[delinearize] clear Subscripts and Sizes vectors (NFC)

llvm/lib/Analysis/Delinearization.cpp

@@ -182,7 +182,7 @@ void llvm::collectParametricTerms(ScalarEvolution &SE, const SCEV *Expr,
   LLVM_DEBUG({
     dbgs() << "Strides:\n";
     for (const SCEV *S : Strides)
-      dbgs() << *S << "\n";
+      dbgs() << "  " << *S << "\n";
   });
 
   for (const SCEV *S : Strides) {
@@ -193,7 +193,7 @@ void llvm::collectParametricTerms(ScalarEvolution &SE, const SCEV *Expr,
   LLVM_DEBUG({
     dbgs() << "Terms:\n";
     for (const SCEV *T : Terms)
-      dbgs() << *T << "\n";
+      dbgs() << "  " << *T << "\n";
   });
 
   SCEVCollectAddRecMultiplies MulCollector(Terms, SE);
@@ -294,7 +294,7 @@ void llvm::findArrayDimensions(ScalarEvolution &SE,
   LLVM_DEBUG({
     dbgs() << "Terms:\n";
     for (const SCEV *T : Terms)
-      dbgs() << *T << "\n";
+      dbgs() << "  " << *T << "\n";
   });
 
   // Remove duplicates.
@@ -325,7 +325,7 @@ void llvm::findArrayDimensions(ScalarEvolution &SE,
   LLVM_DEBUG({
     dbgs() << "Terms after sorting:\n";
     for (const SCEV *T : NewTerms)
-      dbgs() << *T << "\n";
+      dbgs() << "  " << *T << "\n";
   });
 
   if (NewTerms.empty() || !findArrayDimensionsRec(SE, NewTerms, Sizes)) {
@@ -339,7 +339,7 @@ void llvm::findArrayDimensions(ScalarEvolution &SE,
   LLVM_DEBUG({
     dbgs() << "Sizes:\n";
     for (const SCEV *S : Sizes)
-      dbgs() << *S << "\n";
+      dbgs() << "  " << *S << "\n";
   });
 }
 
@@ -354,18 +354,27 @@ void llvm::computeAccessFunctions(ScalarEvolution &SE, const SCEV *Expr,
     if (!AR->isAffine())
       return;
 
+  // Clear output vector.
+  Subscripts.clear();
+
+  LLVM_DEBUG(dbgs() << "\ncomputeAccessFunctions\n"
+                    << "Memory Access Function: " << *Expr << "\n");
+
   const SCEV *Res = Expr;
   int Last = Sizes.size() - 1;
+
   for (int i = Last; i >= 0; i--) {
+    const SCEV *Size = Sizes[i];
     const SCEV *Q, *R;
-    SCEVDivision::divide(SE, Res, Sizes[i], &Q, &R);
+
+    SCEVDivision::divide(SE, Res, Size, &Q, &R);
 
     LLVM_DEBUG({
-      dbgs() << "Res: " << *Res << "\n";
-      dbgs() << "Sizes[i]: " << *Sizes[i] << "\n";
-      dbgs() << "Res divided by Sizes[i]:\n";
-      dbgs() << "Quotient: " << *Q << "\n";
-      dbgs() << "Remainder: " << *R << "\n";
+      dbgs() << "Computing 'MemAccFn / Sizes[" << i << "]':\n";
+      dbgs() << "  MemAccFn: " << *Res << "\n";
+      dbgs() << "  Sizes[" << i << "]: " << *Size << "\n";
+      dbgs() << "  Quotient (Leftover): " << *Q << "\n";
+      dbgs() << "  Remainder (Subscript Access Function): " << *R << "\n";
     });
 
     Res = Q;
@@ -397,7 +406,8 @@ void llvm::computeAccessFunctions(ScalarEvolution &SE, const SCEV *Expr,
   LLVM_DEBUG({
     dbgs() << "Subscripts:\n";
     for (const SCEV *S : Subscripts)
-      dbgs() << *S << "\n";
+      dbgs() << "  " << *S << "\n";
+    dbgs() << "\n";
   });
 }
 
@@ -454,6 +464,10 @@ void llvm::delinearize(ScalarEvolution &SE, const SCEV *Expr,
                        SmallVectorImpl<const SCEV *> &Subscripts,
                        SmallVectorImpl<const SCEV *> &Sizes,
                        const SCEV *ElementSize) {
+  // Clear output vectors.
+  Subscripts.clear();
+  Sizes.clear();
+
   // First step: collect parametric terms.
   SmallVector<const SCEV *, 4> Terms;
   collectParametricTerms(SE, Expr, Terms);
@@ -469,21 +483,6 @@ void llvm::delinearize(ScalarEvolution &SE, const SCEV *Expr,
 
   // Third step: compute the access functions for each subscript.
   computeAccessFunctions(SE, Expr, Subscripts, Sizes);
-
-  if (Subscripts.empty())
-    return;
-
-  LLVM_DEBUG({
-    dbgs() << "succeeded to delinearize " << *Expr << "\n";
-    dbgs() << "ArrayDecl[UnknownSize]";
-    for (const SCEV *S : Sizes)
-      dbgs() << "[" << *S << "]";
-
-    dbgs() << "\nArrayRef";
-    for (const SCEV *S : Subscripts)
-      dbgs() << "[" << *S << "]";
-    dbgs() << "\n";
-  });
 }
 
 static std::optional<APInt> tryIntoAPInt(const SCEV *S) {
@@ -646,6 +645,9 @@ bool llvm::delinearizeFixedSizeArray(ScalarEvolution &SE, const SCEV *Expr,
                                      SmallVectorImpl<const SCEV *> &Subscripts,
                                      SmallVectorImpl<const SCEV *> &Sizes,
                                      const SCEV *ElementSize) {
+  // Clear output vectors.
+  Subscripts.clear();
+  Sizes.clear();
 
   // First step: find the fixed array size.
   SmallVector<uint64_t, 4> ConstSizes;
@@ -671,6 +673,7 @@ bool llvm::getIndexExpressionsFromGEP(ScalarEvolution &SE,
   assert(Subscripts.empty() && Sizes.empty() &&
          "Expected output lists to be empty on entry to this function.");
   assert(GEP && "getIndexExpressionsFromGEP called with a null GEP");
+  LLVM_DEBUG(dbgs() << "\nGEP to delinearize: " << *GEP << "\n");
   Type *Ty = nullptr;
   bool DroppedFirstDim = false;
   for (unsigned i = 1; i < GEP->getNumOperands(); i++) {
@@ -683,28 +686,43 @@ bool llvm::getIndexExpressionsFromGEP(ScalarEvolution &SE,
           continue;
         }
       Subscripts.push_back(Expr);
+      LLVM_DEBUG(dbgs() << "Subscripts push_back: " << *Expr << "\n");
       continue;
     }
 
     auto *ArrayTy = dyn_cast<ArrayType>(Ty);
     if (!ArrayTy) {
+      LLVM_DEBUG(dbgs() << "GEP delinearize failed: " << *Ty
+                        << " is not an array type.\n");
       Subscripts.clear();
       Sizes.clear();
       return false;
     }
 
     Subscripts.push_back(Expr);
+    LLVM_DEBUG(dbgs() << "Subscripts push_back: " << *Expr << "\n");
     if (!(DroppedFirstDim && i == 2))
       Sizes.push_back(ArrayTy->getNumElements());
 
     Ty = ArrayTy->getElementType();
   }
+  LLVM_DEBUG({
+    dbgs() << "Subscripts:\n";
+    for (const SCEV *S : Subscripts)
+      dbgs() << *S << "\n";
+    dbgs() << "\n";
+  });
+
   return !Subscripts.empty();
 }
 
 bool llvm::tryDelinearizeFixedSizeImpl(
     ScalarEvolution *SE, Instruction *Inst, const SCEV *AccessFn,
     SmallVectorImpl<const SCEV *> &Subscripts, SmallVectorImpl<int> &Sizes) {
+  // Clear output vectors.
+  Subscripts.clear();
+  Sizes.clear();
+
   Value *SrcPtr = getLoadStorePointerOperand(Inst);
 
   // Check the simple case where the array dimensions are fixed size.
@@ -769,7 +787,6 @@ void printDelinearization(raw_ostream &O, Function *F, LoopInfo *LI,
 
     O << "\n";
     O << "Inst:" << Inst << "\n";
-    O << "In Loop with Header: " << L->getHeader()->getName() << "\n";
     O << "AccessFunction: " << *AccessFn << "\n";
 
     SmallVector<const SCEV *, 3> Subscripts, Sizes;

llvm/test/Analysis/Delinearization/a.ll

@@ -11,7 +11,6 @@
 define void @foo(i64 %n, i64 %m, i64 %o, ptr nocapture %A) #0 {
 ; CHECK-LABEL: 'foo'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %arrayidx11.us.us, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}(28 + (4 * (-4 + (3 * %m)) * %o)),+,(8 * %m * %o)}<%for.i>,+,(12 * %o)}<%for.j>,+,20}<%for.k>
 ; CHECK-NEXT:  Base offset: %A
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][%m][%o] with elements of 4 bytes.

llvm/test/Analysis/Delinearization/byte_offset.ll

@@ -13,7 +13,6 @@
 define void @foo(ptr %A, i64 %i2, i64 %arg, i1 %c) {
 ; CHECK-LABEL: 'foo'
 ; CHECK-NEXT:  Inst: store float 0.000000e+00, ptr %arrayidx, align 4
-; CHECK-NEXT:  In Loop with Header: inner.loop
 ; CHECK-NEXT:  AccessFunction: ({0,+,%i2}<%outer.loop> + %unknown)
 ; CHECK-NEXT:  failed to delinearize
 ;

llvm/test/Analysis/Delinearization/constant_functions_multi_dim.ll

@@ -7,14 +7,12 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 define void @mat_mul(ptr %C, ptr %A, ptr %B, i64 %N) #0 !kernel_arg_addr_space !2 !kernel_arg_access_qual !3 !kernel_arg_type !4 !kernel_arg_base_type !4 !kernel_arg_type_qual !5 {
 ; CHECK-LABEL: 'mat_mul'
 ; CHECK-NEXT:  Inst: %tmp = load float, ptr %arrayidx, align 4
-; CHECK-NEXT:  In Loop with Header: for.inc
 ; CHECK-NEXT:  AccessFunction: {(4 * %N * %call),+,4}<%for.inc>
 ; CHECK-NEXT:  Base offset: %A
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][%N] with elements of 4 bytes.
 ; CHECK-NEXT:  ArrayRef[%call][{0,+,1}<nuw><nsw><%for.inc>]
 ; CHECK-EMPTY:
 ; CHECK-NEXT:  Inst: %tmp5 = load float, ptr %arrayidx4, align 4
-; CHECK-NEXT:  In Loop with Header: for.inc
 ; CHECK-NEXT:  AccessFunction: {(4 * %call1),+,(4 * %N)}<%for.inc>
 ; CHECK-NEXT:  Base offset: %B
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][%N] with elements of 4 bytes.

llvm/test/Analysis/Delinearization/divide_by_one.ll

@@ -14,14 +14,12 @@ target datalayout = "e-m:e-p:32:32-i1:32-i64:64-a:0-n32"
 define void @test(ptr nocapture %dst, i32 %stride, i32 %bs) {
 ; CHECK-LABEL: 'test'
 ; CHECK-NEXT:  Inst: %0 = load i8, ptr %arrayidx, align 1
-; CHECK-NEXT:  In Loop with Header: for.body3
 ; CHECK-NEXT:  AccessFunction: {{\{\{}}(-1 + ((1 + %bs) * %stride)),+,(-1 * %stride)}<%for.cond1.preheader>,+,1}<nw><%for.body3>
 ; CHECK-NEXT:  Base offset: %dst
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][%stride] with elements of 1 bytes.
 ; CHECK-NEXT:  ArrayRef[{(1 + %bs),+,-1}<nw><%for.cond1.preheader>][{-1,+,1}<nw><%for.body3>]
 ; CHECK-EMPTY:
 ; CHECK-NEXT:  Inst: store i8 %0, ptr %arrayidx7, align 1
-; CHECK-NEXT:  In Loop with Header: for.body3
 ; CHECK-NEXT:  AccessFunction: {{\{\{}}(%stride * %bs),+,(-1 * %stride)}<%for.cond1.preheader>,+,1}<nsw><%for.body3>
 ; CHECK-NEXT:  Base offset: %dst
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][%stride] with elements of 1 bytes.

llvm/test/Analysis/Delinearization/fixed_size_array.ll

@@ -11,7 +11,6 @@
 define void @a_i_j_k(ptr %a) {
 ; CHECK-LABEL: 'a_i_j_k'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,128}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][8][32] with elements of 4 bytes.
@@ -60,7 +59,6 @@ exit:
 define void @a_i_nj_k(ptr %a) {
 ; CHECK-LABEL: 'a_i_nj_k'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}896,+,1024}<nuw><nsw><%for.i.header>,+,-128}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][8][32] with elements of 4 bytes.
@@ -116,14 +114,12 @@ exit:
 define void @a_ijk_b_i2jk(ptr %a, ptr %b) {
 ; CHECK-LABEL: 'a_ijk_b_i2jk'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %a.idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,256}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][4][64] with elements of 4 bytes.
 ; CHECK-NEXT:  ArrayRef[{0,+,1}<nuw><nsw><%for.i.header>][{0,+,1}<nuw><nsw><%for.j.header>][{0,+,1}<nuw><nsw><%for.k>]
 ; CHECK-EMPTY:
 ; CHECK-NEXT:  Inst: store i32 1, ptr %b.idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,256}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %b
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][4][64] with elements of 4 bytes.
@@ -180,7 +176,6 @@ exit:
 define void @a_i_2j1_k(ptr %a) {
 ; CHECK-LABEL: 'a_i_2j1_k'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}128,+,1024}<nuw><nsw><%for.i.header>,+,256}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][4][64] with elements of 4 bytes.
@@ -234,7 +229,6 @@ exit:
 define void @a_i_3j_k(ptr %a) {
 ; CHECK-LABEL: 'a_i_3j_k'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,384}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  failed to delinearize
 ;
@@ -286,7 +280,6 @@ exit:
 define void @a_i_j_3k(ptr %a) {
 ; CHECK-LABEL: 'a_i_j_3k'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,128}<nw><%for.j.header>,+,12}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][8][32] with elements of 4 bytes.
@@ -338,7 +331,6 @@ exit:
 define void @a_i_j2k_i(ptr %a) {
 ; CHECK-LABEL: 'a_i_j2k_i'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1028}<%for.i.header>,+,256}<nw><%for.j.header>,+,128}<nw><%for.k>
 ; CHECK-NEXT:  failed to delinearize
 ;
@@ -390,7 +382,6 @@ exit:
 define void @a_i_i_jk(ptr %a) {
 ; CHECK-LABEL: 'a_i_i_jk'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,1152}<%for.i.header>,+,4}<nw><%for.j.header>,+,4}<nw><%for.k>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][288] with elements of 4 bytes.
@@ -441,7 +432,6 @@ exit:
 define void @a_i_jk_l(ptr %a) {
 ; CHECK-LABEL: 'a_i_jk_l'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.l
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{\{}}0,+,1024}<nuw><nsw><%for.i.header>,+,128}<nw><%for.j.header>,+,128}<nw><%for.k.header>,+,4}<nw><%for.l>
 ; CHECK-NEXT:  Base offset: %a
 ; CHECK-NEXT:  ArrayDecl[UnknownSize][8][32] with elements of 4 bytes.
@@ -502,7 +492,6 @@ exit:
 define void @non_divisible_by_element_size(ptr %a) {
 ; CHECK-LABEL: 'non_divisible_by_element_size'
 ; CHECK-NEXT:  Inst: store i32 1, ptr %idx, align 4
-; CHECK-NEXT:  In Loop with Header: for.k
 ; CHECK-NEXT:  AccessFunction: {{\{\{\{}}0,+,256}<nuw><nsw><%for.i.header>,+,32}<nw><%for.j.header>,+,1}<nw><%for.k>
 ; CHECK-NEXT:  failed to delinearize
 ;