| Age | Commit message (Collapse) | Author |
|---|
|
This commit caused test-all failure with --jit-wait.
I don't know the reason yet, but let me revert it to normalize CI.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64314 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
about the pc motion reason
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64284 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
to fix the wrong line number on #caller_locations or rb_profile_frames.
Actually we would be able to move it only when method call (of
caller_locations) or C extension invocation (calling rb_profile_frames)
can happen.
This degrades performance. Optcarrot fps becomes...
before: 71.78976052783555
after: 67.65429356624131
I think I can lazily move it and fix the performance issue, even
improving the performance for the situation catch table exists.
But let me fix this bug first...
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64283 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
_mjit_compile_send.erb: simplify code using the change
insns.def: adapt to the interface change
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64281 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
implementation. This had no major performance impact by effort to keep
them inlined.
vm_insnhelper.c: ditto
mjit_compile.c: just update the comment about opt_pc=0 assumption
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64280 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
because it's more suitable to describe the current behavior now.
tool/ruby_vm/models/bare_instructions.rb: ditto.
tool/ruby_vm/views/_insn_entry.erb: ditto.
tool/ruby_vm/views/_mjit_compile_insn_body.erb: ditto.
tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb: ditto.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64053 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
This retries r62655, which was reverted at r63863 for r63763.
tool/ruby_vm/views/_mjit_compile_insn.erb: revert the revert.
tool/ruby_vm/views/_mjit_compile_insn_body.erb: ditto.
tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb: ditto.
tool/ruby_vm/views/_mjit_compile_send.erb: ditto.
tool/ruby_vm/views/mjit_compile.inc.erb: ditto.
tool/ruby_vm/views/_insn_entry.erb: revert half of r63763. The commit
was originally reverted since changing pc motion was bad for tracing,
but changing sp motion was totally fine. For JIT, I wanna resurrect
the sp motion change in r62051.
tool/ruby_vm/models/bare_instructions.rb: ditto.
insns.def: ditto.
vm_insnhelper.c: ditto.
vm_insnhelper.h: ditto.
* benchmark
$ benchmark-driver benchmark.yml --rbenv 'before;after;before --jit;after --jit' --repeat-count 12 -v
before: ruby 2.6.0dev (2018-07-19 trunk 63998) [x86_64-linux]
after: ruby 2.6.0dev (2018-07-19 add-sp 63998) [x86_64-linux]
last_commit=mjit_compile.c: reduce sp motion on JIT
before --jit: ruby 2.6.0dev (2018-07-19 trunk 63998) +JIT [x86_64-linux]
after --jit: ruby 2.6.0dev (2018-07-19 add-sp 63998) +JIT [x86_64-linux]
last_commit=mjit_compile.c: reduce sp motion on JIT
Calculating -------------------------------------
before after before --jit after --jit
Optcarrot Lan_Master.nes 51.354 50.238 70.010 72.139 fps
Comparison:
Optcarrot Lan_Master.nes
after --jit: 72.1 fps
before --jit: 70.0 fps - 1.03x slower
before: 51.4 fps - 1.40x slower
after: 50.2 fps - 1.44x slower
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63999 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
Due to trunk-mjit CI failures:
http://ci.rvm.jp/results/trunk-mjit@silicon-docker/1130097
http://ci.rvm.jp/results/trunk-mjit@silicon-docker/1130196
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63991 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
This optimization was reverted on r63863, but this commit resurrects the
optimization to skip some sp motions on JIT execution.
tool/ruby_vm/views/_mjit_compile_insn_body.erb: ditto
tool/ruby_vm/views/_mjit_compile_insn.erb: ditto
insns.def: resurrect handles_frame as handles_stack, which was deleted
on r63763.
tool/ruby_vm/models/bare_instructions.rb: ditto
vm_insnhelper.c: prevent moving sp outside insns.def to allow modifying
it by JIT.
* Optcarrot benchmark
$ benchmark-driver benchmark.yml --rbenv 'before --jit;after --jit' --repeat-count 12 -v
before --jit: ruby 2.6.0dev (2018-07-17 trunk 63987) +JIT [x86_64-linux]
after --jit: ruby 2.6.0dev (2018-07-17 local-stack 63987) +JIT [x86_64-linux]
last_commit=mjit_compile.c: resurrect local variable stack
Calculating -------------------------------------
before --jit after --jit
Optcarrot Lan_Master.nes 70.518 72.144 fps
Comparison:
Optcarrot Lan_Master.nes
after --jit: 72.1 fps
before --jit: 70.5 fps - 1.02x slower
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63988 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
for catch_except_p case
Partially solving Bug#14892
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63874 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
r63655 was tightly coupled to handle_frames and some assumptions seems
to have been broken by r63763.
To partially resolve Bug#14892, this reverts the optimization for now. I
want to make MJIT CI happy first and then I'll probably retry r63655 by
partially reverting r63763 for sp changes.
The skipped test is not fixed yet.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63863 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
I introduced this mechanism in r62051 to speed things up. Later it
was reported that the change causes problems. I searched for
workarounds but nothing seemed appropriate. I hereby officially
give it up. The idea to move ADD_PC around was a mistake.
Fixes [Bug #14809] and [Bug #14834].
Signed-off-by: Urabe, Shyouhei <[email protected]>
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63763 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
It never becomes `dispatched: true` with the current code.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63751 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
for now, which was committed in r63333.
Currently trunk's JIT seems to have some wrong behaviors, and this is
the most suspicious culprit of them for now. In the future, I may have
a strict test environment to detect the cause, but there's no enough
time to test this until preview2. So let me revert this and see how it
goes after this.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63455 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
reverting r63379 (revert of r63360).
The cause of error seems to be r63350. See r63382.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63384 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
Revert "_mjit_compile_send.erb: inline recursive call"
I reverted r63360 in r63379, but the errors were reproductive from
r63350. So I need to revert this.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63382 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
Revert "_mjit_compile_pc_and_sp.erb: make sure no uninitialized"
This triggered some `NoMethodError`s which seem to be caused by the
commit like: https://travis-ci.org/k0kubun/mjit-test/builds/376416934
I'll add tests and fix it later...
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63379 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
area on VM stack to prevent SEGV on GC. GC may mark every value in VM
stack.
Unfortunately I couldn't write a test for it... So let me explain the
situation.
SEGV example:
https://gist.github.com/k0kubun/c7cea2b5761ffdff29ec79ea1a8f7f91
```
$ ruby --dump=insns -e 'def oct(num, len); "%0#{len}o" % num; end'
== disasm: #<ISeq:oct@-e:1 (1,0)-(1,41)> (catch: FALSE)
local table (size: 2, argc: 2 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1])
[ 2] num@0<Arg> [ 1] len@1<Arg>
0000 putobject "%0" ( 1)[LiCa]
0002 getlocal_WC_0 len@1
0004 dup
0005 checktype T_STRING
0007 branchif 14
0009 dup
0010 opt_send_without_block <callinfo!mid:to_s, argc:0, FCALL|ARGS_SIMPLE>, <callcache>
0013 tostring
0014 putobject "o"
0016 concatstrings 3
0018 getlocal_WC_0 num@0
0020 opt_mod <callinfo!mid:%, argc:1, ARGS_SIMPLE>, <callcache>
0023 leave [Re]
```
Prior to this commit, after arguments are pushed on 0010, stacks were:
VM stack: [uninitialized, uninitialized, len]
JIT stack: ["%0", len, len]
And then, when GC is invoked on 0016, VM stack will be [uninitialized, uninitialized]
and those uninitialized values will be marked by GC.
With this commit, after arguments are pushed on 0010, stacks will be:
VM stack: [len]
JIT stack: ["%0", len, len]
And VM stack will be [] on 0016.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63360 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
mjit_compile.c: propagate funcname to compile_insn
test_jit.rb: add test covering this behavior
* Benchmark
```
require 'benchmark_driver'
Benchmark.driver(runner: :time, repeat_count: 4) do |x|
x.prelude %{
def fib(x)
return x if x == 0 || x == 1
fib(x-1) + fib(x-2)
end
}
x.report 'fib(40)'
x.loop_count 1
x.rbenv(
'before,--jit',
'before',
'after,--jit',
'after',
)
x.verbose
end
```
```
before,--jit: ruby 2.6.0dev (2018-05-08 trunk 63349) +JIT [x86_64-linux]
before: ruby 2.6.0dev (2018-05-08 trunk 63349) [x86_64-linux]
after,--jit: ruby 2.6.0dev (2018-05-08 trunk 63349) +JIT [x86_64-linux]
last_commit=_mjit_compile_send.erb: inline recursive call
after: ruby 2.6.0dev (2018-05-08 trunk 63349) [x86_64-linux]
last_commit=_mjit_compile_send.erb: inline recursive call
Calculating -------------------------------------
before,--jit before after,--jit after
fib(40) 2.886 8.685 2.562 8.800 s - 1.000 times
Comparison:
fib(40)
after,--jit: 2.6 s
before,--jit: 2.9 s - 1.13x slower
before: 8.7 s - 3.39x slower
after: 8.8 s - 3.44x slower
```
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63350 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
This reverts r63249 (revert r63212) and fixes a bug in it. The test to
prevent the bug is added as well.
vm_insnhelper.c: add `index` argument to vm_getivar. The argument is
created so that MJIT can pass the value of `cc->aux.index` on compilation
time. The cache invalidation in _mjit_compile_send_guard.erb is only
working for the cache value on compilation time.
Note: As `index` is always passed as constant and it's force-inlined,
the performance of `vm_getivar` won't be degraded in VM.
_mjit_compile_send_guard.erb: New. Used to invalidate inlined values of cc.
common.mk: update dependencies for _mjit_compile_send_guard.erb
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63333 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
between branches.
mjit_compile.inc.erb: move the compiled_for_pos reference to
mjit_compile.c
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63331 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
on JIT compilation. r63092 was risky without this check.
mjit_compile.c: update comment about stack consistency check
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63329 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63318 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
/var/folders/b0/9hgj_tyx10zgkcbyx3_j2dlr0000gn/T//_ruby_mjit_p72619u0.c:37:58: warning: incompatible integer to pointer
conversion passing 'long' to parameter of type 'const struct rb_call_info *' [-Wint-conversion]
vm_caller_setup_arg_block(ec, reg_cfp, &calling, 0x7ff6b2e10ca0, 0x7ff6b3847108, FALSE);
^~~~~~~~~~~~~~
/Users/kokubun/.rbenv/versions/ruby-svn/include/ruby-2.6.0/x86_64-darwin16/rb_mjit_min_header-2.6.0.h:15613:66: note:
passing argument to parameter 'ci' here
struct rb_calling_info *calling, const struct rb_call_info *ci, rb_iseq_t *blockiseq, const int is_super)
^
/var/folders/b0/9hgj_tyx10zgkcbyx3_j2dlr0000gn/T//_ruby_mjit_p72619u0.c:37:74: warning: incompatible integer to pointer
conversion passing 'long' to parameter of type 'rb_iseq_t *' (aka 'struct rb_iseq_struct *') [-Wint-conversion]
vm_caller_setup_arg_block(ec, reg_cfp, &calling, 0x7ff6b2e10ca0, 0x7ff6b3847108, FALSE);
^~~~~~~~~~~~~~
/Users/kokubun/.rbenv/versions/ruby-svn/include/ruby-2.6.0/x86_64-darwin16/rb_mjit_min_header-2.6.0.h:15613:81: note:
passing argument to parameter 'blockiseq' here
struct rb_calling_info *calling, const struct rb_call_info *ci, rb_iseq_t *blockiseq, const int is_super)
^
2 warnings generated.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63298 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
except test_jit.rb.
In some situations, this generates a wrong code. I'll add a test for it
later but let me revert this to make it work for now.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63249 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
_mjit_compile_send_guard.erb: carve out the shared logic to invalidate
inlined method call
common.mk: update dependency for this change
test_jit.rb: add test for attr_reader optimization
* Benchmark
```
require 'benchmark_driver'
Benchmark.driver do |x|
x.prelude %{
class C
attr_reader :a
def initialize
@a = 1
end
end
o = C.new
def l o
i = 0
while i < 1000000
o.a
i += 1
end
end
}
x.report 'aread', %{ l o }
x.loop_count 1000
x.rbenv 'before', 'before,--jit', 'after,--jit'
x.verbose
end
```
```
before: ruby 2.6.0dev (2018-04-20 trunk 63211) [x86_64-linux]
before,--jit: ruby 2.6.0dev (2018-04-20 trunk 63211) +JIT [x86_64-linux]
after,--jit: ruby 2.6.0dev (2018-04-20 trunk 63211) +JIT [x86_64-linux]
last_commit=_mjit_compile_send.erb: inline attr_reader call
Calculating -------------------------------------
before before,--jit after,--jit
aread 54.597 122.894 218.574 i/s - 1.000k times in 18.316102s 8.137089s 4.575106s
Comparison:
aread
after,--jit: 218.6 i/s
before,--jit: 122.9 i/s - 1.78x slower
before: 54.6 i/s - 4.00x slower
```
* Optcarrot
A little made faster?
fps: 71.35 -> 72.11
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63212 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
to introduce additional optimization for another `cc->me->def->type`
later. I carved out the `cc->me->def->type == VM_METHOD_TYPE_ISEQ`
part because I wanted to check other types as well.
mjit_compile.c: drop get_iseq_if_available and define simplified version
of it, has_valid_method_type.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63199 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
on !body->catch_except_p. We need to move pc only when JIT execution is
canceled if the frame does not catch an exception.
_mjit_compile_insn.erb: lazily move pc for such optimized case
_mjit_compile_insn_body.erb: ditto
_mjit_compile_send.erb: ditto
* Optcarrot benchmark (--jit)
Before: 65.31 fps
After: 67.82 fps
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62678 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
if catch_except_p is FALSE. If catch_except_p is TRUE, stack values
should be on VM's stack when exception is thrown and the JIT-ed frame
is re-executed by VM's exception handler. If it's FALSE, the JIT-ed
frame won't be re-executed and don't need to keep values on VM's stack.
Using local variables allows us to reduce cfp->sp motion. Moving cfp->sp
is needed only for insns whose handles_frame? is false. So it improves
performance.
_mjit_compile_insn.erb: Prepare `stack_size` variable for GET_SP,
STACK_ADDR_FROM_TOP, TOPN macros. Share pc and sp motion partial view.
Use cancel handler created in mjit_compile.c.
_mjit_compile_send.erb: ditto. Also, when iseq->body->catch_except_p is
TRUE, this stops to call mjit_exec directly. I described the reason in
vm_insnhelper.h's comment for EXEC_EC_CFP.
_mjit_compile_pc_and_sp.erb: Shared logic for moving sp and pc. As you
can see from thsi file, when status->local_stack_p is TRUE and
insn.handles_frame? is false, moving sp is skipped. But if
insn.handles_frame? is true, values should be rolled back to VM's stack.
common.mk: add dependency for the file
_mjit_compile_insn_body.erb: Set sp value before canceling JIT on
DISPATCH_ORIGINAL_INSN. Replace GET_SP, STACK_ADDR_FROM_TOP, TOPN macros
for the case ocal_stack_p is TRUE and insn.handles_frame? is false.
In that case, values are not available on VM's stack and those macros
should be replaced.
mjit_compile.inc.erb: updated comments of macros which are supported by
JIT compiler. All references to `cfp->sp` should be replaced and thus
INC_SP, SET_SV, PUSH are no longer supported for now, because they are
not used now.
vm_exec.h: moved EXEC_EC_CFP definition to vm_insnhelper.h because it's
tighly coupled to CALL_METHOD.
vm_insnhelper.h: Have revised EXEC_EC_CFP definition moved from vm_exec.h.
Now it triggers mjit_exec for VM, and has the guard for catch_except_p
on JIT-ed code. See comments for details. CALL_METHOD delegates
triggering mjit_exec to EXEC_EC_CFP.
insns.def: Stopped using EXEC_EC_CFP for the case we don't want to
trigger mjit_exec. Those insns (defineclass, opt_call_c_function) are
not supported by JIT and it's safe to use RESTORE_REGS(), NEXT_INSN().
expandarray is changed to pass GET_SP() to replace the macro in
_mjit_compile_insn_body.erb.
vm_insnhelper.c: change to take sp for the above reason.
[close https://github.com/ruby/ruby/pull/1828]
This patch resurrects the performance which was attached in
[Feature #14235].
* Benchmark
Optcarrot (with configuration for benchmark_driver.gem)
https://github.com/benchmark-driver/optcarrot
$ benchmark-driver benchmark.yml --verbose 1 --rbenv 'before;before+JIT::before,--jit;after;after+JIT::after,--jit' --repeat-count 10
before: ruby 2.6.0dev (2018-03-04 trunk 62652) [x86_64-linux]
before+JIT: ruby 2.6.0dev (2018-03-04 trunk 62652) +JIT [x86_64-linux]
after: ruby 2.6.0dev (2018-03-04 local-variable.. 62652) [x86_64-linux]
last_commit=mjit_compile.c: use local variables for stack
after+JIT: ruby 2.6.0dev (2018-03-04 local-variable.. 62652) +JIT [x86_64-linux]
last_commit=mjit_compile.c: use local variables for stack
Calculating -------------------------------------
before before+JIT after after+JIT
optcarrot 53.552 59.680 53.697 63.358 fps
Comparison:
optcarrot
after+JIT: 63.4 fps
before+JIT: 59.7 fps - 1.06x slower
after: 53.7 fps - 1.18x slower
before: 53.6 fps - 1.18x slower
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62655 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
to count up total calls properly. Some places (especially CALL_METHOD)
invoke mjit_exec twice for one method call. It would be problematic when
debugging, or possibly it would result in a wrong profiling result.
This commit doesn't have impact for performance:
* Optcarrot benchmark
** before
fps: 59.37757770848619
fps: 56.49998488958699
fps: 59.07900362739362
fps: 58.924749807695996
fps: 57.667905665594894
fps: 57.540021018385254
fps: 59.5518055679647
fps: 55.93831555148311
fps: 57.82685112863262
fps: 59.22391754481736
checksum: 59662
** after
fps: 58.461881158098194
fps: 59.32685183081354
fps: 54.11334310279802
fps: 59.2281560439788
fps: 58.60495705318312
fps: 55.696478648491045
fps: 58.49003452654724
fps: 58.387771929393224
fps: 59.24156772816439
fps: 56.68804731968107
checksum: 59662
* Discourse
Your Results: (note for timings- percentile is first, duration is second in millisecs)
** before (without JIT)
categories_admin:
50: 16
75: 17
90: 24
99: 37
home_admin:
50: 20
75: 20
90: 24
99: 42
topic_admin:
50: 16
75: 16
90: 18
99: 28
categories:
50: 36
75: 37
90: 45
99: 68
home:
50: 38
75: 40
90: 53
99: 92
topic:
50: 14
75: 15
90: 17
99: 26
** after (without JIT)
categories_admin:
50: 16
75: 16
90: 24
99: 36
home_admin:
50: 19
75: 20
90: 23
99: 41
topic_admin:
50: 16
75: 16
90: 19
99: 33
categories:
50: 35
75: 36
90: 44
99: 61
home:
50: 38
75: 40
90: 52
99: 101
topic:
50: 14
75: 15
90: 15
99: 24
** before (with JIT)
categories_admin:
50: 19
75: 23
90: 29
99: 44
home_admin:
50: 24
75: 26
90: 32
99: 46
topic_admin:
50: 20
75: 22
90: 27
99: 44
categories:
50: 41
75: 43
90: 51
99: 66
home:
50: 46
75: 49
90: 56
99: 68
topic:
50: 18
75: 19
90: 22
99: 31
** after (with JIT)
categories_admin:
50: 18
75: 21
90: 28
99: 42
home_admin:
50: 23
75: 25
90: 31
99: 51
topic_admin:
50: 19
75: 20
90: 24
99: 31
categories:
50: 41
75: 44
90: 52
99: 69
home:
50: 45
75: 48
90: 61
99: 88
topic:
50: 19
75: 20
90: 24
99: 33
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62641 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
with opt_send_without_block insn if call cache has valid ISeq.
If the receiver is not optimized target of opt_key (i.e. Hash or Array),
it triggers JIT cancel and it would be slow.
This change allows JIT to drop the check for Hash/Array and continue to
execute JIT even if the receiver is not Hash or Array.
See the following benchmark results. It's not improved so much, but it
would be effective when we achieve Ruby method inlining in
_mjit_compile_send.erb.
* Micro benchmark
Given the following bench.rb,
```
class HashWithIndifferentAccess < Hash
def []=(key, value)
super(key.to_s, value)
end
def [](key)
super(key.to_s)
end
end
indhash = HashWithIndifferentAccess.new
indhash[:foo] = 'bar'
key = 'foo'
100000000.times do
indhash[key]
end
```
** before
```
$ time ./ruby --disable-gems --jit-verbose=1 /tmp/bench.rb
JIT success (31.4ms): block in <main>@/tmp/bench.rb:15 -> /tmp/_ruby_mjit_p18206u0.c
JIT success (669.3ms): []@/tmp/bench.rb:6 -> /tmp/_ruby_mjit_p18206u1.c
Successful MJIT finish
./ruby --disable-gems --jit-verbose=1 /tmp/bench.rb 12.21s user 0.04s system 107% cpu 11.394 total
```
** after
```
$ time ./ruby --disable-gems --jit-verbose=1 /tmp/bench.rb
JIT success (41.0ms): block in <main>@/tmp/bench.rb:15 -> /tmp/_ruby_mjit_p17293u0.c
JIT success (679.0ms): []@/tmp/bench.rb:6 -> /tmp/_ruby_mjit_p17293u1.c
Successful MJIT finish
./ruby --disable-gems --jit-verbose=1 /tmp/bench.rb 11.54s user 0.06s system 108% cpu 10.726 total
```
The execution time is shortened.
* optcarrot benchmark
Optcarrot has no room to be improved by this change. Almost nothing is changed.
fps: 59.54 (before) -> 59.51 (after)
* discourse benchmark
I expected this to be improved a little, but it isn't too.
** before (JIT)
```
categories_admin:
50: 12
75: 13
90: 14
99: 22
home_admin:
50: 12
75: 13
90: 16
99: 22
topic_admin:
50: 12
75: 13
90: 15
99: 21
categories:
50: 18
75: 19
90: 23
99: 27
home:
50: 3
75: 4
90: 4
99: 12
topic:
50: 11
75: 11
90: 14
99: 20
```
** after (JIT)
```
categories_admin:
50: 12
75: 12
90: 16
99: 24
home_admin:
50: 12
75: 12
90: 14
99: 21
topic_admin:
50: 12
75: 13
90: 16
99: 21
categories:
50: 17
75: 18
90: 23
99: 32
home:
50: 3
75: 4
90: 4
99: 10
topic:
50: 11
75: 12
90: 13
99: 20
```
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62398 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62386 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
renamed from tool/ruby_vm/views/_mjit_compile_insn_line.erb.
Basically this file should handle everything about macro on JIT.
_mjit_compile_insn.erb: follow the refactoring
common.mk: follow the rename
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62384 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
in _mjit_compile_insn.erb to this file. As I'm going to add macro
expansions later, I want to separate such complex things from whole insn
compilation.
_mjit_compile_insn.erb: _mjit_compile_insn_line.erb part was removed.
common.mk: updated build system for them.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62383 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
mjit_compile.inc.erb: show unsupported insn name on --jit-verbose=1 too.
Also, removed osboleted workaround. Now some insn-related functions are
declared with MAYBE_UNUSED.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62382 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
/var/folders/tp/g1f_46nj7md_d5_j799rfb140000gn/T//_ruby_mjit_p17396u162.c:2920:143: warning: incompatible integer
to pointer conversion passing 'long' to parameter of type 'const VALUE *' (aka 'const unsigned long *')
[-Wint-conversion]
...| VM_ENV_FLAG_LOCAL, calling.recv, calling.block_handler, 0x7fc14ceee660, 0x7fc14c870c00, argv + 0, 2, 3);
^~~~~~~~~~~~~~
/Users/k0kubun/.rbenv/versions/ruby-svn/include/ruby-2.6.0/x86_64-darwin16/rb_mjit_min_header-2.6.0.h:21299:21: note:
passing argument to parameter 'pc' here
const VALUE *pc,
^
/var/folders/tp/g1f_46nj7md_d5_j799rfb140000gn/T//_ruby_mjit_p17396u162.c:3073:31: warning: incompatible integer
to pointer conversion passing 'long' to parameter of type 'const rb_iseq_t *' (aka
'const struct rb_iseq_struct *') [-Wint-conversion]
vm_push_frame(ec, 0x7fc14c87d290, VM_FRAME_MAGIC_METHOD | VM_ENV_FLAG_LOCAL, calling.recv, ca...
^~~~~~~~~~~~~~
/Users/k0kubun/.rbenv/versions/ruby-svn/include/ruby-2.6.0/x86_64-darwin16/rb_mjit_min_header-2.6.0.h:21294:25: note:
passing argument to parameter 'iseq' here
const rb_iseq_t *iseq,
^
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62368 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
* tool/ruby_vm/views/_mjit_compile_insn.erb: comment ID of
constant, calling method, and Symbol literal.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62354 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62353 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
* tool/ruby_vm/views/_mjit_compile_send.erb: `printf` modifier for
`rb_serial_t` which may not be `long long`, and '%ll' may not be
supported.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62351 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
* mjit_compile.c (mjit_compile): name the original iseq pointer to
eliminate magic numbers.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62340 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
tool/ruby_vm/views/_insn_name_info.erb: on Linux, rb_vm_insn_name_offset
was needed to compile with --jit-debug (Usually --jit-debug requires
more symbols than the situation without --jit-debug because -O2 skips
some functions to compile).
vm.c: when running transform_mjit_header.rb with --jit-wait,
rb_source_location_cstr was repoted to be missing.
string.c: ditto, for rb_str_eql
numeric.c: ditto, for rb_float_eql
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62313 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
and style of generated code.
I've used 2-space indentation at first but at some moment I started to
use insns.def contents for generated code. So the 4-space indentation
was introduced. But it does no longer make sense.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62255 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62228 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
which has been developed by Takashi Kokubun <takashikkbn@gmail> as
YARV-MJIT. Many of its bugs are fixed by wanabe <[email protected]>.
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 <[email protected]>
Contributor: wanabe <[email protected]>
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
|
|
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62090 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
Now that sp_inc attributes are officially provided as inline
functions. Why not use them directly from the vm core, not just
by the compiler. By doing so, it is now possible for us to
optimize stack manipulations. We can now know exactly how many
words of stack space an instruction consumes before it actually
does. This changeset deletes some lines from insns.def because
they are no longer needed. As a result it reduces the size of
vm_exec_core function from 32,400 bytes to 32,352 bytes on my
machine.
It seems it does not affect performance:
-----------------------------------------------------------
benchmark results:
minimum results in each 3 measurements.
Execution time (sec)
name before after
loop_for 1.093 1.061
loop_generator 1.156 1.152
loop_times 0.982 0.974
loop_whileloop 0.549 0.587
loop_whileloop2 0.115 0.121
Speedup ratio: compare with the result of `before' (greater is better)
name after
loop_for 1.030
loop_generator 1.003
loop_times 1.008
loop_whileloop 0.935
loop_whileloop2 0.949
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62087 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
Instead of using magic numbers, let us define a series of attributes
and use them from the VM core. Proper function declarations makes
these attributes inlined in most modern compilers. On my machine
exact same binary is generated with or without this changeset.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62085 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
This commit introduces new attribute handles_flame and if that is
_not_ the case, places ADD_PC right after INC_SP. This improves
locality of PC manipulations to prevents unnecessary register spill-
outs. As a result, it reduces the size of vm_exec_core from 32,688
bytes to 32,384 bytes on my machine.
Speedup is very faint, but certain.
-----------------------------------------------------------
benchmark results:
minimum results in each 3 measurements.
Execution time (sec)
name before after
so_ackermann 0.476 0.464
so_array 0.742 0.728
so_binary_trees 5.493 5.466
so_concatenate 3.619 3.395
so_count_words 0.190 0.184
so_exception 0.249 0.239
so_fannkuch 0.994 0.953
so_fasta 1.369 1.374
so_k_nucleotide 1.111 1.111
so_lists 0.470 0.481
so_mandelbrot 2.059 2.050
so_matrix 0.466 0.465
so_meteor_contest 2.712 2.781
so_nbody 1.154 1.204
so_nested_loop 0.852 0.846
so_nsieve 1.636 1.623
so_nsieve_bits 2.073 2.039
so_object 0.616 0.584
so_partial_sums 1.464 1.481
so_pidigits 1.075 1.082
so_random 0.321 0.317
so_reverse_complement 0.555 0.558
so_sieve 0.495 0.490
so_spectralnorm 1.634 1.627
Speedup ratio: compare with the result of `before' (greater is better)
name after
so_ackermann 1.025
so_array 1.019
so_binary_trees 1.005
so_concatenate 1.066
so_count_words 1.030
so_exception 1.040
so_fannkuch 1.043
so_fasta 0.996
so_k_nucleotide 1.000
so_lists 0.978
so_mandelbrot 1.004
so_matrix 1.001
so_meteor_contest 0.975
so_nbody 0.959
so_nested_loop 1.007
so_nsieve 1.008
so_nsieve_bits 1.017
so_object 1.056
so_partial_sums 0.989
so_pidigits 0.994
so_random 1.014
so_reverse_complement 0.996
so_sieve 1.010
so_spectralnorm 1.004
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62051 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
give up CALL_ATTRIBUTE macro.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61802 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
|
`signed` is required for Rasbian (x86_64).
* tool/ruby_vm/views/_insn_stack_increase.erb: specify `signed` explicitly
for systems which use `unsigned` for `char` type.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61792 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
|
