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

1 files changed, 16 insertions, 1 deletions

diff --git a/mjit_compile.c b/mjit_compile.c
index 1f92834853..5eafd72329 100644
--- a/mjit_compile.c
+++ b/mjit_compile.c
@@ -24,6 +24,9 @@
 struct compile_status {
     int success; /* has TRUE if compilation has had no issue */
     int *stack_size_for_pos; /* stack_size_for_pos[pos] has stack size for the position (otherwise -1) */
+    /* If TRUE, JIT-ed code will use local variables to store pushed values instead of
+       using VM's stack and moving stack pointer. */
+    int local_stack_p;
 };
 
 /* Storage to keep data which is consistent in each conditional branch.
@@ -172,7 +175,13 @@ compile_insns(FILE *f, const struct rb_iseq_constant_body *body, unsigned int st
 static void
 compile_cancel_handler(FILE *f, const struct rb_iseq_constant_body *body, struct compile_status *status)
 {
+    unsigned int i;
     fprintf(f, "\ncancel:\n");
+    if (status->local_stack_p) {
+        for (i = 0; i < body->stack_max; i++) {
+            fprintf(f, "    *((VALUE *)reg_cfp->bp + %d) = stack[%d];\n", i + 1, i);
+        }
+    }
     fprintf(f, "    return Qundef;\n");
 }
 
@@ -182,6 +191,7 @@ mjit_compile(FILE *f, const struct rb_iseq_constant_body *body, const char *func
 {
     struct compile_status status;
     status.success = TRUE;
+    status.local_stack_p = !body->catch_except_p;
     status.stack_size_for_pos = ALLOC_N(int, body->iseq_size);
     memset(status.stack_size_for_pos, NOT_COMPILED_STACK_SIZE, sizeof(int) * body->iseq_size);
 
@@ -195,7 +205,12 @@ mjit_compile(FILE *f, const struct rb_iseq_constant_body *body, const char *func
     fprintf(f, "__declspec(dllexport)\n");
 #endif
     fprintf(f, "VALUE\n%s(rb_execution_context_t *ec, rb_control_frame_t *reg_cfp)\n{\n", funcname);
-    fprintf(f, "    VALUE *stack = reg_cfp->sp;\n");
+    if (status.local_stack_p) {
+        fprintf(f, "    VALUE stack[%d];\n", body->stack_max);
+    }
+    else {
+        fprintf(f, "    VALUE *stack = reg_cfp->sp;\n");
+    }
     fprintf(f, "    static const VALUE *const original_body_iseq = (VALUE *)0x%"PRIxVALUE";\n",
             (VALUE)body->iseq_encoded);