* vm_core.h, vm_insnhelper.c, vm_eval.c (OPT_CALL_CFUNC_WITHOUT_FRAME):

  add a new otpimization and its macro `OPT_CALL_CFUNC_WITHOUT_FRAME'.
  This optimization makes all cfunc method calls `frameless', which
  is fster than ordinal cfunc method call.
  If `frame' is needed (for example, it calls another method with
  `rb_funcall()'), then build a frame. In other words, this
  optimization delays frame building.
  However, to delay the frame building, we need additional overheads:
  (1) Store the last call information.
  (2) Check the delayed frame buidling before the frame is needed.
  (3) Overhead to build a delayed frame.
  rb_thread_t::passed_ci is storage of delayed cfunc call information.
  (1) is lightweight because it is only 1 assignment to `passed_ci'.
  To achieve (2), we modify GET_THREAD() to check `passed_ci' every
  time. It causes 10% overhead on my envrionment.
  This optimization only works for cfunc methods which do not need
  their `frame'.
  After evaluation on my environment, this optimization does not
  effective every time. Because of this evaluation results, this
  optimization is disabled at default.
* vm_insnhelper.c, vm.c: add VM_PROFILE* macros to measure behaviour
  of VM internals. I will extend this feature.
* vm_method.c, method.h: change parameters of the `invoker' function.
  Receive `func' pointer as the first parameter.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37293 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 22 insertions, 2 deletions

diff --git a/vm_core.h b/vm_core.h
index 5e68b8e9ab..e2d18c1aab 100644
--- a/vm_core.h
+++ b/vm_core.h
@@ -166,7 +166,7 @@ typedef struct rb_call_info_struct {
 	int opt_pc; /* used by iseq */
 	long index; /* used by ivar */
 	int missing_reason; /* used by method_missing */
-	VALUE (*func)(ANYARGS); /* used by cfunc */
+	int inc_sp; /* used by cfunc */
     } aux;
 
     VALUE (*call)(struct rb_thread_struct *th, struct rb_control_frame_struct *cfp, struct rb_call_info_struct *ci);
@@ -478,6 +478,9 @@ typedef struct rb_thread_struct {
     /* for bmethod */
     const rb_method_entry_t *passed_me;
 
+    /* for cfunc */
+    rb_call_info_t *passed_ci;
+
     /* for load(true) */
     VALUE top_self;
     VALUE top_wrapper;
@@ -816,7 +819,24 @@ extern rb_vm_t *ruby_current_vm;
 extern rb_event_flag_t ruby_vm_event_flags;
 
 #define GET_VM() ruby_current_vm
-#define GET_THREAD() ruby_current_thread
+
+#ifndef OPT_CALL_CFUNC_WITHOUT_FRAME
+#define OPT_CALL_CFUNC_WITHOUT_FRAME 0
+#endif
+
+static inline rb_thread_t *
+GET_THREAD(void)
+{
+    rb_thread_t *th = ruby_current_thread;
+#if OPT_CALL_CFUNC_WITHOUT_FRAME
+    if (UNLIKELY(th->passed_ci != 0)) {
+	void vm_call_cfunc_push_frame(rb_thread_t *th);
+	vm_call_cfunc_push_frame(th);
+    }
+#endif
+    return th;
+}
+
 #define rb_thread_set_current_raw(th) (void)(ruby_current_thread = (th))
 #define rb_thread_set_current(th) do { \
     if ((th)->vm->running_thread != (th)) { \