ruby/vm_insnhelper.h

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

278 строки
8.8 KiB
C
Исходник Обычный вид История

#ifndef RUBY_INSNHELPER_H
#define RUBY_INSNHELPER_H
/**********************************************************************
insnhelper.h - helper macros to implement each instructions
$Author$
created at: 04/01/01 15:50:34 JST
Copyright (C) 2004-2007 Koichi Sasada
**********************************************************************/
RUBY_EXTERN VALUE ruby_vm_const_missing_count;
RUBY_EXTERN rb_serial_t ruby_vm_constant_cache_invalidations;
RUBY_EXTERN rb_serial_t ruby_vm_constant_cache_misses;
Add a cache for class variables Redo of 34a2acdac788602c14bf05fb616215187badd504 and 931138b00696419945dc03e10f033b1f53cd50f3 which were reverted. GitHub PR #4340. This change implements a cache for class variables. Previously there was no cache for cvars. Cvar access is slow due to needing to travel all the way up th ancestor tree before returning the cvar value. The deeper the ancestor tree the slower cvar access will be. The benefits of the cache are more visible with a higher number of included modules due to the way Ruby looks up class variables. The benchmark here includes 26 modules and shows with the cache, this branch is 6.5x faster when accessing class variables. ``` compare-ruby: ruby 3.1.0dev (2021-03-15T06:22:34Z master 9e5105c) [x86_64-darwin19] built-ruby: ruby 3.1.0dev (2021-03-15T12:12:44Z add-cache-for-clas.. c6be009) [x86_64-darwin19] | |compare-ruby|built-ruby| |:--------|-----------:|---------:| |vm_cvar | 5.681M| 36.980M| | | -| 6.51x| ``` Benchmark.ips calling `ActiveRecord::Base.logger` from within a Rails application. ActiveRecord::Base.logger has 71 ancestors. The more ancestors a tree has, the more clear the speed increase. IE if Base had only one ancestor we'd see no improvement. This benchmark is run on a vanilla Rails application. Benchmark code: ```ruby require "benchmark/ips" require_relative "config/environment" Benchmark.ips do |x| x.report "logger" do ActiveRecord::Base.logger end end ``` Ruby 3.0 master / Rails 6.1: ``` Warming up -------------------------------------- logger 155.251k i/100ms Calculating ------------------------------------- ``` Ruby 3.0 with cvar cache / Rails 6.1: ``` Warming up -------------------------------------- logger 1.546M i/100ms Calculating ------------------------------------- logger 14.857M (± 4.8%) i/s - 74.198M in 5.006202s ``` Lastly we ran a benchmark to demonstate the difference between master and our cache when the number of modules increases. This benchmark measures 1 ancestor, 30 ancestors, and 100 ancestors. Ruby 3.0 master: ``` Warming up -------------------------------------- 1 module 1.231M i/100ms 30 modules 432.020k i/100ms 100 modules 145.399k i/100ms Calculating ------------------------------------- 1 module 12.210M (± 2.1%) i/s - 61.553M in 5.043400s 30 modules 4.354M (± 2.7%) i/s - 22.033M in 5.063839s 100 modules 1.434M (± 2.9%) i/s - 7.270M in 5.072531s Comparison: 1 module: 12209958.3 i/s 30 modules: 4354217.8 i/s - 2.80x (± 0.00) slower 100 modules: 1434447.3 i/s - 8.51x (± 0.00) slower ``` Ruby 3.0 with cvar cache: ``` Warming up -------------------------------------- 1 module 1.641M i/100ms 30 modules 1.655M i/100ms 100 modules 1.620M i/100ms Calculating ------------------------------------- 1 module 16.279M (± 3.8%) i/s - 82.038M in 5.046923s 30 modules 15.891M (± 3.9%) i/s - 79.459M in 5.007958s 100 modules 16.087M (± 3.6%) i/s - 81.005M in 5.041931s Comparison: 1 module: 16279458.0 i/s 100 modules: 16087484.6 i/s - same-ish: difference falls within error 30 modules: 15891406.2 i/s - same-ish: difference falls within error ``` Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
2021-06-01 20:34:06 +03:00
RUBY_EXTERN rb_serial_t ruby_vm_global_cvar_state;
#if USE_YJIT || USE_RJIT // We want vm_insns_count on any JIT-enabled build.
// Increment vm_insns_count for --yjit-stats. We increment this even when
// --yjit or --yjit-stats is not used because branching to skip it is slower.
// We also don't use ATOMIC_INC for performance, allowing inaccuracy on Ractors.
#define JIT_COLLECT_USAGE_INSN(insn) rb_vm_insns_count++
2023-07-12 03:26:03 +03:00
#else
#define JIT_COLLECT_USAGE_INSN(insn) // none
2023-07-12 03:26:03 +03:00
#endif
#if VM_COLLECT_USAGE_DETAILS
#define COLLECT_USAGE_INSN(insn) vm_collect_usage_insn(insn)
#define COLLECT_USAGE_OPERAND(insn, n, op) vm_collect_usage_operand((insn), (n), ((VALUE)(op)))
#define COLLECT_USAGE_REGISTER(reg, s) vm_collect_usage_register((reg), (s))
#else
#define COLLECT_USAGE_INSN(insn) JIT_COLLECT_USAGE_INSN(insn)
2023-07-12 03:26:03 +03:00
#define COLLECT_USAGE_OPERAND(insn, n, op) // none
#define COLLECT_USAGE_REGISTER(reg, s) // none
#endif
/**********************************************************/
/* deal with stack */
/**********************************************************/
#define PUSH(x) (SET_SV(x), INC_SP(1))
#define TOPN(n) (*(GET_SP()-(n)-1))
#define POPN(n) (DEC_SP(n))
#define POP() (DEC_SP(1))
#define STACK_ADDR_FROM_TOP(n) (GET_SP()-(n))
/**********************************************************/
/* deal with registers */
/**********************************************************/
#define VM_REG_CFP (reg_cfp)
#define VM_REG_PC (VM_REG_CFP->pc)
#define VM_REG_SP (VM_REG_CFP->sp)
#define VM_REG_EP (VM_REG_CFP->ep)
#define RESTORE_REGS() do { \
VM_REG_CFP = ec->cfp; \
} while (0)
typedef enum call_type {
CALL_PUBLIC,
CALL_FCALL,
CALL_VCALL,
CALL_PUBLIC_KW,
CALL_FCALL_KW
} call_type;
Optimized forwarding callers and callees This patch optimizes forwarding callers and callees. It only optimizes methods that only take `...` as their parameter, and then pass `...` to other calls. Calls it optimizes look like this: ```ruby def bar(a) = a def foo(...) = bar(...) # optimized foo(123) ``` ```ruby def bar(a) = a def foo(...) = bar(1, 2, ...) # optimized foo(123) ``` ```ruby def bar(*a) = a def foo(...) list = [1, 2] bar(*list, ...) # optimized end foo(123) ``` All variants of the above but using `super` are also optimized, including a bare super like this: ```ruby def foo(...) super end ``` This patch eliminates intermediate allocations made when calling methods that accept `...`. We can observe allocation elimination like this: ```ruby def m x = GC.stat(:total_allocated_objects) yield GC.stat(:total_allocated_objects) - x end def bar(a) = a def foo(...) = bar(...) def test m { foo(123) } end test p test # allocates 1 object on master, but 0 objects with this patch ``` ```ruby def bar(a, b:) = a + b def foo(...) = bar(...) def test m { foo(1, b: 2) } end test p test # allocates 2 objects on master, but 0 objects with this patch ``` How does it work? ----------------- This patch works by using a dynamic stack size when passing forwarded parameters to callees. The caller's info object (known as the "CI") contains the stack size of the parameters, so we pass the CI object itself as a parameter to the callee. When forwarding parameters, the forwarding ISeq uses the caller's CI to determine how much stack to copy, then copies the caller's stack before calling the callee. The CI at the forwarded call site is adjusted using information from the caller's CI. I think this description is kind of confusing, so let's walk through an example with code. ```ruby def delegatee(a, b) = a + b def delegator(...) delegatee(...) # CI2 (FORWARDING) end def caller delegator(1, 2) # CI1 (argc: 2) end ``` Before we call the delegator method, the stack looks like this: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | 5| delegatee(...) # CI2 (FORWARDING) | 6| end | 7| | 8| def caller | -> 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The ISeq for `delegator` is tagged as "forwardable", so when `caller` calls in to `delegator`, it writes `CI1` on to the stack as a local variable for the `delegator` method. The `delegator` method has a special local called `...` that holds the caller's CI object. Here is the ISeq disasm fo `delegator`: ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` The local called `...` will contain the caller's CI: CI1. Here is the stack when we enter `delegator`: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 -> 4| # | CI1 (argc: 2) 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The CI at `delegatee` on line 5 is tagged as "FORWARDING", so it knows to memcopy the caller's stack before calling `delegatee`. In this case, it will memcopy self, 1, and 2 to the stack before calling `delegatee`. It knows how much memory to copy from the caller because `CI1` contains stack size information (argc: 2). Before executing the `send` instruction, we push `...` on the stack. The `send` instruction pops `...`, and because it is tagged with `FORWARDING`, it knows to memcopy (using the information in the CI it just popped): ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` Instruction 001 puts the caller's CI on the stack. `send` is tagged with FORWARDING, so it reads the CI and _copies_ the callers stack to this stack: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | CI1 (argc: 2) -> 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | self 9| delegator(1, 2) # CI1 (argc: 2) | 1 10| end | 2 ``` The "FORWARDING" call site combines information from CI1 with CI2 in order to support passing other values in addition to the `...` value, as well as perfectly forward splat args, kwargs, etc. Since we're able to copy the stack from `caller` in to `delegator`'s stack, we can avoid allocating objects. I want to do this to eliminate object allocations for delegate methods. My long term goal is to implement `Class#new` in Ruby and it uses `...`. I was able to implement `Class#new` in Ruby [here](https://github.com/ruby/ruby/pull/9289). If we adopt the technique in this patch, then we can optimize allocating objects that take keyword parameters for `initialize`. For example, this code will allocate 2 objects: one for `SomeObject`, and one for the kwargs: ```ruby SomeObject.new(foo: 1) ``` If we combine this technique, plus implement `Class#new` in Ruby, then we can reduce allocations for this common operation. Co-Authored-By: John Hawthorn <john@hawthorn.email> Co-Authored-By: Alan Wu <XrXr@users.noreply.github.com>
2024-04-15 20:48:53 +03:00
struct rb_forwarding_call_data {
struct rb_call_data cd;
CALL_INFO caller_ci;
};
#if VM_COLLECT_USAGE_DETAILS
* vm_core.h: remove lfp (local frame pointer) and rename dfp (dynamic frame pointer) to ep (environment pointer). This change make VM `normal' (similar to other interpreters). Before this commit: Each frame has two env pointers lfp and dfp. lfp points local environment which is method/class/toplevel frame. lfp[0] is block pointer. dfp is block local frame. dfp[0] points previous (parent) environment pointer. lfp == dfp when frame is method/class/toplevel. You can get lfp from dfp by traversing previous environment pointers. After this commit: Each frame has only `ep' to point respective enviornoment. If there is parent environment, then ep[0] points parent envioenment (as dfp). If there are no more environment, then ep[0] points block pointer (as lfp). We call such ep as `LEP' (local EP). We add some macros to get LEP and to detect LEP or not. In short, we replace dfp and lfp with ep and LEP. rb_block_t and rb_binding_t member `lfp' and `dfp' are removed and member `ep' is added. rename rb_thread_t's member `local_lfp' and `local_svar' to `root_lep' and `root_svar'. (VM_EP_PREV_EP(ep)): get previous environment pointer. This macro assume that ep is not LEP. (VM_EP_BLOCK_PTR(ep)): get block pointer. This macro assume that ep is LEP. (VM_EP_LEP_P(ep)): detect ep is LEP or not. (VM_ENVVAL_BLOCK_PTR(ptr)): make block pointer. (VM_ENVVAL_BLOCK_PTR_P(v)): detect v is block pointer. (VM_ENVVAL_PREV_EP_PTR(ptr)): make prev environment pointer. (VM_ENVVAL_PREV_EP_PTR_P(v)): detect v is prev env pointer. * vm.c: apply above changes. (VM_EP_LEP(ep)): get LEP. (VM_CF_LEP(cfp)): get LEP of cfp->ep. (VM_CF_PREV_EP(cfp)): utility function VM_EP_PREV_EP(cfp->ep). (VM_CF_BLOCK_PTR(cfp)): utility function VM_EP_BLOCK_PTR(cfp->ep). * vm.c, vm_eval.c, vm_insnhelper.c, vm_insnhelper.h, insns.def: apply above changes. * cont.c: ditto. * eval.c, eval_intern.h: ditto. * proc.c: ditto. * thread.c: ditto. * vm_dump.c: ditto. * vm_exec.h: fix function name (on vm debug mode). git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36030 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-06-11 07:14:59 +04:00
enum vm_regan_regtype {
VM_REGAN_PC = 0,
VM_REGAN_SP = 1,
VM_REGAN_EP = 2,
VM_REGAN_CFP = 3,
VM_REGAN_SELF = 4,
VM_REGAN_ISEQ = 5
* vm_core.h: remove lfp (local frame pointer) and rename dfp (dynamic frame pointer) to ep (environment pointer). This change make VM `normal' (similar to other interpreters). Before this commit: Each frame has two env pointers lfp and dfp. lfp points local environment which is method/class/toplevel frame. lfp[0] is block pointer. dfp is block local frame. dfp[0] points previous (parent) environment pointer. lfp == dfp when frame is method/class/toplevel. You can get lfp from dfp by traversing previous environment pointers. After this commit: Each frame has only `ep' to point respective enviornoment. If there is parent environment, then ep[0] points parent envioenment (as dfp). If there are no more environment, then ep[0] points block pointer (as lfp). We call such ep as `LEP' (local EP). We add some macros to get LEP and to detect LEP or not. In short, we replace dfp and lfp with ep and LEP. rb_block_t and rb_binding_t member `lfp' and `dfp' are removed and member `ep' is added. rename rb_thread_t's member `local_lfp' and `local_svar' to `root_lep' and `root_svar'. (VM_EP_PREV_EP(ep)): get previous environment pointer. This macro assume that ep is not LEP. (VM_EP_BLOCK_PTR(ep)): get block pointer. This macro assume that ep is LEP. (VM_EP_LEP_P(ep)): detect ep is LEP or not. (VM_ENVVAL_BLOCK_PTR(ptr)): make block pointer. (VM_ENVVAL_BLOCK_PTR_P(v)): detect v is block pointer. (VM_ENVVAL_PREV_EP_PTR(ptr)): make prev environment pointer. (VM_ENVVAL_PREV_EP_PTR_P(v)): detect v is prev env pointer. * vm.c: apply above changes. (VM_EP_LEP(ep)): get LEP. (VM_CF_LEP(cfp)): get LEP of cfp->ep. (VM_CF_PREV_EP(cfp)): utility function VM_EP_PREV_EP(cfp->ep). (VM_CF_BLOCK_PTR(cfp)): utility function VM_EP_BLOCK_PTR(cfp->ep). * vm.c, vm_eval.c, vm_insnhelper.c, vm_insnhelper.h, insns.def: apply above changes. * cont.c: ditto. * eval.c, eval_intern.h: ditto. * proc.c: ditto. * thread.c: ditto. * vm_dump.c: ditto. * vm_exec.h: fix function name (on vm debug mode). git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36030 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-06-11 07:14:59 +04:00
};
enum vm_regan_acttype {
VM_REGAN_ACT_GET = 0,
VM_REGAN_ACT_SET = 1
* vm_core.h: remove lfp (local frame pointer) and rename dfp (dynamic frame pointer) to ep (environment pointer). This change make VM `normal' (similar to other interpreters). Before this commit: Each frame has two env pointers lfp and dfp. lfp points local environment which is method/class/toplevel frame. lfp[0] is block pointer. dfp is block local frame. dfp[0] points previous (parent) environment pointer. lfp == dfp when frame is method/class/toplevel. You can get lfp from dfp by traversing previous environment pointers. After this commit: Each frame has only `ep' to point respective enviornoment. If there is parent environment, then ep[0] points parent envioenment (as dfp). If there are no more environment, then ep[0] points block pointer (as lfp). We call such ep as `LEP' (local EP). We add some macros to get LEP and to detect LEP or not. In short, we replace dfp and lfp with ep and LEP. rb_block_t and rb_binding_t member `lfp' and `dfp' are removed and member `ep' is added. rename rb_thread_t's member `local_lfp' and `local_svar' to `root_lep' and `root_svar'. (VM_EP_PREV_EP(ep)): get previous environment pointer. This macro assume that ep is not LEP. (VM_EP_BLOCK_PTR(ep)): get block pointer. This macro assume that ep is LEP. (VM_EP_LEP_P(ep)): detect ep is LEP or not. (VM_ENVVAL_BLOCK_PTR(ptr)): make block pointer. (VM_ENVVAL_BLOCK_PTR_P(v)): detect v is block pointer. (VM_ENVVAL_PREV_EP_PTR(ptr)): make prev environment pointer. (VM_ENVVAL_PREV_EP_PTR_P(v)): detect v is prev env pointer. * vm.c: apply above changes. (VM_EP_LEP(ep)): get LEP. (VM_CF_LEP(cfp)): get LEP of cfp->ep. (VM_CF_PREV_EP(cfp)): utility function VM_EP_PREV_EP(cfp->ep). (VM_CF_BLOCK_PTR(cfp)): utility function VM_EP_BLOCK_PTR(cfp->ep). * vm.c, vm_eval.c, vm_insnhelper.c, vm_insnhelper.h, insns.def: apply above changes. * cont.c: ditto. * eval.c, eval_intern.h: ditto. * proc.c: ditto. * thread.c: ditto. * vm_dump.c: ditto. * vm_exec.h: fix function name (on vm debug mode). git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36030 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-06-11 07:14:59 +04:00
};
#define COLLECT_USAGE_REGISTER_HELPER(a, b, v) \
(COLLECT_USAGE_REGISTER((VM_REGAN_##a), (VM_REGAN_ACT_##b)), (v))
#else
#define COLLECT_USAGE_REGISTER_HELPER(a, b, v) (v)
#endif
/* PC */
#define GET_PC() (COLLECT_USAGE_REGISTER_HELPER(PC, GET, VM_REG_PC))
#define SET_PC(x) (VM_REG_PC = (COLLECT_USAGE_REGISTER_HELPER(PC, SET, (x))))
#define GET_CURRENT_INSN() (*GET_PC())
#define GET_OPERAND(n) (GET_PC()[(n)])
#define ADD_PC(n) (SET_PC(VM_REG_PC + (n)))
#define JUMP(dst) (SET_PC(VM_REG_PC + (dst)))
* vm_core.h: remove lfp (local frame pointer) and rename dfp (dynamic frame pointer) to ep (environment pointer). This change make VM `normal' (similar to other interpreters). Before this commit: Each frame has two env pointers lfp and dfp. lfp points local environment which is method/class/toplevel frame. lfp[0] is block pointer. dfp is block local frame. dfp[0] points previous (parent) environment pointer. lfp == dfp when frame is method/class/toplevel. You can get lfp from dfp by traversing previous environment pointers. After this commit: Each frame has only `ep' to point respective enviornoment. If there is parent environment, then ep[0] points parent envioenment (as dfp). If there are no more environment, then ep[0] points block pointer (as lfp). We call such ep as `LEP' (local EP). We add some macros to get LEP and to detect LEP or not. In short, we replace dfp and lfp with ep and LEP. rb_block_t and rb_binding_t member `lfp' and `dfp' are removed and member `ep' is added. rename rb_thread_t's member `local_lfp' and `local_svar' to `root_lep' and `root_svar'. (VM_EP_PREV_EP(ep)): get previous environment pointer. This macro assume that ep is not LEP. (VM_EP_BLOCK_PTR(ep)): get block pointer. This macro assume that ep is LEP. (VM_EP_LEP_P(ep)): detect ep is LEP or not. (VM_ENVVAL_BLOCK_PTR(ptr)): make block pointer. (VM_ENVVAL_BLOCK_PTR_P(v)): detect v is block pointer. (VM_ENVVAL_PREV_EP_PTR(ptr)): make prev environment pointer. (VM_ENVVAL_PREV_EP_PTR_P(v)): detect v is prev env pointer. * vm.c: apply above changes. (VM_EP_LEP(ep)): get LEP. (VM_CF_LEP(cfp)): get LEP of cfp->ep. (VM_CF_PREV_EP(cfp)): utility function VM_EP_PREV_EP(cfp->ep). (VM_CF_BLOCK_PTR(cfp)): utility function VM_EP_BLOCK_PTR(cfp->ep). * vm.c, vm_eval.c, vm_insnhelper.c, vm_insnhelper.h, insns.def: apply above changes. * cont.c: ditto. * eval.c, eval_intern.h: ditto. * proc.c: ditto. * thread.c: ditto. * vm_dump.c: ditto. * vm_exec.h: fix function name (on vm debug mode). git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36030 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-06-11 07:14:59 +04:00
/* frame pointer, environment pointer */
#define GET_CFP() (COLLECT_USAGE_REGISTER_HELPER(CFP, GET, VM_REG_CFP))
#define GET_EP() (COLLECT_USAGE_REGISTER_HELPER(EP, GET, VM_REG_EP))
#define SET_EP(x) (VM_REG_EP = (COLLECT_USAGE_REGISTER_HELPER(EP, SET, (x))))
* vm_core.h: remove lfp (local frame pointer) and rename dfp (dynamic frame pointer) to ep (environment pointer). This change make VM `normal' (similar to other interpreters). Before this commit: Each frame has two env pointers lfp and dfp. lfp points local environment which is method/class/toplevel frame. lfp[0] is block pointer. dfp is block local frame. dfp[0] points previous (parent) environment pointer. lfp == dfp when frame is method/class/toplevel. You can get lfp from dfp by traversing previous environment pointers. After this commit: Each frame has only `ep' to point respective enviornoment. If there is parent environment, then ep[0] points parent envioenment (as dfp). If there are no more environment, then ep[0] points block pointer (as lfp). We call such ep as `LEP' (local EP). We add some macros to get LEP and to detect LEP or not. In short, we replace dfp and lfp with ep and LEP. rb_block_t and rb_binding_t member `lfp' and `dfp' are removed and member `ep' is added. rename rb_thread_t's member `local_lfp' and `local_svar' to `root_lep' and `root_svar'. (VM_EP_PREV_EP(ep)): get previous environment pointer. This macro assume that ep is not LEP. (VM_EP_BLOCK_PTR(ep)): get block pointer. This macro assume that ep is LEP. (VM_EP_LEP_P(ep)): detect ep is LEP or not. (VM_ENVVAL_BLOCK_PTR(ptr)): make block pointer. (VM_ENVVAL_BLOCK_PTR_P(v)): detect v is block pointer. (VM_ENVVAL_PREV_EP_PTR(ptr)): make prev environment pointer. (VM_ENVVAL_PREV_EP_PTR_P(v)): detect v is prev env pointer. * vm.c: apply above changes. (VM_EP_LEP(ep)): get LEP. (VM_CF_LEP(cfp)): get LEP of cfp->ep. (VM_CF_PREV_EP(cfp)): utility function VM_EP_PREV_EP(cfp->ep). (VM_CF_BLOCK_PTR(cfp)): utility function VM_EP_BLOCK_PTR(cfp->ep). * vm.c, vm_eval.c, vm_insnhelper.c, vm_insnhelper.h, insns.def: apply above changes. * cont.c: ditto. * eval.c, eval_intern.h: ditto. * proc.c: ditto. * thread.c: ditto. * vm_dump.c: ditto. * vm_exec.h: fix function name (on vm debug mode). git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36030 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-06-11 07:14:59 +04:00
#define GET_LEP() (VM_EP_LEP(GET_EP()))
/* SP */
#define GET_SP() (COLLECT_USAGE_REGISTER_HELPER(SP, GET, VM_REG_SP))
#define SET_SP(x) (VM_REG_SP = (COLLECT_USAGE_REGISTER_HELPER(SP, SET, (x))))
#define INC_SP(x) (VM_REG_SP += (COLLECT_USAGE_REGISTER_HELPER(SP, SET, (x))))
#define DEC_SP(x) (VM_REG_SP -= (COLLECT_USAGE_REGISTER_HELPER(SP, SET, (x))))
#define SET_SV(x) (*GET_SP() = rb_ractor_confirm_belonging(x))
mjit_compile.c: reduce sp motion on JIT 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
2018-07-19 16:25:22 +03:00
/* set current stack value as x */
/* instruction sequence C struct */
#define GET_ISEQ() (GET_CFP()->iseq)
/**********************************************************/
/* deal with variables */
/**********************************************************/
#define GET_PREV_EP(ep) ((VALUE *)((ep)[VM_ENV_DATA_INDEX_SPECVAL] & ~0x03))
/**********************************************************/
/* deal with values */
/**********************************************************/
#define GET_SELF() (COLLECT_USAGE_REGISTER_HELPER(SELF, GET, GET_CFP()->self))
/**********************************************************/
/* deal with control flow 2: method/iterator */
/**********************************************************/
/* set fastpath when cached method is *NOT* protected
* because inline method cache does not care about receiver.
*/
static inline void
CC_SET_FASTPATH(const struct rb_callcache *cc, vm_call_handler func, bool enabled)
{
if (LIKELY(enabled)) {
vm_cc_call_set(cc, func);
}
}
#define GET_BLOCK_HANDLER() (GET_LEP()[VM_ENV_DATA_INDEX_SPECVAL])
/**********************************************************/
/* deal with control flow 3: exception */
/**********************************************************/
/**********************************************************/
/* deal with stack canary */
/**********************************************************/
#if VM_CHECK_MODE > 0
#define SETUP_CANARY(cond) \
VALUE *canary = 0; \
if (cond) { \
canary = GET_SP(); \
SET_SV(vm_stack_canary); \
} \
else {\
SET_SV(Qfalse); /* cleanup */ \
}
#define CHECK_CANARY(cond, insn) \
if (cond) { \
if (*canary == vm_stack_canary) { \
*canary = Qfalse; /* cleanup */ \
} \
else { \
2020-12-25 17:36:25 +03:00
rb_vm_canary_is_found_dead(insn, *canary); \
} \
}
#else
#define SETUP_CANARY(cond) if (cond) {} else {}
#define CHECK_CANARY(cond, insn) if (cond) {(void)(insn);}
#endif
/**********************************************************/
/* others */
/**********************************************************/
move ADD_PC around (take 2) Now that we can say for sure if an instruction calls a method or not internally, it is now possible to reroute the bugs that forced us to revert the "move PC around" optimization. First try: r62051 Reverted: r63763 See also: r63999 ---- trunk: ruby 2.6.0dev (2018-09-13 trunk 64736) [x86_64-darwin15] ours: ruby 2.6.0dev (2018-09-13 trunk 64736) [x86_64-darwin15] last_commit=move ADD_PC around (take 2) Calculating ------------------------------------- trunk ours so_ackermann 1.884 2.278 i/s - 1.000 times in 0.530926s 0.438935s so_array 1.178 1.157 i/s - 1.000 times in 0.848786s 0.864467s so_binary_trees 0.176 0.177 i/s - 1.000 times in 5.683895s 5.657707s so_concatenate 0.220 0.221 i/s - 1.000 times in 4.546896s 4.518949s so_count_words 6.729 6.470 i/s - 1.000 times in 0.148602s 0.154561s so_exception 3.324 3.688 i/s - 1.000 times in 0.300872s 0.271147s so_fannkuch 0.546 0.968 i/s - 1.000 times in 1.831328s 1.033376s so_fasta 0.541 0.547 i/s - 1.000 times in 1.849923s 1.827091s so_k_nucleotide 0.800 0.777 i/s - 1.000 times in 1.250635s 1.286295s so_lists 2.101 1.848 i/s - 1.000 times in 0.475954s 0.541095s so_mandelbrot 0.435 0.408 i/s - 1.000 times in 2.299328s 2.450535s so_matrix 1.946 1.912 i/s - 1.000 times in 0.513872s 0.523076s so_meteor_contest 0.311 0.317 i/s - 1.000 times in 3.219297s 3.152052s so_nbody 0.746 0.703 i/s - 1.000 times in 1.339815s 1.423441s so_nested_loop 0.899 0.901 i/s - 1.000 times in 1.111767s 1.109555s so_nsieve 0.559 0.579 i/s - 1.000 times in 1.787763s 1.726552s so_nsieve_bits 0.435 0.428 i/s - 1.000 times in 2.296282s 2.333852s so_object 1.368 1.442 i/s - 1.000 times in 0.731237s 0.693684s so_partial_sums 0.616 0.546 i/s - 1.000 times in 1.623592s 1.833097s so_pidigits 0.831 0.832 i/s - 1.000 times in 1.203117s 1.202334s so_random 2.934 2.724 i/s - 1.000 times in 0.340791s 0.367150s so_reverse_complement 0.583 0.866 i/s - 1.000 times in 1.714144s 1.154615s so_sieve 1.829 2.081 i/s - 1.000 times in 0.546607s 0.480562s so_spectralnorm 0.524 0.558 i/s - 1.000 times in 1.908716s 1.792382s git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64737 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-14 10:44:44 +03:00
#define CALL_SIMPLE_METHOD() do { \
rb_snum_t insn_width = attr_width_opt_send_without_block(0); \
ADD_PC(-insn_width); \
move ADD_PC around (take 2) Now that we can say for sure if an instruction calls a method or not internally, it is now possible to reroute the bugs that forced us to revert the "move PC around" optimization. First try: r62051 Reverted: r63763 See also: r63999 ---- trunk: ruby 2.6.0dev (2018-09-13 trunk 64736) [x86_64-darwin15] ours: ruby 2.6.0dev (2018-09-13 trunk 64736) [x86_64-darwin15] last_commit=move ADD_PC around (take 2) Calculating ------------------------------------- trunk ours so_ackermann 1.884 2.278 i/s - 1.000 times in 0.530926s 0.438935s so_array 1.178 1.157 i/s - 1.000 times in 0.848786s 0.864467s so_binary_trees 0.176 0.177 i/s - 1.000 times in 5.683895s 5.657707s so_concatenate 0.220 0.221 i/s - 1.000 times in 4.546896s 4.518949s so_count_words 6.729 6.470 i/s - 1.000 times in 0.148602s 0.154561s so_exception 3.324 3.688 i/s - 1.000 times in 0.300872s 0.271147s so_fannkuch 0.546 0.968 i/s - 1.000 times in 1.831328s 1.033376s so_fasta 0.541 0.547 i/s - 1.000 times in 1.849923s 1.827091s so_k_nucleotide 0.800 0.777 i/s - 1.000 times in 1.250635s 1.286295s so_lists 2.101 1.848 i/s - 1.000 times in 0.475954s 0.541095s so_mandelbrot 0.435 0.408 i/s - 1.000 times in 2.299328s 2.450535s so_matrix 1.946 1.912 i/s - 1.000 times in 0.513872s 0.523076s so_meteor_contest 0.311 0.317 i/s - 1.000 times in 3.219297s 3.152052s so_nbody 0.746 0.703 i/s - 1.000 times in 1.339815s 1.423441s so_nested_loop 0.899 0.901 i/s - 1.000 times in 1.111767s 1.109555s so_nsieve 0.559 0.579 i/s - 1.000 times in 1.787763s 1.726552s so_nsieve_bits 0.435 0.428 i/s - 1.000 times in 2.296282s 2.333852s so_object 1.368 1.442 i/s - 1.000 times in 0.731237s 0.693684s so_partial_sums 0.616 0.546 i/s - 1.000 times in 1.623592s 1.833097s so_pidigits 0.831 0.832 i/s - 1.000 times in 1.203117s 1.202334s so_random 2.934 2.724 i/s - 1.000 times in 0.340791s 0.367150s so_reverse_complement 0.583 0.866 i/s - 1.000 times in 1.714144s 1.154615s so_sieve 1.829 2.081 i/s - 1.000 times in 0.546607s 0.480562s so_spectralnorm 0.524 0.558 i/s - 1.000 times in 1.908716s 1.792382s git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64737 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-09-14 10:44:44 +03:00
DISPATCH_ORIGINAL_INSN(opt_send_without_block); \
} while (0)
Add a cache for class variables Redo of 34a2acdac788602c14bf05fb616215187badd504 and 931138b00696419945dc03e10f033b1f53cd50f3 which were reverted. GitHub PR #4340. This change implements a cache for class variables. Previously there was no cache for cvars. Cvar access is slow due to needing to travel all the way up th ancestor tree before returning the cvar value. The deeper the ancestor tree the slower cvar access will be. The benefits of the cache are more visible with a higher number of included modules due to the way Ruby looks up class variables. The benchmark here includes 26 modules and shows with the cache, this branch is 6.5x faster when accessing class variables. ``` compare-ruby: ruby 3.1.0dev (2021-03-15T06:22:34Z master 9e5105c) [x86_64-darwin19] built-ruby: ruby 3.1.0dev (2021-03-15T12:12:44Z add-cache-for-clas.. c6be009) [x86_64-darwin19] | |compare-ruby|built-ruby| |:--------|-----------:|---------:| |vm_cvar | 5.681M| 36.980M| | | -| 6.51x| ``` Benchmark.ips calling `ActiveRecord::Base.logger` from within a Rails application. ActiveRecord::Base.logger has 71 ancestors. The more ancestors a tree has, the more clear the speed increase. IE if Base had only one ancestor we'd see no improvement. This benchmark is run on a vanilla Rails application. Benchmark code: ```ruby require "benchmark/ips" require_relative "config/environment" Benchmark.ips do |x| x.report "logger" do ActiveRecord::Base.logger end end ``` Ruby 3.0 master / Rails 6.1: ``` Warming up -------------------------------------- logger 155.251k i/100ms Calculating ------------------------------------- ``` Ruby 3.0 with cvar cache / Rails 6.1: ``` Warming up -------------------------------------- logger 1.546M i/100ms Calculating ------------------------------------- logger 14.857M (± 4.8%) i/s - 74.198M in 5.006202s ``` Lastly we ran a benchmark to demonstate the difference between master and our cache when the number of modules increases. This benchmark measures 1 ancestor, 30 ancestors, and 100 ancestors. Ruby 3.0 master: ``` Warming up -------------------------------------- 1 module 1.231M i/100ms 30 modules 432.020k i/100ms 100 modules 145.399k i/100ms Calculating ------------------------------------- 1 module 12.210M (± 2.1%) i/s - 61.553M in 5.043400s 30 modules 4.354M (± 2.7%) i/s - 22.033M in 5.063839s 100 modules 1.434M (± 2.9%) i/s - 7.270M in 5.072531s Comparison: 1 module: 12209958.3 i/s 30 modules: 4354217.8 i/s - 2.80x (± 0.00) slower 100 modules: 1434447.3 i/s - 8.51x (± 0.00) slower ``` Ruby 3.0 with cvar cache: ``` Warming up -------------------------------------- 1 module 1.641M i/100ms 30 modules 1.655M i/100ms 100 modules 1.620M i/100ms Calculating ------------------------------------- 1 module 16.279M (± 3.8%) i/s - 82.038M in 5.046923s 30 modules 15.891M (± 3.9%) i/s - 79.459M in 5.007958s 100 modules 16.087M (± 3.6%) i/s - 81.005M in 5.041931s Comparison: 1 module: 16279458.0 i/s 100 modules: 16087484.6 i/s - same-ish: difference falls within error 30 modules: 15891406.2 i/s - same-ish: difference falls within error ``` Co-authored-by: Aaron Patterson <tenderlove@ruby-lang.org>
2021-06-01 20:34:06 +03:00
#define GET_GLOBAL_CVAR_STATE() (ruby_vm_global_cvar_state)
#define INC_GLOBAL_CVAR_STATE() (++ruby_vm_global_cvar_state)
static inline struct vm_throw_data *
THROW_DATA_NEW(VALUE val, const rb_control_frame_t *cf, int st)
{
struct vm_throw_data *obj = IMEMO_NEW(struct vm_throw_data, imemo_throw_data, 0);
*((VALUE *)&obj->throw_obj) = val;
*((struct rb_control_frame_struct **)&obj->catch_frame) = (struct rb_control_frame_struct *)cf;
obj->throw_state = st;
return obj;
}
static inline VALUE
THROW_DATA_VAL(const struct vm_throw_data *obj)
{
VM_ASSERT(THROW_DATA_P(obj));
return obj->throw_obj;
}
static inline const rb_control_frame_t *
THROW_DATA_CATCH_FRAME(const struct vm_throw_data *obj)
{
VM_ASSERT(THROW_DATA_P(obj));
return obj->catch_frame;
}
static inline int
THROW_DATA_STATE(const struct vm_throw_data *obj)
{
VM_ASSERT(THROW_DATA_P(obj));
return obj->throw_state;
}
static inline int
THROW_DATA_CONSUMED_P(const struct vm_throw_data *obj)
{
VM_ASSERT(THROW_DATA_P(obj));
return obj->flags & THROW_DATA_CONSUMED;
}
static inline void
THROW_DATA_CATCH_FRAME_SET(struct vm_throw_data *obj, const rb_control_frame_t *cfp)
{
VM_ASSERT(THROW_DATA_P(obj));
obj->catch_frame = cfp;
}
static inline void
THROW_DATA_STATE_SET(struct vm_throw_data *obj, int st)
{
VM_ASSERT(THROW_DATA_P(obj));
obj->throw_state = st;
}
static inline void
THROW_DATA_CONSUMED_SET(struct vm_throw_data *obj)
{
if (THROW_DATA_P(obj) &&
THROW_DATA_STATE(obj) == TAG_BREAK) {
obj->flags |= THROW_DATA_CONSUMED;
}
}
#define IS_ARGS_SPLAT(ci) (vm_ci_flag(ci) & VM_CALL_ARGS_SPLAT)
#define IS_ARGS_KEYWORD(ci) (vm_ci_flag(ci) & VM_CALL_KWARG)
#define IS_ARGS_KW_SPLAT(ci) (vm_ci_flag(ci) & VM_CALL_KW_SPLAT)
#define IS_ARGS_KW_OR_KW_SPLAT(ci) (vm_ci_flag(ci) & (VM_CALL_KWARG | VM_CALL_KW_SPLAT))
Reduce allocations for keyword argument hashes Previously, passing a keyword splat to a method always allocated a hash on the caller side, and accepting arbitrary keywords in a method allocated a separate hash on the callee side. Passing explicit keywords to a method that accepted a keyword splat did not allocate a hash on the caller side, but resulted in two hashes allocated on the callee side. This commit makes passing a single keyword splat to a method not allocate a hash on the caller side. Passing multiple keyword splats or a mix of explicit keywords and a keyword splat still generates a hash on the caller side. On the callee side, if arbitrary keywords are not accepted, it does not allocate a hash. If arbitrary keywords are accepted, it will allocate a hash, but this commit uses a callinfo flag to indicate whether the caller already allocated a hash, and if so, the callee can use the passed hash without duplicating it. So this commit should make it so that a maximum of a single hash is allocated during method calls. To set the callinfo flag appropriately, method call argument compilation checks if only a single keyword splat is given. If only one keyword splat is given, the VM_CALL_KW_SPLAT_MUT callinfo flag is not set, since in that case the keyword splat is passed directly and not mutable. If more than one splat is used, a new hash needs to be generated on the caller side, and in that case the callinfo flag is set, indicating the keyword splat is mutable by the callee. In compile_hash, used for both hash and keyword argument compilation, if compiling keyword arguments and only a single keyword splat is used, pass the argument directly. On the caller side, in vm_args.c, the callinfo flag needs to be recognized and handled. Because the keyword splat argument may not be a hash, it needs to be converted to a hash first if not. Then, unless the callinfo flag is set, the hash needs to be duplicated. The temporary copy of the callinfo flag, kw_flag, is updated if a hash was duplicated, to prevent the need to duplicate it again. If we are converting to a hash or duplicating a hash, we need to update the argument array, which can including duplicating the positional splat array if one was passed. CALLER_SETUP_ARG and a couple other places needs to be modified to handle similar issues for other types of calls. This includes fairly comprehensive tests for different ways keywords are handled internally, checking that you get equal results but that keyword splats on the caller side result in distinct objects for keyword rest parameters. Included are benchmarks for keyword argument calls. Brief results when compiled without optimization: def kw(a: 1) a end def kws(**kw) kw end h = {a: 1} kw(a: 1) # about same kw(**h) # 2.37x faster kws(a: 1) # 1.30x faster kws(**h) # 2.19x faster kw(a: 1, **h) # 1.03x slower kw(**h, **h) # about same kws(a: 1, **h) # 1.16x faster kws(**h, **h) # 1.14x faster
2020-02-24 23:05:07 +03:00
#define IS_ARGS_KW_SPLAT_MUT(ci) (vm_ci_flag(ci) & VM_CALL_KW_SPLAT_MUT)
static inline bool
vm_call_cacheable(const struct rb_callinfo *ci, const struct rb_callcache *cc)
{
Optimized forwarding callers and callees This patch optimizes forwarding callers and callees. It only optimizes methods that only take `...` as their parameter, and then pass `...` to other calls. Calls it optimizes look like this: ```ruby def bar(a) = a def foo(...) = bar(...) # optimized foo(123) ``` ```ruby def bar(a) = a def foo(...) = bar(1, 2, ...) # optimized foo(123) ``` ```ruby def bar(*a) = a def foo(...) list = [1, 2] bar(*list, ...) # optimized end foo(123) ``` All variants of the above but using `super` are also optimized, including a bare super like this: ```ruby def foo(...) super end ``` This patch eliminates intermediate allocations made when calling methods that accept `...`. We can observe allocation elimination like this: ```ruby def m x = GC.stat(:total_allocated_objects) yield GC.stat(:total_allocated_objects) - x end def bar(a) = a def foo(...) = bar(...) def test m { foo(123) } end test p test # allocates 1 object on master, but 0 objects with this patch ``` ```ruby def bar(a, b:) = a + b def foo(...) = bar(...) def test m { foo(1, b: 2) } end test p test # allocates 2 objects on master, but 0 objects with this patch ``` How does it work? ----------------- This patch works by using a dynamic stack size when passing forwarded parameters to callees. The caller's info object (known as the "CI") contains the stack size of the parameters, so we pass the CI object itself as a parameter to the callee. When forwarding parameters, the forwarding ISeq uses the caller's CI to determine how much stack to copy, then copies the caller's stack before calling the callee. The CI at the forwarded call site is adjusted using information from the caller's CI. I think this description is kind of confusing, so let's walk through an example with code. ```ruby def delegatee(a, b) = a + b def delegator(...) delegatee(...) # CI2 (FORWARDING) end def caller delegator(1, 2) # CI1 (argc: 2) end ``` Before we call the delegator method, the stack looks like this: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | 5| delegatee(...) # CI2 (FORWARDING) | 6| end | 7| | 8| def caller | -> 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The ISeq for `delegator` is tagged as "forwardable", so when `caller` calls in to `delegator`, it writes `CI1` on to the stack as a local variable for the `delegator` method. The `delegator` method has a special local called `...` that holds the caller's CI object. Here is the ISeq disasm fo `delegator`: ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` The local called `...` will contain the caller's CI: CI1. Here is the stack when we enter `delegator`: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 -> 4| # | CI1 (argc: 2) 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | 9| delegator(1, 2) # CI1 (argc: 2) | 10| end | ``` The CI at `delegatee` on line 5 is tagged as "FORWARDING", so it knows to memcopy the caller's stack before calling `delegatee`. In this case, it will memcopy self, 1, and 2 to the stack before calling `delegatee`. It knows how much memory to copy from the caller because `CI1` contains stack size information (argc: 2). Before executing the `send` instruction, we push `...` on the stack. The `send` instruction pops `...`, and because it is tagged with `FORWARDING`, it knows to memcopy (using the information in the CI it just popped): ``` == disasm: #<ISeq:delegator@-e:1 (1,0)-(1,39)> local table (size: 1, argc: 0 [opts: 0, rest: -1, post: 0, block: -1, kw: -1@-1, kwrest: -1]) [ 1] "..."@0 0000 putself ( 1)[LiCa] 0001 getlocal_WC_0 "..."@0 0003 send <calldata!mid:delegatee, argc:0, FCALL|FORWARDING>, nil 0006 leave [Re] ``` Instruction 001 puts the caller's CI on the stack. `send` is tagged with FORWARDING, so it reads the CI and _copies_ the callers stack to this stack: ``` Executing Line | Code | Stack ---------------+---------------------------------------+-------- 1| def delegatee(a, b) = a + b | self 2| | 1 3| def delegator(...) | 2 4| # | CI1 (argc: 2) -> 5| delegatee(...) # CI2 (FORWARDING) | cref_or_me 6| end | specval 7| | type 8| def caller | self 9| delegator(1, 2) # CI1 (argc: 2) | 1 10| end | 2 ``` The "FORWARDING" call site combines information from CI1 with CI2 in order to support passing other values in addition to the `...` value, as well as perfectly forward splat args, kwargs, etc. Since we're able to copy the stack from `caller` in to `delegator`'s stack, we can avoid allocating objects. I want to do this to eliminate object allocations for delegate methods. My long term goal is to implement `Class#new` in Ruby and it uses `...`. I was able to implement `Class#new` in Ruby [here](https://github.com/ruby/ruby/pull/9289). If we adopt the technique in this patch, then we can optimize allocating objects that take keyword parameters for `initialize`. For example, this code will allocate 2 objects: one for `SomeObject`, and one for the kwargs: ```ruby SomeObject.new(foo: 1) ``` If we combine this technique, plus implement `Class#new` in Ruby, then we can reduce allocations for this common operation. Co-Authored-By: John Hawthorn <john@hawthorn.email> Co-Authored-By: Alan Wu <XrXr@users.noreply.github.com>
2024-04-15 20:48:53 +03:00
return !(vm_ci_flag(ci) & VM_CALL_FORWARDING) && ((vm_ci_flag(ci) & VM_CALL_FCALL) ||
METHOD_ENTRY_VISI(vm_cc_cme(cc)) != METHOD_VISI_PROTECTED);
}
/* If this returns true, an optimized function returned by `vm_call_iseq_setup_func`
can be used as a fastpath. */
static inline bool
vm_call_iseq_optimizable_p(const struct rb_callinfo *ci, const struct rb_callcache *cc)
{
return !IS_ARGS_SPLAT(ci) && !IS_ARGS_KEYWORD(ci) && vm_call_cacheable(ci, cc);
}
#endif /* RUBY_INSNHELPER_H */