diff options
| author | Jeremy Evans <code@jeremyevans.net> | 2023-04-01 09:19:35 -0700 |
|---|---|---|
| committer | Jeremy Evans <code@jeremyevans.net> | 2023-04-25 08:06:16 -0700 |
| commit | af2da6419aba1e242e851664b4e6816aeb27f8cb (patch) | |
| tree | 6c9a085aa6ad05f1134a0c52fd6e58f5c3bf39fd /benchmark | |
| parent | f6254f77f7a7c4d1f11180b3b382680868bd9ee4 (diff) | |
| download | ruby-af2da6419aba1e242e851664b4e6816aeb27f8cb.tar.gz | |
Optimize cfunc calls for f(*a) and f(*a, **kw) if kw is empty
This optimizes the following calls:
* ~10-15% for f(*a) when a does not end with a flagged keywords hash
* ~10-15% for f(*a) when a ends with an empty flagged keywords hash
* ~35-40% for f(*a, **kw) if kw is empty
This still copies the array contents to the VM stack, but avoids some
overhead. It would be faster to use the array pointer directly,
but that could cause problems if the array was modified during
the call to the function. You could do that optimization for frozen
arrays, but as splatting frozen arrays is uncommon, and the speedup
is minimal (<5%), it doesn't seem worth it.
The vm_send_cfunc benchmark has been updated to test additional cfunc
call types, and the numbers above were taken from the benchmark results.
Diffstat (limited to 'benchmark')
| -rw-r--r-- | benchmark/vm_send_cfunc.yml | 15 |
1 files changed, 13 insertions, 2 deletions
diff --git a/benchmark/vm_send_cfunc.yml b/benchmark/vm_send_cfunc.yml index b114ac317d..6f12b65176 100644 --- a/benchmark/vm_send_cfunc.yml +++ b/benchmark/vm_send_cfunc.yml @@ -1,3 +1,14 @@ +prelude: | + ary = [] + kw = {a: 1} + empty_kw = {} + kw_ary = [Hash.ruby2_keywords_hash(a: 1)] + empty_kw_ary = [Hash.ruby2_keywords_hash({})] benchmark: - vm_send_cfunc: self.class -loop_count: 100000000 + vm_send_cfunc: itself + vm_send_cfunc_splat: itself(*ary) + vm_send_cfunc_splat_kw_hash: equal?(*kw_ary) + vm_send_cfunc_splat_empty_kw_hash: itself(*empty_kw_ary) + vm_send_cfunc_splat_kw: equal?(*ary, **kw) + vm_send_cfunc_splat_empty_kw: itself(*ary, **empty_kw) +loop_count: 20000000 |