ruby/internal/basic_operators.h
Daniel Colson e69b91fae4 Introduce BOP_CMP for optimized comparison
Prior to this commit the `OPTIMIZED_CMP` macro relied on a method lookup
to determine whether `<=>` was overridden. The result of the lookup was
cached, but only for the duration of the specific method that
initialized the cmp_opt_data cache structure.

With this method lookup, `[x,y].max` is slower than doing `x > y ?
x : y` even though there's an optimized instruction for "new array max".
(John noticed somebody a proposed micro-optimization based on this fact
in https://github.com/mastodon/mastodon/pull/19903.)

```rb
a, b = 1, 2
Benchmark.ips do |bm|
  bm.report('conditional') { a > b ? a : b }
  bm.report('method') { [a, b].max }
  bm.compare!
end
```

Before:

```
Comparison:
         conditional: 22603733.2 i/s
              method: 19820412.7 i/s - 1.14x  (± 0.00) slower
```

This commit replaces the method lookup with a new CMP basic op, which
gives the examples above equivalent performance.

After:

```
Comparison:
              method: 24022466.5 i/s
         conditional: 23851094.2 i/s - same-ish: difference falls within
error
```

Relevant benchmarks show an improvement to Array#max and Array#min when
not using the optimized newarray_max instruction as well. They are
noticeably faster for small arrays with the relevant types, and the same
or maybe a touch faster on larger arrays.

```
$ make benchmark COMPARE_RUBY=<master@5958c305> ITEM=array_min
$ make benchmark COMPARE_RUBY=<master@5958c305> ITEM=array_max
```

The benchmarks added in this commit also look generally improved.

Co-authored-by: John Hawthorn <jhawthorn@github.com>
2022-12-06 12:37:23 -08:00

63 lines
1.4 KiB
C

#ifndef INTERNAL_BOP_H /*-*-C-*-vi:se ft=c:*/
#define INTERNAL_BOP_H
#include "internal.h"
#include "ruby/internal/dllexport.h"
enum ruby_basic_operators {
BOP_PLUS,
BOP_MINUS,
BOP_MULT,
BOP_DIV,
BOP_MOD,
BOP_EQ,
BOP_EQQ,
BOP_LT,
BOP_LE,
BOP_LTLT,
BOP_AREF,
BOP_ASET,
BOP_LENGTH,
BOP_SIZE,
BOP_EMPTY_P,
BOP_NIL_P,
BOP_SUCC,
BOP_GT,
BOP_GE,
BOP_NOT,
BOP_NEQ,
BOP_MATCH,
BOP_FREEZE,
BOP_UMINUS,
BOP_MAX,
BOP_MIN,
BOP_CALL,
BOP_AND,
BOP_OR,
BOP_CMP,
BOP_LAST_
};
MJIT_SYMBOL_EXPORT_BEGIN
RUBY_EXTERN short ruby_vm_redefined_flag[BOP_LAST_];
MJIT_SYMBOL_EXPORT_END
/* optimize insn */
#define INTEGER_REDEFINED_OP_FLAG (1 << 0)
#define FLOAT_REDEFINED_OP_FLAG (1 << 1)
#define STRING_REDEFINED_OP_FLAG (1 << 2)
#define ARRAY_REDEFINED_OP_FLAG (1 << 3)
#define HASH_REDEFINED_OP_FLAG (1 << 4)
/* #define BIGNUM_REDEFINED_OP_FLAG (1 << 5) */
#define SYMBOL_REDEFINED_OP_FLAG (1 << 6)
#define TIME_REDEFINED_OP_FLAG (1 << 7)
#define REGEXP_REDEFINED_OP_FLAG (1 << 8)
#define NIL_REDEFINED_OP_FLAG (1 << 9)
#define TRUE_REDEFINED_OP_FLAG (1 << 10)
#define FALSE_REDEFINED_OP_FLAG (1 << 11)
#define PROC_REDEFINED_OP_FLAG (1 << 12)
#define BASIC_OP_UNREDEFINED_P(op, klass) (LIKELY(ruby_vm_redefined_flag[(op)]&(klass)) == 0)
#endif