Add concattoarray VM instruction

This instruction is similar to concatarray, but assumes the first
object is already an array, and appends to it directly.  This is
different than concatarray, which will create a new array instead
of appending to an existing array.

Additionally, for both concatarray and concattoarray, if the second
argument cannot be converted to an array, then just push it onto
the array, instead of creating a new array to wrap it, and then
using concat array.  This saves an array allocation in that case.

This allows `f(*a, *a, *1)` to allocate only a single array on the
caller side (which can be reused on the callee side in the case of
`def f(*a)`). Prior to this commit, `f(*a, *a, *1)` would generate
4 arrays:

* a dupped by splatarray true
* a dupped again by first concatarray
* 1 wrapped in array by third splatarray
* result of [*a, *a] dupped by second concatarray

Instructions Before for `a = []; f(*a, *a, *1)`:

```
0000 newarray                               0                         (   1)[Li]
0002 setlocal_WC_0                          a@0
0004 putself
0005 getlocal_WC_0                          a@0
0007 splatarray                             true
0009 getlocal_WC_0                          a@0
0011 splatarray                             false
0013 concatarray
0014 putobject_INT2FIX_1_
0015 splatarray                             false
0017 concatarray
0018 opt_send_without_block                 <calldata!mid:g, argc:1, ARGS_SPLAT|ARGS_SPLAT_MUT|FCALL>
0020 leave
```

Instructions After for `a = []; f(*a, *a, *1)`:

```
0000 newarray                               0                         (   1)[Li]
0002 setlocal_WC_0                          a@0
0004 putself
0005 getlocal_WC_0                          a@0
0007 splatarray                             true
0009 getlocal_WC_0                          a@0
0011 concattoarray
0012 putobject_INT2FIX_1_
0013 concattoarray
0014 opt_send_without_block                 <calldata!mid:f, argc:1, ARGS_SPLAT|ARGS_SPLAT_MUT|FCALL>
0016 leave
```
This commit is contained in:
Jeremy Evans 2023-11-24 20:23:58 -08:00
parent 22e488464a
commit 6e06d0d180
3 changed files with 38 additions and 9 deletions

View File

@ -6198,8 +6198,7 @@ setup_args_core(rb_iseq_t *iseq, LINK_ANCHOR *const args, const NODE *argn,
argc += 1;
}
else {
ADD_INSN1(args, argn, splatarray, Qfalse);
ADD_INSN(args, argn, concatarray);
ADD_INSN(args, argn, concattoarray);
}
// f(..., *a, ..., k1:1, ...) #=> f(..., *[*a, ...], **{k1:1, ...})

View File

@ -505,7 +505,9 @@ expandarray
vm_expandarray(GET_CFP(), ary, num, (int)flag);
}
/* concat two arrays */
/* concat two arrays, without modifying first array.
* attempts to convert both objects to arrays using to_a.
*/
DEFINE_INSN
concatarray
()
@ -516,6 +518,20 @@ concatarray
ary = vm_concat_array(ary1, ary2);
}
/* concat second array to first array.
* first argument must already be an array.
* attempts to convert second object to array using to_a.
*/
DEFINE_INSN
concattoarray
()
(VALUE ary1, VALUE ary2)
(VALUE ary)
// attr bool leaf = false; /* has rb_check_array_type() */
{
ary = vm_concat_to_array(ary1, ary2);
}
/* call to_a on array ary to splat */
DEFINE_INSN
splatarray

View File

@ -5204,15 +5204,29 @@ vm_concat_array(VALUE ary1, VALUE ary2st)
if (NIL_P(tmp1)) {
tmp1 = rb_ary_new3(1, ary1);
}
if (NIL_P(tmp2)) {
tmp2 = rb_ary_new3(1, ary2);
}
if (tmp1 == ary1) {
tmp1 = rb_ary_dup(ary1);
}
return rb_ary_concat(tmp1, tmp2);
if (NIL_P(tmp2)) {
return rb_ary_push(tmp1, ary2);
} else {
return rb_ary_concat(tmp1, tmp2);
}
}
static VALUE
vm_concat_to_array(VALUE ary1, VALUE ary2st)
{
/* ary1 must be a newly created array */
const VALUE ary2 = ary2st;
VALUE tmp2 = rb_check_to_array(ary2);
if (NIL_P(tmp2)) {
return rb_ary_push(ary1, ary2);
} else {
return rb_ary_concat(ary1, tmp2);
}
}
// YJIT implementation is using the C function