by calling combined functions specialized for each cancel type.
I'm hoping to improve locality of hot code, but this patch's impact should
be insignificant.
jit_unit to avoid marking wrong cc entries when inlined iseq is compiled
multiple times, resolving the TODO added by daf7c48d88.
This obviates pseudo jit_unit in inlined iseq introduced by 7ec2359374
and fixes memory leak of the adhoc unit.
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.
Now, rb_call_info contains how to call the method with tuple of
(mid, orig_argc, flags, kwarg). Most of cases, kwarg == NULL and
mid+argc+flags only requires 64bits. So this patch packed
rb_call_info to VALUE (1 word) on such cases. If we can not
represent it in VALUE, then use imemo_callinfo which contains
conventional callinfo (rb_callinfo, renamed from rb_call_info).
iseq->body->ci_kw_size is removed because all of callinfo is VALUE
size (packed ci or a pointer to imemo_callinfo).
To access ci information, we need to use these functions:
vm_ci_mid(ci), _flag(ci), _argc(ci), _kwarg(ci).
struct rb_call_info_kw_arg is renamed to rb_callinfo_kwarg.
rb_funcallv_with_cc() and rb_method_basic_definition_p_with_cc()
is temporary removed because cd->ci should be marked.
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).
Support loading builtin features written in Ruby, which implement
with C builtin functions.
[Feature #16254]
Several features:
(1) Load .rb file at boottime with native binary.
Now, prelude.rb is loaded at boottime. However, this file is contained
into the interpreter as a text format and we need to compile it.
This patch contains a feature to load from binary format.
(2) __builtin_func() in Ruby call func() written in C.
In Ruby file, we can write `__builtin_func()` like method call.
However this is not a method call, but special syntax to call
a function `func()` written in C. C functions should be defined
in a file (same compile unit) which load this .rb file.
Functions (`func` in above example) should be defined with
(a) 1st parameter: rb_execution_context_t *ec
(b) rest parameters (0 to 15).
(c) VALUE return type.
This is very similar requirements for functions used by
rb_define_method(), however `rb_execution_context_t *ec`
is new requirement.
(3) automatic C code generation from .rb files.
tool/mk_builtin_loader.rb creates a C code to load .rb files
needed by miniruby and ruby command. This script is run by
BASERUBY, so *.rb should be written in BASERUBY compatbile
syntax. This script load a .rb file and find all of __builtin_
prefix method calls, and generate a part of C code to export
functions.
tool/mk_builtin_binary.rb creates a C code which contains
binary compiled Ruby files needed by ruby command.
Prior to this changeset, majority of inline cache mishits resulted
into the same method entry when rb_callable_method_entry() resolves
a method search. Let's not call the function at the first place on
such situations.
In doing so we extend the struct rb_call_cache from 44 bytes (in
case of 64 bit machine) to 64 bytes, and fill the gap with
secondary class serial(s). Call cache's class serials now behavies
as a LRU cache.
Calculating -------------------------------------
ours 2.7 2.6
vm2_poly_same_method 2.339M 1.744M 1.369M i/s - 6.000M times in 2.565086s 3.441329s 4.381386s
Comparison:
vm2_poly_same_method
ours: 2339103.0 i/s
2.7: 1743512.3 i/s - 1.34x slower
2.6: 1369429.8 i/s - 1.71x slower
To perform a regular method call, the VM needs two structs,
`rb_call_info` and `rb_call_cache`. At the moment, we allocate these two
structures in separate buffers. In the worst case, the CPU needs to read
4 cache lines to complete a method call. Putting the two structures
together reduces the maximum number of cache line reads to 2.
Combining the structures also saves 8 bytes per call site as the current
layout uses separate two pointers for the call info and the call cache.
This saves about 2 MiB on Discourse.
This change improves the Optcarrot benchmark at least 3%. For more
details, see attached bugs.ruby-lang.org ticket.
Complications:
- A new instruction attribute `comptime_sp_inc` is introduced to
calculate SP increase at compile time without using call caches. At
compile time, a `TS_CALLDATA` operand points to a call info struct, but
at runtime, the same operand points to a call data struct. Instruction
that explicitly define `sp_inc` also need to define `comptime_sp_inc`.
- MJIT code for copying call cache becomes slightly more complicated.
- This changes the bytecode format, which might break existing tools.
[Misc #16258]
for ISeq including only leaf and no-handles_sp insns except leaf.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67574 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This refactoring is needed for implementing inlining later.
I've had this since long ago and it has conflicted sometimes. So let me
just commit this now.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67566 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
cfp->bp was (re-)introduced by Kokubun san, but VM doesn't use it
because I (ko1) want to remove it in a future. But using it make
leave instruction fast because of sp consisntency check.
So now VM uses cfp->bp.
To use cfp->bp, I checked the value and I found that it is not a
"initial value of sp" but a "initial value of ep". Fix this problem
and fix all bp references (this is why bp is renamed to bp_).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67342 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
to avoid inlining a method call when it becomes argument_arity_error,
fixing a potential bug.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67330 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
to make it easier to understand what values are grouped.
Just cosmetic changes.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67302 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
by changing interface of `mjit_copy_cache_from_main_thread`.
This is also fixing deadlock introduced by r67299.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67300 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
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
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
Takashi Kokubun
卜部昌平
Koichi Sasada
Alan Wu
k0kubun
usa
ko1