Index: lib/CodeGen/TargetPassConfig.cpp =================================================================== --- lib/CodeGen/TargetPassConfig.cpp +++ lib/CodeGen/TargetPassConfig.cpp @@ -94,10 +94,9 @@ "enable-implicit-null-checks", cl::desc("Fold null checks into faulting memory operations"), cl::init(false), cl::Hidden); -static cl::opt - EnableMergeICmps("enable-mergeicmps", - cl::desc("Merge ICmp chains into a single memcmp"), - cl::init(false), cl::Hidden); +static cl::opt DisableMergeICmps("disable-mergeicmps", + cl::desc("Disable MergeICmps Pass"), + cl::init(false), cl::Hidden); static cl::opt PrintLSR("print-lsr-output", cl::Hidden, cl::desc("Print LLVM IR produced by the loop-reduce pass")); static cl::opt PrintISelInput("print-isel-input", cl::Hidden, @@ -596,7 +595,7 @@ // 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()); } Index: test/CodeGen/Generic/llc-start-stop.ll =================================================================== --- test/CodeGen/Generic/llc-start-stop.ll +++ 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 Index: test/CodeGen/PowerPC/memcmp-mergeexpand.ll =================================================================== --- /dev/null +++ test/CodeGen/PowerPC/memcmp-mergeexpand.ll @@ -0,0 +1,40 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-gnu-linux < %s | FileCheck %s -check-prefix=PPC64LE + +; This tests interaction between MergeICmp and ExpandMemCmp. + +%"struct.std::pair" = type { i32, i32 } + +define zeroext i1 @opeq1( +; PPC64LE-LABEL: opeq1: +; 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 { +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 +} + + Index: test/CodeGen/X86/memcmp-mergeexpand.ll =================================================================== --- /dev/null +++ test/CodeGen/X86/memcmp-mergeexpand.ll @@ -0,0 +1,51 @@ +; 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: +; 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: movl 4(%ecx), %ecx +; X86-NEXT: xorl (%eax), %edx +; X86-NEXT: xorl 4(%eax), %ecx +; X86-NEXT: orl %edx, %ecx +; X86-NEXT: sete %al +; X86-NEXT: retl +; +; X64-LABEL: opeq1: +; X64: # %bb.0: # %opeq1.exit +; X64-NEXT: movq (%rdi), %rax +; X64-NEXT: cmpq (%rsi), %rax +; 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 +} + +