diff --git a/opencl/source/api/api.cpp b/opencl/source/api/api.cpp
index 0b8a7f17a0..629c9e67bd 100644
--- a/opencl/source/api/api.cpp
+++ b/opencl/source/api/api.cpp
@@ -5760,6 +5760,13 @@ CL_API_ENTRY cl_int CL_API_CALL clEnqueueVerifyMemoryINTEL(cl_command_queue comm
         return retVal;
     }
 
+    auto activeCopyEngines = pCommandQueue->peekActiveBcsStates();
+    for (auto &copyEngine : activeCopyEngines) {
+        if (copyEngine.isValid()) {
+            pCommandQueue->getBcsCommandStreamReceiver(copyEngine.engineType)->pollForCompletion();
+        }
+    }
+
     auto &csr = pCommandQueue->getGpgpuCommandStreamReceiver();
     auto status = csr.expectMemory(allocationPtr, expectedData, sizeOfComparison, comparisonMode);
     return status ? CL_SUCCESS : CL_INVALID_VALUE;
diff --git a/opencl/source/command_queue/command_queue.h b/opencl/source/command_queue/command_queue.h
index 4c75789551..a24a876cdb 100644
--- a/opencl/source/command_queue/command_queue.h
+++ b/opencl/source/command_queue/command_queue.h
@@ -368,6 +368,8 @@ class CommandQueue : public BaseObject<_cl_command_queue> {
 
     bool isTextureCacheFlushNeeded(uint32_t commandType) const;
 
+    const std::array<CopyEngineState, bcsInfoMaskSize> &peekActiveBcsStates() const { return bcsStates; }
+
   protected:
     void *enqueueReadMemObjForMap(TransferProperties &transferProperties, EventsRequest &eventsRequest, cl_int &errcodeRet);
     cl_int enqueueWriteMemObjForUnmap(MemObj *memObj, void *mappedPtr, EventsRequest &eventsRequest);
diff --git a/opencl/test/unit_test/api/cl_enqueue_verify_memory.inl b/opencl/test/unit_test/api/cl_enqueue_verify_memory.inl
index c9f8577ca5..3178d7875b 100644
--- a/opencl/test/unit_test/api/cl_enqueue_verify_memory.inl
+++ b/opencl/test/unit_test/api/cl_enqueue_verify_memory.inl
@@ -1,11 +1,12 @@
 /*
- * Copyright (C) 2019-2022 Intel Corporation
+ * Copyright (C) 2019-2023 Intel Corporation
  *
  * SPDX-License-Identifier: MIT
  *
  */
 
 #include "shared/test/common/mocks/mock_csr.h"
+#include "shared/test/common/mocks/mock_os_context.h"
 #include "shared/test/common/test_macros/test.h"
 
 #include "opencl/extensions/public/cl_ext_private.h"
@@ -64,3 +65,38 @@ TEST_F(ClEnqueueVerifyMemoryIntelTests, givenNotEqualMemoryWhenCallingVerifyMemo
     cl_int retval = clEnqueueVerifyMemoryINTEL(pCommandQueue, gpuAddress, &differentMemory, sizeof(differentMemory), comparisonMode);
     EXPECT_EQ(CL_INVALID_VALUE, retval);
 }
+
+HWTEST_F(ClEnqueueVerifyMemoryIntelTests, givenActiveBcsEngineWhenCallingExpectMemoryThenPollForCompletionOnAllEngines) {
+    UltCommandStreamReceiver<FamilyType> ultCsrBcs0(*pDevice->getExecutionEnvironment(), pDevice->getRootDeviceIndex(), pDevice->getDeviceBitfield());
+    UltCommandStreamReceiver<FamilyType> ultCsrBcs1(*pDevice->getExecutionEnvironment(), pDevice->getRootDeviceIndex(), pDevice->getDeviceBitfield());
+
+    MockOsContext osContext0(0, {{aub_stream::ENGINE_BCS, EngineUsage::Regular}, 0, PreemptionMode::Disabled, false, false});
+    MockOsContext osContext1(1, {{aub_stream::ENGINE_BCS1, EngineUsage::Regular}, 0, PreemptionMode::Disabled, false, false});
+
+    EngineControl engineControl[2] = {{&ultCsrBcs0, &osContext0}, {&ultCsrBcs1, &osContext1}};
+
+    pCommandQueue->bcsInitialized = true;
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS)] = &engineControl[0];
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS1)] = &engineControl[1];
+
+    pCommandQueue->bcsStates[0].engineType = aub_stream::ENGINE_BCS;
+    pCommandQueue->bcsStates[1].engineType = aub_stream::ENGINE_BCS1;
+
+    EXPECT_EQ(0u, ultCsrBcs0.pollForCompletionCalled);
+    EXPECT_EQ(0u, ultCsrBcs1.pollForCompletionCalled);
+
+    cl_int retval = clEnqueueVerifyMemoryINTEL(pCommandQueue, gpuAddress, expected, expectedSize, comparisonMode);
+    EXPECT_EQ(CL_SUCCESS, retval);
+
+    EXPECT_EQ(1u, ultCsrBcs0.pollForCompletionCalled);
+    EXPECT_EQ(1u, ultCsrBcs1.pollForCompletionCalled);
+
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS)]->commandStreamReceiver = nullptr;
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS1)]->commandStreamReceiver = nullptr;
+
+    pCommandQueue->bcsStates[0].engineType = aub_stream::NUM_ENGINES;
+    pCommandQueue->bcsStates[1].engineType = aub_stream::NUM_ENGINES;
+
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS)] = nullptr;
+    pCommandQueue->bcsEngines[EngineHelpers::getBcsIndex(aub_stream::ENGINE_BCS1)] = nullptr;
+}
diff --git a/opencl/test/unit_test/mocks/mock_command_queue.h b/opencl/test/unit_test/mocks/mock_command_queue.h
index 9f103a4df9..528038605a 100644
--- a/opencl/test/unit_test/mocks/mock_command_queue.h
+++ b/opencl/test/unit_test/mocks/mock_command_queue.h
@@ -24,6 +24,8 @@ class MockCommandQueue : public CommandQueue {
   public:
     using CommandQueue::bcsEngines;
     using CommandQueue::bcsEngineTypes;
+    using CommandQueue::bcsInitialized;
+    using CommandQueue::bcsStates;
     using CommandQueue::bcsTimestampPacketContainers;
     using CommandQueue::blitEnqueueAllowed;
     using CommandQueue::blitEnqueueImageAllowed;
diff --git a/shared/test/common/libult/ult_command_stream_receiver.h b/shared/test/common/libult/ult_command_stream_receiver.h
index a3c700df9d..96ae90e668 100644
--- a/shared/test/common/libult/ult_command_stream_receiver.h
+++ b/shared/test/common/libult/ult_command_stream_receiver.h
@@ -368,6 +368,10 @@ class UltCommandStreamReceiver : public CommandStreamReceiverHw<GfxFamily>, publ
         return commandStreamReceiverType;
     }
 
+    void pollForCompletion() override {
+        pollForCompletionCalled++;
+    }
+
     std::vector<std::string> aubCommentMessages;
 
     BatchBuffer latestFlushedBatchBuffer = {};
@@ -385,6 +389,7 @@ class UltCommandStreamReceiver : public CommandStreamReceiverHw<GfxFamily>, publ
     uint32_t createPerDssBackedBufferCalled = 0;
     uint32_t initDirectSubmissionCalled = 0;
     uint32_t fillReusableAllocationsListCalled = 0;
+    uint32_t pollForCompletionCalled = 0;
     int ensureCommandBufferAllocationCalled = 0;
     DispatchFlags recordedDispatchFlags;
     BlitPropertiesContainer receivedBlitProperties = {};