1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/tool/transform_mjit_header.rb
k0kubun ed935aa5be mjit_compile.c: merge initial JIT compiler
which has been developed by Takashi Kokubun <takashikkbn@gmail> as
YARV-MJIT. Many of its bugs are fixed by wanabe <s.wanabe@gmail.com>.

This JIT compiler is designed to be a safe migration path to introduce
JIT compiler to MRI. So this commit does not include any bytecode
changes or dynamic instruction modifications, which are done in original
MJIT.

This commit even strips off some aggressive optimizations from
YARV-MJIT, and thus it's slower than YARV-MJIT too. But it's still
fairly faster than Ruby 2.5 in some benchmarks (attached below).

Note that this JIT compiler passes `make test`, `make test-all`, `make
test-spec` without JIT, and even with JIT. Not only it's perfectly safe
with JIT disabled because it does not replace VM instructions unlike
MJIT, but also with JIT enabled it stably runs Ruby applications
including Rails applications.

I'm expecting this version as just "initial" JIT compiler. I have many
optimization ideas which are skipped for initial merging, and you may
easily replace this JIT compiler with a faster one by just replacing
mjit_compile.c. `mjit_compile` interface is designed for the purpose.

common.mk: update dependencies for mjit_compile.c.

internal.h: declare `rb_vm_insn_addr2insn` for MJIT.

vm.c: exclude some definitions if `-DMJIT_HEADER` is provided to
compiler. This avoids to include some functions which take a long time
to compile, e.g. vm_exec_core. Some of the purpose is achieved in
transform_mjit_header.rb (see `IGNORED_FUNCTIONS`) but others are
manually resolved for now. Load mjit_helper.h for MJIT header.
mjit_helper.h: New. This is a file used only by JIT-ed code. I'll
refactor `mjit_call_cfunc` later.
vm_eval.c: add some #ifdef switches to skip compiling some functions
like Init_vm_eval.

win32/mkexports.rb: export thread/ec functions, which are used by MJIT.

include/ruby/defines.h: add MJIT_FUNC_EXPORTED macro alis to clarify
that a function is exported only for MJIT.

array.c: export a function used by MJIT.
bignum.c: ditto.
class.c: ditto.
compile.c: ditto.
error.c: ditto.
gc.c: ditto.
hash.c: ditto.
iseq.c: ditto.
numeric.c: ditto.
object.c: ditto.
proc.c: ditto.
re.c: ditto.
st.c: ditto.
string.c: ditto.
thread.c: ditto.
variable.c: ditto.
vm_backtrace.c: ditto.
vm_insnhelper.c: ditto.
vm_method.c: ditto.

I would like to improve maintainability of function exports, but I
believe this way is acceptable as initial merging if we clarify the
new exports are for MJIT (so that we can use them as TODO list to fix)
and add unit tests to detect unresolved symbols.
I'll add unit tests of JIT compilations in succeeding commits.

Author: Takashi Kokubun <takashikkbn@gmail.com>
Contributor: wanabe <s.wanabe@gmail.com>

Part of [Feature #14235]

---

* Known issues
  * Code generated by gcc is faster than clang. The benchmark may be worse
    in macOS. Following benchmark result is provided by gcc w/ Linux.
  * Performance is decreased when Google Chrome is running
  * JIT can work on MinGW, but it doesn't improve performance at least
    in short running benchmark.
  * Currently it doesn't perform well with Rails. We'll try to fix this
    before release.

---

* Benchmark reslts

Benchmarked with:
Intel 4.0GHz i7-4790K with 16GB memory under x86-64 Ubuntu 8 Cores

- 2.0.0-p0: Ruby 2.0.0-p0
- r62186: Ruby trunk (early 2.6.0), before MJIT changes
- JIT off: On this commit, but without `--jit` option
- JIT on: On this commit, and with `--jit` option

** Optcarrot fps

Benchmark: https://github.com/mame/optcarrot

|         |2.0.0-p0 |r62186   |JIT off  |JIT on   |
|:--------|:--------|:--------|:--------|:--------|
|fps      |37.32    |51.46    |51.31    |58.88    |
|vs 2.0.0 |1.00x    |1.38x    |1.37x    |1.58x    |

** MJIT benchmarks

Benchmark: https://github.com/benchmark-driver/mjit-benchmarks
(Original: https://github.com/vnmakarov/ruby/tree/rtl_mjit_branch/MJIT-benchmarks)

|           |2.0.0-p0 |r62186   |JIT off  |JIT on   |
|:----------|:--------|:--------|:--------|:--------|
|aread      |1.00     |1.09     |1.07     |2.19     |
|aref       |1.00     |1.13     |1.11     |2.22     |
|aset       |1.00     |1.50     |1.45     |2.64     |
|awrite     |1.00     |1.17     |1.13     |2.20     |
|call       |1.00     |1.29     |1.26     |2.02     |
|const2     |1.00     |1.10     |1.10     |2.19     |
|const      |1.00     |1.11     |1.10     |2.19     |
|fannk      |1.00     |1.04     |1.02     |1.00     |
|fib        |1.00     |1.32     |1.31     |1.84     |
|ivread     |1.00     |1.13     |1.12     |2.43     |
|ivwrite    |1.00     |1.23     |1.21     |2.40     |
|mandelbrot |1.00     |1.13     |1.16     |1.28     |
|meteor     |1.00     |2.97     |2.92     |3.17     |
|nbody      |1.00     |1.17     |1.15     |1.49     |
|nest-ntimes|1.00     |1.22     |1.20     |1.39     |
|nest-while |1.00     |1.10     |1.10     |1.37     |
|norm       |1.00     |1.18     |1.16     |1.24     |
|nsvb       |1.00     |1.16     |1.16     |1.17     |
|red-black  |1.00     |1.02     |0.99     |1.12     |
|sieve      |1.00     |1.30     |1.28     |1.62     |
|trees      |1.00     |1.14     |1.13     |1.19     |
|while      |1.00     |1.12     |1.11     |2.41     |

** Discourse's script/bench.rb

Benchmark: https://github.com/discourse/discourse/blob/v1.8.7/script/bench.rb

NOTE: Rails performance was somehow a little degraded with JIT for now.
We should fix this.
(At least I know opt_aref is performing badly in JIT and I have an idea
 to fix it. Please wait for the fix.)

*** JIT off
Your Results: (note for timings- percentile is first, duration is second in millisecs)

categories_admin:
  50: 17
  75: 18
  90: 22
  99: 29
home_admin:
  50: 21
  75: 21
  90: 27
  99: 40
topic_admin:
  50: 17
  75: 18
  90: 22
  99: 32
categories:
  50: 35
  75: 41
  90: 43
  99: 77
home:
  50: 39
  75: 46
  90: 49
  99: 95
topic:
  50: 46
  75: 52
  90: 56
  99: 101

*** JIT on
Your Results: (note for timings- percentile is first, duration is second in millisecs)

categories_admin:
  50: 19
  75: 21
  90: 25
  99: 33
home_admin:
  50: 24
  75: 26
  90: 30
  99: 35
topic_admin:
  50: 19
  75: 20
  90: 25
  99: 30
categories:
  50: 40
  75: 44
  90: 48
  99: 76
home:
  50: 42
  75: 48
  90: 51
  99: 89
topic:
  50: 49
  75: 55
  90: 58
  99: 99

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62197 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-02-04 11:22:28 +00:00

184 lines
6.1 KiB
Ruby

# Copyright (C) 2017 Vladimir Makarov, <vmakarov@redhat.com>
# This is a script to transform functions to static inline.
# Usage: transform_mjit_header.rb <c-compiler> <header file> <out>
require 'fileutils'
require 'tempfile'
module MJITHeader
ATTR_VALUE_REGEXP = /[^()]|\([^()]*\)/
ATTR_REGEXP = /__attribute__\s*\(\((#{ATTR_VALUE_REGEXP})*\)\)/
FUNC_HEADER_REGEXP = /\A(\s*#{ATTR_REGEXP})*[^\[{(]*\((#{ATTR_REGEXP}|[^()])*\)(\s*#{ATTR_REGEXP})*\s*/
# For MinGW's ras.h. Those macros have its name in its definition and can't be preprocessed multiple times.
RECURSIVE_MACROS = %w[
RASCTRYINFO
RASIPADDR
]
IGNORED_FUNCTIONS = [
'vm_search_method_slowpath', # This increases the time to compile when inlined. So we use it as external function.
'rb_equal_opt', # Not used from VM and not compilable
]
# Return start..stop of last decl in CODE ending STOP
def self.find_decl(code, stop)
level = 0
stop.downto(0) do |i|
if level == 0 && stop != i && decl_found?(code, i)
return decl_start(code, i)..stop
elsif code[i] == '}'
level += 1
elsif code[i] == '{'
level -= 1
end
end
0..-1
end
def self.decl_found?(code, i)
i == 0 || code[i] == ';' || code[i] == '}'
end
def self.decl_start(code, i)
if i == 0 && code[i] != ';' && code[i] != '}'
0
else
i + 1
end
end
# Given DECL return the name of it, nil if failed
def self.decl_name_of(decl)
ident_regex = /\w+/
decl = decl.gsub(/^#.+$/, '') # remove macros
reduced_decl = decl.gsub(/#{ATTR_REGEXP}/, '') # remove attributes
su1_regex = /{[^{}]*}/
su2_regex = /{([^{}]|su1_regex)*}/
su3_regex = /{([^{}]|su2_regex)*}/ # 3 nested structs/unions is probably enough
reduced_decl.gsub!(/#{su3_regex}/, '') # remove strutcs/unions in the header
id_seq_regex = /\s*(#{ident_regex}(\s+|\s*[*]+\s*))*/
# Process function header:
match = /\A#{id_seq_regex}(?<name>#{ident_regex})\s*\(/.match(reduced_decl)
return match[:name] if match
# Process non-function declaration:
reduced_decl.gsub!(/\s*=[^;]+(?=;)/, '') # remove initialization
match = /#{id_seq_regex}(?<name>#{ident_regex})/.match(reduced_decl);
return match[:name] if match
nil
end
# Return true if CC with CFLAGS compiles successfully the current code.
# Use STAGE in the message in case of a compilation failure
def self.check_code!(code, cc, cflags, stage)
Tempfile.open(['', '.c']) do |f|
f.puts code
f.close
unless system("#{cc} #{cflags} #{f.path} 2>#{File::NULL}")
STDERR.puts "error in #{stage} header file:"
system("#{cc} #{cflags} #{f.path}")
exit 1
end
end
end
# Remove unpreprocessable macros
def self.remove_harmful_macros!(code)
code.gsub!(/^#define #{Regexp.union(RECURSIVE_MACROS)} .*$/, '')
end
# -dD outputs those macros, and it produces redefinition warnings
def self.remove_default_macros!(code)
code.gsub!(/^#define __STDC_.+$/, '')
code.gsub!(/^#define assert\([^\)]+\) .+$/, '')
end
# This makes easier to process code
def self.separate_macro_and_code(code)
code.lines.partition { |l| !l.start_with?('#') }.flatten.join('')
end
def self.write(code, out)
FileUtils.mkdir_p(File.dirname(out))
File.write("#{out}.new", code)
FileUtils.mv("#{out}.new", out)
end
# Note that this checks runruby. This conservatively covers platform names.
def self.windows?
RUBY_PLATFORM =~ /mswin|mingw|msys/
end
end
if ARGV.size != 3
STDERR.puts 'Usage: transform_mjit_header.rb <c-compiler> <header file> <out>'
exit 1
end
cc = ARGV[0]
code = File.read(ARGV[1]) # Current version of the header file.
outfile = ARGV[2]
if cc =~ /\Acl(\z| |\.exe)/
cflags = '-DMJIT_HEADER -Zs'
else
cflags = '-S -DMJIT_HEADER -fsyntax-only -Werror=implicit-function-declaration -Werror=implicit-int -Wfatal-errors'
end
if MJITHeader.windows?
MJITHeader.remove_harmful_macros!(code)
end
MJITHeader.remove_default_macros!(code)
# Check initial file correctness
MJITHeader.check_code!(code, cc, cflags, 'initial')
if MJITHeader.windows? # transformation is broken with Windows headers for now
STDERR.puts "\nSkipped transforming external functions to static on Windows."
MJITHeader.write(code, outfile)
exit 0
end
STDERR.puts "\nTransforming external functions to static:"
code = MJITHeader.separate_macro_and_code(code) # note: this does not work on MinGW
stop_pos = code.match(/^#/).begin(0) # See `separate_macro_and_code`. This ignores proprocessors.
extern_names = []
# This loop changes function declarations to static inline.
loop do
decl_range = MJITHeader.find_decl(code, stop_pos)
break if decl_range.end < 0
stop_pos = decl_range.begin - 1
decl = code[decl_range]
decl_name = MJITHeader.decl_name_of(decl)
if MJITHeader::IGNORED_FUNCTIONS.include?(decl_name) && /#{MJITHeader::FUNC_HEADER_REGEXP}{/.match(decl)
STDERR.puts "transform_mjit_header: changing definition of '#{decl_name}' to declaration"
code[decl_range] = decl.sub(/{.+}/m, ';')
elsif extern_names.include?(decl_name) && (decl =~ /#{MJITHeader::FUNC_HEADER_REGEXP};/)
decl.sub!(/(extern|static|inline) /, ' ')
unless decl_name =~ /\Aattr_\w+_\w+\z/ # skip too-many false-positive warnings in insns_info.inc.
STDERR.puts "transform_mjit_header: making declaration of '#{decl_name}' static inline"
end
code[decl_range] = "static inline #{decl}"
elsif (match = /#{MJITHeader::FUNC_HEADER_REGEXP}{/.match(decl)) && (header = match[0]) !~ /static/
extern_names << decl_name
decl[match.begin(0)...match.end(0)] = ''
if decl =~ /static/
STDERR.puts "warning: a static decl inside external definition of '#{decl_name}'"
end
header.sub!(/(extern|inline) /, ' ')
unless decl_name =~ /\Aattr_\w+_\w+\z/ # skip too-many false-positive warnings in insns_info.inc.
STDERR.puts "transform_mjit_header: making external definition of '#{decl_name}' static inline"
end
code[decl_range] = "static inline #{header}#{decl}"
end
end
# Check the final file correctness
MJITHeader.check_code!(code, cc, cflags, 'final')
MJITHeader.write(code, outfile)