[MergeICmps] Re-land 324317 "Enable the MergeICmps Pass by default."

Now that PR36557 is fixed.

llvm-svn: 327840

lib/CodeGen/TargetPassConfig.cpp

@@ -94,10 +94,9 @@ static cl::opt<bool> EnableImplicitNullChecks(
     "enable-implicit-null-checks",
     cl::desc("Fold null checks into faulting memory operations"),
     cl::init(false), cl::Hidden);
-static cl::opt<bool>
-    EnableMergeICmps("enable-mergeicmps",
-                     cl::desc("Merge ICmp chains into a single memcmp"),
-                     cl::init(false), cl::Hidden);
+static cl::opt<bool> DisableMergeICmps("disable-mergeicmps",
+    cl::desc("Disable MergeICmps Pass"),
+    cl::init(false), cl::Hidden);
 static cl::opt<bool> PrintLSR("print-lsr-output", cl::Hidden,
     cl::desc("Print LLVM IR produced by the loop-reduce pass"));
 static cl::opt<bool> PrintISelInput("print-isel-input", cl::Hidden,
@@ -596,7 +595,7 @@ void TargetPassConfig::addIRPasses() {
     // loads and compares. ExpandMemCmpPass then tries to expand those calls
     // into optimally-sized loads and compares. The transforms are enabled by a
     // target lowering hook.
-    if (EnableMergeICmps)
+    if (!DisableMergeICmps)
       addPass(createMergeICmpsPass());
     addPass(createExpandMemCmpPass());
   }

test/CodeGen/Generic/llc-start-stop.ll

@@ -13,15 +13,15 @@
 ; STOP-BEFORE-NOT: Loop Strength Reduction
 
 ; RUN: llc < %s -debug-pass=Structure -start-after=loop-reduce -o /dev/null 2>&1 | FileCheck %s -check-prefix=START-AFTER
-; START-AFTER: -machine-branch-prob -expandmemcmp
+; START-AFTER: -machine-branch-prob -mergeicmps
 ; START-AFTER: FunctionPass Manager
-; START-AFTER-NEXT: Expand memcmp() to load/stores
+; START-AFTER-NEXT: Merge contiguous icmps into a memcmp
 
 ; RUN: llc < %s -debug-pass=Structure -start-before=loop-reduce -o /dev/null 2>&1 | FileCheck %s -check-prefix=START-BEFORE
 ; START-BEFORE: -machine-branch-prob -domtree
 ; START-BEFORE: FunctionPass Manager
 ; START-BEFORE: Loop Strength Reduction
-; START-BEFORE-NEXT: Expand memcmp() to load/stores
+; START-BEFORE-NEXT: Merge contiguous icmps into a memcmp
 
 ; RUN: not llc < %s -start-before=nonexistent -o /dev/null 2>&1 | FileCheck %s -check-prefix=NONEXISTENT-START-BEFORE
 ; RUN: not llc < %s -stop-before=nonexistent -o /dev/null 2>&1 | FileCheck %s -check-prefix=NONEXISTENT-STOP-BEFORE

test/CodeGen/PowerPC/memcmp-mergeexpand.ll

@@ -7,22 +7,12 @@
 
 define zeroext i1 @opeq1(
 ; PPC64LE-LABEL: opeq1:
-; PPC64LE:       # %bb.0: # %entry
-; PPC64LE-NEXT:    lwz 5, 0(3)
-; PPC64LE-NEXT:    lwz 6, 0(4)
-; PPC64LE-NEXT:    cmplw 5, 6
-; PPC64LE-NEXT:    bne 0, .LBB0_2
-; PPC64LE-NEXT:  # %bb.1: # %land.rhs.i
-; PPC64LE-NEXT:    lwz 3, 4(3)
-; PPC64LE-NEXT:    lwz 4, 4(4)
-; PPC64LE-NEXT:    cmpw 3, 4
-; PPC64LE-NEXT:    b .LBB0_3
-; PPC64LE-NEXT:  .LBB0_2:
-; PPC64LE-NEXT:    crxor 2, 2, 2
-; PPC64LE-NEXT:  .LBB0_3: # %opeq1.exit
-; PPC64LE-NEXT:    li 3, 0
-; PPC64LE-NEXT:    li 4, 1
-; PPC64LE-NEXT:    isel 3, 4, 3, 2
+; PPC64LE:       # %bb.0: # %opeq1.exit
+; PPC64LE-NEXT:    ld 3, 0(3)
+; PPC64LE-NEXT:    ld 4, 0(4)
+; PPC64LE-NEXT:    xor 3, 3, 4
+; PPC64LE-NEXT:    cntlzd 3, 3
+; PPC64LE-NEXT:    rldicl 3, 3, 58, 63
 ; PPC64LE-NEXT:    blr
   %"struct.std::pair"* nocapture readonly dereferenceable(8) %a,
   %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 {

test/CodeGen/X86/memcmp-mergeexpand.ll

@@ -8,37 +8,22 @@
 
 define zeroext i1 @opeq1(
 ; X86-LABEL: opeq1:
-; X86:       # %bb.0: # %entry
+; X86:       # %bb.0: # %opeq1.exit
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %edx
-; X86-NEXT:    cmpl (%eax), %edx
-; X86-NEXT:    jne .LBB0_1
-; X86-NEXT:  # %bb.2: # %land.rhs.i
 ; X86-NEXT:    movl 4(%ecx), %ecx
-; X86-NEXT:    cmpl 4(%eax), %ecx
+; X86-NEXT:    xorl (%eax), %edx
+; X86-NEXT:    xorl 4(%eax), %ecx
+; X86-NEXT:    orl %edx, %ecx
 ; X86-NEXT:    sete %al
-; X86-NEXT:    # kill: def $al killed $al killed $eax
-; X86-NEXT:    retl
-; X86-NEXT:  .LBB0_1:
-; X86-NEXT:    xorl %eax, %eax
-; X86-NEXT:    # kill: def $al killed $al killed $eax
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: opeq1:
-; X64:       # %bb.0: # %entry
-; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    cmpl (%rsi), %eax
-; X64-NEXT:    jne .LBB0_1
-; X64-NEXT:  # %bb.2: # %land.rhs.i
-; X64-NEXT:    movl 4(%rdi), %eax
-; X64-NEXT:    cmpl 4(%rsi), %eax
+; X64:       # %bb.0: # %opeq1.exit
+; X64-NEXT:    movq (%rdi), %rax
+; X64-NEXT:    cmpq (%rsi), %rax
 ; X64-NEXT:    sete %al
-; X64-NEXT:    # kill: def $al killed $al killed $eax
-; X64-NEXT:    retq
-; X64-NEXT:  .LBB0_1:
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq
   %"struct.std::pair"* nocapture readonly dereferenceable(8) %a,
   %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 {