3099b7eb5d
As mentioned in https://github.com/llvm/llvm-project/pull/145071, LoopInterchange should be part of the optimization pipeline rather than the simplification pipeline. This patch moves LoopInterchange into the optimization pipeline. More contexts: - By default, LoopInterchange attempts to improve data locality, however, it also takes increasing vectorization opportunities into account. Given that, it is reasonable to run it as close to vectorization as possible. - I looked into previous changes related to the placement of LoopInterchange, but couldn’t find any strong motivation suggesting that it benefits other simplifications. - As far as I tried some tests (including llvm-test-suite), removing LoopInterchange from the simplification pipeline does not affect other simplifications. Therefore, there doesn't seem to be much value in keeping it there. - The new position reduces compile-time for ThinLTO, probably because it only runs once per function in post-link optimization, rather than both in pre-link and post-link optimization. I haven't encountered any cases where the positional difference affects optimization results, so please feel free to revert if you run into any issues.
49 lines
1.5 KiB
LLVM
49 lines
1.5 KiB
LLVM
; RUN: opt -passes='default<O3>' -enable-loopinterchange -disable-output \
|
|
; RUN: -disable-verify -verify-analysis-invalidation=0 \
|
|
; RUN: -debug-pass-manager=quiet %s 2>&1 | FileCheck %s
|
|
|
|
; Test the position of LoopInterchange in the pass pipeline.
|
|
|
|
; CHECK-NOT: Running pass: LoopInterchangePass
|
|
; CHECK: Running pass: ControlHeightReductionPass
|
|
; CHECK-NEXT: Running pass: LoopSimplifyPass
|
|
; CHECK-NEXT: Running pass: LCSSAPass
|
|
; CHECK-NEXT: Running pass: LoopRotatePass
|
|
; CHECK-NEXT: Running pass: LoopDeletionPass
|
|
; CHECK-NEXT: Running pass: LoopRotatePass
|
|
; CHECK-NEXT: Running pass: LoopDeletionPass
|
|
; CHECK-NEXT: Running pass: LoopInterchangePass
|
|
; CHECK-NEXT: Running pass: LoopDistributePass
|
|
; CHECK-NEXT: Running pass: InjectTLIMappings
|
|
; CHECK-NEXT: Running pass: LoopVectorizePass
|
|
|
|
|
|
define void @foo(ptr %a, i32 %n) {
|
|
entry:
|
|
br label %for.i.header
|
|
|
|
for.i.header:
|
|
%i = phi i32 [ 0, %entry ], [ %i.next, %for.i.latch ]
|
|
br label %for.j
|
|
|
|
for.j:
|
|
%j = phi i32 [ 0, %for.i.header ], [ %j.next, %for.j ]
|
|
%tmp = mul i32 %i, %n
|
|
%offset = add i32 %tmp, %j
|
|
%idx = getelementptr inbounds i32, ptr %a, i32 %offset
|
|
%load = load i32, ptr %idx, align 4
|
|
%inc = add i32 %load, 1
|
|
store i32 %inc, ptr %idx, align 4
|
|
%j.next = add i32 %j, 1
|
|
%j.exit = icmp eq i32 %j.next, %n
|
|
br i1 %j.exit, label %for.i.latch, label %for.j
|
|
|
|
for.i.latch:
|
|
%i.next = add i32 %i, 1
|
|
%i.exit = icmp eq i32 %i.next, %n
|
|
br i1 %i.exit, label %for.i.header, label %exit
|
|
|
|
exit:
|
|
ret void
|
|
}
|