Merge branch 'main' into generalize-fusion

Author: srcarroll

.ci/compute_projects.py

@@ -19,6 +19,7 @@
 PROJECT_DEPENDENCIES = {
     "llvm": set(),
     "clang": {"llvm"},
+    "CIR": {"clang", "mlir"},
     "bolt": {"clang", "lld", "llvm"},
     "clang-tools-extra": {"clang", "llvm"},
     "compiler-rt": {"clang", "lld"},
@@ -49,12 +50,23 @@
     },
     "lld": {"bolt", "cross-project-tests"},
     # TODO(issues/132795): LLDB should be enabled on clang changes.
-    "clang": {"clang-tools-extra", "compiler-rt", "cross-project-tests"},
-    "clang-tools-extra": {"libc"},
+    "clang": {"clang-tools-extra", "cross-project-tests"},
     "mlir": {"flang"},
     # Test everything if ci scripts are changed.
-    # FIXME: Figure out what is missing and add here.
-    ".ci": {"llvm", "clang", "lld", "lldb"},
+    ".ci": {
+        "llvm",
+        "clang",
+        "CIR",
+        "lld",
+        "lldb",
+        "bolt",
+        "clang-tools-extra",
+        "mlir",
+        "polly",
+        "flang",
+        "libclc",
+        "openmp",
+    },
 }
 
 # This mapping describes runtimes that should be enabled for a specific project,
@@ -64,7 +76,17 @@
 
 # This mapping describes runtimes that should be tested when the key project is
 # touched.
-DEPENDENT_RUNTIMES_TO_TEST = {"clang": {"libcxx", "libcxxabi", "libunwind"}}
+DEPENDENT_RUNTIMES_TO_TEST = {
+    "clang": {"compiler-rt"},
+    "clang-tools-extra": {"libc"},
+    "libc": {"libc"},
+    ".ci": {"compiler-rt", "libc"},
+}
+DEPENDENT_RUNTIMES_TO_TEST_NEEDS_RECONFIG = {
+    "llvm": {"libcxx", "libcxxabi", "libunwind"},
+    "clang": {"libcxx", "libcxxabi", "libunwind"},
+    ".ci": {"libcxx", "libcxxabi", "libunwind"},
+}
 
 EXCLUDE_LINUX = {
     "cross-project-tests",  # TODO(issues/132796): Tests are failing.
@@ -93,9 +115,6 @@
     "cross-project-tests",
     "flang",
     "libc",
-    "libcxx",
-    "libcxxabi",
-    "libunwind",
     "lldb",
     "openmp",
     "polly",
@@ -111,6 +130,7 @@
     "lldb": "check-lldb",
     "llvm": "check-llvm",
     "clang": "check-clang",
+    "CIR": "check-clang-cir",
     "bolt": "check-bolt",
     "lld": "check-lld",
     "flang": "check-flang",
@@ -122,21 +142,52 @@
     "polly": "check-polly",
 }
 
-RUNTIMES = {"libcxx", "libcxxabi", "libunwind"}
+RUNTIMES = {"libcxx", "libcxxabi", "libunwind", "compiler-rt", "libc"}
+
+# Meta projects are projects that need explicit handling but do not reside
+# in their own top level folder. To add a meta project, the start of the path
+# for the metaproject should be mapped to the name of the project below.
+# Multiple paths can map to the same metaproject.
+META_PROJECTS = {
+    ("clang", "lib", "CIR"): "CIR",
+    ("clang", "test", "CIR"): "CIR",
+    ("clang", "include", "clang", "CIR"): "CIR",
+    ("*", "docs"): "docs",
+    ("llvm", "utils", "gn"): "gn",
+    (".github", "workflows", "premerge.yaml"): ".ci",
+    ("third-party",): ".ci",
+}
+
+# Projects that should not run any tests. These need to be metaprojects.
+SKIP_PROJECTS = ["docs", "gn"]
 
 
-def _add_dependencies(projects: Set[str]) -> Set[str]:
+def _add_dependencies(projects: Set[str], runtimes: Set[str]) -> Set[str]:
     projects_with_dependents = set(projects)
     current_projects_count = 0
     while current_projects_count != len(projects_with_dependents):
         current_projects_count = len(projects_with_dependents)
         for project in list(projects_with_dependents):
-            if project not in PROJECT_DEPENDENCIES:
-                continue
-            projects_with_dependents.update(PROJECT_DEPENDENCIES[project])
+            if project in PROJECT_DEPENDENCIES:
+                projects_with_dependents.update(PROJECT_DEPENDENCIES[project])
+    for runtime in runtimes:
+        if runtime in PROJECT_DEPENDENCIES:
+            projects_with_dependents.update(PROJECT_DEPENDENCIES[runtime])
     return projects_with_dependents
 
 
+def _exclude_projects(current_projects: Set[str], platform: str) -> Set[str]:
+    if platform == "Linux":
+        to_exclude = EXCLUDE_LINUX
+    elif platform == "Windows":
+        to_exclude = EXCLUDE_WINDOWS
+    elif platform == "Darwin":
+        to_exclude = EXCLUDE_MAC
+    else:
+        raise ValueError(f"Unexpected platform: {platform}")
+    return current_projects.difference(to_exclude)
+
+
 def _compute_projects_to_test(modified_projects: Set[str], platform: str) -> Set[str]:
     projects_to_test = set()
     for modified_project in modified_projects:
@@ -154,81 +205,108 @@ def _compute_projects_to_test(modified_projects: Set[str], platform: str) -> Set
             ):
                 continue
             projects_to_test.add(dependent_project)
-    if platform == "Linux":
-        for to_exclude in EXCLUDE_LINUX:
-            if to_exclude in projects_to_test:
-                projects_to_test.remove(to_exclude)
-    elif platform == "Windows":
-        for to_exclude in EXCLUDE_WINDOWS:
-            if to_exclude in projects_to_test:
-                projects_to_test.remove(to_exclude)
-    elif platform == "Darwin":
-        for to_exclude in EXCLUDE_MAC:
-            if to_exclude in projects_to_test:
-                projects_to_test.remove(to_exclude)
-    else:
-        raise ValueError("Unexpected platform.")
+    projects_to_test = _exclude_projects(projects_to_test, platform)
     return projects_to_test
 
 
-def _compute_projects_to_build(projects_to_test: Set[str]) -> Set[str]:
-    return _add_dependencies(projects_to_test)
+def _compute_projects_to_build(
+    projects_to_test: Set[str], runtimes: Set[str]
+) -> Set[str]:
+    return _add_dependencies(projects_to_test, runtimes)
 
 
 def _compute_project_check_targets(projects_to_test: Set[str]) -> Set[str]:
     check_targets = set()
     for project_to_test in projects_to_test:
-        if project_to_test not in PROJECT_CHECK_TARGETS:
-            continue
-        check_targets.add(PROJECT_CHECK_TARGETS[project_to_test])
+        if project_to_test in PROJECT_CHECK_TARGETS:
+            check_targets.add(PROJECT_CHECK_TARGETS[project_to_test])
     return check_targets
 
 
-def _compute_runtimes_to_test(projects_to_test: Set[str]) -> Set[str]:
+def _compute_runtimes_to_test(modified_projects: Set[str], platform: str) -> Set[str]:
     runtimes_to_test = set()
-    for project_to_test in projects_to_test:
-        if project_to_test in DEPENDENT_RUNTIMES_TO_TEST:
-            runtimes_to_test.update(DEPENDENT_RUNTIMES_TO_TEST[project_to_test])
-        if project_to_test in DEPENDENT_RUNTIMES_TO_BUILD:
-            runtimes_to_test.update(DEPENDENT_RUNTIMES_TO_BUILD[project_to_test])
-    return runtimes_to_test
+    for modified_project in modified_projects:
+        if modified_project in DEPENDENT_RUNTIMES_TO_TEST:
+            runtimes_to_test.update(DEPENDENT_RUNTIMES_TO_TEST[modified_project])
+    return _exclude_projects(runtimes_to_test, platform)
 
 
-def _compute_runtime_check_targets(projects_to_test: Set[str]) -> Set[str]:
-    check_targets = set()
-    for project_to_test in projects_to_test:
-        if project_to_test not in DEPENDENT_RUNTIMES_TO_TEST:
+def _compute_runtimes_to_test_needs_reconfig(
+    modified_projects: Set[str], platform: str
+) -> Set[str]:
+    runtimes_to_test = set()
+    for modified_project in modified_projects:
+        if modified_project in DEPENDENT_RUNTIMES_TO_TEST_NEEDS_RECONFIG:
+            runtimes_to_test.update(
+                DEPENDENT_RUNTIMES_TO_TEST_NEEDS_RECONFIG[modified_project]
+            )
+    return _exclude_projects(runtimes_to_test, platform)
+
+
+def _compute_runtimes_to_build(
+    runtimes_to_test: Set[str], modified_projects: Set[str], platform: str
+) -> Set[str]:
+    runtimes_to_build = set(runtimes_to_test)
+    for modified_project in modified_projects:
+        if modified_project in DEPENDENT_RUNTIMES_TO_BUILD:
+            runtimes_to_build.update(DEPENDENT_RUNTIMES_TO_BUILD[modified_project])
+    return _exclude_projects(runtimes_to_build, platform)
+
+
+def _path_matches(matcher: tuple[str], file_path: tuple[str]) -> bool:
+    if len(file_path) < len(matcher):
+        return False
+    for match_part, file_part in zip(matcher, file_path):
+        if match_part == "*" or file_part == "*":
             continue
-        for runtime_to_test in DEPENDENT_RUNTIMES_TO_TEST[project_to_test]:
-            check_targets.add(PROJECT_CHECK_TARGETS[runtime_to_test])
-    return check_targets
+        if match_part != file_part:
+            return False
+    return True
+
+
+def _get_modified_projects_for_file(modified_file: str) -> Set[str]:
+    modified_projects = set()
+    path_parts = pathlib.Path(modified_file).parts
+    for meta_project_files in META_PROJECTS.keys():
+        if _path_matches(meta_project_files, path_parts):
+            meta_project = META_PROJECTS[meta_project_files]
+            if meta_project in SKIP_PROJECTS:
+                return set()
+            modified_projects.add(meta_project)
+    modified_projects.add(pathlib.Path(modified_file).parts[0])
+    return modified_projects
 
 
 def _get_modified_projects(modified_files: list[str]) -> Set[str]:
     modified_projects = set()
     for modified_file in modified_files:
-        path_parts = pathlib.Path(modified_file).parts
-        # Exclude files in the docs directory. They do not impact an test
-        # targets and there is a separate workflow used for ensuring the
-        # documentation builds.
-        if len(path_parts) > 2 and path_parts[1] == "docs":
-            continue
-        # Exclude files for the gn build. We do not test it within premerge
-        # and changes occur often enough that they otherwise take up
-        # capacity.
-        if len(path_parts) > 3 and path_parts[:3] == ("llvm", "utils", "gn"):
-            continue
-        modified_projects.add(pathlib.Path(modified_file).parts[0])
+        modified_projects.update(_get_modified_projects_for_file(modified_file))
     return modified_projects
 
 
 def get_env_variables(modified_files: list[str], platform: str) -> Set[str]:
     modified_projects = _get_modified_projects(modified_files)
     projects_to_test = _compute_projects_to_test(modified_projects, platform)
-    projects_to_build = _compute_projects_to_build(projects_to_test)
+    runtimes_to_test = _compute_runtimes_to_test(modified_projects, platform)
+    runtimes_to_test_needs_reconfig = _compute_runtimes_to_test_needs_reconfig(
+        modified_projects, platform
+    )
+    runtimes_to_build = _compute_runtimes_to_build(
+        runtimes_to_test | runtimes_to_test_needs_reconfig, modified_projects, platform
+    )
+    projects_to_build = _compute_projects_to_build(projects_to_test, runtimes_to_build)
     projects_check_targets = _compute_project_check_targets(projects_to_test)
-    runtimes_to_build = _compute_runtimes_to_test(projects_to_test)
-    runtimes_check_targets = _compute_runtime_check_targets(projects_to_test)
+    runtimes_check_targets = _compute_project_check_targets(runtimes_to_test)
+    runtimes_check_targets_needs_reconfig = _compute_project_check_targets(
+        runtimes_to_test_needs_reconfig
+    )
+
+    # CIR is used as a pseudo-project in this script. It is built as part of the
+    # clang build, but it requires an explicit option to enable. We set that
+    # option here, and remove it from the projects_to_build list.
+    enable_cir = "ON" if "CIR" in projects_to_build else "OFF"
+    projects_to_build.discard("CIR")
+
     # We use a semicolon to separate the projects/runtimes as they get passed
     # to the CMake invocation and thus we need to use the CMake list separator
     # (;). We use spaces to separate the check targets as they end up getting
@@ -238,6 +316,10 @@ def get_env_variables(modified_files: list[str], platform: str) -> Set[str]:
         "project_check_targets": " ".join(sorted(projects_check_targets)),
         "runtimes_to_build": ";".join(sorted(runtimes_to_build)),
         "runtimes_check_targets": " ".join(sorted(runtimes_check_targets)),
+        "runtimes_check_targets_needs_reconfig": " ".join(
+            sorted(runtimes_check_targets_needs_reconfig)
+        ),
+        "enable_cir": enable_cir,
     }