ruby/vm_exec.h

203 строки
4.9 KiB
C
Исходник Обычный вид История

/**********************************************************************
vm.h -
$Author$
created at: 04/01/01 16:56:59 JST
Copyright (C) 2004-2007 Koichi Sasada
**********************************************************************/
#ifndef RUBY_VM_EXEC_H
#define RUBY_VM_EXEC_H
typedef long OFFSET;
typedef unsigned long lindex_t;
typedef VALUE GENTRY;
typedef rb_iseq_t *ISEQ;
#ifdef __GNUC__
/* TODO: machine dependent prefetch instruction */
#define PREFETCH(pc)
#else
#define PREFETCH(pc)
#endif
#if VMDEBUG > 0
#define debugs printf
#define DEBUG_ENTER_INSN(insn) \
rb_vmdebug_debug_print_pre(ec, GET_CFP(), GET_PC());
#if OPT_STACK_CACHING
#define SC_REGS() , reg_a, reg_b
#else
#define SC_REGS()
#endif
#define DEBUG_END_INSN() \
rb_vmdebug_debug_print_post(ec, GET_CFP() SC_REGS());
#else
#define debugs
#define DEBUG_ENTER_INSN(insn)
#define DEBUG_END_INSN()
#endif
#define throwdebug if(0)printf
/* #define throwdebug printf */
/************************************************/
#if defined(DISPATCH_XXX)
error !
/************************************************/
#elif OPT_CALL_THREADED_CODE
#define LABEL(x) insn_func_##x
#define ELABEL(x)
#define LABEL_PTR(x) &LABEL(x)
#define INSN_ENTRY(insn) \
static rb_control_frame_t * \
FUNC_FASTCALL(LABEL(insn))(rb_execution_context_t *ec, rb_control_frame_t *reg_cfp) {
#define END_INSN(insn) return reg_cfp;}
#define NEXT_INSN() return reg_cfp;
#define START_OF_ORIGINAL_INSN(x) /* ignore */
#define DISPATCH_ORIGINAL_INSN(x) return LABEL(x)(ec, reg_cfp);
/************************************************/
#elif OPT_TOKEN_THREADED_CODE || OPT_DIRECT_THREADED_CODE
/* threaded code with gcc */
#define LABEL(x) INSN_LABEL_##x
#define ELABEL(x) INSN_ELABEL_##x
#define LABEL_PTR(x) RB_GNUC_EXTENSION(&&LABEL(x))
#define INSN_ENTRY_SIG(insn) \
if (0) fprintf(stderr, "exec: %s@(%d, %d)@%s:%d\n", #insn, \
(int)(reg_pc - reg_cfp->iseq->body->iseq_encoded), \
(int)(reg_cfp->pc - reg_cfp->iseq->body->iseq_encoded), \
RSTRING_PTR(rb_iseq_path(reg_cfp->iseq)), \
(int)(rb_iseq_line_no(reg_cfp->iseq, reg_pc - reg_cfp->iseq->body->iseq_encoded)));
#define INSN_DISPATCH_SIG(insn)
#define INSN_ENTRY(insn) \
LABEL(insn): \
INSN_ENTRY_SIG(insn); \
/* dispatcher */
#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) && __GNUC__ == 3
#define DISPATCH_ARCH_DEPEND_WAY(addr) \
__asm__ __volatile__("jmp *%0;\t# -- inserted by vm.h\t[length = 2]" : : "r" (addr))
#else
#define DISPATCH_ARCH_DEPEND_WAY(addr) \
/* do nothing */
#endif
/**********************************/
#if OPT_DIRECT_THREADED_CODE
/* for GCC 3.4.x */
#define TC_DISPATCH(insn) \
INSN_DISPATCH_SIG(insn); \
RB_GNUC_EXTENSION_BLOCK(goto *(void const *)GET_CURRENT_INSN()); \
;
#else
/* token threaded code */
#define TC_DISPATCH(insn) \
DISPATCH_ARCH_DEPEND_WAY(insns_address_table[GET_CURRENT_INSN()]); \
INSN_DISPATCH_SIG(insn); \
RB_GNUC_EXTENSION_BLOCK(goto *insns_address_table[GET_CURRENT_INSN()]); \
rb_bug("tc error");
#endif /* DISPATCH_DIRECT_THREADED_CODE */
#define END_INSN(insn) \
DEBUG_END_INSN(); \
TC_DISPATCH(insn);
#define INSN_DISPATCH() \
TC_DISPATCH(__START__) \
{
#define END_INSNS_DISPATCH() \
rb_bug("unknown insn: %"PRIdVALUE, GET_CURRENT_INSN()); \
} /* end of while loop */ \
#define NEXT_INSN() TC_DISPATCH(__NEXT_INSN__)
#define START_OF_ORIGINAL_INSN(x) start_of_##x:
#define DISPATCH_ORIGINAL_INSN(x) goto start_of_##x;
/************************************************/
#else /* no threaded code */
/* most common method */
#define INSN_ENTRY(insn) \
case BIN(insn):
#define END_INSN(insn) \
DEBUG_END_INSN(); \
break;
#define INSN_DISPATCH() \
while (1) { \
switch (GET_CURRENT_INSN()) {
#define END_INSNS_DISPATCH() \
default: \
SDR(); \
rb_bug("unknown insn: %ld", GET_CURRENT_INSN()); \
} /* end of switch */ \
} /* end of while loop */ \
#define NEXT_INSN() goto first
#define START_OF_ORIGINAL_INSN(x) start_of_##x:
#define DISPATCH_ORIGINAL_INSN(x) goto start_of_##x;
#endif
#define VM_SP_CNT(ec, sp) ((sp) - (ec)->vm_stack)
mjit_compile.c: merge initial JIT compiler which has been developed by Takashi Kokubun <takashikkbn@gmail> as YARV-MJIT. Many of its bugs are fixed by wanabe <s.wanabe@gmail.com>. This JIT compiler is designed to be a safe migration path to introduce JIT compiler to MRI. So this commit does not include any bytecode changes or dynamic instruction modifications, which are done in original MJIT. This commit even strips off some aggressive optimizations from YARV-MJIT, and thus it's slower than YARV-MJIT too. But it's still fairly faster than Ruby 2.5 in some benchmarks (attached below). Note that this JIT compiler passes `make test`, `make test-all`, `make test-spec` without JIT, and even with JIT. Not only it's perfectly safe with JIT disabled because it does not replace VM instructions unlike MJIT, but also with JIT enabled it stably runs Ruby applications including Rails applications. I'm expecting this version as just "initial" JIT compiler. I have many optimization ideas which are skipped for initial merging, and you may easily replace this JIT compiler with a faster one by just replacing mjit_compile.c. `mjit_compile` interface is designed for the purpose. common.mk: update dependencies for mjit_compile.c. internal.h: declare `rb_vm_insn_addr2insn` for MJIT. vm.c: exclude some definitions if `-DMJIT_HEADER` is provided to compiler. This avoids to include some functions which take a long time to compile, e.g. vm_exec_core. Some of the purpose is achieved in transform_mjit_header.rb (see `IGNORED_FUNCTIONS`) but others are manually resolved for now. Load mjit_helper.h for MJIT header. mjit_helper.h: New. This is a file used only by JIT-ed code. I'll refactor `mjit_call_cfunc` later. vm_eval.c: add some #ifdef switches to skip compiling some functions like Init_vm_eval. win32/mkexports.rb: export thread/ec functions, which are used by MJIT. include/ruby/defines.h: add MJIT_FUNC_EXPORTED macro alis to clarify that a function is exported only for MJIT. array.c: export a function used by MJIT. bignum.c: ditto. class.c: ditto. compile.c: ditto. error.c: ditto. gc.c: ditto. hash.c: ditto. iseq.c: ditto. numeric.c: ditto. object.c: ditto. proc.c: ditto. re.c: ditto. st.c: ditto. string.c: ditto. thread.c: ditto. variable.c: ditto. vm_backtrace.c: ditto. vm_insnhelper.c: ditto. vm_method.c: ditto. I would like to improve maintainability of function exports, but I believe this way is acceptable as initial merging if we clarify the new exports are for MJIT (so that we can use them as TODO list to fix) and add unit tests to detect unresolved symbols. I'll add unit tests of JIT compilations in succeeding commits. Author: Takashi Kokubun <takashikkbn@gmail.com> Contributor: wanabe <s.wanabe@gmail.com> Part of [Feature #14235] --- * Known issues * Code generated by gcc is faster than clang. The benchmark may be worse in macOS. Following benchmark result is provided by gcc w/ Linux. * Performance is decreased when Google Chrome is running * JIT can work on MinGW, but it doesn't improve performance at least in short running benchmark. * Currently it doesn't perform well with Rails. We'll try to fix this before release. --- * Benchmark reslts Benchmarked with: Intel 4.0GHz i7-4790K with 16GB memory under x86-64 Ubuntu 8 Cores - 2.0.0-p0: Ruby 2.0.0-p0 - r62186: Ruby trunk (early 2.6.0), before MJIT changes - JIT off: On this commit, but without `--jit` option - JIT on: On this commit, and with `--jit` option ** Optcarrot fps Benchmark: https://github.com/mame/optcarrot | |2.0.0-p0 |r62186 |JIT off |JIT on | |:--------|:--------|:--------|:--------|:--------| |fps |37.32 |51.46 |51.31 |58.88 | |vs 2.0.0 |1.00x |1.38x |1.37x |1.58x | ** MJIT benchmarks Benchmark: https://github.com/benchmark-driver/mjit-benchmarks (Original: https://github.com/vnmakarov/ruby/tree/rtl_mjit_branch/MJIT-benchmarks) | |2.0.0-p0 |r62186 |JIT off |JIT on | |:----------|:--------|:--------|:--------|:--------| |aread |1.00 |1.09 |1.07 |2.19 | |aref |1.00 |1.13 |1.11 |2.22 | |aset |1.00 |1.50 |1.45 |2.64 | |awrite |1.00 |1.17 |1.13 |2.20 | |call |1.00 |1.29 |1.26 |2.02 | |const2 |1.00 |1.10 |1.10 |2.19 | |const |1.00 |1.11 |1.10 |2.19 | |fannk |1.00 |1.04 |1.02 |1.00 | |fib |1.00 |1.32 |1.31 |1.84 | |ivread |1.00 |1.13 |1.12 |2.43 | |ivwrite |1.00 |1.23 |1.21 |2.40 | |mandelbrot |1.00 |1.13 |1.16 |1.28 | |meteor |1.00 |2.97 |2.92 |3.17 | |nbody |1.00 |1.17 |1.15 |1.49 | |nest-ntimes|1.00 |1.22 |1.20 |1.39 | |nest-while |1.00 |1.10 |1.10 |1.37 | |norm |1.00 |1.18 |1.16 |1.24 | |nsvb |1.00 |1.16 |1.16 |1.17 | |red-black |1.00 |1.02 |0.99 |1.12 | |sieve |1.00 |1.30 |1.28 |1.62 | |trees |1.00 |1.14 |1.13 |1.19 | |while |1.00 |1.12 |1.11 |2.41 | ** Discourse's script/bench.rb Benchmark: https://github.com/discourse/discourse/blob/v1.8.7/script/bench.rb NOTE: Rails performance was somehow a little degraded with JIT for now. We should fix this. (At least I know opt_aref is performing badly in JIT and I have an idea to fix it. Please wait for the fix.) *** JIT off Your Results: (note for timings- percentile is first, duration is second in millisecs) categories_admin: 50: 17 75: 18 90: 22 99: 29 home_admin: 50: 21 75: 21 90: 27 99: 40 topic_admin: 50: 17 75: 18 90: 22 99: 32 categories: 50: 35 75: 41 90: 43 99: 77 home: 50: 39 75: 46 90: 49 99: 95 topic: 50: 46 75: 52 90: 56 99: 101 *** JIT on Your Results: (note for timings- percentile is first, duration is second in millisecs) categories_admin: 50: 19 75: 21 90: 25 99: 33 home_admin: 50: 24 75: 26 90: 30 99: 35 topic_admin: 50: 19 75: 20 90: 25 99: 30 categories: 50: 40 75: 44 90: 48 99: 76 home: 50: 42 75: 48 90: 51 99: 89 topic: 50: 49 75: 55 90: 58 99: 99 git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62197 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-02-04 14:22:28 +03:00
#ifdef MJIT_HEADER
#define THROW_EXCEPTION(exc) do { \
ec->errinfo = (VALUE)(exc); \
EC_JUMP_TAG(ec, ec->tag->state); \
} while (0)
#else
#if OPT_CALL_THREADED_CODE
#define THROW_EXCEPTION(exc) do { \
ec->errinfo = (VALUE)(exc); \
return 0; \
} while (0)
#else
#define THROW_EXCEPTION(exc) return (VALUE)(exc)
#endif
mjit_compile.c: merge initial JIT compiler which has been developed by Takashi Kokubun <takashikkbn@gmail> as YARV-MJIT. Many of its bugs are fixed by wanabe <s.wanabe@gmail.com>. This JIT compiler is designed to be a safe migration path to introduce JIT compiler to MRI. So this commit does not include any bytecode changes or dynamic instruction modifications, which are done in original MJIT. This commit even strips off some aggressive optimizations from YARV-MJIT, and thus it's slower than YARV-MJIT too. But it's still fairly faster than Ruby 2.5 in some benchmarks (attached below). Note that this JIT compiler passes `make test`, `make test-all`, `make test-spec` without JIT, and even with JIT. Not only it's perfectly safe with JIT disabled because it does not replace VM instructions unlike MJIT, but also with JIT enabled it stably runs Ruby applications including Rails applications. I'm expecting this version as just "initial" JIT compiler. I have many optimization ideas which are skipped for initial merging, and you may easily replace this JIT compiler with a faster one by just replacing mjit_compile.c. `mjit_compile` interface is designed for the purpose. common.mk: update dependencies for mjit_compile.c. internal.h: declare `rb_vm_insn_addr2insn` for MJIT. vm.c: exclude some definitions if `-DMJIT_HEADER` is provided to compiler. This avoids to include some functions which take a long time to compile, e.g. vm_exec_core. Some of the purpose is achieved in transform_mjit_header.rb (see `IGNORED_FUNCTIONS`) but others are manually resolved for now. Load mjit_helper.h for MJIT header. mjit_helper.h: New. This is a file used only by JIT-ed code. I'll refactor `mjit_call_cfunc` later. vm_eval.c: add some #ifdef switches to skip compiling some functions like Init_vm_eval. win32/mkexports.rb: export thread/ec functions, which are used by MJIT. include/ruby/defines.h: add MJIT_FUNC_EXPORTED macro alis to clarify that a function is exported only for MJIT. array.c: export a function used by MJIT. bignum.c: ditto. class.c: ditto. compile.c: ditto. error.c: ditto. gc.c: ditto. hash.c: ditto. iseq.c: ditto. numeric.c: ditto. object.c: ditto. proc.c: ditto. re.c: ditto. st.c: ditto. string.c: ditto. thread.c: ditto. variable.c: ditto. vm_backtrace.c: ditto. vm_insnhelper.c: ditto. vm_method.c: ditto. I would like to improve maintainability of function exports, but I believe this way is acceptable as initial merging if we clarify the new exports are for MJIT (so that we can use them as TODO list to fix) and add unit tests to detect unresolved symbols. I'll add unit tests of JIT compilations in succeeding commits. Author: Takashi Kokubun <takashikkbn@gmail.com> Contributor: wanabe <s.wanabe@gmail.com> Part of [Feature #14235] --- * Known issues * Code generated by gcc is faster than clang. The benchmark may be worse in macOS. Following benchmark result is provided by gcc w/ Linux. * Performance is decreased when Google Chrome is running * JIT can work on MinGW, but it doesn't improve performance at least in short running benchmark. * Currently it doesn't perform well with Rails. We'll try to fix this before release. --- * Benchmark reslts Benchmarked with: Intel 4.0GHz i7-4790K with 16GB memory under x86-64 Ubuntu 8 Cores - 2.0.0-p0: Ruby 2.0.0-p0 - r62186: Ruby trunk (early 2.6.0), before MJIT changes - JIT off: On this commit, but without `--jit` option - JIT on: On this commit, and with `--jit` option ** Optcarrot fps Benchmark: https://github.com/mame/optcarrot | |2.0.0-p0 |r62186 |JIT off |JIT on | |:--------|:--------|:--------|:--------|:--------| |fps |37.32 |51.46 |51.31 |58.88 | |vs 2.0.0 |1.00x |1.38x |1.37x |1.58x | ** MJIT benchmarks Benchmark: https://github.com/benchmark-driver/mjit-benchmarks (Original: https://github.com/vnmakarov/ruby/tree/rtl_mjit_branch/MJIT-benchmarks) | |2.0.0-p0 |r62186 |JIT off |JIT on | |:----------|:--------|:--------|:--------|:--------| |aread |1.00 |1.09 |1.07 |2.19 | |aref |1.00 |1.13 |1.11 |2.22 | |aset |1.00 |1.50 |1.45 |2.64 | |awrite |1.00 |1.17 |1.13 |2.20 | |call |1.00 |1.29 |1.26 |2.02 | |const2 |1.00 |1.10 |1.10 |2.19 | |const |1.00 |1.11 |1.10 |2.19 | |fannk |1.00 |1.04 |1.02 |1.00 | |fib |1.00 |1.32 |1.31 |1.84 | |ivread |1.00 |1.13 |1.12 |2.43 | |ivwrite |1.00 |1.23 |1.21 |2.40 | |mandelbrot |1.00 |1.13 |1.16 |1.28 | |meteor |1.00 |2.97 |2.92 |3.17 | |nbody |1.00 |1.17 |1.15 |1.49 | |nest-ntimes|1.00 |1.22 |1.20 |1.39 | |nest-while |1.00 |1.10 |1.10 |1.37 | |norm |1.00 |1.18 |1.16 |1.24 | |nsvb |1.00 |1.16 |1.16 |1.17 | |red-black |1.00 |1.02 |0.99 |1.12 | |sieve |1.00 |1.30 |1.28 |1.62 | |trees |1.00 |1.14 |1.13 |1.19 | |while |1.00 |1.12 |1.11 |2.41 | ** Discourse's script/bench.rb Benchmark: https://github.com/discourse/discourse/blob/v1.8.7/script/bench.rb NOTE: Rails performance was somehow a little degraded with JIT for now. We should fix this. (At least I know opt_aref is performing badly in JIT and I have an idea to fix it. Please wait for the fix.) *** JIT off Your Results: (note for timings- percentile is first, duration is second in millisecs) categories_admin: 50: 17 75: 18 90: 22 99: 29 home_admin: 50: 21 75: 21 90: 27 99: 40 topic_admin: 50: 17 75: 18 90: 22 99: 32 categories: 50: 35 75: 41 90: 43 99: 77 home: 50: 39 75: 46 90: 49 99: 95 topic: 50: 46 75: 52 90: 56 99: 101 *** JIT on Your Results: (note for timings- percentile is first, duration is second in millisecs) categories_admin: 50: 19 75: 21 90: 25 99: 33 home_admin: 50: 24 75: 26 90: 30 99: 35 topic_admin: 50: 19 75: 20 90: 25 99: 30 categories: 50: 40 75: 44 90: 48 99: 76 home: 50: 42 75: 48 90: 51 99: 89 topic: 50: 49 75: 55 90: 58 99: 99 git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62197 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2018-02-04 14:22:28 +03:00
#endif
#define SCREG(r) (reg_##r)
#define VM_DEBUG_STACKOVERFLOW 0
#if VM_DEBUG_STACKOVERFLOW
#define CHECK_VM_STACK_OVERFLOW_FOR_INSN(cfp, margin) \
WHEN_VM_STACK_OVERFLOWED(cfp, (cfp)->sp, margin) vm_stack_overflow_for_insn()
#else
#define CHECK_VM_STACK_OVERFLOW_FOR_INSN(cfp, margin)
#endif
#define INSN_LABEL2(insn, name) INSN_LABEL_ ## insn ## _ ## name
#define INSN_LABEL(x) INSN_LABEL2(NAME_OF_CURRENT_INSN, x)
#endif /* RUBY_VM_EXEC_H */