resource_plan: count physical cores on Windows (GetLogicalProcessorInformationEx)

os.cpu_count() returns logical processors, so on SMT machines the plan sets OMP_NUM_THREADS to 2 threads/core, which thrashes the AVX-512 units during expert matmul (9950X3D: 32 logical vs 16 physical). Count RelationProcessorCore records instead, with the existing lscpu/cpu_count fallbacks intact. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 22:05:38 -05:00
parent 3fd47b7bbd
commit f72ee6532d
1 changed files with 24 additions and 0 deletions
@@ -167,6 +167,30 @@ def discover_gpus():


 def physical_cpu_count():
+    if sys.platform == "win32":
+        # os.cpu_count() conta i processori logici (SMT): 2 thread/core saturano
+        # le unita' AVX-512 e peggiorano il matmul. Contiamo i core fisici veri
+        # con GetLogicalProcessorInformationEx(RelationProcessorCore).
+        try:
+            import ctypes
+            k32 = ctypes.windll.kernel32
+            need = ctypes.c_ulong(0)
+            k32.GetLogicalProcessorInformationEx(0, None, ctypes.byref(need))
+            buf = (ctypes.c_char * need.value)()
+            if k32.GetLogicalProcessorInformationEx(0, buf, ctypes.byref(need)):
+                raw, cores, off = bytes(buf), 0, 0
+                while off + 8 <= need.value:
+                    relationship = int.from_bytes(raw[off:off + 4], "little")
+                    size = int.from_bytes(raw[off + 4:off + 8], "little")
+                    if size <= 0:
+                        break
+                    if relationship == 0:  # RelationProcessorCore
+                        cores += 1
+                    off += size
+                if cores:
+                    return cores
+        except (OSError, ValueError, AttributeError):
+            pass
    try:
        result = subprocess.run(["lscpu", "-p=core,socket"], text=True,
                                capture_output=True, check=True, timeout=5)