[DirectX] ForwardHandle needs to check if globals were stored on allocas

fixes #140819

SROA pass is making it so that some globals get loaded into stack
allocations. This means we find an alloca where we use to expect a load
and now need to walk an alloca -> store -> maybe load chain before
we find the global. Doing so fixes All but two instances of #137715
And fixes every instance of `Load of "8.sroa.0" is not a global resource handle
we are currently seeing in the DML shaders.

Author: farzonl

llvm/lib/Target/DirectX/DXILForwardHandleAccesses.cpp

@@ -87,17 +87,48 @@ static bool forwardHandleAccesses(Function &F, DominatorTree &DT) {
 
   for (LoadInst *LI : LoadsToProcess) {
     Value *V = LI->getPointerOperand();
-    auto *GV = dyn_cast<GlobalVariable>(LI->getPointerOperand());
+    auto *GV = dyn_cast<GlobalVariable>(V);
 
     // If we didn't find the global, we may need to walk through a level of
     // indirection. This generally happens at -O0.
-    if (!GV)
+    if (!GV) {
       if (auto *NestedLI = dyn_cast<LoadInst>(V)) {
         BasicBlock::iterator BBI(NestedLI);
         Value *Loaded = FindAvailableLoadedValue(
             NestedLI, NestedLI->getParent(), BBI, 0, nullptr, nullptr);
         GV = dyn_cast_or_null<GlobalVariable>(Loaded);
+      } else if (auto *NestedAlloca = dyn_cast<AllocaInst>(V)) {
+        for (auto &Use : NestedAlloca->uses()) {
+          auto *Store = dyn_cast<StoreInst>(Use.getUser());
+          if (!Store)
+            continue;
+
+          Value *StoredVal = Store->getValueOperand();
+          if (!StoredVal)
+            continue;
+
+          // Try direct global match
+          GV = dyn_cast<GlobalVariable>(StoredVal);
+          if (GV)
+            break;
+
+          // If it's a load, check its source
+          if (auto *Load = dyn_cast<LoadInst>(StoredVal)) {
+            GV = dyn_cast<GlobalVariable>(Load->getPointerOperand());
+            if (GV)
+              break;
+
+            // Try to find available loaded value
+            BasicBlock::iterator BBI(Load);
+            Value *Loaded = FindAvailableLoadedValue(Load, Load->getParent(),
+                                                     BBI, 0, nullptr, nullptr);
+            GV = dyn_cast<GlobalVariable>(Loaded);
+            if (GV)
+              break;
+          }
+        }
       }
+    }
 
     auto It = HandleMap.find(GV);
     if (It == HandleMap.end()) {

llvm/test/CodeGen/DirectX/issue-140819_allow_forward_handle_on_alloca.ll

@@ -0,0 +1,39 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -dxil-forward-handle-accesses  %s | FileCheck %s
+
+%"class.hlsl::RWStructuredBuffer" = type { target("dx.RawBuffer", i32, 1, 0) }
+@_ZL4dest = internal unnamed_addr global %"class.hlsl::RWStructuredBuffer" poison, align 4
+@.str = private unnamed_addr constant [5 x i8] c"dest\00", align 1
+
+
+; NOTE: intent of this test is to confirm load target("dx.RawBuffer", i32, 1, 0)
+;       is replaced with call @llvm.dx.resource.getpointer
+define void @CSMain() local_unnamed_addr {
+; CHECK-LABEL: define void @CSMain() local_unnamed_addr {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[AGG_TMP_I1_SROA_0:%.*]] = alloca target("dx.RawBuffer", i32, 1, 0), align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call target("dx.RawBuffer", i32, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_i32_1_0t(i32 0, i32 3, i32 1, i32 0, i1 false, ptr nonnull @.str)
+; CHECK-NEXT:    store target("dx.RawBuffer", i32, 1, 0) [[TMP0]], ptr @_ZL4dest, align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.dx.thread.id(i32 0)
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr @_ZL4dest, align 4
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[AGG_TMP_I1_SROA_0]])
+; CHECK-NEXT:    store i32 [[TMP2]], ptr [[AGG_TMP_I1_SROA_0]], align 8
+; CHECK-NEXT:    [[TMP3:%.*]] = tail call noundef nonnull align 4 dereferenceable(4) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_i32_1_0t(target("dx.RawBuffer", i32, 1, 0) [[TMP0]], i32 [[TMP1]])
+; CHECK-NEXT:    store i32 0, ptr [[TMP3]], align 4
+; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[AGG_TMP_I1_SROA_0]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %agg.tmp.i1.sroa.0 = alloca target("dx.RawBuffer", i32, 1, 0), align 8
+  %0 = tail call target("dx.RawBuffer", i32, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_i32_1_0t(i32 0, i32 3, i32 1, i32 0, i1 false, ptr nonnull @.str)
+  store target("dx.RawBuffer", i32, 1, 0) %0, ptr @_ZL4dest, align 4
+  %1 = tail call i32 @llvm.dx.thread.id(i32 0)
+  %2 = load i32, ptr @_ZL4dest, align 4
+  call void @llvm.lifetime.start.p0(i64 4, ptr nonnull %agg.tmp.i1.sroa.0)
+  store i32 %2, ptr %agg.tmp.i1.sroa.0, align 8
+  %agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0. = load target("dx.RawBuffer", i32, 1, 0), ptr %agg.tmp.i1.sroa.0, align 8
+  %3 = tail call noundef nonnull align 4 dereferenceable(4) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_i32_1_0t(target("dx.RawBuffer", i32, 1, 0) %agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0.agg.tmp.i1.sroa.0.0., i32 %1)
+  store i32 0, ptr %3, align 4
+  call void @llvm.lifetime.end.p0(i64 4, ptr nonnull %agg.tmp.i1.sroa.0)
+  ret void
+}