This patch contains several ideas:
(1) Disposable inline method cache (IMC) for race-free inline method cache
* Making call-cache (CC) as a RVALUE (GC target object) and allocate new
CC on cache miss.
* This technique allows race-free access from parallel processing
elements like RCU.
(2) Introduce per-Class method cache (pCMC)
* Instead of fixed-size global method cache (GMC), pCMC allows flexible
cache size.
* Caching CCs reduces CC allocation and allow sharing CC's fast-path
between same call-info (CI) call-sites.
(3) Invalidate an inline method cache by invalidating corresponding method
entries (MEs)
* Instead of using class serials, we set "invalidated" flag for method
entry itself to represent cache invalidation.
* Compare with using class serials, the impact of method modification
(add/overwrite/delete) is small.
* Updating class serials invalidate all method caches of the class and
sub-classes.
* Proposed approach only invalidate the method cache of only one ME.
See [Feature #16614] for more details.
Starting clang 11, casts between pointer and (narrower-than-pointer) int
are now warned. However all such thing in our repository are guaranteed
safe. Let's suppress the warnings.
Saves comitters' daily life by avoid #include-ing everything from
internal.h to make each file do so instead. This would significantly
speed up incremental builds.
We take the following inclusion order in this changeset:
1. "ruby/config.h", where _GNU_SOURCE is defined (must be the very
first thing among everything).
2. RUBY_EXTCONF_H if any.
3. Standard C headers, sorted alphabetically.
4. Other system headers, maybe guarded by #ifdef
5. Everything else, sorted alphabetically.
Exceptions are those win32-related headers, which tend not be self-
containing (headers have inclusion order dependencies).
This is a secret feature for me. It's only for testing and any behavior
with this flag override is unsupported.
I needed this because I sometimes want to add debug options but do not
want to disable optimizations, for using Linux perf.
Looking at the list of symbols inside of libruby-static.a, I found
hundreds of functions that are defined, but used from nowhere.
There can be reasons for each of them (e.g. some functions are
specific to some platform, some are useful when debugging, etc).
However it seems the functions deleted here exist for no reason.
This changeset reduces the size of ruby binary from 26,671,456
bytes to 26,592,864 bytes on my machine.
ISeq can move, so we need to tell MJIT where the new location is.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67624 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
I'm writing `//` comments in newer MJIT code after C99 enablement
(because I write 1-line comments more often than multi-line comments
and `//` requires fewer chars on 1-line) and then they are mixed
with `/* */` now.
For consistency and to avoid the conversion in future changes, let me
finish the rewrite in MJIT-related code.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67533 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
I noticed that r67287 was illegal because memory allocated by `alloca`
was used after the stack is expired.
So I just replaced that with `malloc` and `free` for now.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67299 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Take 2 of r67287.
For some reasons, passing pointer of pointer on stack to a function
and assigning an addresse to a pointer dereferenced from the pointer
seems not working on mswin.
So I achieved to return multiple values by returning struct instead of
taking pointers.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67296 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit 4161674b2f.
Revert "Eliminate mjit_copy_job_t reference from mjit_worker"
This reverts commit d86a1aa045.
Reverting them because of CI failures
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67291 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
rather than preparing beforehand.
By having this change, implementing inlining by calling
`mjit_copy_cache_from_main_thread` for inlined methods was made
possible.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67288 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
and functions to clarify the intention and make sure it's not used in a
surprising way (like using 2, 3, ... other than 0, 1 even while it seems
to be a boolean).
This is a retry of r66775. It included some typos...
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66778 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit bb1a1aeab0.
We hit something on ci.rvm.jp, reverting until investigation is done.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66776 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
and functions to clarify the intention and make sure it's not used in a
surprising way (like using 2, 3, ... other than 0, 1 even while it seems
to be a boolean).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66775 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
http://ci.rvm.jp/results/trunk-mjit-wait@silicon-docker/1480173
It tries to print C backtrace but fails. And core file on the server
seems to be stopping on the irrelevant place due to its own signal
handler for the dump.
And I failed to reproduce this SEGV on my machine.
I don't know why it's broken, so let me try this change to investigate
the reason of SEGV.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65997 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
to prevent ruby from leaving MJIT-related files.
test_jit.rb: add a test to prevent that
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65994 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
on VM_CHECK_INTS. Letting MJIT worker directly see inline cache which
may be being updated could result in inconsistent IC index and serial.
mjit_worker.c: request the copy job after dequeue, and receive the
result synchronously.
tool/ruby_vm/views/_mjit_compile_ivar.erb: use the copied IC
mjit_compile.c: change the interface to pass is_entries
mjit.h: ditto
=== Optcarrot Benchmark ===
Thankfully this didn't have major performance regression.
$ benchmark-driver benchmark.yml --rbenv 'before::before --disable-gems --jit;after::after --disable-gems --jit' -v --repeat-count 24
before: ruby 2.6.0dev (2018-10-21 trunk 65263) +JIT [x86_64-linux]
after: ruby 2.6.0dev (2018-10-21 trunk 65263) +JIT [x86_64-linux]
last_commit=mjit.c: copy inline cache values to MJIT worker
Calculating -------------------------------------
before after
Optcarrot Lan_Master.nes 85.421 85.454 fps
Comparison:
Optcarrot Lan_Master.nes
after: 85.5 fps
before: 85.4 fps - 1.00x slower
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65275 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* configure.ac: introduce new configure option `--enable-mjit` and
`--disable-mjit`. Default is "enable".
`--disable-mjit` disables all of MJIT features so that `ruby --jit`
can't enable MJIT.
This option affect a macro `USE_MJIT`.
This change remove `--enable/disable-install-mjit-header` option.
* Makefile.in: introduce the `ENABLE_MJIT` variable.
* common.mk: use `ENABLE_MJIT` option.
* internal.h: respect `USE_MJIT`. Same as other *.c, *.h.
* test/ruby/test_jit.rb: check `ENABLE_MJIT` key of rbconfg.rb.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65204 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
like "error: static declaration of 'xxx' follows non-static declaration".
r64940 is successfully built on mswin but not built on almost all other environments.
internal.h: ditto
include/ruby/intern.h: MJIT_STATIC is moved to this file since this file
also needs to use this.
mjit.h: MJIT_STATIC is moved from this.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64941 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This change resolves most of major remaining MJIT bugs on mswin.
Since Visual Studio doesn't support generating pre-processed code
preserving macros, we can't use transform_mjit_header approach for mswin.
So we need to transform MJIT header using macro like this.
vm.c: use MJIT_STATIC for non-static functions that exist on MJIT header
and cause conflict on link.
vm_insnhelper.c: ditto
test_jit.rb: remove many skips for mswin.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64940 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
after the first compilation on --jit-wait.
Previously the assignment to `func` didn't have meaning for the behavior,
and the compiled code wasn't called immediately after the synchronous
compilation. It wasn't intentional.
Fixing this issue without impacting performance without --jit-wait is
not so obvious. Adding branch or goto to call func in mjit_exec spoiled
the performance without --jit-wait. Instead of that, I called the func
inside mjit_wait_call() (former mjit_get_iseq_func()) which is never
inlined to mjit_exec(). Thanks to that, this commit has no impact for
normal performance.
mjit.c: ditto
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64929 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit r64711, because EXEC_EC_CFP on JIT-ed code does not
call jit_func with the patch when catch_except_p is true. It wasn't intentional.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64730 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
from mjit.c because it's executed only on MJIT worker thread.
Instead of that, `valid_class_serials` is shared with mjit_ prefix.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64288 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
The motivation of this change is to make sure rb_funcall or GC-related
functions are not called on worker-related code. Currently such
functions are used in some places and I believe it's partly because it's
hard to identify which part is called on MJIT worker thread.
Now, mjit.c is safe to use them but we know we need to safely deal with
mjit_compile.c, mjit_worker.c and mjit_internal.h.
mjit_compile.c: update the comment about it
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64285 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
by sharing it with vm.c in internal.h.
vm.c: ditto
internal.h: ditto
mjit.h: share more.
mjit.c: make sure the third arguemnt is not used
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64253 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
By this commit's changes in other files, now MJIT started to work on VC++.
Unfortunately some features are still broken and they'll be fixed later.
This also suppresses cl.exe's default output to stdout because there
seems to be no option to do it. Tweaking some log messages as well.
vm_core.h: declare `__declspec(dllimport)` to export them correctly on mswin.
vm_insnhelper.h: ditto
mjit.h: ditto
test_jit.rb: skipped some pending tests.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64221 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
units, renaming it from NOT_COMPILABLE_JIT_ISEQ_FUNC.
NOT_READY_JIT_ISEQ_FUNC is for ones being compiled, so
mjit_get_iseq_func treats it specially and it shouldn't be used for the
purpose.
I renamed it instead of adding a new one because I'm not sure about the
impact for the performance by increasing the switch branches in mjit_exec.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64076 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
by promoting jit to feature flag.
mjit.h: update comment about mjit_opts.on
test_rubyoptions.rb: add test for switching JIT enablement
"--jit" flag usage may be deprecated later, but not discussed yet.
[Feature #14878]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63995 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
ptrdiff_t is a signed type, use uintptr_t instead for unsigned
comparisons.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
when TracePoint is enabled. We're cancelling JIT-ed code execution AFTER
each instruction, but there is no guard before the first insn of method.
To prevent spoiling performance, I don't want to modify the JIT-ed code
to fix this. So this commit replaces `mjit_enabled` check with `mjit_call_p`
check.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63734 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
`RubyVM::MJIT.enabled?`.
It's set to be TRUE even before initialization is finished.
So it was actually not "mjit initialized predicate".
This flag is also used to check whether JIT-ed code should be called
or not, but I'm going to split the responsibility to another flag.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63732 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
We want to skip checking `mjit_opts.wait` for already JIT-ed case.
Optcarrot is slightly improved like 65.20 fps -> 66.60 fps.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63480 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Sometimes test hangs in `mjit_get_iseq_func` like this:
http://ci.rvm.jp/results/trunk-test@ruby-sky3/659391
It seems that a process waiting in `mjit_get_iseq_func` does no longer
have MJIT worker thread. We don't wait for JIT finish forever. So I
added timeout for the case. I'm not sure why there was no MJIT worker
thread in ruby-sky3 test process though.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62785 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* mjit.c (mjit_get_iseq_func), mjit.h (mjit_exec): do not compare
a pointer as shorter type. by loosing the precision, different
values can result in "equal" wrongly. enum type is an alias of
`int`, and is often shorter than a pointer type nowadays.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62401 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* ruby.c (setup_mjit_options): removed --jit-cc option, since
mjit header is affected by generated config.h which depends on
the given compiler, so it cannot work with different compilers.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62379 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Takashi Kokubun
Koichi Sasada
卜部昌平
Nobuyoshi Nakada
k0kubun
tenderlove
ko1
normal
nobu