[llvm] [AMDGPU] Extended vector promotion to aggregate types. (PR #143784)

[via llvm-commits]

================
@@ -828,42 +861,43 @@ bool AMDGPUPromoteAllocaImpl::tryPromoteAllocaToVector(AllocaInst &Alloca) {
   }
 
   Type *AllocaTy = Alloca.getAllocatedType();
-  auto *VectorTy = dyn_cast<FixedVectorType>(AllocaTy);
-  if (auto *ArrayTy = dyn_cast<ArrayType>(AllocaTy)) {
-    uint64_t NumElems = 1;
-    Type *ElemTy;
-    do {
-      NumElems *= ArrayTy->getNumElements();
-      ElemTy = ArrayTy->getElementType();
-    } while ((ArrayTy = dyn_cast<ArrayType>(ElemTy)));
-
-    // Check for array of vectors
-    auto *InnerVectorTy = dyn_cast<FixedVectorType>(ElemTy);
-    if (InnerVectorTy) {
-      NumElems *= InnerVectorTy->getNumElements();
-      ElemTy = InnerVectorTy->getElementType();
-    }
+  Type *ElemTy = getHomogeneousType(AllocaTy);
 
-    if (VectorType::isValidElementType(ElemTy) && NumElems > 0) {
-      unsigned ElementSize = DL->getTypeSizeInBits(ElemTy) / 8;
-      if (ElementSize > 0) {
-        unsigned AllocaSize = DL->getTypeStoreSize(AllocaTy);
-        // Expand vector if required to match padding of inner type,
-        // i.e. odd size subvectors.
-        // Storage size of new vector must match that of alloca for correct
-        // behaviour of byte offsets and GEP computation.
-        if (NumElems * ElementSize != AllocaSize)
-          NumElems = AllocaSize / ElementSize;
-        if (NumElems > 0 && (AllocaSize % ElementSize) == 0)
-          VectorTy = FixedVectorType::get(ElemTy, NumElems);
-      }
-    }
+  if (!ElemTy || !VectorType::isValidElementType(ElemTy)) {
+    LLVM_DEBUG(dbgs() << "  Cannot convert type to vector\n");
+    return false;
   }
 
-  if (!VectorTy) {
-    LLVM_DEBUG(dbgs() << "  Cannot convert type to vector\n");
+  unsigned ElementSizeInBits = DL->getTypeSizeInBits(ElemTy);
+  if (ElementSizeInBits == 0) {
+    LLVM_DEBUG(dbgs() << "  Cannot create vector of zero-sized elements.");
+    return false;
+  }
+  if (ElementSizeInBits != DL->getTypeAllocSizeInBits(ElemTy)) {
+    LLVM_DEBUG(dbgs() << "  Cannot convert to vector if the allocation size "
+                         "does not match the type's size\n");
+    return false;
+  }
+  unsigned ElementSize = ElementSizeInBits / 8;
+  if (ElementSize == 0)
+    return false;
+
+  // Calculate the size of the corresponding vector, accounting for padding of
+  // inner types, e.g., odd-sized subvectors. Storage size of new vector must
+  // match that of alloca for correct behaviour of byte offsets and GEP
+  // computation.
+  unsigned AllocaSize = DL->getTypeStoreSize(AllocaTy);
+  unsigned NumElems = AllocaSize / ElementSize;
+  if (NumElems == 0) {
----------------
zGoldthorpe wrote:

You're right, the check is redundant.

https://github.com/llvm/llvm-project/pull/143784