This commit implements the Object Shapes technique in CRuby.

Object Shapes is used for accessing instance variables and representing the
"frozenness" of objects.  Object instances have a "shape" and the shape
represents some attributes of the object (currently which instance variables are
set and the "frozenness").  Shapes form a tree data structure, and when a new
instance variable is set on an object, that object "transitions" to a new shape
in the shape tree.  Each shape has an ID that is used for caching. The shape
structure is independent of class, so objects of different types can have the
same shape.

For example:

```ruby
class Foo
  def initialize
    # Starts with shape id 0
    @a = 1 # transitions to shape id 1
    @b = 1 # transitions to shape id 2
  end
end

class Bar
  def initialize
    # Starts with shape id 0
    @a = 1 # transitions to shape id 1
    @b = 1 # transitions to shape id 2
  end
end

foo = Foo.new # `foo` has shape id 2
bar = Bar.new # `bar` has shape id 2
```

Both `foo` and `bar` instances have the same shape because they both set
instance variables of the same name in the same order.

This technique can help to improve inline cache hits as well as generate more
efficient machine code in JIT compilers.

This commit also adds some methods for debugging shapes on objects.  See
`RubyVM::Shape` for more details.

For more context on Object Shapes, see [Feature: #18776]

Co-Authored-By: Aaron Patterson <tenderlove@ruby-lang.org>
Co-Authored-By: Eileen M. Uchitelle <eileencodes@gmail.com>
Co-Authored-By: John Hawthorn <john@hawthorn.email>
This commit is contained in:
Jemma Issroff 2022-09-23 13:54:42 -04:00 committed by Aaron Patterson
parent a05b261464
commit d594a5a8bd
No known key found for this signature in database
GPG key ID: 953170BCB4FFAFC6
41 changed files with 2328 additions and 919 deletions

View file

@ -39,6 +39,7 @@
#include "ruby/st.h"
#include "ruby/util.h"
#include "builtin.h"
#include "shape.h"
#define BITSPERSHORT (2*CHAR_BIT)
#define SHORTMASK ((1<<BITSPERSHORT)-1)
@ -622,10 +623,6 @@ w_obj_each(st_data_t key, st_data_t val, st_data_t a)
}
return ST_CONTINUE;
}
if (!ivarg->num_ivar) {
rb_raise(rb_eRuntimeError, "instance variable added to %"PRIsVALUE" instance",
CLASS_OF(arg->obj));
}
--ivarg->num_ivar;
w_symbol(ID2SYM(id), arg->arg);
w_object(value, arg->arg, arg->limit);
@ -720,6 +717,7 @@ has_ivars(VALUE obj, VALUE encname, VALUE *ivobj)
static void
w_ivar_each(VALUE obj, st_index_t num, struct dump_call_arg *arg)
{
shape_id_t shape_id = rb_shape_get_shape_id(arg->obj);
struct w_ivar_arg ivarg = {arg, num};
if (!num) return;
rb_ivar_foreach(obj, w_obj_each, (st_data_t)&ivarg);
@ -727,6 +725,10 @@ w_ivar_each(VALUE obj, st_index_t num, struct dump_call_arg *arg)
rb_raise(rb_eRuntimeError, "instance variable removed from %"PRIsVALUE" instance",
CLASS_OF(arg->obj));
}
if (shape_id != rb_shape_get_shape_id(arg->obj)) {
rb_raise(rb_eRuntimeError, "instance variable added to %"PRIsVALUE" instance",
CLASS_OF(arg->obj));
}
}
static void