diff --git a/onnxruntime/core/mlas/lib/mlasi.h b/onnxruntime/core/mlas/lib/mlasi.h
index ea620877ed..7155a9dd27 100644
--- a/onnxruntime/core/mlas/lib/mlasi.h
+++ b/onnxruntime/core/mlas/lib/mlasi.h
@@ -782,7 +782,7 @@ extern "C" {
 // value.
 //
 
-#define MLAS_DEFAULT_PREFERRED_BUFFER_ALIGNMENT     32
+#define MLAS_DEFAULT_PREFERRED_BUFFER_ALIGNMENT     64
 
 //
 // Define the target number of per-thread multiplies before using another
diff --git a/onnxruntime/core/providers/dml/DmlExecutionProvider/src/BucketizedBufferAllocator.cpp b/onnxruntime/core/providers/dml/DmlExecutionProvider/src/BucketizedBufferAllocator.cpp
index f5abeb5d7b..aae73dca46 100644
--- a/onnxruntime/core/providers/dml/DmlExecutionProvider/src/BucketizedBufferAllocator.cpp
+++ b/onnxruntime/core/providers/dml/DmlExecutionProvider/src/BucketizedBufferAllocator.cpp
@@ -244,17 +244,12 @@ namespace Dml
 
     void* CPUAllocator::Alloc(size_t size)
     {
-        if (size <= 0)
-        {
-            return nullptr;
-        }
-        void* p = malloc(size);
-        return p;
+        return onnxruntime::AllocatorDefaultAlloc(size);
     }
 
     void CPUAllocator::Free(void* p)
     {
-        free(p);
+        return onnxruntime::AllocatorDefaultFree(p);
     }
 
 } // namespace Dml