ZJIT: Profile opt_ltlt and opt_aset (#14834)

These bring `send_without_block_no_profiles` numbers down dramatically.

On lobsters:
  Before: send_without_block_no_profiles: 3,466,375
  After:  send_without_block_no_profiles: 1,293,375

all stats before:

```
***ZJIT: Printing ZJIT statistics on exit***
Top-20 not inlined C methods (70.4% of total 14,174,061):
                                    Hash#[]: 4,519,771 (31.9%)
                               Kernel#is_a?: 1,030,757 ( 7.3%)
                              Regexp#match?:   399,885 ( 2.8%)
                              String#empty?:   353,775 ( 2.5%)
                                  Hash#key?:   349,125 ( 2.5%)
                                   Hash#[]=:   344,348 ( 2.4%)
                         String#start_with?:   334,961 ( 2.4%)
                         Kernel#respond_to?:   316,527 ( 2.2%)
                 ObjectSpace::WeakKeyMap#[]:   238,978 ( 1.7%)
                              TrueClass#===:   235,770 ( 1.7%)
                             FalseClass#===:   231,143 ( 1.6%)
                             Array#include?:   211,383 ( 1.5%)
                                 Hash#fetch:   204,702 ( 1.4%)
                        Kernel#block_given?:   181,793 ( 1.3%)
         ActiveSupport::OrderedOptions#_get:   181,272 ( 1.3%)
                                 Kernel#dup:   179,341 ( 1.3%)
                             BasicObject#!=:   175,996 ( 1.2%)
                                  Class#new:   168,079 ( 1.2%)
                            Kernel#kind_of?:   165,600 ( 1.2%)
                                  String#==:   157,734 ( 1.1%)
Top-20 not annotated C methods (71.1% of total 14,336,035):
                                    Hash#[]: 4,519,781 (31.5%)
                               Kernel#is_a?: 1,212,647 ( 8.5%)
                              Regexp#match?:   399,885 ( 2.8%)
                              String#empty?:   361,013 ( 2.5%)
                                  Hash#key?:   349,125 ( 2.4%)
                                   Hash#[]=:   344,348 ( 2.4%)
                         String#start_with?:   334,961 ( 2.3%)
                         Kernel#respond_to?:   316,527 ( 2.2%)
                 ObjectSpace::WeakKeyMap#[]:   238,978 ( 1.7%)
                              TrueClass#===:   235,770 ( 1.6%)
                             FalseClass#===:   231,143 ( 1.6%)
                             Array#include?:   211,383 ( 1.5%)
                                 Hash#fetch:   204,702 ( 1.4%)
                        Kernel#block_given?:   191,662 ( 1.3%)
         ActiveSupport::OrderedOptions#_get:   181,272 ( 1.3%)
                                 Kernel#dup:   179,348 ( 1.3%)
                             BasicObject#!=:   176,180 ( 1.2%)
                                  Class#new:   168,079 ( 1.2%)
                            Kernel#kind_of?:   165,634 ( 1.2%)
                                  String#==:   163,666 ( 1.1%)
Top-2 not optimized method types for send (100.0% of total 72,318):
  cfunc: 48,055 (66.4%)
   iseq: 24,263 (33.6%)
Top-6 not optimized method types for send_without_block (100.0% of total 4,536,895):
       iseq: 2,281,897 (50.3%)
    bmethod:   985,679 (21.7%)
  optimized:   952,914 (21.0%)
      alias:   310,745 ( 6.8%)
       null:     5,106 ( 0.1%)
      cfunc:       554 ( 0.0%)
Top-13 not optimized instructions (100.0% of total 4,293,123):
             invokesuper: 2,373,396 (55.3%)
             invokeblock:   811,891 (18.9%)
             sendforward:   505,449 (11.8%)
                  opt_eq:   451,754 (10.5%)
                opt_plus:    74,403 ( 1.7%)
               opt_minus:    36,227 ( 0.8%)
  opt_send_without_block:    21,792 ( 0.5%)
                 opt_neq:     7,231 ( 0.2%)
                opt_mult:     6,752 ( 0.2%)
                  opt_or:     3,753 ( 0.1%)
                  opt_lt:       348 ( 0.0%)
                  opt_ge:        91 ( 0.0%)
                  opt_gt:        36 ( 0.0%)
Top-9 send fallback reasons (100.0% of total 27,795,022):
                send_without_block_polymorphic: 9,505,835 (34.2%)
                              send_no_profiles: 5,894,763 (21.2%)
  send_without_block_not_optimized_method_type: 4,536,895 (16.3%)
                     not_optimized_instruction: 4,293,123 (15.4%)
                send_without_block_no_profiles: 3,466,407 (12.5%)
                send_not_optimized_method_type:    72,318 ( 0.3%)
       send_without_block_cfunc_array_variadic:    15,134 ( 0.1%)
                      obj_to_string_not_string:     9,918 ( 0.0%)
       send_without_block_direct_too_many_args:       629 ( 0.0%)
Top-9 unhandled YARV insns (100.0% of total 690,482):
         expandarray: 328,490 (47.6%)
        checkkeyword: 190,694 (27.6%)
    getclassvariable:  59,901 ( 8.7%)
  invokesuperforward:  49,503 ( 7.2%)
       getblockparam:  48,651 ( 7.0%)
   opt_duparray_send:  11,978 ( 1.7%)
         getconstant:     952 ( 0.1%)
          checkmatch:     290 ( 0.0%)
                once:      23 ( 0.0%)
Top-3 compile error reasons (100.0% of total 3,752,391):
  register_spill_on_alloc: 3,457,680 (92.1%)
  register_spill_on_ccall:   176,348 ( 4.7%)
        exception_handler:   118,363 ( 3.2%)
Top-14 side exit reasons (100.0% of total 10,852,021):
                        compile_error: 3,752,391 (34.6%)
                   guard_type_failure: 2,630,877 (24.2%)
                  guard_shape_failure: 1,917,208 (17.7%)
                  unhandled_yarv_insn:   690,482 ( 6.4%)
  block_param_proxy_not_iseq_or_ifunc:   535,784 ( 4.9%)
                      unhandled_kwarg:   421,989 ( 3.9%)
                           patchpoint:   369,799 ( 3.4%)
                unknown_newarray_send:   314,786 ( 2.9%)
                      unhandled_splat:   122,062 ( 1.1%)
                   unhandled_hir_insn:    76,394 ( 0.7%)
           block_param_proxy_modified:    19,193 ( 0.2%)
               obj_to_string_fallback:       566 ( 0.0%)
                            interrupt:       468 ( 0.0%)
               guard_type_not_failure:        22 ( 0.0%)
                             send_count: 66,989,407
                     dynamic_send_count: 27,795,022 (41.5%)
                   optimized_send_count: 39,194,385 (58.5%)
              iseq_optimized_send_count: 18,060,194 (27.0%)
      inline_cfunc_optimized_send_count:  6,960,130 (10.4%)
non_variadic_cfunc_optimized_send_count: 11,523,682 (17.2%)
    variadic_cfunc_optimized_send_count:  2,650,379 ( 4.0%)
dynamic_getivar_count:                        7,365,982
dynamic_setivar_count:                        7,245,929
compiled_iseq_count:                              4,795
failed_iseq_count:                                  449
compile_time:                                     846ms
profile_time:                                      12ms
gc_time:                                            9ms
invalidation_time:                                 61ms
vm_write_pc_count:                           64,326,442
vm_write_sp_count:                           62,982,524
vm_write_locals_count:                       62,982,524
vm_write_stack_count:                        62,982,524
vm_write_to_parent_iseq_local_count:            292,448
vm_read_from_parent_iseq_local_count:         6,471,353
code_region_bytes:                           22,708,224
side_exit_count:                             10,852,021
total_insn_count:                           517,550,288
vm_insn_count:                              162,946,459
zjit_insn_count:                            354,603,829
ratio_in_zjit:                                    68.5%
```

all stats after:

```
***ZJIT: Printing ZJIT statistics on exit***
Top-20 not inlined C methods (71.1% of total 15,575,343):
                                    Hash#[]: 4,519,778 (29.0%)
                               Kernel#is_a?: 1,030,758 ( 6.6%)
                                  String#<<:   851,931 ( 5.5%)
                                   Hash#[]=:   742,938 ( 4.8%)
                              Regexp#match?:   399,886 ( 2.6%)
                              String#empty?:   353,775 ( 2.3%)
                                  Hash#key?:   349,127 ( 2.2%)
                         String#start_with?:   334,961 ( 2.2%)
                         Kernel#respond_to?:   316,529 ( 2.0%)
                 ObjectSpace::WeakKeyMap#[]:   238,978 ( 1.5%)
                              TrueClass#===:   235,771 ( 1.5%)
                             FalseClass#===:   231,144 ( 1.5%)
                             Array#include?:   211,380 ( 1.4%)
                                 Hash#fetch:   204,701 ( 1.3%)
                        Kernel#block_given?:   181,792 ( 1.2%)
         ActiveSupport::OrderedOptions#_get:   181,272 ( 1.2%)
                                 Kernel#dup:   179,341 ( 1.2%)
                             BasicObject#!=:   175,997 ( 1.1%)
                                  Class#new:   168,079 ( 1.1%)
                            Kernel#kind_of?:   165,600 ( 1.1%)
Top-20 not annotated C methods (71.6% of total 15,737,486):
                                    Hash#[]: 4,519,788 (28.7%)
                               Kernel#is_a?: 1,212,649 ( 7.7%)
                                  String#<<:   851,931 ( 5.4%)
                                   Hash#[]=:   743,117 ( 4.7%)
                              Regexp#match?:   399,886 ( 2.5%)
                              String#empty?:   361,013 ( 2.3%)
                                  Hash#key?:   349,127 ( 2.2%)
                         String#start_with?:   334,961 ( 2.1%)
                         Kernel#respond_to?:   316,529 ( 2.0%)
                 ObjectSpace::WeakKeyMap#[]:   238,978 ( 1.5%)
                              TrueClass#===:   235,771 ( 1.5%)
                             FalseClass#===:   231,144 ( 1.5%)
                             Array#include?:   211,380 ( 1.3%)
                                 Hash#fetch:   204,701 ( 1.3%)
                        Kernel#block_given?:   191,661 ( 1.2%)
         ActiveSupport::OrderedOptions#_get:   181,272 ( 1.2%)
                                 Kernel#dup:   179,348 ( 1.1%)
                             BasicObject#!=:   176,181 ( 1.1%)
                                  Class#new:   168,079 ( 1.1%)
                            Kernel#kind_of?:   165,634 ( 1.1%)
Top-2 not optimized method types for send (100.0% of total 72,318):
  cfunc: 48,055 (66.4%)
   iseq: 24,263 (33.6%)
Top-6 not optimized method types for send_without_block (100.0% of total 4,523,650):
       iseq: 2,271,911 (50.2%)
    bmethod:   985,636 (21.8%)
  optimized:   949,696 (21.0%)
      alias:   310,747 ( 6.9%)
       null:     5,106 ( 0.1%)
      cfunc:       554 ( 0.0%)
Top-13 not optimized instructions (100.0% of total 4,293,126):
             invokesuper: 2,373,395 (55.3%)
             invokeblock:   811,894 (18.9%)
             sendforward:   505,449 (11.8%)
                  opt_eq:   451,754 (10.5%)
                opt_plus:    74,403 ( 1.7%)
               opt_minus:    36,228 ( 0.8%)
  opt_send_without_block:    21,792 ( 0.5%)
                 opt_neq:     7,231 ( 0.2%)
                opt_mult:     6,752 ( 0.2%)
                  opt_or:     3,753 ( 0.1%)
                  opt_lt:       348 ( 0.0%)
                  opt_ge:        91 ( 0.0%)
                  opt_gt:        36 ( 0.0%)
Top-9 send fallback reasons (100.0% of total 25,824,512):
                send_without_block_polymorphic: 9,721,725 (37.6%)
                              send_no_profiles: 5,894,761 (22.8%)
  send_without_block_not_optimized_method_type: 4,523,650 (17.5%)
                     not_optimized_instruction: 4,293,126 (16.6%)
                send_without_block_no_profiles: 1,293,404 ( 5.0%)
                send_not_optimized_method_type:    72,318 ( 0.3%)
       send_without_block_cfunc_array_variadic:    15,134 ( 0.1%)
                      obj_to_string_not_string:     9,765 ( 0.0%)
       send_without_block_direct_too_many_args:       629 ( 0.0%)
Top-9 unhandled YARV insns (100.0% of total 690,482):
         expandarray: 328,490 (47.6%)
        checkkeyword: 190,694 (27.6%)
    getclassvariable:  59,901 ( 8.7%)
  invokesuperforward:  49,503 ( 7.2%)
       getblockparam:  48,651 ( 7.0%)
   opt_duparray_send:  11,978 ( 1.7%)
         getconstant:     952 ( 0.1%)
          checkmatch:     290 ( 0.0%)
                once:      23 ( 0.0%)
Top-3 compile error reasons (100.0% of total 3,752,504):
  register_spill_on_alloc: 3,457,793 (92.1%)
  register_spill_on_ccall:   176,348 ( 4.7%)
        exception_handler:   118,363 ( 3.2%)
Top-14 side exit reasons (100.0% of total 10,860,754):
                        compile_error: 3,752,504 (34.6%)
                   guard_type_failure: 2,638,901 (24.3%)
                  guard_shape_failure: 1,917,198 (17.7%)
                  unhandled_yarv_insn:   690,482 ( 6.4%)
  block_param_proxy_not_iseq_or_ifunc:   535,785 ( 4.9%)
                      unhandled_kwarg:   421,947 ( 3.9%)
                           patchpoint:   370,447 ( 3.4%)
                unknown_newarray_send:   314,786 ( 2.9%)
                      unhandled_splat:   122,065 ( 1.1%)
                   unhandled_hir_insn:    76,395 ( 0.7%)
           block_param_proxy_modified:    19,193 ( 0.2%)
               obj_to_string_fallback:       566 ( 0.0%)
                            interrupt:       463 ( 0.0%)
               guard_type_not_failure:        22 ( 0.0%)
                             send_count: 66,945,926
                     dynamic_send_count: 25,824,512 (38.6%)
                   optimized_send_count: 41,121,414 (61.4%)
              iseq_optimized_send_count: 18,587,430 (27.8%)
      inline_cfunc_optimized_send_count:  6,958,641 (10.4%)
non_variadic_cfunc_optimized_send_count: 12,911,166 (19.3%)
    variadic_cfunc_optimized_send_count:  2,664,177 ( 4.0%)
dynamic_getivar_count:                        7,365,985
dynamic_setivar_count:                        7,245,942
compiled_iseq_count:                              4,794
failed_iseq_count:                                  450
compile_time:                                     852ms
profile_time:                                      13ms
gc_time:                                           11ms
invalidation_time:                                 63ms
vm_write_pc_count:                           64,284,194
vm_write_sp_count:                           62,940,427
vm_write_locals_count:                       62,940,427
vm_write_stack_count:                        62,940,427
vm_write_to_parent_iseq_local_count:            292,447
vm_read_from_parent_iseq_local_count:         6,470,931
code_region_bytes:                           23,019,520
side_exit_count:                             10,860,754
total_insn_count:                           517,576,267
vm_insn_count:                              163,188,187
zjit_insn_count:                            354,388,080
ratio_in_zjit:                                    68.5%
```

4 files changed, 71 insertions, 6 deletions

diff --git a/insns.def b/insns.def
index eef0d3f5dc..b895bffe22 100644
--- a/insns.def
+++ b/insns.def
@@ -1470,6 +1470,7 @@ opt_ltlt
  * string.  Then what happens if that codepoint does not exist in the
  * string's encoding?  Of course an exception.  That's not a leaf. */
 // attr bool leaf = false; /* has "invalid codepoint" exception */
+// attr bool zjit_profile = true;
 {
     val = vm_opt_ltlt(recv, obj);
 
@@ -1537,6 +1538,7 @@ opt_aset
 /* This is another story than opt_aref.  When vm_opt_aset() resorts
  * to rb_hash_aset(), which should call #hash for `obj`. */
 // attr bool leaf = false; /* has rb_funcall() */ /* calls #hash */
+// attr bool zjit_profile = true;
 {
     val = vm_opt_aset(recv, obj, set);
 
diff --git a/zjit/src/cruby_bindings.inc.rs b/zjit/src/cruby_bindings.inc.rs
index ea1bf68acc..6e3ae05194 100644
--- a/zjit/src/cruby_bindings.inc.rs
+++ b/zjit/src/cruby_bindings.inc.rs
@@ -694,12 +694,14 @@ pub const YARVINSN_zjit_opt_lt: ruby_vminsn_type = 229;
 pub const YARVINSN_zjit_opt_le: ruby_vminsn_type = 230;
 pub const YARVINSN_zjit_opt_gt: ruby_vminsn_type = 231;
 pub const YARVINSN_zjit_opt_ge: ruby_vminsn_type = 232;
-pub const YARVINSN_zjit_opt_and: ruby_vminsn_type = 233;
-pub const YARVINSN_zjit_opt_or: ruby_vminsn_type = 234;
-pub const YARVINSN_zjit_opt_aref: ruby_vminsn_type = 235;
-pub const YARVINSN_zjit_opt_empty_p: ruby_vminsn_type = 236;
-pub const YARVINSN_zjit_opt_not: ruby_vminsn_type = 237;
-pub const VM_INSTRUCTION_SIZE: ruby_vminsn_type = 238;
+pub const YARVINSN_zjit_opt_ltlt: ruby_vminsn_type = 233;
+pub const YARVINSN_zjit_opt_and: ruby_vminsn_type = 234;
+pub const YARVINSN_zjit_opt_or: ruby_vminsn_type = 235;
+pub const YARVINSN_zjit_opt_aref: ruby_vminsn_type = 236;
+pub const YARVINSN_zjit_opt_aset: ruby_vminsn_type = 237;
+pub const YARVINSN_zjit_opt_empty_p: ruby_vminsn_type = 238;
+pub const YARVINSN_zjit_opt_not: ruby_vminsn_type = 239;
+pub const VM_INSTRUCTION_SIZE: ruby_vminsn_type = 240;
 pub type ruby_vminsn_type = u32;
 pub type rb_iseq_callback = ::std::option::Option<
     unsafe extern "C" fn(arg1: *const rb_iseq_t, arg2: *mut ::std::os::raw::c_void),
diff --git a/zjit/src/hir.rs b/zjit/src/hir.rs
index e32c15702e..022451e8ab 100644
--- a/zjit/src/hir.rs
+++ b/zjit/src/hir.rs
@@ -12817,4 +12817,63 @@ mod opt_tests {
           Return v25
         ");
     }
+
+    #[test]
+    fn test_optimize_array_aset() {
+        eval("
+            def test(arr)
+              arr[1] = 10
+            end
+            test([])
+        ");
+        assert_snapshot!(hir_string("test"), @r"
+        fn test@<compiled>:3:
+        bb0():
+          EntryPoint interpreter
+          v1:BasicObject = LoadSelf
+          v2:BasicObject = GetLocal l0, SP@4
+          Jump bb2(v1, v2)
+        bb1(v5:BasicObject, v6:BasicObject):
+          EntryPoint JIT(0)
+          Jump bb2(v5, v6)
+        bb2(v8:BasicObject, v9:BasicObject):
+          v14:Fixnum[1] = Const Value(1)
+          v15:Fixnum[10] = Const Value(10)
+          PatchPoint MethodRedefined(Array@0x1000, []=@0x1008, cme:0x1010)
+          PatchPoint NoSingletonClass(Array@0x1000)
+          v28:ArrayExact = GuardType v9, ArrayExact
+          v29:BasicObject = CCallVariadic []=@0x1038, v28, v14, v15
+          CheckInterrupts
+          Return v15
+        ");
+    }
+
+    #[test]
+    fn test_optimize_array_ltlt() {
+        eval("
+            def test(arr)
+              arr << 1
+            end
+            test([])
+        ");
+        assert_snapshot!(hir_string("test"), @r"
+        fn test@<compiled>:3:
+        bb0():
+          EntryPoint interpreter
+          v1:BasicObject = LoadSelf
+          v2:BasicObject = GetLocal l0, SP@4
+          Jump bb2(v1, v2)
+        bb1(v5:BasicObject, v6:BasicObject):
+          EntryPoint JIT(0)
+          Jump bb2(v5, v6)
+        bb2(v8:BasicObject, v9:BasicObject):
+          v13:Fixnum[1] = Const Value(1)
+          PatchPoint MethodRedefined(Array@0x1000, <<@0x1008, cme:0x1010)
+          PatchPoint NoSingletonClass(Array@0x1000)
+          v26:ArrayExact = GuardType v9, ArrayExact
+          v27:BasicObject = CCallWithFrame <<@0x1038, v26, v13
+          CheckInterrupts
+          Return v27
+        ");
+    }
 }
diff --git a/zjit/src/profile.rs b/zjit/src/profile.rs
index 67f2fdc740..c2c35f687b 100644
--- a/zjit/src/profile.rs
+++ b/zjit/src/profile.rs
@@ -74,6 +74,8 @@ fn profile_insn(bare_opcode: ruby_vminsn_type, ec: EcPtr) {
         YARVINSN_opt_or    => profile_operands(profiler, profile, 2),
         YARVINSN_opt_empty_p => profile_operands(profiler, profile, 1),
         YARVINSN_opt_aref  => profile_operands(profiler, profile, 2),
+        YARVINSN_opt_ltlt  => profile_operands(profiler, profile, 2),
+        YARVINSN_opt_aset  => profile_operands(profiler, profile, 3),
         YARVINSN_opt_not   => profile_operands(profiler, profile, 1),
         YARVINSN_getinstancevariable => profile_self(profiler, profile),
         YARVINSN_objtostring   => profile_operands(profiler, profile, 1),