increase (0.7, 1.3 and 2.1 are their % increases). On
the other side of the spectrum, 31 benchmarks see >10% size reduction
and 6 of them are MultiSource.
I haven't run the test-suite with other values of inlinecold-threshold.
Since we have a cold callsite threshold of 45, I picked this value.
Differential revision: https://reviews.llvm.org/D33106
llvm-svn: 302829
Summary:
The motivation example is like below which has 13 cases but only 2 distinct targets
```
lor.lhs.false2: ; preds = %if.then
switch i32 %Status, label %if.then27 [
i32 -7012, label %if.end35
i32 -10008, label %if.end35
i32 -10016, label %if.end35
i32 15000, label %if.end35
i32 14013, label %if.end35
i32 10114, label %if.end35
i32 10107, label %if.end35
i32 10105, label %if.end35
i32 10013, label %if.end35
i32 10011, label %if.end35
i32 7008, label %if.end35
i32 7007, label %if.end35
i32 5002, label %if.end35
]
```
which is compiled into a balanced binary tree like this on AArch64 (similar on X86)
```
.LBB853_9: // %lor.lhs.false2
mov w8, #10012
cmp w19, w8
b.gt .LBB853_14
// BB#10: // %lor.lhs.false2
mov w8, #5001
cmp w19, w8
b.gt .LBB853_18
// BB#11: // %lor.lhs.false2
mov w8, #-10016
cmp w19, w8
b.eq .LBB853_23
// BB#12: // %lor.lhs.false2
mov w8, #-10008
cmp w19, w8
b.eq .LBB853_23
// BB#13: // %lor.lhs.false2
mov w8, #-7012
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_14: // %lor.lhs.false2
mov w8, #14012
cmp w19, w8
b.gt .LBB853_21
// BB#15: // %lor.lhs.false2
mov w8, #-10105
add w8, w19, w8
cmp w8, #9 // =9
b.hi .LBB853_17
// BB#16: // %lor.lhs.false2
orr w9, wzr, #0x1
lsl w8, w9, w8
mov w9, #517
and w8, w8, w9
cbnz w8, .LBB853_23
.LBB853_17: // %lor.lhs.false2
mov w8, #10013
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_18: // %lor.lhs.false2
mov w8, #-7007
add w8, w19, w8
cmp w8, #2 // =2
b.lo .LBB853_23
// BB#19: // %lor.lhs.false2
mov w8, #5002
cmp w19, w8
b.eq .LBB853_23
// BB#20: // %lor.lhs.false2
mov w8, #10011
cmp w19, w8
b.eq .LBB853_23
b .LBB853_3
.LBB853_21: // %lor.lhs.false2
mov w8, #14013
cmp w19, w8
b.eq .LBB853_23
// BB#22: // %lor.lhs.false2
mov w8, #15000
cmp w19, w8
b.ne .LBB853_3
```
However, the inline cost model estimates the cost to be linear with the number
of distinct targets and the cost of the above switch is just 2 InstrCosts.
The function containing this switch is then inlined about 900 times.
This change use the general way of switch lowering for the inline heuristic. It
etimate the number of case clusters with the suitability check for a jump table
or bit test. Considering the binary search tree built for the clusters, this
change modifies the model to be linear with the size of the balanced binary
tree. The model is off by default for now :
-inline-generic-switch-cost=false
This change was originally proposed by Haicheng in D29870.
Reviewers: hans, bmakam, chandlerc, eraman, haicheng, mcrosier
Reviewed By: hans
Subscribers: joerg, aemerson, llvm-commits, rengolin
Differential Revision: https://reviews.llvm.org/D31085
llvm-svn: 301649
This avoids the confusing 'CS.paramHasAttr(ArgNo + 1, Foo)' pattern.
Previously we were testing return value attributes with index 0, so I
introduced hasReturnAttr() for that use case.
llvm-svn: 300367
and to expose a handle to represent the actual case rather than having
the iterator return a reference to itself.
All of this allows the iterator to be used with common STL facilities,
standard algorithms, etc.
Doing this exposed some missing facilities in the iterator facade that
I've fixed and required some work to the actual iterator to fully
support the necessary API.
Differential Revision: https://reviews.llvm.org/D31548
llvm-svn: 300032
Summary: Because SamplePGO passes will be invoked twice in ThinLTO build: once at compile phase, the other at backend. We want to make sure the IR at the 2nd phase matches the hot part in profile, thus we do not want to inline hot callsites in the first phase.
Reviewers: tejohnson, eraman
Reviewed By: tejohnson
Subscribers: mehdi_amini, llvm-commits, Prazek
Differential Revision: https://reviews.llvm.org/D31201
llvm-svn: 298428
Several visitors check if operands to the instruction are constants,
either as it is or after looking up SimplifiedValues, check if the
result is a constant and update the SimplifiedValues map. This
refactoring splits it into a common function that does the checking of
whether the operands are constants and updating of the SimplifiedValues
table, and an instruction specific part that is implemented by each
instruction visitor as a lambda and passed to the common function.
Differential revision: https://reviews.llvm.org/D30104
llvm-svn: 295552
This adds the following to the new PM based inliner in PGO mode:
* Use block frequency analysis to derive callsite's profile count and use
that to adjust thresholds of hot and cold callsites.
* Incrementally update the BFI of the caller after a callee gets inlined
into it. This incremental update is only within an invocation of the run
method - BFI is not preserved across calls to run.
Update the function entry count of the callee after inlining it into a
caller.
* I've tuned the thresholds for the hot and cold callsites using a hacked
up version of the old inliner that explicitly computes BFI on a set of
internal benchmarks and spec. Once the new PM based pipeline stabilizes
(IIRC Chandler mentioned there are known issues) I'll benchmark this
again and adjust the thresholds if required.
Inliner PGO support.
Differential revision: https://reviews.llvm.org/D28331
llvm-svn: 292666
This is the third attemp to recommit r292526.
The original summary:
Currently, a GEP is considered free only if its indices are all constant.
TTI::getGEPCost() can give target-specific more accurate analysis. TTI is
already used for the cost of many other instructions.
llvm-svn: 292633
This is the second attemp to recommit r292526.
The original summary:
Currently, a GEP is considered free only if its indices are all constant.
TTI::getGEPCost() can give target-specific more accurate analysis. TTI is
already used for the cost of many other instructions.
llvm-svn: 292616
This recommits r292526 which is reverted in r292529 after fixing the test case.
The original summary:
Currently, a GEP is considered free only if its indices are all constant.
TTI::getGEPCost() can give target-specific more accurate analysis. TTI is
already used for the cost of many other instructions.
llvm-svn: 292570
Currently, a GEP is considered free only if its indices are all constant.
TTI::getGEPCost() can give target-specific more accurate analysis. TTI is
already used for the cost of many other instructions.
Differential Revision: https://reviews.llvm.org/D28693
llvm-svn: 292526
Functional change: Previously, if a callee is cold, we used ColdThreshold if it minimizes the existing threshold. This was irrespective of whether we were optimizing for minsize (-Oz) or not. But -Oz uses very low threshold to begin with and the inlining with -Oz is expected to be tuned for lowering code size, so there is no good reason to set an even lower threshold for cold callees. We now lower the threshold for cold callees only when -Oz is not used. For default values of -inlinethreshold and -inlinecold-threshold, this change has no effect and this simplifies the code.
NFC changes: Group all threshold updates that are guarded by !Caller->optForMinSize() and within that group threshold updates that require profile summary info.
Differential revision: https://reviews.llvm.org/D28369
llvm-svn: 291487
This doesn't implement *every* feature of the existing inliner, but
tries to implement the most important ones for building a functional
optimization pipeline and beginning to sort out bugs, regressions, and
other problems.
Notable, but intentional omissions:
- No alloca merging support. Why? Because it isn't clear we want to do
this at all. Active discussion and investigation is going on to remove
it, so for simplicity I omitted it.
- No support for trying to iterate on "internally" devirtualized calls.
Why? Because it adds what I suspect is inappropriate coupling for
little or no benefit. We will have an outer iteration system that
tracks devirtualization including that from function passes and
iterates already. We should improve that rather than approximate it
here.
- Optimization remarks. Why? Purely to make the patch smaller, no other
reason at all.
The last one I'll probably work on almost immediately. But I wanted to
skip it in the initial patch to try to focus the change as much as
possible as there is already a lot of code moving around and both of
these *could* be skipped without really disrupting the core logic.
A summary of the different things happening here:
1) Adding the usual new PM class and rigging.
2) Fixing minor underlying assumptions in the inline cost analysis or
inline logic that don't generally hold in the new PM world.
3) Adding the core pass logic which is in essence a loop over the calls
in the nodes in the call graph. This is a bit duplicated from the old
inliner, but only a handful of lines could realistically be shared.
(I tried at first, and it really didn't help anything.) All told,
this is only about 100 lines of code, and most of that is the
mechanics of wiring up analyses from the new PM world.
4) Updating the LazyCallGraph (in the new PM) based on the *newly
inlined* calls and references. This is very minimal because we cannot
form cycles.
5) When inlining removes the last use of a function, eagerly nuking the
body of the function so that any "one use remaining" inline cost
heuristics are immediately refined, and queuing these functions to be
completely deleted once inlining is complete and the call graph
updated to reflect that they have become dead.
6) After all the inlining for a particular function, updating the
LazyCallGraph and the CGSCC pass manager to reflect the
function-local simplifications that are done immediately and
internally by the inline utilties. These are the exact same
fundamental set of CG updates done by arbitrary function passes.
7) Adding a bunch of test cases to specifically target CGSCC and other
subtle aspects in the new PM world.
Many thanks to the careful review from Easwaran and Sanjoy and others!
Differential Revision: https://reviews.llvm.org/D24226
llvm-svn: 290161
After r289755, the AssumptionCache is no longer needed. Variables affected by
assumptions are now found by using the new operand-bundle-based scheme. This
new scheme is more computationally efficient, and also we need much less
code...
llvm-svn: 289756
Instead, expose whether the current type is an array or a struct, if an array
what the upper bound is, and if a struct the struct type itself. This is
in preparation for a later change which will make PointerType derive from
Type rather than SequentialType.
Differential Revision: https://reviews.llvm.org/D26594
llvm-svn: 288458
When calculating the cost of a call instruction we were applying a heuristic penalty as well as the cost of the instruction itself.
However, when calculating the benefit from inlining we weren't discounting the equivalent penalty for the call instruction that would be removed! This caused skew in the calculation and meant we wouldn't inline in the following, trivial case:
int g() {
h();
}
int f() {
g();
}
llvm-svn: 286814
Summary:
I think it is much better this way.
When I firstly saw line:
Cost += InlineConstants::LastCallToStaticBonus;
I though that this is a bug, because everywhere where the cost is being reduced
it is usuing -=.
Reviewers: eraman, tejohnson, mehdi_amini
Subscribers: llvm-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D23222
llvm-svn: 278290
This adds an InlineParams struct which is populated from the command line options by getInlineParams and passed to getInlineCost for the call analyzer to use.
Differential revision: https://reviews.llvm.org/D22120
llvm-svn: 278189
Summary: Hot callsites should have higher threshold than inline hints. This patch uses separate threshold parameter for hot callsites.
Reviewers: davidxl, eraman
Subscribers: Prazek, llvm-commits
Differential Revision: https://reviews.llvm.org/D22368
llvm-svn: 277860
This unblocks the new PM part of River's patch in
https://reviews.llvm.org/D22706
Conveniently, this same change was needed for D21921 and so these
changes are just spun out from there.
llvm-svn: 276515
Summary:
For sample-based PGO, using BFI to calculate callsite count is sometime not accurate. This is because with sampling based approach, if a callsite resides in a hot loop deeply nested in a bunch of cold branches, the callsite's BFI frequency would be inaccurately calculated due to lack of samples in the cold branch.
E.g.
if (A1 && A2 && A3 && ..... && A10) {
for (i=0; i < 100000000; i++) {
callsite();
}
}
Assume that A1 to A100 are all 100% taken, and callsite has 1000 samples and thus is considerred hot. Because the loop's trip count is huge, it's normal that all branches outside the loop has no sample at all. As a result, we can only use static branch probability to derive the the frequency of the loop header. Assuming that static heuristic thinks each branch is 50% taken, then the count calculated from BFI will be 1/(2^10) of the actual value.
In order to get more accurate callsite count, we directly annotate the weight on the call instruction, and directly use it when checking callsite hotness.
Note that this mechanism can also be shared by instrumentation based callsite hotness analysis. The side benefit is that it breaks the dependency from Inliner to BFI as call count is embedded in the IR.
Reviewers: davidxl, eraman, dnovillo
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D22118
llvm-svn: 275073
Instead of directly using MaxFunctionCount and function entry count to determine callee hotness, use the isHotFunction/isColdFunction methods provided by ProfileSummaryInfo.
Differential revision: http://reviews.llvm.org/D21045
llvm-svn: 272321
Before r257832, the threshold used by SimpleInliner was explicitly specified or generated from opt levels and passed to the base class Inliner's constructor. There, it was first overridden by explicitly specified -inline-threshold. The refactoring in r257832 did not preserve this behavior for all opt levels. This change brings back the original behavior.
Differential Revision: http://reviews.llvm.org/D20452
llvm-svn: 270153
Eric Christopher