diff --git a/opencl/source/command_queue/command_queue.cpp b/opencl/source/command_queue/command_queue.cpp
index 16c3a59793..bc13fced53 100644
--- a/opencl/source/command_queue/command_queue.cpp
+++ b/opencl/source/command_queue/command_queue.cpp
@@ -1209,7 +1209,7 @@ WaitStatus CommandQueue::waitForAllEngines(bool blockedQueue, PrintfHandler *pri
     }
 
     auto waitStatus = WaitStatus::NotReady;
-    auto waitedOnTimestamps = waitForTimestamps(activeBcsStates, taskCount, waitStatus);
+    auto waitedOnTimestamps = waitForTimestamps(activeBcsStates, taskCount, waitStatus, this->timestampPacketContainer.get(), this->deferredTimestampPackets.get());
     if (waitStatus == WaitStatus::GpuHang) {
         return WaitStatus::GpuHang;
     }
diff --git a/opencl/source/command_queue/command_queue.h b/opencl/source/command_queue/command_queue.h
index 4251ac82da..37fdc5b0c4 100644
--- a/opencl/source/command_queue/command_queue.h
+++ b/opencl/source/command_queue/command_queue.h
@@ -204,7 +204,7 @@ class CommandQueue : public BaseObject<_cl_command_queue> {
     bool isCompleted(uint32_t gpgpuTaskCount, CopyEngineState bcsState);
 
     bool isWaitForTimestampsEnabled() const;
-    virtual bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status) = 0;
+    virtual bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status, TimestampPacketContainer *mainContainer, TimestampPacketContainer *deferredContainer) = 0;
 
     MOCKABLE_VIRTUAL bool isQueueBlocked();
 
diff --git a/opencl/source/command_queue/command_queue_hw.h b/opencl/source/command_queue/command_queue_hw.h
index 3d3eeeccc1..216ce6de07 100644
--- a/opencl/source/command_queue/command_queue_hw.h
+++ b/opencl/source/command_queue/command_queue_hw.h
@@ -427,7 +427,7 @@ class CommandQueueHw : public CommandQueue {
 
     bool isCacheFlushCommand(uint32_t commandType) const override;
 
-    bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status) override;
+    bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status, TimestampPacketContainer *mainContainer, TimestampPacketContainer *deferredContainer) override;
 
     MOCKABLE_VIRTUAL bool isCacheFlushForBcsRequired() const;
 
diff --git a/opencl/source/command_queue/command_queue_hw_base.inl b/opencl/source/command_queue/command_queue_hw_base.inl
index 5b7007be52..8040661212 100644
--- a/opencl/source/command_queue/command_queue_hw_base.inl
+++ b/opencl/source/command_queue/command_queue_hw_base.inl
@@ -167,14 +167,14 @@ inline bool waitForTimestampsWithinContainer(TimestampPacketContainer *container
 }
 
 template <typename Family>
-bool CommandQueueHw<Family>::waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status) {
+bool CommandQueueHw<Family>::waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status, TimestampPacketContainer *mainContainer, TimestampPacketContainer *deferredContainer) {
     using TSPacketType = typename Family::TimestampPacketType;
     bool waited = false;
 
     if (isWaitForTimestampsEnabled()) {
-        waited = waitForTimestampsWithinContainer<TSPacketType>(timestampPacketContainer.get(), getGpgpuCommandStreamReceiver(), status);
+        waited = waitForTimestampsWithinContainer<TSPacketType>(mainContainer, getGpgpuCommandStreamReceiver(), status);
         if (isOOQEnabled()) {
-            waitForTimestampsWithinContainer<TSPacketType>(deferredTimestampPackets.get(), getGpgpuCommandStreamReceiver(), status);
+            waitForTimestampsWithinContainer<TSPacketType>(deferredContainer, getGpgpuCommandStreamReceiver(), status);
         }
 
         if (waited) {
diff --git a/opencl/source/event/event.cpp b/opencl/source/event/event.cpp
index 956ec73a36..3236cc99d4 100644
--- a/opencl/source/event/event.cpp
+++ b/opencl/source/event/event.cpp
@@ -428,7 +428,9 @@ inline WaitStatus Event::wait(bool blocking, bool useQuickKmdSleep) {
     }
 
     Range<CopyEngineState> states{&bcsState, bcsState.isValid() ? 1u : 0u};
-    const auto waitStatus = cmdQueue->waitUntilComplete(taskCount.load(), states, flushStamp->peekStamp(), useQuickKmdSleep);
+    auto waitStatus = WaitStatus::NotReady;
+    auto waitedOnTimestamps = cmdQueue->waitForTimestamps(states, taskCount.load(), waitStatus, this->timestampPacketContainer.get(), nullptr);
+    waitStatus = cmdQueue->waitUntilComplete(taskCount.load(), states, flushStamp->peekStamp(), useQuickKmdSleep, true, waitedOnTimestamps);
     if (waitStatus == WaitStatus::GpuHang) {
         return WaitStatus::GpuHang;
     }
diff --git a/opencl/test/unit_test/command_queue/command_queue_hw_1_tests.cpp b/opencl/test/unit_test/command_queue/command_queue_hw_1_tests.cpp
index ebf405623f..782b71dfc9 100644
--- a/opencl/test/unit_test/command_queue/command_queue_hw_1_tests.cpp
+++ b/opencl/test/unit_test/command_queue/command_queue_hw_1_tests.cpp
@@ -52,7 +52,7 @@ HWTEST_F(CommandQueueHwTest, givenNoTimestampPacketsWhenWaitForTimestampsThenNoW
     auto taskCount = device->getUltCommandStreamReceiver<FamilyType>().peekLatestFlushedTaskCount();
     auto status = WaitStatus::NotReady;
 
-    cmdQ.waitForTimestamps({}, 101u, status);
+    cmdQ.waitForTimestamps({}, 101u, status, cmdQ.timestampPacketContainer.get(), cmdQ.deferredTimestampPackets.get());
 
     EXPECT_EQ(device->getUltCommandStreamReceiver<FamilyType>().peekLatestFlushedTaskCount(), taskCount);
 }
diff --git a/opencl/test/unit_test/event/event_tests.cpp b/opencl/test/unit_test/event/event_tests.cpp
index 02d4d540b3..0955a3b483 100644
--- a/opencl/test/unit_test/event/event_tests.cpp
+++ b/opencl/test/unit_test/event/event_tests.cpp
@@ -909,6 +909,16 @@ TEST_F(InternalsEventTest, givenPassingEventWhenWaitingForEventsThenWaititingIsS
     EXPECT_NE(Event::executionAbortedDueToGpuHang, passingEvent.peekExecutionStatus());
 }
 
+TEST_F(InternalsEventTest, givenEventWhenWaitThenWaitForTimestampsCalled) {
+    MockCommandQueue cmdQ(mockContext, pClDevice, nullptr, false);
+    MockEvent<Event> event(&cmdQ, CL_COMMAND_NDRANGE_KERNEL, 0, 0);
+    EXPECT_FALSE(cmdQ.waitForTimestampsCalled);
+
+    event.wait(false, false);
+
+    EXPECT_TRUE(cmdQ.waitForTimestampsCalled);
+}
+
 TEST_F(InternalsEventTest, GivenProfilingWHENMapOperationTHENTimesSet) {
     const cl_queue_properties props[3] = {CL_QUEUE_PROPERTIES, CL_QUEUE_PROFILING_ENABLE, 0};
     MockCommandQueue *pCmdQ = new MockCommandQueue(mockContext, pClDevice, props, false);
diff --git a/opencl/test/unit_test/mocks/mock_command_queue.h b/opencl/test/unit_test/mocks/mock_command_queue.h
index c123735dcd..533edb0ce5 100644
--- a/opencl/test/unit_test/mocks/mock_command_queue.h
+++ b/opencl/test/unit_test/mocks/mock_command_queue.h
@@ -212,10 +212,13 @@ class MockCommandQueue : public CommandQueue {
 
     bool obtainTimestampPacketForCacheFlush(bool isCacheFlushRequired) const override { return isCacheFlushRequired; }
 
-    bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status) override { return false; };
+    bool waitForTimestamps(Range<CopyEngineState> copyEnginesToWait, uint32_t taskCount, WaitStatus &status, TimestampPacketContainer *mainContainer, TimestampPacketContainer *deferredContainer) override {
+        waitForTimestampsCalled = true;
+        return false;
+    };
 
     bool releaseIndirectHeapCalled = false;
-
+    bool waitForTimestampsCalled = false;
     cl_int writeBufferRetValue = CL_SUCCESS;
     uint32_t writeBufferCounter = 0;
     bool writeBufferBlocking = false;