Index: llvm/trunk/lib/CodeGen/GlobalMerge.cpp =================================================================== --- llvm/trunk/lib/CodeGen/GlobalMerge.cpp +++ llvm/trunk/lib/CodeGen/GlobalMerge.cpp @@ -49,9 +49,19 @@ // str r0, [r5], #4 // // note that we saved 2 registers here almostly "for free". +// +// However, merging globals can have tradeoffs: +// - it confuses debuggers, tools, and users +// - it makes linker optimizations less useful (order files, LOHs, ...) +// - it forces usage of indexed addressing (which isn't necessarily "free") +// - it can increase register pressure when the uses are disparate enough. +// +// We use heuristics to discover the best global grouping we can (cf cl::opts). // ===---------------------------------------------------------------------===// #include "llvm/Transforms/Scalar.h" +#include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/SmallBitVector.h" #include "llvm/ADT/SmallPtrSet.h" #include "llvm/ADT/Statistic.h" #include "llvm/CodeGen/Passes.h" @@ -66,9 +76,12 @@ #include "llvm/IR/Module.h" #include "llvm/Pass.h" #include "llvm/Support/CommandLine.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/raw_ostream.h" #include "llvm/Target/TargetLowering.h" #include "llvm/Target/TargetLoweringObjectFile.h" #include "llvm/Target/TargetSubtargetInfo.h" +#include using namespace llvm; #define DEBUG_TYPE "global-merge" @@ -79,6 +92,15 @@ cl::desc("Enable the global merge pass"), cl::init(true)); +static cl::opt GlobalMergeGroupByUse( + "global-merge-group-by-use", cl::Hidden, + cl::desc("Improve global merge pass to look at uses"), cl::init(true)); + +static cl::opt GlobalMergeIgnoreSingleUse( + "global-merge-ignore-single-use", cl::Hidden, + cl::desc("Improve global merge pass to ignore globals only used alone"), + cl::init(true)); + static cl::opt EnableGlobalMergeOnConst("global-merge-on-const", cl::Hidden, cl::desc("Enable global merge pass on constants"), @@ -104,6 +126,11 @@ bool doMerge(SmallVectorImpl &Globals, Module &M, bool isConst, unsigned AddrSpace) const; + /// \brief Merge everything in \p Globals for which the corresponding bit + /// in \p GlobalSet is set. + bool doMerge(SmallVectorImpl &Globals, + const BitVector &GlobalSet, Module &M, bool isConst, + unsigned AddrSpace) const; /// \brief Check if the given variable has been identified as must keep /// \pre setMustKeepGlobalVariables must have been called on the Module that @@ -163,26 +190,227 @@ return (DL->getTypeAllocSize(Ty1) < DL->getTypeAllocSize(Ty2)); }); + // If we want to just blindly group all globals together, do so. + if (!GlobalMergeGroupByUse) { + BitVector AllGlobals(Globals.size()); + AllGlobals.set(); + return doMerge(Globals, AllGlobals, M, isConst, AddrSpace); + } + + // If we want to be smarter, look at all uses of each global, to try to + // discover all sets of globals used together, and how many times each of + // these sets occured. + // + // Keep this reasonably efficient, by having an append-only list of all sets + // discovered so far (UsedGlobalSet), and mapping each "together-ness" unit of + // code (currently, a Function) to the set of globals seen so far that are + // used together in that unit (GlobalUsesByFunction). + // + // When we look at the Nth global, we now that any new set is either: + // - the singleton set {N}, containing this global only, or + // - the union of {N} and a previously-discovered set, containing some + // combination of the previous N-1 globals. + // Using that knowledge, when looking at the Nth global, we can keep: + // - a reference to the singleton set {N} (CurGVOnlySetIdx) + // - a list mapping each previous set to its union with {N} (EncounteredUGS), + // if it actually occurs. + + // We keep track of the sets of globals used together "close enough". + struct UsedGlobalSet { + UsedGlobalSet(size_t Size) : Globals(Size), UsageCount(1) {} + BitVector Globals; + unsigned UsageCount; + }; + + // Each set is unique in UsedGlobalSets. + std::vector UsedGlobalSets; + + // Avoid repeating the create-global-set pattern. + auto CreateGlobalSet = [&]() -> UsedGlobalSet & { + UsedGlobalSets.emplace_back(Globals.size()); + return UsedGlobalSets.back(); + }; + + // The first set is the empty set. + CreateGlobalSet().UsageCount = 0; + + // We define "close enough" to be "in the same function". + // FIXME: Grouping uses by function is way too aggressive, so we should have + // a better metric for distance between uses. + // The obvious alternative would be to group by BasicBlock, but that's in + // turn too conservative.. + // Anything in between wouldn't be trivial to compute, so just stick with + // per-function grouping. + + // The value type is an index into UsedGlobalSets. + // The default (0) conveniently points to the empty set. + DenseMap GlobalUsesByFunction; + + // Now, look at each merge-eligible global in turn. + + // Keep track of the sets we already encountered to which we added the + // current global. + // Each element matches the same-index element in UsedGlobalSets. + // This lets us efficiently tell whether a set has already been expanded to + // include the current global. + std::vector EncounteredUGS; + + for (size_t GI = 0, GE = Globals.size(); GI != GE; ++GI) { + GlobalVariable *GV = Globals[GI]; + + // Reset the encountered sets for this global... + std::fill(EncounteredUGS.begin(), EncounteredUGS.end(), 0); + // ...and grow it in case we created new sets for the previous global. + EncounteredUGS.resize(UsedGlobalSets.size()); + + // We might need to create a set that only consists of the current global. + // Keep track of its index into UsedGlobalSets. + size_t CurGVOnlySetIdx = 0; + + // For each global, look at all its Uses. + for (auto &U : GV->uses()) { + // This Use might be a ConstantExpr. We're interested in Instruction + // users, so look through ConstantExpr... + Use *UI, *UE; + if (ConstantExpr *CE = dyn_cast(U.getUser())) { + UI = &*CE->use_begin(); + UE = nullptr; + } else if (isa(U.getUser())) { + UI = &U; + UE = UI->getNext(); + } else { + continue; + } + + // ...to iterate on all the instruction users of the global. + // Note that we iterate on Uses and not on Users to be able to getNext(). + for (; UI != UE; UI = UI->getNext()) { + Instruction *I = dyn_cast(UI->getUser()); + if (!I) + continue; + + Function *ParentFn = I->getParent()->getParent(); + size_t UGSIdx = GlobalUsesByFunction[ParentFn]; + + // If this is the first global the basic block uses, map it to the set + // consisting of this global only. + if (!UGSIdx) { + // If that set doesn't exist yet, create it. + if (!CurGVOnlySetIdx) { + CurGVOnlySetIdx = UsedGlobalSets.size(); + CreateGlobalSet().Globals.set(GI); + } else { + ++UsedGlobalSets[CurGVOnlySetIdx].UsageCount; + } + + GlobalUsesByFunction[ParentFn] = CurGVOnlySetIdx; + continue; + } + + // If we already encountered this BB, just increment the counter. + if (UsedGlobalSets[UGSIdx].Globals.test(GI)) { + ++UsedGlobalSets[UGSIdx].UsageCount; + continue; + } + + // If not, the previous set wasn't actually used in this function. + --UsedGlobalSets[UGSIdx].UsageCount; + + // If we already expanded the previous set to include this global, just + // reuse that expanded set. + if (size_t ExpandedIdx = EncounteredUGS[UGSIdx]) { + ++UsedGlobalSets[ExpandedIdx].UsageCount; + GlobalUsesByFunction[ParentFn] = ExpandedIdx; + continue; + } + + // If not, create a new set consisting of the union of the previous set + // and this global. Mark it as encountered, so we can reuse it later. + GlobalUsesByFunction[ParentFn] = EncounteredUGS[UGSIdx] = + UsedGlobalSets.size(); + + UsedGlobalSet &NewUGS = CreateGlobalSet(); + NewUGS.Globals.set(GI); + NewUGS.Globals |= UsedGlobalSets[UGSIdx].Globals; + } + } + } + + // Now we found a bunch of sets of globals used together. We accumulated + // the number of times we encountered the sets (i.e., the number of blocks + // that use that exact set of globals). + // + // Multiply that by the size of the set to give us a crude profitability + // metric. + std::sort(UsedGlobalSets.begin(), UsedGlobalSets.end(), + [](const UsedGlobalSet &UGS1, const UsedGlobalSet &UGS2) { + return UGS1.Globals.count() * UGS1.UsageCount < + UGS2.Globals.count() * UGS2.UsageCount; + }); + + // We can choose to merge all globals together, but ignore globals never used + // with another global. This catches the obviously non-profitable cases of + // having a single global, but is aggressive enough for any other case. + if (GlobalMergeIgnoreSingleUse) { + BitVector AllGlobals(Globals.size()); + for (size_t i = 0, e = UsedGlobalSets.size(); i != e; ++i) { + const UsedGlobalSet &UGS = UsedGlobalSets[e - i - 1]; + if (UGS.UsageCount == 0) + continue; + if (UGS.Globals.count() > 1) + AllGlobals |= UGS.Globals; + } + return doMerge(Globals, AllGlobals, M, isConst, AddrSpace); + } + + // Starting from the sets with the best (=biggest) profitability, find a + // good combination. + // The ideal (and expensive) solution can only be found by trying all + // combinations, looking for the one with the best profitability. + // Don't be smart about it, and just pick the first compatible combination, + // starting with the sets with the best profitability. + BitVector PickedGlobals(Globals.size()); + bool Changed = false; + + for (size_t i = 0, e = UsedGlobalSets.size(); i != e; ++i) { + const UsedGlobalSet &UGS = UsedGlobalSets[e - i - 1]; + if (UGS.UsageCount == 0) + continue; + if (PickedGlobals.anyCommon(UGS.Globals)) + continue; + PickedGlobals |= UGS.Globals; + // If the set only contains one global, there's no point in merging. + // Ignore the global for inclusion in other sets though, so keep it in + // PickedGlobals. + if (UGS.Globals.count() < 2) + continue; + Changed |= doMerge(Globals, UGS.Globals, M, isConst, AddrSpace); + } + + return Changed; +} + +bool GlobalMerge::doMerge(SmallVectorImpl &Globals, + const BitVector &GlobalSet, Module &M, bool isConst, + unsigned AddrSpace) const { + Type *Int32Ty = Type::getInt32Ty(M.getContext()); assert(Globals.size() > 1); - // FIXME: This simple solution merges globals all together as maximum as - // possible. However, with this solution it would be hard to remove dead - // global symbols at link-time. An alternative solution could be checking - // global symbols references function by function, and make the symbols - // being referred in the same function merged and we would probably need - // to introduce heuristic algorithm to solve the merge conflict from - // different functions. - for (size_t i = 0, e = Globals.size(); i != e; ) { - size_t j = 0; + DEBUG(dbgs() << " Trying to merge set, starts with #" + << GlobalSet.find_first() << "\n"); + + ssize_t i = GlobalSet.find_first(); + while (i != -1) { + ssize_t j = 0; uint64_t MergedSize = 0; std::vector Tys; std::vector Inits; bool HasExternal = false; GlobalVariable *TheFirstExternal = 0; - for (j = i; j != e; ++j) { + for (j = i; j != -1; j = GlobalSet.find_next(j)) { Type *Ty = Globals[j]->getType()->getElementType(); MergedSize += DL->getTypeAllocSize(Ty); if (MergedSize > MaxOffset) { @@ -215,13 +443,13 @@ : "_MergedGlobals", nullptr, GlobalVariable::NotThreadLocal, AddrSpace); - for (size_t k = i; k < j; ++k) { + for (ssize_t k = i, idx = 0; k != j; k = GlobalSet.find_next(k)) { GlobalValue::LinkageTypes Linkage = Globals[k]->getLinkage(); std::string Name = Globals[k]->getName(); Constant *Idx[2] = { ConstantInt::get(Int32Ty, 0), - ConstantInt::get(Int32Ty, k-i) + ConstantInt::get(Int32Ty, idx++) }; Constant *GEP = ConstantExpr::getInBoundsGetElementPtr(MergedTy, MergedGV, Idx); Index: llvm/trunk/test/CodeGen/AArch64/global-merge-group-by-use.ll =================================================================== --- llvm/trunk/test/CodeGen/AArch64/global-merge-group-by-use.ll +++ llvm/trunk/test/CodeGen/AArch64/global-merge-group-by-use.ll @@ -0,0 +1,94 @@ +; RUN: llc -mtriple=aarch64-apple-ios -asm-verbose=false -aarch64-collect-loh=false \ +; RUN: -aarch64-global-merge -global-merge-group-by-use -global-merge-ignore-single-use=false \ +; RUN: %s -o - | FileCheck %s + +; We assume that globals of the same size aren't reordered inside a set. + +; Check that we create two MergedGlobal instances for two functions using +; disjoint sets of globals + +@m1 = internal global i32 0, align 4 +@n1 = internal global i32 0, align 4 + +; CHECK-LABEL: f1: +define void @f1(i32 %a1, i32 %a2) #0 { +; CHECK-NEXT: adrp x8, [[SET1:__MergedGlobals[0-9]*]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET1]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8] +; CHECK-NEXT: ret + store i32 %a1, i32* @m1, align 4 + store i32 %a2, i32* @n1, align 4 + ret void +} + +@m2 = internal global i32 0, align 4 +@n2 = internal global i32 0, align 4 +@o2 = internal global i32 0, align 4 + +; CHECK-LABEL: f2: +define void @f2(i32 %a1, i32 %a2, i32 %a3) #0 { +; CHECK-NEXT: adrp x8, [[SET2:__MergedGlobals[0-9]*]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET2]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8] +; CHECK-NEXT: str w2, [x8, #8] +; CHECK-NEXT: ret + store i32 %a1, i32* @m2, align 4 + store i32 %a2, i32* @n2, align 4 + store i32 %a3, i32* @o2, align 4 + ret void +} + +; Sanity-check (don't worry about cost models) that we pick the biggest subset +; of all global used "together" directly or indirectly. Here, that means +; merging n3, m4, and n4 together, but ignoring m3. + +@m3 = internal global i32 0, align 4 +@n3 = internal global i32 0, align 4 + +; CHECK-LABEL: f3: +define void @f3(i32 %a1, i32 %a2) #0 { +; CHECK-NEXT: adrp x8, _m3@PAGE +; CHECK-NEXT: adrp x9, [[SET3:__MergedGlobals[0-9]*]]@PAGE +; CHECK-NEXT: str w0, [x8, _m3@PAGEOFF] +; CHECK-NEXT: str w1, [x9, [[SET3]]@PAGEOFF] +; CHECK-NEXT: ret + store i32 %a1, i32* @m3, align 4 + store i32 %a2, i32* @n3, align 4 + ret void +} + +@m4 = internal global i32 0, align 4 +@n4 = internal global i32 0, align 4 + +; CHECK-LABEL: f4: +define void @f4(i32 %a1, i32 %a2, i32 %a3) #0 { +; CHECK-NEXT: adrp x8, [[SET3]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET3]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8, #4] +; CHECK-NEXT: str w2, [x8] +; CHECK-NEXT: ret + store i32 %a1, i32* @m4, align 4 + store i32 %a2, i32* @n4, align 4 + store i32 %a3, i32* @n3, align 4 + ret void +} + +; Finally, check that we don't do anything with one-element global sets. +@o5 = internal global i32 0, align 4 + +; CHECK-LABEL: f5: +define void @f5(i32 %a1) #0 { +; CHECK-NEXT: adrp x8, _o5@PAGE +; CHECK-NEXT: str w0, [x8, _o5@PAGEOFF] +; CHECK-NEXT: ret + store i32 %a1, i32* @o5, align 4 + ret void +} + +; CHECK-DAG: .zerofill __DATA,__bss,_o5,4,2 + +; CHECK-DAG: .zerofill __DATA,__bss,[[SET1]],8,3 +; CHECK-DAG: .zerofill __DATA,__bss,[[SET2]],12,3 +; CHECK-DAG: .zerofill __DATA,__bss,[[SET3]],12,3 + +attributes #0 = { nounwind } Index: llvm/trunk/test/CodeGen/AArch64/global-merge-ignore-single-use.ll =================================================================== --- llvm/trunk/test/CodeGen/AArch64/global-merge-ignore-single-use.ll +++ llvm/trunk/test/CodeGen/AArch64/global-merge-ignore-single-use.ll @@ -0,0 +1,63 @@ +; RUN: llc -mtriple=aarch64-apple-ios -asm-verbose=false -aarch64-collect-loh=false \ +; RUN: -aarch64-global-merge -global-merge-group-by-use -global-merge-ignore-single-use \ +; RUN: %s -o - | FileCheck %s + +; We assume that globals of the same size aren't reordered inside a set. + +@m1 = internal global i32 0, align 4 +@n1 = internal global i32 0, align 4 +@o1 = internal global i32 0, align 4 + +; CHECK-LABEL: f1: +define void @f1(i32 %a1, i32 %a2) #0 { +; CHECK-NEXT: adrp x8, [[SET:__MergedGlobals]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8] +; CHECK-NEXT: ret + store i32 %a1, i32* @m1, align 4 + store i32 %a2, i32* @n1, align 4 + ret void +} + +@m2 = internal global i32 0, align 4 +@n2 = internal global i32 0, align 4 + +; CHECK-LABEL: f2: +define void @f2(i32 %a1, i32 %a2, i32 %a3) #0 { +; CHECK-NEXT: adrp x8, [[SET]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8] +; CHECK-NEXT: str w2, [x8, #8] +; CHECK-NEXT: ret + store i32 %a1, i32* @m1, align 4 + store i32 %a2, i32* @n1, align 4 + store i32 %a3, i32* @o1, align 4 + ret void +} + +; CHECK-LABEL: f3: +define void @f3(i32 %a1, i32 %a2) #0 { +; CHECK-NEXT: adrp x8, [[SET]]@PAGE +; CHECK-NEXT: add x8, x8, [[SET]]@PAGEOFF +; CHECK-NEXT: stp w0, w1, [x8, #12] +; CHECK-NEXT: ret + store i32 %a1, i32* @m2, align 4 + store i32 %a2, i32* @n2, align 4 + ret void +} + +@o2 = internal global i32 0, align 4 + +; CHECK-LABEL: f4: +define void @f4(i32 %a1) #0 { +; CHECK-NEXT: adrp x8, _o2@PAGE +; CHECK-NEXT: str w0, [x8, _o2@PAGEOFF] +; CHECK-NEXT: ret + store i32 %a1, i32* @o2, align 4 + ret void +} + +; CHECK-DAG: .zerofill __DATA,__bss,[[SET]],20,4 +; CHECK-DAG: .zerofill __DATA,__bss,_o2,4,2 + +attributes #0 = { nounwind } Index: llvm/trunk/test/CodeGen/ARM/2010-12-15-elf-lcomm.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/2010-12-15-elf-lcomm.ll +++ llvm/trunk/test/CodeGen/ARM/2010-12-15-elf-lcomm.ll @@ -1,6 +1,6 @@ -; RUN: llc %s -mtriple=armv7-linux-gnueabi -O3 -filetype=obj -o - | \ +; RUN: llc %s -mtriple=armv7-linux-gnueabi -filetype=obj -o - | \ ; RUN: llvm-readobj -s -t | FileCheck -check-prefix=OBJ %s -; RUN: llc %s -mtriple=armv7-linux-gnueabi -O3 -o - | \ +; RUN: llc %s -mtriple=armv7-linux-gnueabi -o - | \ ; RUN: FileCheck -check-prefix=ASM %s @@ -12,7 +12,7 @@ ; ASM: .type array00,%object @ @array00 ; ASM-NEXT: .local array00 ; ASM-NEXT: .comm array00,80,1 -; ASM-NEXT: .type _MergedGlobals,%object @ @_MergedGlobals +; ASM-NEXT: .type sum,%object @ @sum ; OBJ: Symbols [ Index: llvm/trunk/test/CodeGen/ARM/2011-01-19-MergedGlobalDbg.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/2011-01-19-MergedGlobalDbg.ll +++ llvm/trunk/test/CodeGen/ARM/2011-01-19-MergedGlobalDbg.ll @@ -1,4 +1,4 @@ -; RUN: llc -O3 -filetype=obj < %s | llvm-dwarfdump -debug-dump=info - | FileCheck %s +; RUN: llc -arm-global-merge -global-merge-group-by-use=false -filetype=obj < %s | llvm-dwarfdump -debug-dump=info - | FileCheck %s target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32" target triple = "thumbv7-apple-darwin10" Index: llvm/trunk/test/CodeGen/ARM/2011-06-29-MergeGlobalsAlign.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/2011-06-29-MergeGlobalsAlign.ll +++ llvm/trunk/test/CodeGen/ARM/2011-06-29-MergeGlobalsAlign.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=thumbv7-apple-darwin10 -O3 | FileCheck %s +; RUN: llc < %s -mtriple=thumbv7-apple-darwin10 -arm-global-merge -global-merge-group-by-use=false | FileCheck %s ; CHECK: .zerofill __DATA,__bss,__MergedGlobals,16,2 @prev = external global [0 x i16] Index: llvm/trunk/test/CodeGen/ARM/2011-08-02-MergedGlobalDbg.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/2011-08-02-MergedGlobalDbg.ll +++ llvm/trunk/test/CodeGen/ARM/2011-08-02-MergedGlobalDbg.ll @@ -1,4 +1,4 @@ -; RUN: llc -O3 -filetype=obj < %s | llvm-dwarfdump -debug-dump=info - | FileCheck %s +; RUN: llc -arm-global-merge -global-merge-group-by-use=false -filetype=obj < %s | llvm-dwarfdump -debug-dump=info - | FileCheck %s ; Check debug info output for merged global. ; DW_AT_location Index: llvm/trunk/test/CodeGen/ARM/global-merge-addrspace.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/global-merge-addrspace.ll +++ llvm/trunk/test/CodeGen/ARM/global-merge-addrspace.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=thumb-apple-darwin -O3 | FileCheck %s +; RUN: llc < %s -mtriple=thumb-apple-darwin -arm-global-merge -global-merge-group-by-use=false | FileCheck %s ; Test the GlobalMerge pass. Check that the pass does not crash when using ; multiple address spaces. Index: llvm/trunk/test/CodeGen/ARM/global-merge.ll =================================================================== --- llvm/trunk/test/CodeGen/ARM/global-merge.ll +++ llvm/trunk/test/CodeGen/ARM/global-merge.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=thumb-apple-darwin -O3 -global-merge-on-const=true | FileCheck %s +; RUN: llc < %s -mtriple=thumb-apple-darwin -arm-global-merge -global-merge-group-by-use=false -global-merge-on-const=true | FileCheck %s ; Test the ARMGlobalMerge pass. Use -march=thumb because it has a small ; value for the maximum offset (127).