diff --git a/mlir/include/mlir/Dialect/GPU/GPUOps.td b/mlir/include/mlir/Dialect/GPU/GPUOps.td
--- a/mlir/include/mlir/Dialect/GPU/GPUOps.td
+++ b/mlir/include/mlir/Dialect/GPU/GPUOps.td
@@ -834,6 +834,8 @@
     custom<AsyncDependencies>(type($asyncToken), $asyncDependencies) ` `
     `(` $dynamicSizes `)` (`` `[` $symbolOperands^ `]`)? attr-dict `:` type($memref)
   }];
+
+  let hasCanonicalizer = 1;
 }
 
 def GPU_DeallocOp : GPU_Op<"dealloc", [GPU_AsyncOpInterface]> {
@@ -1040,7 +1042,7 @@
     the same value.
 
     This op is meant to be used along with `gpu.subgroup_mma_compute`.
-    
+
     Example:
 
     ```mlir
diff --git a/mlir/lib/Dialect/GPU/CMakeLists.txt b/mlir/lib/Dialect/GPU/CMakeLists.txt
--- a/mlir/lib/Dialect/GPU/CMakeLists.txt
+++ b/mlir/lib/Dialect/GPU/CMakeLists.txt
@@ -18,6 +18,7 @@
 
 add_mlir_dialect_library(MLIRGPUOps
   IR/GPUDialect.cpp
+  IR/GPUOps.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/GPU
diff --git a/mlir/lib/Dialect/GPU/IR/GPUOps.cpp b/mlir/lib/Dialect/GPU/IR/GPUOps.cpp
new file mode 100644
--- /dev/null
+++ b/mlir/lib/Dialect/GPU/IR/GPUOps.cpp
@@ -0,0 +1,67 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "mlir/Dialect/GPU/GPUDialect.h"
+#include "mlir/Dialect/MemRef/IR/MemRef.h"
+#include "mlir/IR/PatternMatch.h"
+
+#include "mlir/Dialect/MemRef/IR/MemRef.h"
+#include "mlir/Dialect/MemRef/Utils/MemRefUtils.h"
+#include "mlir/Dialect/StandardOps/IR/Ops.h"
+#include "mlir/Dialect/StandardOps/Utils/Utils.h"
+// #include "mlir/Dialect/Tensor/IR/Tensor.h"
+#include "mlir/Dialect/Utils/StaticValueUtils.h"
+// #include "mlir/IR/AffineMap.h"
+#include "mlir/IR/Builders.h"
+#include "mlir/IR/BuiltinTypes.h"
+#include "mlir/IR/Matchers.h"
+#include "mlir/IR/PatternMatch.h"
+#include "mlir/IR/TypeUtilities.h"
+#include "mlir/Interfaces/InferTypeOpInterface.h"
+#include "mlir/Interfaces/ViewLikeInterface.h"
+#include "llvm/ADT/STLExtras.h"
+
+using namespace mlir;
+using namespace mlir::gpu;
+
+namespace {
+
+// Folding of memref.dim(gpu.alloca(%size), %idx) -> %size similar to
+// `memref::AllocOp`.
+struct SimplifyDimOfAllocOp : public OpRewritePattern<memref::DimOp> {
+  using OpRewritePattern<memref::DimOp>::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(memref::DimOp dimOp,
+                                PatternRewriter &rewriter) const override {
+    auto index =
+        dyn_cast_or_null<ConstantIndexOp>(dimOp.getOperand(1).getDefiningOp());
+    if (!index)
+      return failure();
+
+    auto memrefType = dimOp.source().getType().dyn_cast<MemRefType>();
+    if (!memrefType)
+      return failure();
+
+    Operation *definingOp = dimOp.source().getDefiningOp();
+    if (auto alloc = dyn_cast_or_null<AllocOp>(definingOp)) {
+      auto substituteOp = *(alloc.dynamicSizes().begin() +
+                            memrefType.getDynamicDimIndex(index.getValue()));
+      rewriter.replaceOp(dimOp, substituteOp);
+      return success();
+    }
+
+    return failure();
+  }
+};
+
+} // end anonymous namespace.
+
+void AllocOp::getCanonicalizationPatterns(RewritePatternSet &results,
+                                          MLIRContext *context) {
+  results.add<SimplifyDimOfAllocOp>(context);
+}
diff --git a/mlir/test/Dialect/GPU/canonicalize.mlir b/mlir/test/Dialect/GPU/canonicalize.mlir
--- a/mlir/test/Dialect/GPU/canonicalize.mlir
+++ b/mlir/test/Dialect/GPU/canonicalize.mlir
@@ -9,3 +9,16 @@
   gpu.memcpy %0,%1 : memref<?xf32>, memref<?xf32>
   return
 }
+
+// -----
+
+// Test case: Folding of memref.dim(gpu.alloca(%size), %idx) -> %size
+// CHECK-LABEL: func @gpu_dim_of_alloc(
+//  CHECK-SAME:     %[[SIZE:[0-9a-z]+]]: index
+//  CHECK-NEXT:   return %[[SIZE]] : index
+func @gpu_dim_of_alloc(%size: index) -> index {
+  %0 = gpu.alloc(%size) : memref<?xindex>
+  %c0 = constant 0 : index
+  %1 = memref.dim %0, %c0 : memref<?xindex>
+  return %1 : index
+}
\ No newline at end of file