python
diff --git a/‎Include/internal/pycore_code.h
Lines changed: 7 additions & 0 deletions b/‎Include/internal/pycore_code.h
Lines changed: 7 additions & 0 deletions
diff --git a/‎Include/opcode.h
Lines changed: 24 additions & 23 deletions b/‎Include/opcode.h
Lines changed: 24 additions & 23 deletions
diff --git a/‎Lib/opcode.py
Lines changed: 1 addition & 0 deletions b/‎Lib/opcode.py
Lines changed: 1 addition & 0 deletions
diff --git a/‎Misc/NEWS.d/next/Core and Builtins/2021-10-20-11-57-31.bpo-44525.veL4lJ.rst
Lines changed: 1 addition & 0 deletions b/‎Misc/NEWS.d/next/Core and Builtins/2021-10-20-11-57-31.bpo-44525.veL4lJ.rst
Lines changed: 1 addition & 0 deletions
diff --git a/‎Python/ceval.c
Lines changed: 42 additions & 3 deletions b/‎Python/ceval.c
Lines changed: 42 additions & 3 deletions
diff --git a/‎Python/opcode_targets.h
Lines changed: 14 additions & 14 deletions b/‎Python/opcode_targets.h
Lines changed: 14 additions & 14 deletions
@@ -35,6 +35,12 @@ typedef struct {
     PyObject *obj;
 } _PyObjectCache;
 
+typedef struct {
+    uint32_t func_version;
+    uint16_t defaults_start;
+    uint16_t defaults_len;
+} _PyCallCache;
+
 /* Add specialized versions of entries to this union.
  *
  * Do not break the invariant: sizeof(SpecializedCacheEntry) == 8
@@ -51,6 +57,7 @@ typedef union {
     _PyAttrCache attr;
     _PyLoadGlobalCache load_global;
     _PyObjectCache obj;
+    _PyCallCache call;
 } SpecializedCacheEntry;
 
 #define INSTRUCTIONS_PER_ENTRY (sizeof(SpecializedCacheEntry)/sizeof(_Py_CODEUNIT))
 
@@ -237,6 +237,7 @@ def jabs_op(name, op):
     "CALL_FUNCTION_BUILTIN_FAST",
     "CALL_FUNCTION_LEN",
     "CALL_FUNCTION_ISINSTANCE",
+    "CALL_FUNCTION_PY_SIMPLE",
     "JUMP_ABSOLUTE_QUICK",
     "LOAD_ATTR_ADAPTIVE",
     "LOAD_ATTR_INSTANCE_VALUE",
 
@@ -0,0 +1 @@
+Specialize simple calls to Python functions (no starargs, keyowrd dict, or closure)
@@ -4720,9 +4720,9 @@ _PyEval_EvalFrameDefault(PyThreadState *tstate, InterpreterFrame *frame, int thr
 
         TARGET(CALL_FUNCTION_ADAPTIVE) {
             SpecializedCacheEntry *cache = GET_CACHE();
+            nargs = cache->adaptive.original_oparg;
             if (cache->adaptive.counter == 0) {
                 next_instr--;
-                int nargs = cache->adaptive.original_oparg;
                 if (_Py_Specialize_CallFunction(
                     PEEK(nargs + 1), next_instr, nargs, cache, BUILTINS()) < 0) {
                     goto error;
@@ -4732,9 +4732,48 @@ _PyEval_EvalFrameDefault(PyThreadState *tstate, InterpreterFrame *frame, int thr
             else {
                 STAT_INC(CALL_FUNCTION, deferred);
                 cache->adaptive.counter--;
-                oparg = cache->adaptive.original_oparg;
-                JUMP_TO_INSTRUCTION(CALL_FUNCTION);
+                oparg = nargs;
+                kwnames = NULL;
+                postcall_shrink = 1;
+                goto call_function;
+            }
+        }
+
+        TARGET(CALL_FUNCTION_PY_SIMPLE) {
+            SpecializedCacheEntry *caches = GET_CACHE();
+            _PyAdaptiveEntry *cache0 = &caches[0].adaptive;
+            int argcount = cache0->original_oparg;
+            _PyCallCache *cache1 = &caches[-1].call;
+            PyObject *callable = PEEK(argcount+1);
+            DEOPT_IF(!PyFunction_Check(callable), CALL_FUNCTION);
+            PyFunctionObject *func = (PyFunctionObject *)callable;
+            DEOPT_IF(func->func_version != cache1->func_version, CALL_FUNCTION);
+            /* PEP 523 */
+            DEOPT_IF(tstate->interp->eval_frame != NULL, CALL_FUNCTION);
+            STAT_INC(CALL_FUNCTION, hit);
+            record_cache_hit(cache0);
+            InterpreterFrame *new_frame = _PyThreadState_PushFrame(
+                tstate, PyFunction_AS_FRAME_CONSTRUCTOR(func), NULL);
+            if (new_frame == NULL) {
+                goto error;
+            }
+            STACK_SHRINK(argcount);
+            for (int i = 0; i < argcount; i++) {
+                new_frame->localsplus[i] = stack_pointer[i];
+            }
+            int deflen = cache1->defaults_len;
+            for (int i = 0; i < deflen; i++) {
+                PyObject *def = PyTuple_GET_ITEM(func->func_defaults, cache1->defaults_start+i);
+                Py_INCREF(def);
+                new_frame->localsplus[argcount+i] = def;
             }
+            STACK_SHRINK(1);
+            Py_DECREF(func);
+            _PyFrame_SetStackPointer(frame, stack_pointer);
+            new_frame->previous = tstate->frame;
+            new_frame->depth = frame->depth + 1;
+            tstate->frame = frame = new_frame;
+            goto start_frame;
         }
 
         TARGET(CALL_FUNCTION_BUILTIN_O) {
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Specialize simple calls to Python functions (no starargs, keyowrd dict, or closure)`