feature: Add validation layer Timing Checker for host-side API timing

scripts/generate_code.py

@@ -182,6 +182,7 @@ def _mako_loader_cpp(path, namespace, tags, version, specs, meta):
     'handle_lifetime.h.mako' : ('handle_lifetime_tracking', 'handle_lifetime.h'),
     'handle_lifetime.cpp.mako' : ('handle_lifetime_tracking', 'handle_lifetime.cpp'),
     'certification.h.mako' : ('checkers/certification/generated', 'certification.h'),
+    'timing.h.mako' : ('checkers/timing/generated', 'timing.h'),
     'to_string.h.mako' : ('../../utils', 'to_string.h'),
 }
 

scripts/templates/validation/timing.h.mako

@@ -0,0 +1,63 @@
+<%!
+import re
+from templates import helper as th
+%><%
+    n=namespace
+    N=n.upper()
+%>/*
+ * ***THIS FILE IS GENERATED. ***
+ * See timing.h.mako for modifications
+ *
+ * Copyright (C) 2026 Intel Corporation
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * @file ${name}
+ *
+ */
+#pragma once
+#include "../zel_global_timing_state.h"
+#include "${n}_entry_points.h"
+
+namespace validation_layer {
+class ${N}timingCheckerGenerated : public ${N}ValidationEntryPoints {
+public:
+    %for obj in th.extract_objs(specs, r"function"):
+    <%
+    param_lines = [line for line in th.make_param_lines(n, tags, obj, format=["type", "name", "delim"])]
+    is_void_params = len(param_lines) == 1 and "void" in param_lines[0]
+    func_name = th.make_func_name(n, tags, obj)
+    %>virtual ze_result_t ${func_name}Prologue( \
+%for line in param_lines:
+${line} \
+%endfor
+) override {
+        GlobalTimingState::getInstance().recordStart();
+        return ZE_RESULT_SUCCESS;
+    }
+    virtual ze_result_t ${func_name}Epilogue( \
+%if not is_void_params:
+%for line in param_lines:
+${line} \
+%endfor
+, ${obj['return_type']} result) override {
+%else:
+${obj['return_type']} result ) override {
+%endif
+        GlobalTimingState::getInstance().recordEnd("${func_name}");
+        return ZE_RESULT_SUCCESS;
+    }
+    %endfor
+%if n == 'ze':
+    // Experimental Intel extension for counter-based events
+    virtual ze_result_t zexCounterBasedEventCreate2Prologue( ze_context_handle_t hContext, ze_device_handle_t hDevice, const void* desc, ze_event_handle_t* phEvent ) override {
+        GlobalTimingState::getInstance().recordStart();
+        return ZE_RESULT_SUCCESS;
+    }
+    virtual ze_result_t zexCounterBasedEventCreate2Epilogue( ze_context_handle_t hContext, ze_device_handle_t hDevice, const void* desc, ze_event_handle_t* phEvent , ze_result_t result) override {
+        GlobalTimingState::getInstance().recordEnd("zexCounterBasedEventCreate2");
+        return ZE_RESULT_SUCCESS;
+    }
+%endif
+};
+} // namespace validation_layer

source/layers/validation/README.md

@@ -23,6 +23,7 @@ By default, no validation modes will be enabled. The individual validation modes
 - `ZE_ENABLE_THREADING_VALIDATION` (Not yet Implemented)
 - `ZEL_ENABLE_CERTIFICATION_CHECKER`
 - `ZEL_ENABLE_SYSTEM_RESOURCE_TRACKER_CHECKER`
+- `ZEL_ENABLE_TIMING_CHECKER`
 
 ## Validation Modes
 
@@ -141,6 +142,41 @@ export ZEL_LOADER_LOGGING_LEVEL=debug
 
 See [System Resource Tracker documentation](checkers/system_resource_tracker/system_resource_tracker.md) for detailed usage and CSV format.
 
+### `ZEL_ENABLE_TIMING_CHECKER`
+
+The Timing Checker measures the host-side (CPU) duration of every Level Zero API
+call and aggregates per-API statistics (call count, total, min, max and average
+time in nanoseconds).
+
+For each API call the checker stamps a high-resolution monotonic timestamp in the
+Prologue and reads it again in the Epilogue. The clock is
+`QueryPerformanceCounter` on Windows and `clock_gettime(CLOCK_MONOTONIC_RAW)`
+elsewhere. The measured span is dominated by the underlying driver call and is
+consistent across calls, making it suitable for relative host-cost analysis.
+
+To enable, set:
+```bash
+export ZE_ENABLE_VALIDATION_LAYER=1
+export ZEL_ENABLE_TIMING_CHECKER=1
+```
+
+Output modes (each independently controlled):
+
+| Environment Variable | Default | Description |
+|---|---|---|
+| `ZEL_ENABLE_TIMING_CHECKER` | `0` | Enable the checker; a per-API summary table is printed at teardown |
+| `ZEL_TIMING_CHECKER_CSV` | (unset) | Also export the per-API statistics to a CSV file (the process id is appended to the filename) |
+| `ZEL_TIMING_CHECKER_LIVE` | `0` | Also print each call's duration as it happens (verbose) |
+
+The summary and live output are written directly to `stderr` and the rows are
+sorted by their share of total host time (highest first). The Timing Checker does
+not use the loader logging system, so the `ZEL_ENABLE_LOADER_LOGGING` /
+`ZEL_LOADER_LOGGING_LEVEL` variables are **not** required (in particular you do
+not need to set logging to `trace`, which would also enable API-call logging).
+
+See [Timing Checker documentation](checkers/timing/timing_checker.md) for detailed
+usage, output examples, and the CSV format.
+
 ## Testing
 
 There is a small set of negative test cases designed to test the validation layer in the [level zero tests repo](https://github.com/oneapi-src/level-zero-tests/tree/master/negative_tests).   

source/layers/validation/checkers/CMakeLists.txt

@@ -5,3 +5,4 @@ add_subdirectory(performance)
 add_subdirectory(parameter_validation)
 add_subdirectory(template)
 add_subdirectory(system_resource_tracker)
+add_subdirectory(timing)

source/layers/validation/checkers/timing/CMakeLists.txt

@@ -0,0 +1,13 @@
+# Copyright (C) 2026 Intel Corporation
+# SPDX-License-Identifier: MIT
+
+target_sources(${TARGET_NAME}
+    PRIVATE
+        ${CMAKE_CURRENT_LIST_DIR}/zel_timing_checker.h
+        ${CMAKE_CURRENT_LIST_DIR}/zel_timing_checker.cpp
+        ${CMAKE_CURRENT_LIST_DIR}/zel_global_timing_state.h
+        ${CMAKE_CURRENT_LIST_DIR}/generated/ze_timing.h
+        ${CMAKE_CURRENT_LIST_DIR}/generated/zes_timing.h
+        ${CMAKE_CURRENT_LIST_DIR}/generated/zet_timing.h
+        ${CMAKE_CURRENT_LIST_DIR}/generated/zer_timing.h
+)