Revert "[Taildup] Don't tail-duplicate loop header with multiple successors as its latches"

This reverts commit 1f9fa54.

Author: junparser

llvm/lib/CodeGen/TailDuplicator.cpp

@@ -70,12 +70,6 @@ static cl::opt<unsigned> TailDupIndirectBranchSize(
              "end with indirect branches."), cl::init(20),
     cl::Hidden);
 
-static cl::opt<unsigned> TailDupJmpTableLoopSize(
-    "tail-dup-jmptable-loop-size",
-    cl::desc("Maximum loop latches to consider tail duplication that are "
-             "successors of loop header."),
-    cl::init(128), cl::Hidden);
-
 static cl::opt<bool>
     TailDupVerify("tail-dup-verify",
                   cl::desc("Verify sanity of PHI instructions during taildup"),
@@ -569,29 +563,6 @@ bool TailDuplicator::shouldTailDuplicate(bool IsSimple,
   if (TailBB.isSuccessor(&TailBB))
     return false;
 
-  // When doing tail-duplication with jumptable loops like:
-  //    1 -> 2 <-> 3                 |
-  //          \  <-> 4               |
-  //           \   <-> 5             |
-  //            \    <-> ...         |
-  //             \---> rest          |
-  // quadratic number of edges and much more loops are added to CFG. This
-  // may cause compile time regression when jumptable is quiet large.
-  // So set the limit on jumptable cases.
-  auto isLargeJumpTableLoop = [](const MachineBasicBlock &TailBB) {
-    const SmallPtrSet<const MachineBasicBlock *, 8> Preds(TailBB.pred_begin(),
-                                                          TailBB.pred_end());
-    // Check the basic block has large number of successors, all of them only
-    // have one successor which is the basic block itself.
-    return llvm::count_if(
-               TailBB.successors(), [&](const MachineBasicBlock *SuccBB) {
-                 return Preds.count(SuccBB) && SuccBB->succ_size() == 1;
-               }) > TailDupJmpTableLoopSize;
-  };
-
-  if (isLargeJumpTableLoop(TailBB))
-    return false;
-
   // Set the limit on the cost to duplicate. When optimizing for size,
   // duplicate only one, because one branch instruction can be eliminated to
   // compensate for the duplication.

llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll

@@ -1,48 +1,76 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -tail-dup-jmptable-loop-size=5 -mtriple=x86_64-unknown-linux-gnu  | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
 define i8* @large_loop_switch(i8* %p) {
 ; CHECK-LABEL: large_loop_switch:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    .cfi_offset %rbx, -16
-; CHECK-NEXT:    movq %rdi, %rsi
+; CHECK-NEXT:    movq %rdi, %rax
 ; CHECK-NEXT:    movl $6, %ebx
-; CHECK-NEXT:    movl %ebx, %eax
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rax,8)
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:  .LBB0_1: # %for.cond.cleanup
+; CHECK-NEXT:    movl $530, %edi # imm = 0x212
+; CHECK-NEXT:    movq %rax, %rsi
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    jmp ccc@PLT # TAILCALL
+; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  .LBB0_2: # %sw.bb1
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    movl $531, %edi # imm = 0x213
-; CHECK-NEXT:  .LBB0_3: # %for.body
-; CHECK-NEXT:    callq ccc@PLT
-; CHECK-NEXT:  .LBB0_4: # %for.body
 ; CHECK-NEXT:    movq %rax, %rsi
+; CHECK-NEXT:    callq ccc@PLT
 ; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    movl %ebx, %eax
-; CHECK-NEXT:    jmpq *.LJTI0_0(,%rax,8)
-; CHECK-NEXT:  .LBB0_5: # %sw.bb3
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_3: # %sw.bb3
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $532, %edi # imm = 0x214
+; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    jmp .LBB0_4
-; CHECK-NEXT:  .LBB0_7: # %sw.bb5
+; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_4: # %sw.bb5
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $533, %edi # imm = 0x215
+; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    jmp .LBB0_4
-; CHECK-NEXT:  .LBB0_8: # %sw.bb7
+; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_5: # %sw.bb7
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $535, %edi # imm = 0x217
+; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    jmp .LBB0_4
-; CHECK-NEXT:  .LBB0_9: # %sw.bb9
+; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_6: # %sw.bb9
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $536, %edi # imm = 0x218
-; CHECK-NEXT:    jmp .LBB0_3
-; CHECK-NEXT:  .LBB0_10: # %sw.bb11
+; CHECK-NEXT:    movq %rax, %rsi
+; CHECK-NEXT:    callq ccc@PLT
+; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_7: # %sw.bb11
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $658, %edi # imm = 0x292
+; CHECK-NEXT:    movq %rax, %rsi
 ; CHECK-NEXT:    callq bbb@PLT
-; CHECK-NEXT:    jmp .LBB0_4
-; CHECK-NEXT:  .LBB0_11: # %for.cond.cleanup
-; CHECK-NEXT:    movl $530, %edi # imm = 0x212
-; CHECK-NEXT:    popq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
-; CHECK-NEXT:    jmp ccc@PLT # TAILCALL
+; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    movl %ebx, %ecx
+; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
 entry:
   br label %for.body