From 346aa557b31fe96760e505d30da26eb7a846bac9 Mon Sep 17 00:00:00 2001
From: Takashi Kokubun <takashikkbn@gmail.com>
Date: Sun, 4 Aug 2019 20:11:00 +0900
Subject: Make opt_eq and opt_neq insns leaf

# Benchmark zero?

```
require 'benchmark/ips'

Numeric.class_eval do
  def ruby_zero?
    self == 0
  end
end

Benchmark.ips do |x|
  x.report('0.zero?') { 0.ruby_zero? }
  x.report('1.zero?') { 1.ruby_zero? }
  x.compare!
end
```

## VM
No significant impact for VM.

### before
ruby 2.7.0dev (2019-08-04T02:56:02Z master 2d8c037e97) [x86_64-linux]

  0.zero?: 21855445.5 i/s
  1.zero?: 21770817.3 i/s - same-ish: difference falls within error

### after
ruby 2.7.0dev (2019-08-04T11:17:10Z opt-eq-leaf 6404bebd6a) [x86_64-linux]

  1.zero?: 21958912.3 i/s
  0.zero?: 21881625.9 i/s - same-ish: difference falls within error

## JIT
The performance improves about 1.23x.

### before
ruby 2.7.0dev (2019-08-04T02:56:02Z master 2d8c037e97) +JIT [x86_64-linux]

  0.zero?: 36343111.6 i/s
  1.zero?: 36295153.3 i/s - same-ish: difference falls within error

### after
ruby 2.7.0dev (2019-08-04T11:17:10Z opt-eq-leaf 6404bebd6a) +JIT [x86_64-linux]

  0.zero?: 44740467.2 i/s
  1.zero?: 44363616.1 i/s - same-ish: difference falls within error

# Benchmark str == str / str != str

```
# frozen_string_literal: true
require 'benchmark/ips'

Benchmark.ips do |x|
  x.report('a == a') { 'a' == 'a' }
  x.report('a == b') { 'a' == 'b' }
  x.report('a != a') { 'a' != 'a' }
  x.report('a != b') { 'a' != 'b' }
  x.compare!
end
```

## VM
No significant impact for VM.

### before
ruby 2.7.0dev (2019-08-04T02:56:02Z master 2d8c037e97) [x86_64-linux]

  a == a: 27286219.0 i/s
  a != a: 24892389.5 i/s - 1.10x  slower
  a == b: 23623635.8 i/s - 1.16x  slower
  a != b: 21800958.0 i/s - 1.25x  slower

### after
ruby 2.7.0dev (2019-08-04T11:17:10Z opt-eq-leaf 6404bebd6a) [x86_64-linux]

  a == a: 27224016.2 i/s
  a != a: 24490109.5 i/s - 1.11x  slower
  a == b: 23391052.4 i/s - 1.16x  slower
  a != b: 21811321.7 i/s - 1.25x  slower

## JIT
The performance improves on JIT a little.

### before
ruby 2.7.0dev (2019-08-04T02:56:02Z master 2d8c037e97) +JIT [x86_64-linux]

  a == a: 42010674.7 i/s
  a != a: 38920311.2 i/s - same-ish: difference falls within error
  a == b: 32574262.2 i/s - 1.29x  slower
  a != b: 32099790.3 i/s - 1.31x  slower

### after
ruby 2.7.0dev (2019-08-04T11:17:10Z opt-eq-leaf 6404bebd6a) +JIT [x86_64-linux]

  a == a: 46902738.8 i/s
  a != a: 43097258.6 i/s - 1.09x  slower
  a == b: 35822018.4 i/s - 1.31x  slower
  a != b: 33377257.8 i/s - 1.41x  slower

This is needed towards Bug#15589.
Closes: https://github.com/ruby/ruby/pull/2318
---
 internal.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'internal.h')

diff --git a/internal.h b/internal.h
index 5ecb229413..d391597d54 100644
--- a/internal.h
+++ b/internal.h
@@ -2125,6 +2125,22 @@ VALUE rb_str_eql(VALUE str1, VALUE str2);
 VALUE rb_obj_as_string_result(VALUE str, VALUE obj);
 const char *ruby_escaped_char(int c);
 
+/* expect tail call optimization */
+static inline VALUE
+rb_str_eql_internal(const VALUE str1, const VALUE str2)
+{
+    const long len = RSTRING_LEN(str1);
+    const char *ptr1, *ptr2;
+
+    if (len != RSTRING_LEN(str2)) return Qfalse;
+    if (!rb_str_comparable(str1, str2)) return Qfalse;
+    if ((ptr1 = RSTRING_PTR(str1)) == (ptr2 = RSTRING_PTR(str2)))
+        return Qtrue;
+    if (memcmp(ptr1, ptr2, len) == 0)
+        return Qtrue;
+    return Qfalse;
+}
+
 /* symbol.c */
 #ifdef RUBY_ENCODING_H
 VALUE rb_sym_intern(const char *ptr, long len, rb_encoding *enc);
-- 
cgit v1.2.3