Optimize library runtime builders with -O3 -march=native -mtune=native -fomit-frame-pointer

tools/build-riot-cxx-runtime.py

@@ -15,6 +15,7 @@ generation only. Outputs build/riot-libc++.1.dylib and build/riot-libc++abi.dyli
 """
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
+import os
 import re
 import shlex
 import subprocess
@@ -47,20 +48,22 @@ def build(library, object_dir, link_dir, output):
             obj = root / ("build/riot-opt-%s-%s.o" % (library, relative.replace("/", "_")))
             jobs.append((relative, obj))
             link[index] = str(obj)
-    print(library, "recompiling", len(jobs), "objects at -O2", flush=True)
+    print(library, "recompiling", len(jobs), "objects at -O3", flush=True)
 
     def compile_one(job):
         relative, obj = job
-        subprocess.run(["clang++", *flags["CXX_DEFINES"], *flags["CXX_INCLUDES"], *flags["CXX_FLAGS"],
-                        "-O2", "-fno-strict-aliasing", "-c", str(source / relative), "-o", str(obj)],
+        cxx_flags = [f for f in flags["CXX_FLAGS"] if f not in ("-g", "-O0", "-O1", "-O2")]
+        subprocess.run(["clang++", *flags["CXX_DEFINES"], *flags["CXX_INCLUDES"], *cxx_flags,
+                        "-O3", "-march=native", "-mtune=native", "-fomit-frame-pointer", "-fno-strict-aliasing",
+                        "-c", str(source / relative), "-o", str(obj)],
                        check=True, capture_output=True)
 
     riot_build_gate.wait_until_free()
-    with ThreadPoolExecutor(max_workers=6) as pool:
+    with ThreadPoolExecutor(max_workers=os.cpu_count() or 8) as pool:
         list(pool.map(compile_one, jobs))
     link[link.index("-o") + 1] = str(root / "build" / output)
     subprocess.run(link, cwd=folder, check=True)
-    print("built build/" + output, len(jobs), "objects at -O2", flush=True)
+    print("built build/" + output, len(jobs), "objects at -O3", flush=True)
 
 
 if __name__ == "__main__":

tools/build-riot-libc-runtime.py

@@ -100,9 +100,8 @@ def compile_command(target_folder, source, object_path):
                 skip = True
                 continue
             cleaned.append(token)
-        if "-O2" not in cleaned:
-            cleaned.append("-O2")
-            cleaned.append("-fno-strict-aliasing")
+        cleaned = [t for t in cleaned if t not in ("-g", "-O0", "-O1", "-O2")]
+        cleaned.extend(["-O3", "-march=native", "-mtune=native", "-fno-strict-aliasing", "-fomit-frame-pointer"])
         return cleaned
     return None
 

tools/build-riot-platform-strings.py

@@ -27,10 +27,11 @@ for original in list(link):
  if not original.startswith('CMakeFiles/platform_obj.dir/src/string/generic/') or not original.endswith('.c.o'):continue
  relative=original.split('platform_obj.dir/',1)[1].removesuffix('.o')
  obj=root/('build/riot-platform-'+Path(relative).name+'.o')
- subprocess.run(['clang',*flags['C_DEFINES'],*flags['C_INCLUDES'],*flags['C_FLAGS'],'-O2','-fno-builtin','-fno-strict-aliasing','-c',str(root/'build/darling-src/src/external/libplatform'/relative),'-o',str(obj)],check=True)
+ c_flags = [f for f in flags['C_FLAGS'] if f not in ('-g', '-O0', '-O1', '-O2')]
+ subprocess.run(['clang',*flags['C_DEFINES'],*flags['C_INCLUDES'],*c_flags,'-O3','-march=native','-mtune=native','-fomit-frame-pointer','-fno-builtin','-fno-strict-aliasing','-c',str(root/'build/darling-src/src/external/libplatform'/relative),'-o',str(obj)],check=True)
  link[link.index(original)]=str(obj)
  recompiled+=1
 link[link.index('-o')+1]=str(root/'build/riot-libsystem_platform.dylib')
 subprocess.run(link,cwd=folder,check=True)
-print('built build/riot-libsystem_platform.dylib with',recompiled,'string objects at -O2')
+print('built build/riot-libsystem_platform.dylib with',recompiled,'string objects at -O3')
 p=root/'build/m810-platform-runtime';p.mkdir(exist_ok=True);shutil.copy2(root/'build/riot-libsystem_platform.dylib',p/'libsystem_platform.dylib')