[Benchmarks] Benchmarks scripts cleanup

devops/scripts/benchmarks/CONTRIB.md

@@ -20,7 +20,6 @@ The suite is structured around four main components: Suites, Benchmarks, Results
     * **Required Methods:**
         * `setup()`: Initializes the benchmark (e.g., build, download data). Use `self.download()` for data dependencies. **Do not** perform setup in `__init__`.
         * `run(env_vars)`: Executes the benchmark binary (use `self.run_bench()`) and returns a list of `Result` objects. Can be called multiple times, must produce consistent results.
-        * `teardown()`: Cleans up resources. Can be empty. No need to remove build artifacts or downloaded datasets.
         * `name()`: Returns a unique identifier string for the benchmark across *all* suites. If a benchmark class is instantiated multiple times with different parameters (e.g., "Submit In Order", "Submit Out Of Order"), the `name()` must reflect this uniqueness.
     * **Optional Methods:**
         * `lower_is_better()`: Returns `True` if lower result values are better (default: `True`).
@@ -165,7 +164,7 @@ The benchmark suite generates an interactive HTML dashboard that visualizes `Res
 
 ## Adding New Benchmarks
 
-1. **Create Benchmark Class:** Implement a new class inheriting from `benches.base.Benchmark`. Implement required methods (`setup`, `run`, `teardown`, `name`) and optional ones (`description`, `get_tags`, etc.) as needed.
+1. **Create Benchmark Class:** Implement a new class inheriting from `benches.base.Benchmark`. Implement required methods (`run`, `name`) and optional ones (`description`, `get_tags`, etc.) as needed.
 2. **Add to Suite:**
     * If adding to an existing category, modify the corresponding `Suite` class (e.g., `benches/compute.py`) to instantiate and return your new benchmark in its `benchmarks()` method.
     * If creating a new category, create a new `Suite` class inheriting from `benches.base.Suite`. Implement `name()` and `benchmarks()`. Add necessary `setup()` if the suite requires shared setup. Add group metadata via `additional_metadata()` if needed.

devops/scripts/benchmarks/benches/base.py

@@ -56,6 +56,28 @@ def __init__(self, suite):
     def name(self) -> str:
         pass
 
+    @abstractmethod
+    def run(
+        self,
+        env_vars,
+        run_trace: TracingType = TracingType.NONE,
+        force_trace: bool = False,
+    ) -> list[Result]:
+        """Execute the benchmark with the given environment variables.
+
+        Args:
+            env_vars: Environment variables to use when running the benchmark.
+            run_trace: The type of tracing to run (NONE, UNITRACE, or FLAMEGRAPH).
+            force_trace: If True, ignore the traceable() method and force tracing.
+
+        Returns:
+            A list of Result objects with the benchmark results.
+
+        Raises:
+            Exception: If the benchmark fails for any reason.
+        """
+        pass
+
     def display_name(self) -> str:
         """Returns a user-friendly name for display in charts.
         By default returns the same as name(), but can be overridden.
@@ -87,44 +109,6 @@ def setup(self):
         """Extra setup steps to be performed before running the benchmark."""
         pass
 
-    @abstractmethod
-    def teardown(self):
-        pass
-
-    @abstractmethod
-    def run(
-        self,
-        env_vars,
-        run_trace: TracingType = TracingType.NONE,
-        force_trace: bool = False,
-    ) -> list[Result]:
-        """Execute the benchmark with the given environment variables.
-
-        Args:
-            env_vars: Environment variables to use when running the benchmark.
-            run_trace: The type of tracing to run (NONE, UNITRACE, or FLAMEGRAPH).
-            force_trace: If True, ignore the traceable() method and force tracing.
-
-        Returns:
-            A list of Result objects with the benchmark results.
-
-        Raises:
-            Exception: If the benchmark fails for any reason.
-        """
-        pass
-
-    @staticmethod
-    def get_adapter_full_path():
-        for libs_dir_name in ["lib", "lib64"]:
-            adapter_path = os.path.join(
-                options.ur, libs_dir_name, f"libur_adapter_{options.ur_adapter}.so"
-            )
-            if os.path.isfile(adapter_path):
-                return adapter_path
-        assert (
-            False
-        ), f"could not find adapter file {adapter_path} (and in similar lib paths)"
-
     def run_bench(
         self,
         command,
@@ -268,6 +252,18 @@ def get_metadata(self) -> dict[str, BenchmarkMetadata]:
             )
         }
 
+    @staticmethod
+    def get_adapter_full_path():
+        for libs_dir_name in ["lib", "lib64"]:
+            adapter_path = os.path.join(
+                options.ur, libs_dir_name, f"libur_adapter_{options.ur_adapter}.so"
+            )
+            if os.path.isfile(adapter_path):
+                return adapter_path
+        assert (
+            False
+        ), f"could not find adapter file {adapter_path} (and in similar lib paths)"
+
 
 class Suite(ABC):
     @abstractmethod

devops/scripts/benchmarks/benches/benchdnn.py

@@ -91,9 +91,6 @@ def setup(self) -> None:
             timeout=60 * 20,
         )
 
-    def teardown(self):
-        pass
-
 
 class OneDnnBenchmark(Benchmark):
     def __init__(self, suite, bench_driver, bench_name, bench_args, syclgraph=True):
@@ -207,6 +204,3 @@ def _extract_time(self, output):
         if values:
             return sum(values)
         return 0.0
-
-    def teardown(self):
-        pass

devops/scripts/benchmarks/benches/compute.py

@@ -462,9 +462,6 @@ def parse_output(self, output: str) -> list[tuple[float, float]]:
             raise ValueError("Benchmark output does not contain data.")
         return results
 
-    def teardown(self):
-        return
-
     def _validate_attr(self, attr_name: str):
         if (
             not hasattr(self, attr_name)

devops/scripts/benchmarks/benches/gromacs.py

@@ -93,9 +93,6 @@ def setup(self) -> None:
             untar=True,
         )
 
-    def teardown(self):
-        pass
-
 
 class GromacsBenchmark(Benchmark):
     def __init__(self, suite, model, type, option):
@@ -274,6 +271,3 @@ def _validate_correctness(self, log_file):
                         )
 
         raise ValueError(f"Conserved Energy Drift not found in log file: {log_file}")
-
-    def teardown(self):
-        pass

devops/scripts/benchmarks/benches/llamacpp.py

@@ -179,6 +179,3 @@ def parse_output(self, output):
                 raise ValueError(f"Error parsing output: {e}")
 
         return results
-
-    def teardown(self):
-        return

devops/scripts/benchmarks/benches/syclbench.py

@@ -177,9 +177,6 @@ def run(
     def name(self):
         return f"{self.bench.name()} {self.test}"
 
-    def teardown(self):
-        return
-
 
 # multi benchmarks
 class Blocked_transform(SyclBenchmark):

devops/scripts/benchmarks/benches/test.py

@@ -100,6 +100,3 @@ def run(
                 unit="ms",
             )
         ]
-
-    def teardown(self):
-        return

devops/scripts/benchmarks/benches/umf.py

@@ -205,9 +205,6 @@ def parse_output(self, output):
 
         return results
 
-    def teardown(self):
-        return
-
 
 class GBenchPreloaded(GBench):
     def __init__(self, bench, lib_to_be_replaced, replacing_lib):

devops/scripts/benchmarks/benches/velocity.py

@@ -178,9 +178,6 @@ def run(
             )
         ]
 
-    def teardown(self):
-        return
-
 
 class Hashtable(VelocityBase):
     def __init__(self, vb: VelocityBench):

devops/scripts/benchmarks/main.py

@@ -333,12 +333,6 @@ def main(directory, additional_env_vars, compare_names, filter):
                 failures[benchmark.name()] = f"Benchmark run failure: {e}"
                 log.error(f"failed: {e}")
 
-    for benchmark in benchmarks:
-        # this never has any useful information anyway, so hide it behind verbose
-        log.debug(f"tearing down {benchmark.name()}... ")
-        benchmark.teardown()
-        log.debug(f"{benchmark.name()} teardown complete.")
-
     this_name = options.current_run_name
     chart_data = {}