Move Array#select to Ruby

tenderlove · tenderlove · commit 4c9134d2b2ab · 2024-07-03T11:32:40.000-07:00
This speeds up the mail benchmark by about 7% on the interpreter: ``` before: ruby 3.4.0dev (2024-07-03T17:01:41Z master f4b313f) [arm64-darwin23] after: ruby 3.4.0dev (2024-07-03T17:45:50Z ruby-select de282cacd5) [arm64-darwin23] ----- ----------- ---------- ---------- ---------- ------------- ------------ bench before (ms) stddev (%) after (ms) stddev (%) after 1st itr before/after mail 72.9 0.8 68.2 1.0 1.02 1.07 ----- ----------- ---------- ---------- ---------- ------------- ------------ Legend: - after 1st itr: ratio of before/after time for the first benchmarking iteration. - before/after: ratio of before/after time. Higher is better for after. Above 1 represents a speedup. ``` YJIT is about 13% faster: ``` before: ruby 3.4.0dev (2024-07-03T17:01:41Z master f4b313f) +YJIT [arm64-darwin23] after: ruby 3.4.0dev (2024-07-03T17:45:50Z ruby-select de282cacd5) +YJIT [arm64-darwin23] ----- ----------- ---------- ---------- ---------- ------------- ------------ bench before (ms) stddev (%) after (ms) stddev (%) after 1st itr before/after mail 51.0 0.8 45.2 0.6 1.00 1.13 ----- ----------- ---------- ---------- ---------- ------------- ------------ Legend: - after 1st itr: ratio of before/after time for the first benchmarking iteration. - before/after: ratio of before/after time. Higher is better for after. Above 1 represents a speedup. ```
diff --git a/array.c b/array.c
@@ -3807,42 +3807,6 @@ rb_ary_values_at(int argc, VALUE *argv, VALUE ary)
 }
 
 
-/*
- *  call-seq:
- *    array.select {|element| ... } -> new_array
- *    array.select -> new_enumerator
- *
- *  Calls the block, if given, with each element of +self+;
- *  returns a new +Array+ containing those elements of +self+
- *  for which the block returns a truthy value:
- *
- *    a = [:foo, 'bar', 2, :bam]
- *    a1 = a.select {|element| element.to_s.start_with?('b') }
- *    a1 # => ["bar", :bam]
- *
- *  Returns a new Enumerator if no block given:
- *
- *    a = [:foo, 'bar', 2, :bam]
- *    a.select # => #<Enumerator: [:foo, "bar", 2, :bam]:select>
- *
- */
-
-static VALUE
-rb_ary_select(VALUE ary)
-{
-    VALUE result;
-    long i;
-
-    RETURN_SIZED_ENUMERATOR(ary, 0, 0, ary_enum_length);
-    result = rb_ary_new2(RARRAY_LEN(ary));
-    for (i = 0; i < RARRAY_LEN(ary); i++) {
-        if (RTEST(rb_yield(RARRAY_AREF(ary, i)))) {
-            rb_ary_push(result, rb_ary_elt(ary, i));
-        }
-    }
-    return result;
-}
-
 struct select_bang_arg {
     VALUE ary;
     long len[2];
@@ -6696,6 +6660,12 @@ ary_sample(rb_execution_context_t *ec, VALUE ary, VALUE randgen, VALUE nv, VALUE
     return result;
 }
 
+static VALUE
+ary_sized_alloc(rb_execution_context_t *ec, VALUE self)
+{
+    return rb_ary_new2(RARRAY_LEN(self));
+}
+
 static VALUE
 ary_sample0(rb_execution_context_t *ec, VALUE ary)
 {
@@ -8702,9 +8672,7 @@ Init_Array(void)
     rb_define_method(rb_cArray, "collect!", rb_ary_collect_bang, 0);
     rb_define_method(rb_cArray, "map", rb_ary_collect, 0);
     rb_define_method(rb_cArray, "map!", rb_ary_collect_bang, 0);
-    rb_define_method(rb_cArray, "select", rb_ary_select, 0);
     rb_define_method(rb_cArray, "select!", rb_ary_select_bang, 0);
-    rb_define_method(rb_cArray, "filter", rb_ary_select, 0);
     rb_define_method(rb_cArray, "filter!", rb_ary_select_bang, 0);
     rb_define_method(rb_cArray, "keep_if", rb_ary_keep_if, 0);
     rb_define_method(rb_cArray, "values_at", rb_ary_values_at, -1);
diff --git a/array.rb b/array.rb
@@ -56,6 +56,41 @@ def each
     self
   end
 
+  # call-seq:
+  #   array.select {|element| ... } -> new_array
+  #   array.select -> new_enumerator
+  #
+  # Calls the block, if given, with each element of +self+;
+  # returns a new +Array+ containing those elements of +self+
+  # for which the block returns a truthy value:
+  #
+  #   a = [:foo, 'bar', 2, :bam]
+  #   a1 = a.select {|element| element.to_s.start_with?('b') }
+  #   a1 # => ["bar", :bam]
+  #
+  # Returns a new Enumerator if no block given:
+  #
+  #   a = [:foo, 'bar', 2, :bam]
+  #   a.select # => #<Enumerator: [:foo, "bar", 2, :bam]:select>
+  def select
+    Primitive.attr! :inline_block
+    Primitive.attr! :use_block
+
+    unless defined?(yield)
+      return Primitive.cexpr! 'SIZED_ENUMERATOR(self, 0, 0, ary_enum_length)'
+    end
+
+    _i = 0
+    value = nil
+    result = Primitive.ary_sized_alloc
+    while Primitive.cexpr!(%q{ ary_fetch_next(self, LOCAL_PTR(_i), LOCAL_PTR(value)) })
+      result << value if yield value
+    end
+    result
+  end
+
+  alias filter select
+
   # call-seq:
   #    array.shuffle!(random: Random) -> array
   #
