Revert "[DirectX] Array GEPs need two indices (#142853)" and "Adjust bit cast instruction filter for DXIL Prepare pass (#142678)" (#143043)

- This reverts commit 9ab4c16.
- This reverts commit 1d6e8ec.

Noticed a really weird behavior where release and debug builds have
different codegen for loads with geps after this PR. This is going to
take a minute to debug and figure out why so revert seems to make the
most sense.

```diff
diff --git a/llvm/test/CodeGen/DirectX/flatten-array.ll b/llvm/test/CodeGen/DirectX/flatten-array.ll
index 47d7b50..efa9efeff13a 100644
--- a/llvm/test/CodeGen/DirectX/flatten-array.ll
+++ b/llvm/test/CodeGen/DirectX/flatten-array.ll
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
@b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 6
+  ; CHECK-NEXT: %2 = load i32, ptr %1, align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @A, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
}
define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: %1 = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 0, i32 13
+  ; CHECK-NEXT: store i32 1, ptr %1, align 4
   ; CHECK-NEXT:    ret void
```

Author: farzonl

llvm/lib/Target/DirectX/DXILFlattenArrays.cpp

@@ -272,9 +272,8 @@ bool DXILFlattenArraysVisitor::visitGetElementPtrInstInGEPChainBase(
 
   ArrayType *FlattenedArrayType = GEPInfo.ParentArrayType;
   Value *FlatGEP =
-      Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand,
-                        {Builder.getInt32(0), FlatIndex},
-                        GEP.getName() + ".flat", GEP.getNoWrapFlags());
+      Builder.CreateGEP(FlattenedArrayType, GEPInfo.ParendOperand, FlatIndex,
+                        GEP.getName() + ".flat", GEP.isInBounds());
 
   GEP.replaceAllUsesWith(FlatGEP);
   GEP.eraseFromParent();

llvm/lib/Target/DirectX/DXILPrepare.cpp

@@ -148,49 +148,9 @@ class DXILPrepareModule : public ModulePass {
                                      Type *Ty) {
     // Omit bitcasts if the incoming value matches the instruction type.
     auto It = PointerTypes.find(Operand);
-    if (It != PointerTypes.end()) {
-      auto *OpTy = cast<TypedPointerType>(It->second)->getElementType();
-      if (OpTy == Ty)
+    if (It != PointerTypes.end())
+      if (cast<TypedPointerType>(It->second)->getElementType() == Ty)
         return nullptr;
-    }
-
-    Type *ValTy = Operand->getType();
-    // Also omit the bitcast for matching global array types
-    if (auto *GlobalVar = dyn_cast<GlobalVariable>(Operand))
-      ValTy = GlobalVar->getValueType();
-
-    if (auto *AI = dyn_cast<AllocaInst>(Operand))
-      ValTy = AI->getAllocatedType();
-
-    if (auto *ArrTy = dyn_cast<ArrayType>(ValTy)) {
-      Type *ElTy = ArrTy->getElementType();
-      if (ElTy == Ty)
-        return nullptr;
-    }
-
-    // finally, drill down GEP instructions until we get the array
-    // that is being accessed, and compare element types
-    if (ConstantExpr *GEPInstr = dyn_cast<ConstantExpr>(Operand)) {
-      while (GEPInstr->getOpcode() == Instruction::GetElementPtr) {
-        Value *OpArg = GEPInstr->getOperand(0);
-        if (ConstantExpr *NewGEPInstr = dyn_cast<ConstantExpr>(OpArg)) {
-          GEPInstr = NewGEPInstr;
-          continue;
-        }
-
-        if (auto *GlobalVar = dyn_cast<GlobalVariable>(OpArg))
-          ValTy = GlobalVar->getValueType();
-        if (auto *AI = dyn_cast<AllocaInst>(Operand))
-          ValTy = AI->getAllocatedType();
-        if (auto *ArrTy = dyn_cast<ArrayType>(ValTy)) {
-          Type *ElTy = ArrTy->getElementType();
-          if (ElTy == Ty)
-            return nullptr;
-        }
-        break;
-      }
-    }
-
     // Insert bitcasts where we are removing the instruction.
     Builder.SetInsertPoint(&Inst);
     // This code only gets hit in opaque-pointer mode, so the type of the

llvm/test/CodeGen/DirectX/flatten-array.ll

@@ -31,7 +31,7 @@ define void @alloca_4d_test ()  {
 ; CHECK-LABEL: gep_2d_test
 define void @gep_2d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [9 x i32], align 4
-    ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 0, i32 {{[0-8]}}
+    ; CHECK-COUNT-9: getelementptr inbounds [9 x i32], ptr [[a]], i32 {{[0-8]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [3 x [3 x i32]], align 4
     %g2d0 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* %1, i32 0, i32 0
@@ -53,7 +53,7 @@ define void @gep_2d_test ()  {
 ; CHECK-LABEL: gep_3d_test
 define void @gep_3d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [8 x i32], align 4
-    ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 0, i32 {{[0-7]}}
+    ; CHECK-COUNT-8: getelementptr inbounds [8 x i32], ptr [[a]], i32 {{[0-7]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [2 x[2 x [2 x i32]]], align 4
     %g3d0 = getelementptr inbounds [2 x[2 x [2 x i32]]], [2 x[2 x [2 x i32]]]* %1, i32 0, i32 0
@@ -76,7 +76,7 @@ define void @gep_3d_test ()  {
 ; CHECK-LABEL: gep_4d_test
 define void @gep_4d_test ()  {
     ; CHECK: [[a:%.*]] = alloca [16 x i32], align 4
-    ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 0, i32 {{[0-9]|1[0-5]}}
+    ; CHECK-COUNT-16: getelementptr inbounds [16 x i32], ptr [[a]], i32 {{[0-9]|1[0-5]}}
     ; CHECK-NEXT:    ret void
     %1 = alloca [2x[2 x[2 x [2 x i32]]]], align 4
     %g4d0 = getelementptr inbounds [2x[2 x[2 x [2 x i32]]]], [2x[2 x[2 x [2 x i32]]]]* %1, i32 0, i32 0
@@ -123,7 +123,8 @@ define void @gep_4d_test ()  {
 @b = internal global [2 x [3 x [4 x i32]]] zeroinitializer, align 16
 
 define void @global_gep_load() {
-  ; CHECK: load i32, ptr getelementptr inbounds ([24 x i32], ptr @a.1dim, i32 0, i32 6), align 4
+  ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 6
+  ; CHECK: load i32, ptr [[GEP_PTR]], align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @a, i32 0, i32 0
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 1
@@ -141,7 +142,7 @@ define void @global_gep_load_index(i32 %row, i32 %col, i32 %timeIndex) {
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul i32 [[ROW]], 12
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[TMP4]], [[TMP5]]
-; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP6]]
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP6]]
 ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}}
@@ -162,7 +163,7 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 0, [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i32 [[ROW]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[TMP2]], [[TMP3]]
-; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 0, i32 [[TMP4]]
+; CHECK-NEXT:    [[DOTFLAT:%.*]] = getelementptr inbounds [24 x i32], ptr @a.1dim, i32 [[TMP4]]
 ; CHECK-NOT: getelementptr inbounds [2 x [3 x [4 x i32]]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [3 x [4 x i32]]{{.*}}
 ; CHECK-NOT: getelementptr inbounds [4 x i32]{{.*}}
@@ -176,7 +177,8 @@ define void @global_incomplete_gep_chain(i32 %row, i32 %col) {
 }
 
 define void @global_gep_store() {
-  ; CHECK: store i32 1, ptr getelementptr inbounds ([24 x i32], ptr @b.1dim, i32 0, i32 13), align 4
+  ; CHECK: [[GEP_PTR:%.*]] = getelementptr inbounds [24 x i32], ptr @b.1dim, i32 13
+  ; CHECK:  store i32 1, ptr [[GEP_PTR]], align 4
   ; CHECK-NEXT:    ret void
   %1 = getelementptr inbounds [2 x [3 x [4 x i32]]], [2 x [3 x [4 x i32]]]* @b, i32 0, i32 1
   %2 = getelementptr inbounds [3 x [4 x i32]], [3 x [4 x i32]]* %1, i32 0, i32 0

llvm/test/CodeGen/DirectX/flatten-bug-117273.ll

@@ -8,9 +8,9 @@
 define internal void @main() {
 ; CHECK-LABEL: define internal void @main() {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 0, i32 1
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 1
 ; CHECK-NEXT:    [[DOTI0:%.*]] = load float, ptr [[TMP0]], align 16
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 0, i32 2
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [24 x float], ptr @ZerroInitArr.1dim, i32 2
 ; CHECK-NEXT:    [[DOTI03:%.*]] = load float, ptr [[TMP1]], align 16
 ; CHECK-NEXT:    ret void
 ;