Index: polly/trunk/include/polly/ScopBuilder.h =================================================================== --- polly/trunk/include/polly/ScopBuilder.h +++ polly/trunk/include/polly/ScopBuilder.h @@ -233,7 +233,7 @@ /// /// Consecutive instructions are associated to the same statement until a /// separator is found. - void buildSequentialBlockStmts(BasicBlock *BB); + void buildSequentialBlockStmts(BasicBlock *BB, bool SplitOnStore = false); /// Create one or more ScopStmts for @p BB using equivalence classes. /// Index: polly/trunk/lib/Analysis/ScopBuilder.cpp =================================================================== --- polly/trunk/lib/Analysis/ScopBuilder.cpp +++ polly/trunk/lib/Analysis/ScopBuilder.cpp @@ -103,7 +103,7 @@ cl::desc("Disable multiplicative reductions"), cl::Hidden, cl::ZeroOrMore, cl::init(false), cl::cat(PollyCategory)); -enum class GranularityChoice { BasicBlocks, ScalarIndependence }; +enum class GranularityChoice { BasicBlocks, ScalarIndependence, Stores }; static cl::opt StmtGranularity( "polly-stmt-granularity", @@ -112,7 +112,9 @@ cl::values(clEnumValN(GranularityChoice::BasicBlocks, "bb", "One statement per basic block"), clEnumValN(GranularityChoice::ScalarIndependence, "scalar-indep", - "Scalar independence heuristic")), + "Scalar independence heuristic"), + clEnumValN(GranularityChoice::Stores, "store", + "Store-level granularity")), cl::init(GranularityChoice::BasicBlocks), cl::cat(PollyCategory)); void ScopBuilder::buildPHIAccesses(ScopStmt *PHIStmt, PHINode *PHI, @@ -686,7 +688,7 @@ !canSynthesize(Inst, *scop, &SE, L); } -void ScopBuilder::buildSequentialBlockStmts(BasicBlock *BB) { +void ScopBuilder::buildSequentialBlockStmts(BasicBlock *BB, bool SplitOnStore) { Loop *SurroundingLoop = LI.getLoopFor(BB); int Count = 0; @@ -694,7 +696,8 @@ for (Instruction &Inst : *BB) { if (shouldModelInst(&Inst, SurroundingLoop)) Instructions.push_back(&Inst); - if (Inst.getMetadata("polly_split_after")) { + if (Inst.getMetadata("polly_split_after") || + (SplitOnStore && isa(Inst))) { scop->addScopStmt(BB, SurroundingLoop, Instructions, Count); Count++; Instructions.clear(); @@ -900,6 +903,9 @@ case GranularityChoice::ScalarIndependence: buildEqivClassBlockStmts(BB); break; + case GranularityChoice::Stores: + buildSequentialBlockStmts(BB, true); + break; } } } Index: polly/trunk/test/ScopInfo/stmt_split_on_store.ll =================================================================== --- polly/trunk/test/ScopInfo/stmt_split_on_store.ll +++ polly/trunk/test/ScopInfo/stmt_split_on_store.ll @@ -0,0 +1,62 @@ +; RUN: opt %loadPolly -polly-scops -analyze -polly-stmt-granularity=store -polly-print-instructions < %s | FileCheck %s + +; void func(int *A, int *B){ +; for (int i = 0; i < 1024; i+=1) { +; Stmt: +; A[i] = i; +; B[i] = i; +; } +; } +; +; CHECK: Statements { +; CHECK-NEXT: Stmt_Stmt +; CHECK-NEXT: Domain := +; CHECK-NEXT: { Stmt_Stmt[i0] : 0 <= i0 <= 1023 }; +; CHECK-NEXT: Schedule := +; CHECK-NEXT: { Stmt_Stmt[i0] -> [i0, 0] }; +; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0] +; CHECK-NEXT: { Stmt_Stmt[i0] -> MemRef_A[i0] }; +; CHECK-NEXT: Instructions { +; CHECK-NEXT: store i32 %i.0, i32* %arrayidx, align 4 +; CHECK-NEXT: } +; CHECK-NEXT: Stmt_Stmt1 +; CHECK-NEXT: Domain := +; CHECK-NEXT: { Stmt_Stmt1[i0] : 0 <= i0 <= 1023 }; +; CHECK-NEXT: Schedule := +; CHECK-NEXT: { Stmt_Stmt1[i0] -> [i0, 1] }; +; CHECK-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0] +; CHECK-NEXT: { Stmt_Stmt1[i0] -> MemRef_B[i0] }; +; CHECK-NEXT: Instructions { +; CHECK-NEXT: store i32 %i.0, i32* %arrayidx2, align 4 +; CHECK-NEXT: } +; CHECK-NEXT: } +; +; Function Attrs: noinline nounwind uwtable +define void @func(i32* %A, i32* %B) #0 { +entry: + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %i.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ] + %cmp = icmp slt i32 %i.0, 1024 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + br label %Stmt + +Stmt: ; preds = %for.body + %idxprom = sext i32 %i.0 to i64 + %arrayidx = getelementptr inbounds i32, i32* %A, i64 %idxprom + store i32 %i.0, i32* %arrayidx, align 4 + %idxprom1 = sext i32 %i.0 to i64 + %arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %idxprom1 + store i32 %i.0, i32* %arrayidx2, align 4 + br label %for.inc + +for.inc: ; preds = %Stmt + %add = add nsw i32 %i.0, 1 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +}