mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
029d974b53
Summary:
Two utils methods have essentially the same functionality. This is an attempt to merge them into one.
1. lib/Transforms/Utils/Local.cpp : MergeBasicBlockIntoOnlyPred
2. lib/Transforms/Utils/BasicBlockUtils.cpp : MergeBlockIntoPredecessor
Prior to the patch:
1. MergeBasicBlockIntoOnlyPred
Updates either DomTree or DeferredDominance
Moves all instructions from Pred to BB, deletes Pred
Asserts BB has single predecessor
If address was taken, replace the block address with constant 1 (?)
2. MergeBlockIntoPredecessor
Updates DomTree, LoopInfo and MemoryDependenceResults
Moves all instruction from BB to Pred, deletes BB
Returns if doesn't have a single predecessor
Returns if BB's address was taken
After the patch:
Method 2. MergeBlockIntoPredecessor is attempting to become the new default:
Updates DomTree or DeferredDominance, and LoopInfo and MemoryDependenceResults
Moves all instruction from BB to Pred, deletes BB
Returns if doesn't have a single predecessor
Returns if BB's address was taken
Uses of MergeBasicBlockIntoOnlyPred that need to be replaced:
1. lib/Transforms/Scalar/LoopSimplifyCFG.cpp
Updated in this patch. No challenges.
2. lib/CodeGen/CodeGenPrepare.cpp
Updated in this patch.
i. eliminateFallThrough is straightforward, but I added using a temporary array to avoid the iterator invalidation.
ii. eliminateMostlyEmptyBlock(s) methods also now use a temporary array for blocks
Some interesting aspects:
- Since Pred is not deleted (BB is), the entry block does not need updating.
- The entry block was being updated with the deleted block in eliminateMostlyEmptyBlock. Added assert to make obvious that BB=SinglePred.
- isMergingEmptyBlockProfitable assumes BB is the one to be deleted.
- eliminateMostlyEmptyBlock(BB) does not delete BB on one path, it deletes its unique predecessor instead.
- adding some test owner as subscribers for the interesting tests modified:
test/CodeGen/X86/avx-cmp.ll
test/CodeGen/AMDGPU/nested-loop-conditions.ll
test/CodeGen/AMDGPU/si-annotate-cf.ll
test/CodeGen/X86/hoist-spill.ll
test/CodeGen/X86/2006-11-17-IllegalMove.ll
3. lib/Transforms/Scalar/JumpThreading.cpp
Not covered in this patch. It is the only use case using the DeferredDominance.
I would defer to Brian Rzycki to make this replacement.
Reviewers: chandlerc, spatel, davide, brzycki, bkramer, javed.absar
Subscribers: qcolombet, sanjoy, nemanjai, nhaehnle, jlebar, tpr, kbarton, RKSimon, wmi, arsenm, llvm-commits
Differential Revision: https://reviews.llvm.org/D48202
llvm-svn: 335183
42 lines
1.1 KiB
LLVM
42 lines
1.1 KiB
LLVM
; RUN: opt -passes='loop(loop-instsimplify,simplify-cfg,unswitch),verify<loops>' -S < %s | FileCheck %s
|
|
|
|
declare void @some_func() noreturn
|
|
|
|
define i32 @test1(i32* %var, i1 %cond1, i1 %cond2) {
|
|
; CHECK-LABEL: @test1(
|
|
entry:
|
|
br label %loop_begin
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br i1 %{{.*}}, label %entry.split, label %loop_exit.split
|
|
;
|
|
; CHECK: entry.split:
|
|
; CHECK-NEXT: br i1 %{{.*}}, label %entry.split.split, label %loop_exit
|
|
;
|
|
; CHECK: entry.split.split:
|
|
; CHECK-NEXT: br label %loop_begin
|
|
|
|
loop_begin:
|
|
br i1 %cond1, label %continue, label %loop_exit ; first trivial condition
|
|
|
|
continue:
|
|
%var_val = load i32, i32* %var
|
|
%var_cond = trunc i32 %var_val to i1
|
|
%maybe_cond = select i1 %cond1, i1 %cond2, i1 %var_cond
|
|
br i1 %maybe_cond, label %do_something, label %loop_exit ; second trivial condition
|
|
|
|
do_something:
|
|
call void @some_func() noreturn nounwind
|
|
br label %loop_begin
|
|
; CHECK: loop_begin:
|
|
; CHECK-NEXT: call
|
|
; CHECK-NEXT: br label %loop_begin
|
|
|
|
loop_exit:
|
|
ret i32 0
|
|
; CHECK: loop_exit:
|
|
; CHECK-NEXT: br label %loop_exit.split
|
|
;
|
|
; CHECK: loop_exit.split:
|
|
; CHECK-NEXT: ret
|
|
}
|