mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-01 08:23:21 +01:00
8cacff57bf
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
59 lines
1.3 KiB
LLVM
59 lines
1.3 KiB
LLVM
; RUN: opt -inline < %s -S -o - -inline-threshold=10 | FileCheck %s
|
|
|
|
target datalayout = "p:32:32"
|
|
|
|
define i32 @outer1() {
|
|
; CHECK: @outer1
|
|
; CHECK-NOT: call
|
|
; CHECK: ret i32
|
|
|
|
%ptr = alloca i32
|
|
%ptr1 = getelementptr inbounds i32* %ptr, i32 0
|
|
%ptr2 = getelementptr inbounds i32* %ptr, i32 42
|
|
%result = call i32 @inner1(i32* %ptr1, i32* %ptr2)
|
|
ret i32 %result
|
|
}
|
|
|
|
define i32 @inner1(i32* %begin, i32* %end) {
|
|
%begin.i = ptrtoint i32* %begin to i32
|
|
%end.i = ptrtoint i32* %end to i32
|
|
%distance = sub i32 %end.i, %begin.i
|
|
%icmp = icmp sle i32 %distance, 42
|
|
br i1 %icmp, label %then, label %else
|
|
|
|
then:
|
|
ret i32 3
|
|
|
|
else:
|
|
%t = load i32* %begin
|
|
ret i32 %t
|
|
}
|
|
|
|
define i32 @outer2(i32* %ptr) {
|
|
; Test that an inbounds GEP disables this -- it isn't safe in general as
|
|
; wrapping changes the behavior of lessthan and greaterthan comparisions.
|
|
; CHECK: @outer2
|
|
; CHECK: call i32 @inner2
|
|
; CHECK: ret i32
|
|
|
|
%ptr1 = getelementptr i32* %ptr, i32 0
|
|
%ptr2 = getelementptr i32* %ptr, i32 42
|
|
%result = call i32 @inner2(i32* %ptr1, i32* %ptr2)
|
|
ret i32 %result
|
|
}
|
|
|
|
define i32 @inner2(i32* %begin, i32* %end) {
|
|
%begin.i = ptrtoint i32* %begin to i32
|
|
%end.i = ptrtoint i32* %end to i32
|
|
%distance = sub i32 %end.i, %begin.i
|
|
%icmp = icmp sle i32 %distance, 42
|
|
br i1 %icmp, label %then, label %else
|
|
|
|
then:
|
|
ret i32 3
|
|
|
|
else:
|
|
%t = load i32* %begin
|
|
ret i32 %t
|
|
}
|