1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/vm_insnhelper.h

300 lines
9.4 KiB
C
Raw Normal View History

/**********************************************************************
insnhelper.h - helper macros to implement each instructions
$Author$
created at: 04/01/01 15:50:34 JST
Copyright (C) 2004-2007 Koichi Sasada
**********************************************************************/
#ifndef RUBY_INSNHELPER_H
#define RUBY_INSNHELPER_H
RUBY_SYMBOL_EXPORT_BEGIN
extern VALUE ruby_vm_const_missing_count;
extern rb_serial_t ruby_vm_global_method_state;
extern rb_serial_t ruby_vm_global_constant_state;
extern rb_serial_t ruby_vm_class_serial;
RUBY_SYMBOL_EXPORT_END
#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)))
* probes.d: add DTrace probe declarations. [ruby-core:27448] * array.c (empty_ary_alloc, ary_new): added array create DTrace probe. * compile.c (rb_insns_name): allowing DTrace probes to access instruction sequence name. * Makefile.in: translate probes.d file to appropriate header file. * common.mk: declare dependencies on the DTrace header. * configure.in: add a test for existence of DTrace. * eval.c (setup_exception): add a probe for when an exception is raised. * gc.c: Add DTrace probes for mark begin and end, and sweep begin and end. * hash.c (empty_hash_alloc): Add a probe for hash allocation. * insns.def: Add probes for function entry and return. * internal.h: function declaration for compile.c change. * load.c (rb_f_load): add probes for `load` entry and exit, require entry and exit, and wrapping search_required for load path search. * object.c (rb_obj_alloc): added a probe for general object creation. * parse.y (yycompile0): added a probe around parse and compile phase. * string.c (empty_str_alloc, str_new): DTrace probes for string allocation. * test/dtrace/*: tests for DTrace probes. * vm.c (vm_invoke_proc): add probes for function return on exception raise, hash create, and instruction sequence execution. * vm_core.h: add probe declarations for function entry and exit. * vm_dump.c: add probes header file. * vm_eval.c (vm_call0_cfunc, vm_call0_cfunc_with_frame): add probe on function entry and return. * vm_exec.c: expose instruction number to instruction name function. * vm_insnshelper.c: add function entry and exit probes for cfunc methods. * vm_insnhelper.h: vm usage information is always collected, so uncomment the functions. 12 19:14:50 2012 Akinori MUSHA <knu@iDaemons.org> * configure.in (isinf, isnan): isinf() and isnan() are macros on DragonFly which cannot be found by AC_REPLACE_FUNCS(). This workaround enforces the fact that they exist on DragonFly. 12 15:59:38 2012 Shugo Maeda <shugo@ruby-lang.org> * vm_core.h (rb_call_info_t::refinements), compile.c (new_callinfo), vm_insnhelper.c (vm_search_method): revert r37616 because it's too slow. [ruby-dev:46477] * test/ruby/test_refinement.rb (test_inline_method_cache): skip the test until the bug is fixed efficiently. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37631 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2012-11-12 16:52:12 -05:00
#define COLLECT_USAGE_REGISTER(reg, s) vm_collect_usage_register((reg), (s))
#else
#define COLLECT_USAGE_INSN(insn) /* none */
#define COLLECT_USAGE_OPERAND(insn, n, op) /* none */
#define COLLECT_USAGE_REGISTER(reg, s) /* none */
#endif
/**********************************************************/
/* deal with stack */
/**********************************************************/
static inline int
rb_obj_hidden_p(VALUE obj)
{
if (SPECIAL_CONST_P(obj)) {
return FALSE;
}
else {
return RBASIC_CLASS(obj) ? FALSE : TRUE;
}
}
#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))
#define GET_TOS() (tos) /* dummy */
/**********************************************************/
/* 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)
#define REG_A reg_a
#define REG_B reg_b
* 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
2012-06-10 23:14:59 -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
2012-06-10 23:14:59 -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
2012-06-10 23:14:59 -04:00
};
#if VM_COLLECT_USAGE_DETAILS
#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
2012-06-10 23:14:59 -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
2012-06-10 23:14:59 -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() = (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 09:25:22 -04:00
/* set current stack value as x */
#define ADJ_SP(x) INC_SP(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))
#define GET_GLOBAL(entry) rb_gvar_get((struct rb_global_entry*)(entry))
#define SET_GLOBAL(entry, val) rb_gvar_set((struct rb_global_entry*)(entry), (val))
#define GET_CONST_INLINE_CACHE(dst) ((IC) * (GET_PC() + (dst) + 2))
/**********************************************************/
/* deal with values */
/**********************************************************/
#define GET_SELF() (COLLECT_USAGE_REGISTER_HELPER(SELF, GET, GET_CFP()->self))
/**********************************************************/
/* deal with control flow 2: method/iterator */
/**********************************************************/
mjit_compile.c: use local variables for stack 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
2018-03-04 02:04:40 -05:00
#ifdef MJIT_HEADER
/* When calling ISeq which may catch an exception from JIT-ed code, we should not call
mjit_exec directly to prevent the caller frame from being canceled. That's because
the caller frame may have stack values in the local variables and the cancelling
the caller frame will purge them. But directly calling mjit_exec is faster... */
#define EXEC_EC_CFP(val) do { \
if (ec->cfp->iseq->body->catch_except_p) { \
VM_ENV_FLAGS_SET(ec->cfp->ep, VM_FRAME_FLAG_FINISH); \
val = vm_exec(ec, TRUE); \
} \
else if ((val = mjit_exec(ec)) == Qundef) { \
VM_ENV_FLAGS_SET(ec->cfp->ep, VM_FRAME_FLAG_FINISH); \
val = vm_exec(ec, FALSE); \
} \
} while (0)
#else
/* When calling from VM, longjmp in the callee won't purge any JIT-ed caller frames.
So it's safe to directly call mjit_exec. */
#define EXEC_EC_CFP(val) do { \
if ((val = mjit_exec(ec)) == Qundef) { \
RESTORE_REGS(); \
NEXT_INSN(); \
} \
} while (0)
#endif
#define CALL_METHOD(calling, ci, cc) do { \
VALUE v = (*(cc)->call)(ec, GET_CFP(), (calling), (ci), (cc)); \
mjit_compile.c: use local variables for stack 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
2018-03-04 02:04:40 -05:00
if (v == Qundef) { \
EXEC_EC_CFP(val); \
} \
else { \
val = v; \
} \
} while (0)
/* set fastpath when cached method is *NOT* protected
* because inline method cache does not care about receiver.
*/
#ifndef OPT_CALL_FASTPATH
#define OPT_CALL_FASTPATH 1
#endif
#if OPT_CALL_FASTPATH
#define CI_SET_FASTPATH(cc, func, enabled) do { \
if (LIKELY(enabled)) ((cc)->call = (func)); \
} while (0)
#else
#define CI_SET_FASTPATH(ci, func, enabled) /* do nothing */
#endif
#define GET_BLOCK_HANDLER() (GET_LEP()[VM_ENV_DATA_INDEX_SPECVAL])
#define WIDTH_OF_opt_send_without_block \
((rb_snum_t)attr_width_opt_send_without_block(0, 0))
/**********************************************************/
/* deal with control flow 3: exception */
/**********************************************************/
/**********************************************************/
/* others */
/**********************************************************/
/* optimize insn */
#define FIXNUM_2_P(a, b) ((a) & (b) & 1)
#if USE_FLONUM
#define FLONUM_2_P(a, b) (((((a)^2) | ((b)^2)) & 3) == 0) /* (FLONUM_P(a) && FLONUM_P(b)) */
#else
#define FLONUM_2_P(a, b) 0
#endif
#define FLOAT_HEAP_P(x) (!SPECIAL_CONST_P(x) && RBASIC_CLASS(x) == rb_cFloat)
#define FLOAT_INSTANCE_P(x) (FLONUM_P(x) || FLOAT_HEAP_P(x))
#ifndef USE_IC_FOR_SPECIALIZED_METHOD
#define USE_IC_FOR_SPECIALIZED_METHOD 1
#endif
#define NEXT_CLASS_SERIAL() (++ruby_vm_class_serial)
#define GET_GLOBAL_METHOD_STATE() (ruby_vm_global_method_state)
#define INC_GLOBAL_METHOD_STATE() (++ruby_vm_global_method_state)
#define GET_GLOBAL_CONSTANT_STATE() (ruby_vm_global_constant_state)
#define INC_GLOBAL_CONSTANT_STATE() (++ruby_vm_global_constant_state)
extern rb_method_definition_t *rb_method_definition_create(rb_method_type_t type, ID mid);
extern void rb_method_definition_set(const rb_method_entry_t *me, rb_method_definition_t *def, void *opts);
extern int rb_method_definition_eq(const rb_method_definition_t *d1, const rb_method_definition_t *d2);
extern VALUE rb_make_no_method_exception(VALUE exc, VALUE format, VALUE obj,
int argc, const VALUE *argv, int priv);
static inline struct vm_throw_data *
THROW_DATA_NEW(VALUE val, const rb_control_frame_t *cf, VALUE st)
{
return (struct vm_throw_data *)rb_imemo_new(imemo_throw_data, val, (VALUE)cf, st, 0);
}
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 (int)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 = (VALUE)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) ((ci)->flag & VM_CALL_ARGS_SPLAT)
#define IS_ARGS_KEYWORD(ci) ((ci)->flag & VM_CALL_KWARG)
#define CALLER_SETUP_ARG(cfp, calling, ci) do { \
if (UNLIKELY(IS_ARGS_SPLAT(ci))) vm_caller_setup_arg_splat((cfp), (calling)); \
if (UNLIKELY(IS_ARGS_KEYWORD(ci))) vm_caller_setup_arg_kw((cfp), (calling), (ci)); \
} while (0)
#endif /* RUBY_INSNHELPER_H */