1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

string.c: use str_enc_fastpath in TERM_LEN

Browse Source 
Not having to fetch the rb_encoding save a significant
amount of time.

Additionally, even when we have to fetch it, we can do
it faster using `ENCODING_GET` rather than `rb_enc_get`.

```
compare-ruby: ruby 3.2.0dev (2022-07-19T08:41:40Z master cb9fd920a3) [arm64-darwin21]
built-ruby: ruby 3.2.0dev (2022-07-21T11:16:16Z faster-buffer-conc.. 4f001f0748) [arm64-darwin21]
warming up...

|                      |compare-ruby|built-ruby|
|:---------------------|-----------:|---------:|
|binary_concat_utf8    |    510.580k|  565.600k|
|                      |           -|     1.11x|
|binary_concat_binary  |    512.653k|  571.483k|
|                      |           -|     1.11x|
|utf8_concat_utf8      |    511.396k|  566.879k|
|                      |           -|     1.11x|
```
This commit is contained in:
Jean Boussier 2022-07-21 13:16:16 +02:00
parent 80672b2d0e
commit f954c5dae4
Notes: git 2022-07-21 22:07:11 +09:00 
Merged: https://github.com/ruby/ruby/pull/6160
2 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
benchmark/string_concat.yml
View File

@ -1,6 +1,7 @@
prelude: | prelude: |
CHUNK = "a" * 64 CHUNK = "a" * 64
BCHUNK = "a".b * 64 BCHUNK = "a".b * 64
GC.disable # GC causes a lot of variance
benchmark: benchmark:
binary_concat_utf8: | binary_concat_utf8: |
buffer = String.new(capacity: 4096, encoding: Encoding::BINARY) buffer = String.new(capacity: 4096, encoding: Encoding::BINARY)
@ -11,7 +12,7 @@ benchmark:
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
binary_concat_binary: | binary_concat_binary: |
buffer = String.new(capacity: 4096, encoding: Encoding::BINARY) buffer = String.new(capacity: 4096, encoding: Encoding::BINARY)
buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK
@ -21,7 +22,7 @@ benchmark:
buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK
buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK
buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK
buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK buffer << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK << BCHUNK
utf8_concat_utf8: | utf8_concat_utf8: |
buffer = String.new(capacity: 4096, encoding: Encoding::UTF_8) buffer = String.new(capacity: 4096, encoding: Encoding::UTF_8)
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
@ -31,4 +32,4 @@ benchmark:
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK
buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK buffer << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK << CHUNK

30
string.c
View File

@ -150,7 +150,21 @@ VALUE rb_cSymbol;
}\ }\
} while (0) } while (0)
#define TERM_LEN(str) rb_enc_mbminlen(rb_enc_get(str)) static inline bool
str_enc_fastpath(VALUE str)
{
// The overwhelming majority of strings are in one of these 3 encodings.
switch (ENCODING_GET_INLINED(str)) {
case ENCINDEX_ASCII_8BIT:
case ENCINDEX_UTF_8:
case ENCINDEX_US_ASCII:
return true;
default:
return false;
}
}
#define TERM_LEN(str) (str_enc_fastpath(str) ? 1 : rb_enc_mbminlen(rb_enc_from_index(ENCODING_GET(str))))
#define TERM_FILL(ptr, termlen) do {\ #define TERM_FILL(ptr, termlen) do {\
char *const term_fill_ptr = (ptr);\ char *const term_fill_ptr = (ptr);\
const int term_fill_len = (termlen);\ const int term_fill_len = (termlen);\
@ -3311,20 +3325,6 @@ rb_str_buf_cat_ascii(VALUE str, const char *ptr)
} }
} }
static inline bool
str_enc_fastpath(VALUE str)
{
// The overwhelming majority of strings are in one of these 3 encodings.
switch (ENCODING_GET_INLINED(str)) {
case ENCINDEX_ASCII_8BIT:
case ENCINDEX_UTF_8:
case ENCINDEX_US_ASCII:
return true;
default:
return false;
}
}
VALUE VALUE
rb_str_buf_append(VALUE str, VALUE str2) rb_str_buf_append(VALUE str, VALUE str2)
{ {