Add memory backed buffer allocation for L0 ray tracing.

This allocates the buffer on a per-device basis and enables ray
tracing on devices that support it when given a kernel with ray
tracing calls.

Signed-off-by: Jim Snow <jim.m.snow@intel.com>

opencl/test/unit_test/helpers/ray_tracing_helper_tests.cpp

@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2020-2021 Intel Corporation
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ */
+
+#include "shared/source/helpers/constants.h"
+#include "shared/source/helpers/ray_tracing_helper.h"
+#include "shared/test/common/mocks/mock_device.h"
+
+#include "opencl/test/unit_test/mocks/mock_cl_device.h"
+#include "opencl/test/unit_test/mocks/mock_context.h"
+#include "test.h"
+
+using namespace NEO;
+
+TEST(RayTracingHelperTests, whenMemoryBackedFifoSizeIsRequestedThenCorrectValueIsReturned) {
+    MockDevice device;
+
+    size_t size = RayTracingHelper::getTotalMemoryBackedFifoSize(device);
+    size_t expectedSize = device.getHardwareInfo().gtSystemInfo.DualSubSliceCount * RayTracingHelper::memoryBackedFifoSizePerDss;
+    EXPECT_EQ(expectedSize, size);
+}