[CI][UR] Merge latest updates in UR benchmarking suite

devops/actions/run-tests/benchmark/action.yml

@@ -95,7 +95,6 @@ runs:
     if: always()
     shell: bash
     run: |
-      # TODO -- waiting on security clearance
       # Load configuration values
       $(python ./devops/scripts/benchmarking/load_config.py ./devops constants)
 

unified-runtime/scripts/benchmarks/README.md → devops/scripts/benchmarks/README.md

@@ -6,6 +6,8 @@ Scripts for running performance tests on SYCL and Unified Runtime.
 
 - [Velocity Bench](https://github.com/oneapi-src/Velocity-Bench)
 - [Compute Benchmarks](https://github.com/intel/compute-benchmarks/)
+- [LlamaCpp Benchmarks](https://github.com/ggerganov/llama.cpp)
+- [SYCL-Bench](https://github.com/unisa-hpc/sycl-bench)
 
 ## Running
 
@@ -27,8 +29,6 @@ You can also include additional benchmark parameters, such as environment variab
 
 Once all the required information is entered, click the "Run workflow" button to initiate a new workflow run. This will execute the benchmarks and then post the results as a comment on the specified Pull Request.
 
-By default, all benchmark runs are compared against `baseline`, which is a well-established set of the latest data.
-
 You must be a member of the `oneapi-src` organization to access these features.
 
 ## Comparing results
@@ -37,8 +37,8 @@ By default, the benchmark results are not stored. To store them, use the option
 
 You can compare benchmark results using `--compare` option. The comparison will be presented in a markdown output file (see below). If you want to calculate the relative performance of the new results against the previously saved data, use `--compare <previously_saved_data>` (i.e. `--compare baseline`). In case of comparing only stored data without generating new results, use `--dry-run --compare <name1> --compare <name2> --relative-perf <name1>`, where `name1` indicates the baseline for the relative performance calculation and `--dry-run` prevents the script for running benchmarks. Listing more than two `--compare` options results in displaying only execution time, without statistical analysis.
 
-Baseline, as well as baseline-v2 (for the level-zero adapter v2) is updated automatically during a nightly job. The results
-are stored [here](https://oneapi-src.github.io/unified-runtime/benchmark_results.html).
+Baseline_L0, as well as Baseline_L0v2 (for the level-zero adapter v2) is updated automatically during a nightly job. The results
+are stored [here](https://oneapi-src.github.io/unified-runtime/performance/).
 
 ## Output formats
 You can display the results in the form of a HTML file by using `--ouptut-html` and a markdown file by using `--output-markdown`. Due to character limits for posting PR comments, the final content of the markdown file might be reduced. In order to obtain the full markdown output, use `--output-markdown full`.

unified-runtime/scripts/benchmarks/benches/base.py → devops/scripts/benchmarks/benches/base.py

@@ -1,12 +1,12 @@
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2024-2025 Intel Corporation
 # Part of the Unified-Runtime Project, under the Apache License v2.0 with LLVM Exceptions.
 # See LICENSE.TXT
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 import os
 import shutil
 from pathlib import Path
-from .result import Result
+from utils.result import BenchmarkMetadata, Result
 from options import options
 from utils.utils import download, run
 import urllib.request
@@ -55,19 +55,25 @@ def create_data_path(self, name, skip_data_dir=False):
             data_path = os.path.join(self.directory, name)
         else:
             data_path = os.path.join(self.directory, "data", name)
-            if options.rebuild and Path(data_path).exists():
+            if options.redownload and Path(data_path).exists():
                 shutil.rmtree(data_path)
 
         Path(data_path).mkdir(parents=True, exist_ok=True)
 
         return data_path
 
-    def download(self, name, url, file, untar=False, unzip=False, skip_data_dir=False):
+    def download(
+        self,
+        name,
+        url,
+        file,
+        untar=False,
+        unzip=False,
+        skip_data_dir=False,
+        checksum="",
+    ):
         self.data_path = self.create_data_path(name, skip_data_dir)
-        return download(self.data_path, url, file, untar, unzip)
-
-    def name(self):
-        raise NotImplementedError()
+        return download(self.data_path, url, file, untar, unzip, checksum)
 
     def lower_is_better(self):
         return True
@@ -87,6 +93,26 @@ def stddev_threshold(self):
     def get_suite_name(self) -> str:
         return self.suite.name()
 
+    def name(self):
+        raise NotImplementedError()
+
+    def description(self):
+        return "No description provided."
+
+    def notes(self) -> str:
+        return None
+
+    def unstable(self) -> str:
+        return None
+
+    def get_metadata(self) -> BenchmarkMetadata:
+        return BenchmarkMetadata(
+            type="benchmark",
+            description=self.description(),
+            notes=self.notes(),
+            unstable=self.unstable(),
+        )
+
 
 class Suite:
     def benchmarks(self) -> list[Benchmark]:
@@ -97,3 +123,6 @@ def name(self) -> str:
 
     def setup(self):
         return
+
+    def additionalMetadata(self) -> dict[str, BenchmarkMetadata]:
+        return {}