Index: llvm/trunk/lib/Transforms/Scalar/MergeICmps.cpp =================================================================== --- llvm/trunk/lib/Transforms/Scalar/MergeICmps.cpp +++ llvm/trunk/lib/Transforms/Scalar/MergeICmps.cpp @@ -28,6 +28,8 @@ #include #include "llvm/ADT/APSInt.h" #include "llvm/Analysis/Loads.h" +#include "llvm/Analysis/TargetLibraryInfo.h" +#include "llvm/Analysis/TargetTransformInfo.h" #include "llvm/IR/Function.h" #include "llvm/IR/IRBuilder.h" #include "llvm/IR/IntrinsicInst.h" @@ -41,8 +43,6 @@ #define DEBUG_TYPE "mergeicmps" -#define MERGEICMPS_DOT_ON - // A BCE atom. struct BCEAtom { BCEAtom() : GEP(nullptr), LoadI(nullptr), Offset() {} @@ -589,22 +589,30 @@ bool runOnFunction(Function &F) override { if (skipFunction(F)) return false; const auto &TLI = getAnalysis().getTLI(); - auto PA = runImpl(F, &TLI); + const auto &TTI = getAnalysis().getTTI(F); + auto PA = runImpl(F, &TLI, &TTI); return !PA.areAllPreserved(); } private: void getAnalysisUsage(AnalysisUsage &AU) const override { AU.addRequired(); + AU.addRequired(); } - PreservedAnalyses runImpl(Function &F, const TargetLibraryInfo *TLI); + PreservedAnalyses runImpl(Function &F, const TargetLibraryInfo *TLI, + const TargetTransformInfo *TTI); }; -PreservedAnalyses MergeICmps::runImpl(Function &F, - const TargetLibraryInfo *TLI) { +PreservedAnalyses MergeICmps::runImpl(Function &F, const TargetLibraryInfo *TLI, + const TargetTransformInfo *TTI) { DEBUG(dbgs() << "MergeICmpsPass: " << F.getName() << "\n"); + // We only try merging comparisons if the target wants to expand memcmp later. + // The rationale is to avoid turning small chains into memcmp calls. + unsigned MaxLoadSize; + if (!TTI->enableMemCmpExpansion(MaxLoadSize)) return PreservedAnalyses::all(); + bool MadeChange = false; for (auto BBIt = ++F.begin(); BBIt != F.end(); ++BBIt) { @@ -623,6 +631,7 @@ INITIALIZE_PASS_BEGIN(MergeICmps, "mergeicmps", "Merge contiguous icmps into a memcmp", false, false) INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass) +INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass) INITIALIZE_PASS_END(MergeICmps, "mergeicmps", "Merge contiguous icmps into a memcmp", false, false) Index: llvm/trunk/test/Transforms/MergeICmps/X86/lit.local.cfg =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/X86/lit.local.cfg +++ llvm/trunk/test/Transforms/MergeICmps/X86/lit.local.cfg @@ -0,0 +1,3 @@ +if not 'X86' in config.root.targets: + config.unsupported = True + Index: llvm/trunk/test/Transforms/MergeICmps/X86/pair-int32-int32.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/X86/pair-int32-int32.ll +++ llvm/trunk/test/Transforms/MergeICmps/X86/pair-int32-int32.ll @@ -0,0 +1,91 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mergeicmps -mtriple=x86_64-unknown-unknown -S | FileCheck %s --check-prefix=X86 + +%"struct.std::pair" = type { i32, i32 } + +define zeroext i1 @opeq1( +; X86-LABEL: @opeq1( +; X86-NEXT: entry: +; X86-NEXT: [[FIRST_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A:%.*]], i64 0, i32 0 +; X86-NEXT: [[FIRST1_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B:%.*]], i64 0, i32 0 +; X86-NEXT: [[CSTR:%.*]] = bitcast i32* [[FIRST_I]] to i8* +; X86-NEXT: [[CSTR1:%.*]] = bitcast i32* [[FIRST1_I]] to i8* +; X86-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[CSTR]], i8* [[CSTR1]], i64 8) +; X86-NEXT: [[TMP0:%.*]] = icmp eq i32 [[MEMCMP]], 0 +; X86-NEXT: br label [[OPEQ1_EXIT:%.*]] +; X86: opeq1.exit: +; X86-NEXT: [[TMP1:%.*]] = phi i1 [ [[TMP0]], [[ENTRY:%.*]] ] +; X86-NEXT: ret i1 [[TMP1]] +; + %"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 +; The entry block with zero-offset GEPs is kept, loads are removed. +; The two 4 byte loads and compares are replaced with a single 8-byte memcmp. +; The branch is now a direct branch; the other block has been removed. +; The phi is updated. +} + +; Same as above, but the two blocks are in inverse order. +define zeroext i1 @opeq1_inverse( +; X86-LABEL: @opeq1_inverse( +; X86-NEXT: land.rhs.i: +; X86-NEXT: [[SECOND_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A:%.*]], i64 0, i32 0 +; X86-NEXT: [[SECOND2_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B:%.*]], i64 0, i32 0 +; X86-NEXT: [[CSTR:%.*]] = bitcast i32* [[SECOND_I]] to i8* +; X86-NEXT: [[CSTR1:%.*]] = bitcast i32* [[SECOND2_I]] to i8* +; X86-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[CSTR]], i8* [[CSTR1]], i64 8) +; X86-NEXT: [[TMP0:%.*]] = icmp eq i32 [[MEMCMP]], 0 +; X86-NEXT: br label [[OPEQ1_EXIT:%.*]] +; X86: opeq1.exit: +; X86-NEXT: [[TMP1:%.*]] = phi i1 [ [[TMP0]], [[LAND_RHS_I:%.*]] ] +; X86-NEXT: ret i1 [[TMP1]] +; + %"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 1 + %0 = load i32, i32* %first.i, align 4 + %first1.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 1 + %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 0 + %2 = load i32, i32* %second.i, align 4 + %second2.i = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* %b, i64 0, i32 0 + %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 +; The second block with zero-offset GEPs is kept, loads are removed. +; CHECK: land.rhs.i +; The two 4 byte loads and compares are replaced with a single 8-byte memcmp. +; The branch is now a direct branch; the other block has been removed. +; The phi is updated. +} + + + Index: llvm/trunk/test/Transforms/MergeICmps/X86/tuple-four-int8.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/X86/tuple-four-int8.ll +++ llvm/trunk/test/Transforms/MergeICmps/X86/tuple-four-int8.ll @@ -0,0 +1,92 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mergeicmps -mtriple=x86_64-unknown-unknown -S | FileCheck %s + +; This is a more involved test: clang generates this weird pattern for +; tuple. Right now we skip the entry block +; (which defines the base pointer for other blocks) and the last one (which +; does not have the expected structure). Only middle blocks (bytes [1,2]) are +; merged. + +%"class.std::tuple" = type { %"struct.std::_Tuple_impl" } +%"struct.std::_Tuple_impl" = type { %"struct.std::_Tuple_impl.0", %"struct.std::_Head_base.6" } +%"struct.std::_Tuple_impl.0" = type { %"struct.std::_Tuple_impl.1", %"struct.std::_Head_base.5" } +%"struct.std::_Tuple_impl.1" = type { %"struct.std::_Tuple_impl.2", %"struct.std::_Head_base.4" } +%"struct.std::_Tuple_impl.2" = type { %"struct.std::_Head_base" } +%"struct.std::_Head_base" = type { i8 } +%"struct.std::_Head_base.4" = type { i8 } +%"struct.std::_Head_base.5" = type { i8 } +%"struct.std::_Head_base.6" = type { i8 } + +define zeroext i1 @opeq( +; CHECK-LABEL: @opeq( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* [[A:%.*]], i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 +; CHECK-NEXT: [[ADD_PTR_I_I_I_I_I:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 3 +; CHECK-NEXT: [[TMP1:%.*]] = load i8, i8* [[ADD_PTR_I_I_I_I_I]], align 1 +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* [[B:%.*]], i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 +; CHECK-NEXT: [[ADD_PTR_I_I_I6_I_I:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i64 3 +; CHECK-NEXT: [[TMP3:%.*]] = load i8, i8* [[ADD_PTR_I_I_I6_I_I]], align 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8 [[TMP1]], [[TMP3]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[LAND_RHS_I_I_I_I:%.*]], label [[OPEQ_EXIT:%.*]] +; CHECK: land.rhs.i.i.i: +; CHECK-NEXT: [[ADD_PTR_I_I_I_I_I_I_I:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 1 +; CHECK-NEXT: [[ADD_PTR_I_I_I6_I_I_I_I:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i64 1 +; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[ADD_PTR_I_I_I6_I_I_I_I]], i8* [[ADD_PTR_I_I_I_I_I_I_I]], i64 2) +; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[MEMCMP]], 0 +; CHECK-NEXT: br label [[OPEQ_EXIT]] +; CHECK: land.rhs.i.i.i.i: +; CHECK-NEXT: [[TMP5:%.*]] = load i8, i8* [[TMP0]], align 1 +; CHECK-NEXT: [[TMP6:%.*]] = load i8, i8* [[TMP2]], align 1 +; CHECK-NEXT: [[CMP_I_I_I_I_I:%.*]] = icmp eq i8 [[TMP5]], [[TMP6]] +; CHECK-NEXT: br i1 [[CMP_I_I_I_I_I]], label [[LAND_RHS_I_I_I:%.*]], label [[OPEQ_EXIT]] +; CHECK: opeq.exit: +; CHECK-NEXT: [[TMP7:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[CMP_I_I_I_I_I]], [[LAND_RHS_I_I_I_I]] ], [ [[TMP4]], [[LAND_RHS_I_I_I]] ] +; CHECK-NEXT: ret i1 [[TMP7]] +; + %"class.std::tuple"* nocapture readonly dereferenceable(4) %a, + %"class.std::tuple"* nocapture readonly dereferenceable(4) %b) local_unnamed_addr #1 { +entry: + %0 = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* %a, i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 + %add.ptr.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 3 + %1 = load i8, i8* %add.ptr.i.i.i.i.i, align 1 + %2 = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* %b, i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 + %add.ptr.i.i.i6.i.i = getelementptr inbounds i8, i8* %2, i64 3 + %3 = load i8, i8* %add.ptr.i.i.i6.i.i, align 1 + %cmp.i.i = icmp eq i8 %1, %3 + br i1 %cmp.i.i, label %land.rhs.i.i, label %opeq.exit + +land.rhs.i.i: + %add.ptr.i.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 2 + %4 = load i8, i8* %add.ptr.i.i.i.i.i.i, align 1 + %add.ptr.i.i.i6.i.i.i = getelementptr inbounds i8, i8* %2, i64 2 + %5 = load i8, i8* %add.ptr.i.i.i6.i.i.i, align 1 + %cmp.i.i.i = icmp eq i8 %4, %5 + br i1 %cmp.i.i.i, label %land.rhs.i.i.i, label %opeq.exit + +land.rhs.i.i.i: + %add.ptr.i.i.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 1 + %6 = load i8, i8* %add.ptr.i.i.i.i.i.i.i, align 1 + %add.ptr.i.i.i6.i.i.i.i = getelementptr inbounds i8, i8* %2, i64 1 + %7 = load i8, i8* %add.ptr.i.i.i6.i.i.i.i, align 1 + %cmp.i.i.i.i = icmp eq i8 %6, %7 + br i1 %cmp.i.i.i.i, label %land.rhs.i.i.i.i, label %opeq.exit + +land.rhs.i.i.i.i: + %8 = load i8, i8* %0, align 1 + %9 = load i8, i8* %2, align 1 + %cmp.i.i.i.i.i = icmp eq i8 %8, %9 + br label %opeq.exit + +opeq.exit: + %10 = phi i1 [ false, %entry ], [ false, %land.rhs.i.i ], [ false, %land.rhs.i.i.i ], [ %cmp.i.i.i.i.i, %land.rhs.i.i.i.i ] + ret i1 %10 +; The entry block is kept as is, but the next block is now the merged comparison +; block for bytes [1,2] or the block for the head. +; The two 1 byte loads and compares at offset 1 are replaced with a single +; 2-byte memcmp. +; In the end we have three blocks. +; CHECK-SAME %entry +; CHECK-SAME %land.rhs.i.i.i.i +; CHECK-SAME %land.rhs.i.i.i +} + Index: llvm/trunk/test/Transforms/MergeICmps/X86/volatile.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/X86/volatile.ll +++ llvm/trunk/test/Transforms/MergeICmps/X86/volatile.ll @@ -0,0 +1,48 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mergeicmps -mtriple=x86_64-unknown-unknown -S | FileCheck %s + +%"struct.std::pair" = type { i32, i32 } + +define zeroext i1 @opeq( +; CHECK-LABEL: @opeq( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[FIRST_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[FIRST_I]], align 4 +; CHECK-NEXT: [[FIRST1_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B:%.*]], i64 0, i32 0 +; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[FIRST1_I]], align 4 +; CHECK-NEXT: [[CMP_I:%.*]] = icmp eq i32 [[TMP0]], [[TMP1]] +; CHECK-NEXT: br i1 [[CMP_I]], label [[LAND_RHS_I:%.*]], label [[OPEQ1_EXIT:%.*]] +; CHECK: land.rhs.i: +; CHECK-NEXT: [[SECOND_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A]], i64 0, i32 1 +; CHECK-NEXT: [[TMP2:%.*]] = load volatile i32, i32* [[SECOND_I]], align 4 +; CHECK-NEXT: [[SECOND2_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B]], i64 0, i32 1 +; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[SECOND2_I]], align 4 +; CHECK-NEXT: [[CMP3_I:%.*]] = icmp eq i32 [[TMP2]], [[TMP3]] +; CHECK-NEXT: br label [[OPEQ1_EXIT]] +; CHECK: opeq1.exit: +; CHECK-NEXT: [[TMP4:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[CMP3_I]], [[LAND_RHS_I]] ] +; CHECK-NEXT: ret i1 [[TMP4]] +; + %"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 volatile 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: llvm/trunk/test/Transforms/MergeICmps/pair-int32-int32.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/pair-int32-int32.ll +++ llvm/trunk/test/Transforms/MergeICmps/pair-int32-int32.ll @@ -1,10 +1,30 @@ -; RUN: opt -mergeicmps -S -o - %s | FileCheck %s +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -mergeicmps -S | FileCheck %s --check-prefix=NOEXPANSION %"struct.std::pair" = type { i32, i32 } define zeroext i1 @opeq1( - %"struct.std::pair"* nocapture readonly dereferenceable(8) %a, - %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 { +; NOEXPANSION-LABEL: @opeq1( +; NOEXPANSION-NEXT: entry: +; NOEXPANSION-NEXT: [[FIRST_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A:%.*]], i64 0, i32 0 +; NOEXPANSION-NEXT: [[TMP0:%.*]] = load i32, i32* [[FIRST_I]], align 4 +; NOEXPANSION-NEXT: [[FIRST1_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B:%.*]], i64 0, i32 0 +; NOEXPANSION-NEXT: [[TMP1:%.*]] = load i32, i32* [[FIRST1_I]], align 4 +; NOEXPANSION-NEXT: [[CMP_I:%.*]] = icmp eq i32 [[TMP0]], [[TMP1]] +; NOEXPANSION-NEXT: br i1 [[CMP_I]], label [[LAND_RHS_I:%.*]], label [[OPEQ1_EXIT:%.*]] +; NOEXPANSION: land.rhs.i: +; NOEXPANSION-NEXT: [[SECOND_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A]], i64 0, i32 1 +; NOEXPANSION-NEXT: [[TMP2:%.*]] = load i32, i32* [[SECOND_I]], align 4 +; NOEXPANSION-NEXT: [[SECOND2_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B]], i64 0, i32 1 +; NOEXPANSION-NEXT: [[TMP3:%.*]] = load i32, i32* [[SECOND2_I]], align 4 +; NOEXPANSION-NEXT: [[CMP3_I:%.*]] = icmp eq i32 [[TMP2]], [[TMP3]] +; NOEXPANSION-NEXT: br label [[OPEQ1_EXIT]] +; NOEXPANSION: opeq1.exit: +; NOEXPANSION-NEXT: [[TMP4:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[CMP3_I]], [[LAND_RHS_I]] ] +; NOEXPANSION-NEXT: ret i1 [[TMP4]] +; + %"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 @@ -24,28 +44,31 @@ opeq1.exit: %4 = phi i1 [ false, %entry ], [ %cmp3.i, %land.rhs.i ] ret i1 %4 -; CHECK-LABEL: @opeq1( -; The entry block with zero-offset GEPs is kept, loads are removed. -; CHECK: entry -; CHECK: getelementptr {{.*}} i32 0 -; CHECK-NOT: load -; CHECK: getelementptr {{.*}} i32 0 -; CHECK-NOT: load -; The two 4 byte loads and compares are replaced with a single 8-byte memcmp. -; CHECK: @memcmp({{.*}}8) -; CHECK: icmp eq {{.*}} 0 -; The branch is now a direct branch; the other block has been removed. -; CHECK: br label %opeq1.exit -; CHECK-NOT: br -; The phi is updated. -; CHECK: phi i1 [ %{{[^,]*}}, %entry ] -; CHECK-NEXT: ret } ; Same as above, but the two blocks are in inverse order. define zeroext i1 @opeq1_inverse( - %"struct.std::pair"* nocapture readonly dereferenceable(8) %a, - %"struct.std::pair"* nocapture readonly dereferenceable(8) %b) local_unnamed_addr #0 { +; NOEXPANSION-LABEL: @opeq1_inverse( +; NOEXPANSION-NEXT: entry: +; NOEXPANSION-NEXT: [[FIRST_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A:%.*]], i64 0, i32 1 +; NOEXPANSION-NEXT: [[TMP0:%.*]] = load i32, i32* [[FIRST_I]], align 4 +; NOEXPANSION-NEXT: [[FIRST1_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B:%.*]], i64 0, i32 1 +; NOEXPANSION-NEXT: [[TMP1:%.*]] = load i32, i32* [[FIRST1_I]], align 4 +; NOEXPANSION-NEXT: [[CMP_I:%.*]] = icmp eq i32 [[TMP0]], [[TMP1]] +; NOEXPANSION-NEXT: br i1 [[CMP_I]], label [[LAND_RHS_I:%.*]], label [[OPEQ1_EXIT:%.*]] +; NOEXPANSION: land.rhs.i: +; NOEXPANSION-NEXT: [[SECOND_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[A]], i64 0, i32 0 +; NOEXPANSION-NEXT: [[TMP2:%.*]] = load i32, i32* [[SECOND_I]], align 4 +; NOEXPANSION-NEXT: [[SECOND2_I:%.*]] = getelementptr inbounds %"struct.std::pair", %"struct.std::pair"* [[B]], i64 0, i32 0 +; NOEXPANSION-NEXT: [[TMP3:%.*]] = load i32, i32* [[SECOND2_I]], align 4 +; NOEXPANSION-NEXT: [[CMP3_I:%.*]] = icmp eq i32 [[TMP2]], [[TMP3]] +; NOEXPANSION-NEXT: br label [[OPEQ1_EXIT]] +; NOEXPANSION: opeq1.exit: +; NOEXPANSION-NEXT: [[TMP4:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[CMP3_I]], [[LAND_RHS_I]] ] +; NOEXPANSION-NEXT: ret i1 [[TMP4]] +; + %"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 1 %0 = load i32, i32* %first.i, align 4 @@ -65,22 +88,6 @@ opeq1.exit: %4 = phi i1 [ false, %entry ], [ %cmp3.i, %land.rhs.i ] ret i1 %4 -; CHECK-LABEL: @opeq1_inverse( -; The second block with zero-offset GEPs is kept, loads are removed. -; CHECK: land.rhs.i -; CHECK: getelementptr {{.*}} i32 0 -; CHECK-NOT: load -; CHECK: getelementptr {{.*}} i32 0 -; CHECK-NOT: load -; The two 4 byte loads and compares are replaced with a single 8-byte memcmp. -; CHECK: @memcmp({{.*}}8) -; CHECK: icmp eq {{.*}} 0 -; The branch is now a direct branch; the other block has been removed. -; CHECK: br label %opeq1.exit -; CHECK-NOT: br -; The phi is updated. -; CHECK: phi i1 [ %{{[^,]*}}, %land.rhs.i ] -; CHECK-NEXT: ret } Index: llvm/trunk/test/Transforms/MergeICmps/tuple-four-int8.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/tuple-four-int8.ll +++ llvm/trunk/test/Transforms/MergeICmps/tuple-four-int8.ll @@ -1,73 +0,0 @@ -; RUN: opt -mergeicmps -S -o - %s | FileCheck %s - -; This is a more involved test: clang generates this weird pattern for -; tuple. Right now we skip the entry block -; (which defines the base pointer for other blocks) and the last one (which -; does not have the expected structure). Only middle blocks (bytes [1,2]) are -; merged. - -%"class.std::tuple" = type { %"struct.std::_Tuple_impl" } -%"struct.std::_Tuple_impl" = type { %"struct.std::_Tuple_impl.0", %"struct.std::_Head_base.6" } -%"struct.std::_Tuple_impl.0" = type { %"struct.std::_Tuple_impl.1", %"struct.std::_Head_base.5" } -%"struct.std::_Tuple_impl.1" = type { %"struct.std::_Tuple_impl.2", %"struct.std::_Head_base.4" } -%"struct.std::_Tuple_impl.2" = type { %"struct.std::_Head_base" } -%"struct.std::_Head_base" = type { i8 } -%"struct.std::_Head_base.4" = type { i8 } -%"struct.std::_Head_base.5" = type { i8 } -%"struct.std::_Head_base.6" = type { i8 } - -define zeroext i1 @opeq( - %"class.std::tuple"* nocapture readonly dereferenceable(4) %a, - %"class.std::tuple"* nocapture readonly dereferenceable(4) %b) local_unnamed_addr #1 { -entry: - %0 = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* %a, i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 - %add.ptr.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 3 - %1 = load i8, i8* %add.ptr.i.i.i.i.i, align 1 - %2 = getelementptr inbounds %"class.std::tuple", %"class.std::tuple"* %b, i64 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0 - %add.ptr.i.i.i6.i.i = getelementptr inbounds i8, i8* %2, i64 3 - %3 = load i8, i8* %add.ptr.i.i.i6.i.i, align 1 - %cmp.i.i = icmp eq i8 %1, %3 - br i1 %cmp.i.i, label %land.rhs.i.i, label %opeq.exit - -land.rhs.i.i: - %add.ptr.i.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 2 - %4 = load i8, i8* %add.ptr.i.i.i.i.i.i, align 1 - %add.ptr.i.i.i6.i.i.i = getelementptr inbounds i8, i8* %2, i64 2 - %5 = load i8, i8* %add.ptr.i.i.i6.i.i.i, align 1 - %cmp.i.i.i = icmp eq i8 %4, %5 - br i1 %cmp.i.i.i, label %land.rhs.i.i.i, label %opeq.exit - -land.rhs.i.i.i: - %add.ptr.i.i.i.i.i.i.i = getelementptr inbounds i8, i8* %0, i64 1 - %6 = load i8, i8* %add.ptr.i.i.i.i.i.i.i, align 1 - %add.ptr.i.i.i6.i.i.i.i = getelementptr inbounds i8, i8* %2, i64 1 - %7 = load i8, i8* %add.ptr.i.i.i6.i.i.i.i, align 1 - %cmp.i.i.i.i = icmp eq i8 %6, %7 - br i1 %cmp.i.i.i.i, label %land.rhs.i.i.i.i, label %opeq.exit - -land.rhs.i.i.i.i: - %8 = load i8, i8* %0, align 1 - %9 = load i8, i8* %2, align 1 - %cmp.i.i.i.i.i = icmp eq i8 %8, %9 - br label %opeq.exit - -opeq.exit: - %10 = phi i1 [ false, %entry ], [ false, %land.rhs.i.i ], [ false, %land.rhs.i.i.i ], [ %cmp.i.i.i.i.i, %land.rhs.i.i.i.i ] - ret i1 %10 -; CHECK-LABEL: @opeq( -; The entry block is kept as is, but the next block is now the merged comparison -; block for bytes [1,2] or the block for the head. -; CHECK: entry -; CHECK: br i1 %cmp.i.i, label %land.rhs.i.i.i{{(.i)?}}, label %opeq.exit -; The two 1 byte loads and compares at offset 1 are replaced with a single -; 2-byte memcmp. -; CHECK: land.rhs.i.i.i -; CHECK: @memcmp({{.*}}2) -; CHECK: icmp eq {{.*}} 0 -; In the end we have three blocks. -; CHECK: phi i1 -; CHECK-SAME %entry -; CHECK-SAME %land.rhs.i.i.i.i -; CHECK-SAME %land.rhs.i.i.i -} - Index: llvm/trunk/test/Transforms/MergeICmps/volatile.ll =================================================================== --- llvm/trunk/test/Transforms/MergeICmps/volatile.ll +++ llvm/trunk/test/Transforms/MergeICmps/volatile.ll @@ -1,30 +0,0 @@ -; RUN: opt -mergeicmps -S -o - %s | FileCheck %s - -%"struct.std::pair" = type { i32, i32 } - -define zeroext i1 @opeq( - %"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 volatile 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 -; CHECK-LABEL: @opeq( -; CHECK-NOT: memcmp -} -