2018-02-02 23:54:17 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
|
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X86
|
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64
|
|
|
|
|
|
|
|
|
|
; This tests interaction between MergeICmp and ExpandMemCmp.
|
|
|
|
|
|
|
|
|
|
%"struct.std::pair" = type { i32, i32 }
|
|
|
|
|
|
|
|
|
|
define zeroext i1 @opeq1(
|
|
|
|
|
; X86-LABEL: opeq1:
|
Generalize MergeBlockIntoPredecessor. Replace uses of MergeBasicBlockIntoOnlyPred.
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
2018-06-21 06:01:04 +08:00
|
|
|
; X86: # %bb.0: # %entry
|
2018-02-02 23:54:17 +08:00
|
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
|
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
|
|
|
|
; X86-NEXT: movl (%ecx), %edx
|
|
|
|
|
; X86-NEXT: movl 4(%ecx), %ecx
|
2018-03-19 21:37:04 +08:00
|
|
|
; X86-NEXT: xorl (%eax), %edx
|
|
|
|
|
; X86-NEXT: xorl 4(%eax), %ecx
|
|
|
|
|
; X86-NEXT: orl %edx, %ecx
|
2018-02-02 23:54:17 +08:00
|
|
|
; X86-NEXT: sete %al
|
|
|
|
|
; X86-NEXT: retl
|
|
|
|
|
;
|
|
|
|
|
; X64-LABEL: opeq1:
|
Generalize MergeBlockIntoPredecessor. Replace uses of MergeBasicBlockIntoOnlyPred.
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
2018-06-21 06:01:04 +08:00
|
|
|
; X64: # %bb.0: # %entry
|
2018-03-19 21:37:04 +08:00
|
|
|
; X64-NEXT: movq (%rdi), %rax
|
|
|
|
|
; X64-NEXT: cmpq (%rsi), %rax
|
2018-02-02 23:54:17 +08:00
|
|
|
; X64-NEXT: sete %al
|
|
|
|
|
; X64-NEXT: retq
|
|
|
|
|
%"struct.std::pair"* nocapture readonly dereferenceable(8) %a,
|
|
|
|
|
%"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 {
|
|
|
|
|
entry:
|
|
|
|
|
%first.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 0
|
|
|
|
|
%0 = load i32, i32* %first.i, align 4
|
|
|
|
|
%first1.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 0
|
|
|
|
|
%1 = load i32, i32* %first1.i, align 4
|
|
|
|
|
%cmp.i = icmp eq i32 %0, %1
|
|
|
|
|
br i1 %cmp.i, label %land.rhs.i, label %opeq1.exit
|
|
|
|
|
|
|
|
|
|
land.rhs.i:
|
|
|
|
|
%second.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %a, i64 0, i32 1
|
|
|
|
|
%2 = load i32, i32* %second.i, align 4
|
|
|
|
|
%second2.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 1
|
|
|
|
|
%3 = load i32, i32* %second2.i, align 4
|
|
|
|
|
%cmp3.i = icmp eq i32 %2, %3
|
|
|
|
|
br label %opeq1.exit
|
|
|
|
|
|
|
|
|
|
opeq1.exit:
|
|
|
|
|
%4 = phi i1 [ false, %entry ], [ %cmp3.i, %land.rhs.i ]
|
|
|
|
|
ret i1 %4
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|