Mercurial
annotate third_party/luajit/src/lj_opt_narrow.c @ 194:fb28063dc490 hg-web
Adding few more images.
| author | MrJuneJune <me@mrjunejune.com> |
|---|---|
| date | Sun, 25 Jan 2026 20:19:42 -0800 |
| parents | 94705b5986b3 |
| children |
| rev | line source |
|---|---|
|
178
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
1 /* |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
2 ** NARROW: Narrowing of numbers to integers (double to int32_t). |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
3 ** STRIPOV: Stripping of overflow checks. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
4 ** Copyright (C) 2005-2023 Mike Pall. See Copyright Notice in luajit.h |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
5 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
6 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
7 #define lj_opt_narrow_c |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
8 #define LUA_CORE |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
9 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
10 #include "lj_obj.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
11 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
12 #if LJ_HASJIT |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
13 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
14 #include "lj_bc.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
15 #include "lj_ir.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
16 #include "lj_jit.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
17 #include "lj_iropt.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
18 #include "lj_trace.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
19 #include "lj_vm.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
20 #include "lj_strscan.h" |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
21 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
22 /* Rationale for narrowing optimizations: |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
23 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
24 ** Lua has only a single number type and this is a FP double by default. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
25 ** Narrowing doubles to integers does not pay off for the interpreter on a |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
26 ** current-generation x86/x64 machine. Most FP operations need the same |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
27 ** amount of execution resources as their integer counterparts, except |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
28 ** with slightly longer latencies. Longer latencies are a non-issue for |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
29 ** the interpreter, since they are usually hidden by other overhead. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
30 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
31 ** The total CPU execution bandwidth is the sum of the bandwidth of the FP |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
32 ** and the integer units, because they execute in parallel. The FP units |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
33 ** have an equal or higher bandwidth than the integer units. Not using |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
34 ** them means losing execution bandwidth. Moving work away from them to |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
35 ** the already quite busy integer units is a losing proposition. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
36 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
37 ** The situation for JIT-compiled code is a bit different: the higher code |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
38 ** density makes the extra latencies much more visible. Tight loops expose |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
39 ** the latencies for updating the induction variables. Array indexing |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
40 ** requires narrowing conversions with high latencies and additional |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
41 ** guards (to check that the index is really an integer). And many common |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
42 ** optimizations only work on integers. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
43 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
44 ** One solution would be speculative, eager narrowing of all number loads. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
45 ** This causes many problems, like losing -0 or the need to resolve type |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
46 ** mismatches between traces. It also effectively forces the integer type |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
47 ** to have overflow-checking semantics. This impedes many basic |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
48 ** optimizations and requires adding overflow checks to all integer |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
49 ** arithmetic operations (whereas FP arithmetics can do without). |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
50 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
51 ** Always replacing an FP op with an integer op plus an overflow check is |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
52 ** counter-productive on a current-generation super-scalar CPU. Although |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
53 ** the overflow check branches are highly predictable, they will clog the |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
54 ** execution port for the branch unit and tie up reorder buffers. This is |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
55 ** turning a pure data-flow dependency into a different data-flow |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
56 ** dependency (with slightly lower latency) *plus* a control dependency. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
57 ** In general, you don't want to do this since latencies due to data-flow |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
58 ** dependencies can be well hidden by out-of-order execution. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
59 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
60 ** A better solution is to keep all numbers as FP values and only narrow |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
61 ** when it's beneficial to do so. LuaJIT uses predictive narrowing for |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
62 ** induction variables and demand-driven narrowing for index expressions, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
63 ** integer arguments and bit operations. Additionally it can eliminate or |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
64 ** hoist most of the resulting overflow checks. Regular arithmetic |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
65 ** computations are never narrowed to integers. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
66 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
67 ** The integer type in the IR has convenient wrap-around semantics and |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
68 ** ignores overflow. Extra operations have been added for |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
69 ** overflow-checking arithmetic (ADDOV/SUBOV) instead of an extra type. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
70 ** Apart from reducing overall complexity of the compiler, this also |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
71 ** nicely solves the problem where you want to apply algebraic |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
72 ** simplifications to ADD, but not to ADDOV. And the x86/x64 assembler can |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
73 ** use lea instead of an add for integer ADD, but not for ADDOV (lea does |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
74 ** not affect the flags, but it helps to avoid register moves). |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
75 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
76 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
77 ** All of the above has to be reconsidered for architectures with slow FP |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
78 ** operations or without a hardware FPU. The dual-number mode of LuaJIT |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
79 ** addresses this issue. Arithmetic operations are performed on integers |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
80 ** as far as possible and overflow checks are added as needed. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
81 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
82 ** This implies that narrowing for integer arguments and bit operations |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
83 ** should also strip overflow checks, e.g. replace ADDOV with ADD. The |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
84 ** original overflow guards are weak and can be eliminated by DCE, if |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
85 ** there's no other use. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
86 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
87 ** A slight twist is that it's usually beneficial to use overflow-checked |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
88 ** integer arithmetics if all inputs are already integers. This is the only |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
89 ** change that affects the single-number mode, too. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
90 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
91 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
92 /* Some local macros to save typing. Undef'd at the end. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
93 #define IR(ref) (&J->cur.ir[(ref)]) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
94 #define fins (&J->fold.ins) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
95 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
96 /* Pass IR on to next optimization in chain (FOLD). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
97 #define emitir(ot, a, b) (lj_ir_set(J, (ot), (a), (b)), lj_opt_fold(J)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
98 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
99 #define emitir_raw(ot, a, b) (lj_ir_set(J, (ot), (a), (b)), lj_ir_emit(J)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
100 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
101 /* -- Elimination of narrowing type conversions --------------------------- */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
102 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
103 /* Narrowing of index expressions and bit operations is demand-driven. The |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
104 ** trace recorder emits a narrowing type conversion (CONV.int.num or TOBIT) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
105 ** in all of these cases (e.g. array indexing or string indexing). FOLD |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
106 ** already takes care of eliminating simple redundant conversions like |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
107 ** CONV.int.num(CONV.num.int(x)) ==> x. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
108 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
109 ** But the surrounding code is FP-heavy and arithmetic operations are |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
110 ** performed on FP numbers (for the single-number mode). Consider a common |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
111 ** example such as 'x=t[i+1]', with 'i' already an integer (due to induction |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
112 ** variable narrowing). The index expression would be recorded as |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
113 ** CONV.int.num(ADD(CONV.num.int(i), 1)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
114 ** which is clearly suboptimal. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
115 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
116 ** One can do better by recursively backpropagating the narrowing type |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
117 ** conversion across FP arithmetic operations. This turns FP ops into |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
118 ** their corresponding integer counterparts. Depending on the semantics of |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
119 ** the conversion they also need to check for overflow. Currently only ADD |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
120 ** and SUB are supported. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
121 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
122 ** The above example can be rewritten as |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
123 ** ADDOV(CONV.int.num(CONV.num.int(i)), 1) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
124 ** and then into ADDOV(i, 1) after folding of the conversions. The original |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
125 ** FP ops remain in the IR and are eliminated by DCE since all references to |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
126 ** them are gone. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
127 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
128 ** [In dual-number mode the trace recorder already emits ADDOV etc., but |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
129 ** this can be further reduced. See below.] |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
130 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
131 ** Special care has to be taken to avoid narrowing across an operation |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
132 ** which is potentially operating on non-integral operands. One obvious |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
133 ** case is when an expression contains a non-integral constant, but ends |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
134 ** up as an integer index at runtime (like t[x+1.5] with x=0.5). |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
135 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
136 ** Operations with two non-constant operands illustrate a similar problem |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
137 ** (like t[a+b] with a=1.5 and b=2.5). Backpropagation has to stop there, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
138 ** unless it can be proven that either operand is integral (e.g. by CSEing |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
139 ** a previous conversion). As a not-so-obvious corollary this logic also |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
140 ** applies for a whole expression tree (e.g. t[(a+1)+(b+1)]). |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
141 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
142 ** Correctness of the transformation is guaranteed by avoiding to expand |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
143 ** the tree by adding more conversions than the one we would need to emit |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
144 ** if not backpropagating. TOBIT employs a more optimistic rule, because |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
145 ** the conversion has special semantics, designed to make the life of the |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
146 ** compiler writer easier. ;-) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
147 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
148 ** Using on-the-fly backpropagation of an expression tree doesn't work |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
149 ** because it's unknown whether the transform is correct until the end. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
150 ** This either requires IR rollback and cache invalidation for every |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
151 ** subtree or a two-pass algorithm. The former didn't work out too well, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
152 ** so the code now combines a recursive collector with a stack-based |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
153 ** emitter. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
154 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
155 ** [A recursive backpropagation algorithm with backtracking, employing |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
156 ** skip-list lookup and round-robin caching, emitting stack operations |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
157 ** on-the-fly for a stack-based interpreter -- and all of that in a meager |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
158 ** kilobyte? Yep, compilers are a great treasure chest. Throw away your |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
159 ** textbooks and read the codebase of a compiler today!] |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
160 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
161 ** There's another optimization opportunity for array indexing: it's |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
162 ** always accompanied by an array bounds-check. The outermost overflow |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
163 ** check may be delegated to the ABC operation. This works because ABC is |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
164 ** an unsigned comparison and wrap-around due to overflow creates negative |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
165 ** numbers. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
166 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
167 ** But this optimization is only valid for constants that cannot overflow |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
168 ** an int32_t into the range of valid array indexes [0..2^27+1). A check |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
169 ** for +-2^30 is safe since -2^31 - 2^30 wraps to 2^30 and 2^31-1 + 2^30 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
170 ** wraps to -2^30-1. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
171 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
172 ** It's also good enough in practice, since e.g. t[i+1] or t[i-10] are |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
173 ** quite common. So the above example finally ends up as ADD(i, 1)! |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
174 ** |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
175 ** Later on, the assembler is able to fuse the whole array reference and |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
176 ** the ADD into the memory operands of loads and other instructions. This |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
177 ** is why LuaJIT is able to generate very pretty (and fast) machine code |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
178 ** for array indexing. And that, my dear, concludes another story about |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
179 ** one of the hidden secrets of LuaJIT ... |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
180 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
181 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
182 /* Maximum backpropagation depth and maximum stack size. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
183 #define NARROW_MAX_BACKPROP 100 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
184 #define NARROW_MAX_STACK 256 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
185 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
186 /* The stack machine has a 32 bit instruction format: [IROpT | IRRef1] |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
187 ** The lower 16 bits hold a reference (or 0). The upper 16 bits hold |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
188 ** the IR opcode + type or one of the following special opcodes: |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
189 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
190 enum { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
191 NARROW_REF, /* Push ref. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
192 NARROW_CONV, /* Push conversion of ref. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
193 NARROW_SEXT, /* Push sign-extension of ref. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
194 NARROW_INT /* Push KINT ref. The next code holds an int32_t. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
195 }; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
196 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
197 typedef uint32_t NarrowIns; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
198 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
199 #define NARROWINS(op, ref) (((op) << 16) + (ref)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
200 #define narrow_op(ins) ((IROpT)((ins) >> 16)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
201 #define narrow_ref(ins) ((IRRef1)(ins)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
202 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
203 /* Context used for narrowing of type conversions. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
204 typedef struct NarrowConv { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
205 jit_State *J; /* JIT compiler state. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
206 NarrowIns *sp; /* Current stack pointer. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
207 NarrowIns *maxsp; /* Maximum stack pointer minus redzone. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
208 IRRef mode; /* Conversion mode (IRCONV_*). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
209 IRType t; /* Destination type: IRT_INT or IRT_I64. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
210 NarrowIns stack[NARROW_MAX_STACK]; /* Stack holding stack-machine code. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
211 } NarrowConv; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
212 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
213 /* Lookup a reference in the backpropagation cache. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
214 static BPropEntry *narrow_bpc_get(jit_State *J, IRRef1 key, IRRef mode) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
215 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
216 ptrdiff_t i; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
217 for (i = 0; i < BPROP_SLOTS; i++) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
218 BPropEntry *bp = &J->bpropcache[i]; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
219 /* Stronger checks are ok, too. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
220 if (bp->key == key && bp->mode >= mode && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
221 ((bp->mode ^ mode) & IRCONV_MODEMASK) == 0) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
222 return bp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
223 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
224 return NULL; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
225 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
226 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
227 /* Add an entry to the backpropagation cache. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
228 static void narrow_bpc_set(jit_State *J, IRRef1 key, IRRef1 val, IRRef mode) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
229 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
230 uint32_t slot = J->bpropslot; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
231 BPropEntry *bp = &J->bpropcache[slot]; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
232 J->bpropslot = (slot + 1) & (BPROP_SLOTS-1); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
233 bp->key = key; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
234 bp->val = val; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
235 bp->mode = mode; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
236 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
237 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
238 /* Backpropagate overflow stripping. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
239 static void narrow_stripov_backprop(NarrowConv *nc, IRRef ref, int depth) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
240 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
241 jit_State *J = nc->J; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
242 IRIns *ir = IR(ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
243 if (ir->o == IR_ADDOV || ir->o == IR_SUBOV || |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
244 (ir->o == IR_MULOV && (nc->mode & IRCONV_CONVMASK) == IRCONV_ANY)) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
245 BPropEntry *bp = narrow_bpc_get(nc->J, ref, IRCONV_TOBIT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
246 if (bp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
247 ref = bp->val; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
248 } else if (++depth < NARROW_MAX_BACKPROP && nc->sp < nc->maxsp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
249 NarrowIns *savesp = nc->sp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
250 narrow_stripov_backprop(nc, ir->op1, depth); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
251 if (nc->sp < nc->maxsp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
252 narrow_stripov_backprop(nc, ir->op2, depth); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
253 if (nc->sp < nc->maxsp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
254 *nc->sp++ = NARROWINS(IRT(ir->o - IR_ADDOV + IR_ADD, IRT_INT), ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
255 return; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
256 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
257 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
258 nc->sp = savesp; /* Path too deep, need to backtrack. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
259 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
260 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
261 *nc->sp++ = NARROWINS(NARROW_REF, ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
262 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
263 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
264 /* Backpropagate narrowing conversion. Return number of needed conversions. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
265 static int narrow_conv_backprop(NarrowConv *nc, IRRef ref, int depth) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
266 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
267 jit_State *J = nc->J; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
268 IRIns *ir = IR(ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
269 IRRef cref; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
270 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
271 if (nc->sp >= nc->maxsp) return 10; /* Path too deep. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
272 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
273 /* Check the easy cases first. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
274 if (ir->o == IR_CONV && (ir->op2 & IRCONV_SRCMASK) == IRT_INT) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
275 if ((nc->mode & IRCONV_CONVMASK) <= IRCONV_ANY) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
276 narrow_stripov_backprop(nc, ir->op1, depth+1); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
277 else |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
278 *nc->sp++ = NARROWINS(NARROW_REF, ir->op1); /* Undo conversion. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
279 if (nc->t == IRT_I64) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
280 *nc->sp++ = NARROWINS(NARROW_SEXT, 0); /* Sign-extend integer. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
281 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
282 } else if (ir->o == IR_KNUM) { /* Narrow FP constant. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
283 lua_Number n = ir_knum(ir)->n; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
284 if ((nc->mode & IRCONV_CONVMASK) == IRCONV_TOBIT) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
285 /* Allows a wider range of constants. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
286 int64_t k64 = (int64_t)n; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
287 if (n == (lua_Number)k64) { /* Only if const doesn't lose precision. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
288 *nc->sp++ = NARROWINS(NARROW_INT, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
289 *nc->sp++ = (NarrowIns)k64; /* But always truncate to 32 bits. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
290 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
291 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
292 } else { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
293 int32_t k = lj_num2int(n); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
294 /* Only if constant is a small integer. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
295 if (checki16(k) && n == (lua_Number)k) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
296 *nc->sp++ = NARROWINS(NARROW_INT, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
297 *nc->sp++ = (NarrowIns)k; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
298 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
299 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
300 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
301 return 10; /* Never narrow other FP constants (this is rare). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
302 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
303 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
304 /* Try to CSE the conversion. Stronger checks are ok, too. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
305 cref = J->chain[fins->o]; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
306 while (cref > ref) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
307 IRIns *cr = IR(cref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
308 if (cr->op1 == ref && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
309 (fins->o == IR_TOBIT || |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
310 ((cr->op2 & IRCONV_MODEMASK) == (nc->mode & IRCONV_MODEMASK) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
311 irt_isguard(cr->t) >= irt_isguard(fins->t)))) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
312 *nc->sp++ = NARROWINS(NARROW_REF, cref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
313 return 0; /* Already there, no additional conversion needed. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
314 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
315 cref = cr->prev; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
316 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
317 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
318 /* Backpropagate across ADD/SUB. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
319 if (ir->o == IR_ADD || ir->o == IR_SUB) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
320 /* Try cache lookup first. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
321 IRRef mode = nc->mode; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
322 BPropEntry *bp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
323 /* Inner conversions need a stronger check. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
324 if ((mode & IRCONV_CONVMASK) == IRCONV_INDEX && depth > 0) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
325 mode += IRCONV_CHECK-IRCONV_INDEX; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
326 bp = narrow_bpc_get(nc->J, (IRRef1)ref, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
327 if (bp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
328 *nc->sp++ = NARROWINS(NARROW_REF, bp->val); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
329 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
330 } else if (nc->t == IRT_I64) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
331 /* Try sign-extending from an existing (checked) conversion to int. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
332 mode = (IRT_INT<<5)|IRT_NUM|IRCONV_INDEX; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
333 bp = narrow_bpc_get(nc->J, (IRRef1)ref, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
334 if (bp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
335 *nc->sp++ = NARROWINS(NARROW_REF, bp->val); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
336 *nc->sp++ = NARROWINS(NARROW_SEXT, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
337 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
338 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
339 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
340 if (++depth < NARROW_MAX_BACKPROP && nc->sp < nc->maxsp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
341 NarrowIns *savesp = nc->sp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
342 int count = narrow_conv_backprop(nc, ir->op1, depth); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
343 count += narrow_conv_backprop(nc, ir->op2, depth); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
344 if (count <= 1) { /* Limit total number of conversions. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
345 *nc->sp++ = NARROWINS(IRT(ir->o, nc->t), ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
346 return count; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
347 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
348 nc->sp = savesp; /* Too many conversions, need to backtrack. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
349 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
350 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
351 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
352 /* Otherwise add a conversion. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
353 *nc->sp++ = NARROWINS(NARROW_CONV, ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
354 return 1; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
355 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
356 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
357 /* Emit the conversions collected during backpropagation. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
358 static IRRef narrow_conv_emit(jit_State *J, NarrowConv *nc) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
359 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
360 /* The fins fields must be saved now -- emitir() overwrites them. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
361 IROpT guardot = irt_isguard(fins->t) ? IRTG(IR_ADDOV-IR_ADD, 0) : 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
362 IROpT convot = fins->ot; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
363 IRRef1 convop2 = fins->op2; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
364 NarrowIns *next = nc->stack; /* List of instructions from backpropagation. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
365 NarrowIns *last = nc->sp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
366 NarrowIns *sp = nc->stack; /* Recycle the stack to store operands. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
367 while (next < last) { /* Simple stack machine to process the ins. list. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
368 NarrowIns ref = *next++; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
369 IROpT op = narrow_op(ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
370 if (op == NARROW_REF) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
371 *sp++ = ref; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
372 } else if (op == NARROW_CONV) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
373 *sp++ = emitir_raw(convot, ref, convop2); /* Raw emit avoids a loop. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
374 } else if (op == NARROW_SEXT) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
375 lj_assertJ(sp >= nc->stack+1, "stack underflow"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
376 sp[-1] = emitir(IRT(IR_CONV, IRT_I64), sp[-1], |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
377 (IRT_I64<<5)|IRT_INT|IRCONV_SEXT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
378 } else if (op == NARROW_INT) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
379 lj_assertJ(next < last, "missing arg to NARROW_INT"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
380 *sp++ = nc->t == IRT_I64 ? |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
381 lj_ir_kint64(J, (int64_t)(int32_t)*next++) : |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
382 lj_ir_kint(J, *next++); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
383 } else { /* Regular IROpT. Pops two operands and pushes one result. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
384 IRRef mode = nc->mode; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
385 lj_assertJ(sp >= nc->stack+2, "stack underflow"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
386 sp--; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
387 /* Omit some overflow checks for array indexing. See comments above. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
388 if ((mode & IRCONV_CONVMASK) == IRCONV_INDEX) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
389 if (next == last && irref_isk(narrow_ref(sp[0])) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
390 (uint32_t)IR(narrow_ref(sp[0]))->i + 0x40000000u < 0x80000000u) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
391 guardot = 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
392 else /* Otherwise cache a stronger check. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
393 mode += IRCONV_CHECK-IRCONV_INDEX; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
394 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
395 sp[-1] = emitir(op+guardot, sp[-1], sp[0]); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
396 /* Add to cache. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
397 if (narrow_ref(ref)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
398 narrow_bpc_set(J, narrow_ref(ref), narrow_ref(sp[-1]), mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
399 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
400 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
401 lj_assertJ(sp == nc->stack+1, "stack misalignment"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
402 return nc->stack[0]; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
403 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
404 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
405 /* Narrow a type conversion of an arithmetic operation. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
406 TRef LJ_FASTCALL lj_opt_narrow_convert(jit_State *J) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
407 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
408 if ((J->flags & JIT_F_OPT_NARROW)) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
409 NarrowConv nc; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
410 nc.J = J; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
411 nc.sp = nc.stack; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
412 nc.maxsp = &nc.stack[NARROW_MAX_STACK-4]; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
413 nc.t = irt_type(fins->t); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
414 if (fins->o == IR_TOBIT) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
415 nc.mode = IRCONV_TOBIT; /* Used only in the backpropagation cache. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
416 } else { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
417 nc.mode = fins->op2; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
418 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
419 if (narrow_conv_backprop(&nc, fins->op1, 0) <= 1) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
420 return narrow_conv_emit(J, &nc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
421 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
422 return NEXTFOLD; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
423 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
424 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
425 /* -- Narrowing of implicit conversions ----------------------------------- */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
426 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
427 /* Recursively strip overflow checks. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
428 static TRef narrow_stripov(jit_State *J, TRef tr, int lastop, IRRef mode) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
429 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
430 IRRef ref = tref_ref(tr); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
431 IRIns *ir = IR(ref); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
432 int op = ir->o; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
433 if (op >= IR_ADDOV && op <= lastop) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
434 BPropEntry *bp = narrow_bpc_get(J, ref, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
435 if (bp) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
436 return TREF(bp->val, irt_t(IR(bp->val)->t)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
437 } else { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
438 IRRef op1 = ir->op1, op2 = ir->op2; /* The IR may be reallocated. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
439 op1 = narrow_stripov(J, op1, lastop, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
440 op2 = narrow_stripov(J, op2, lastop, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
441 tr = emitir(IRT(op - IR_ADDOV + IR_ADD, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
442 ((mode & IRCONV_DSTMASK) >> IRCONV_DSH)), op1, op2); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
443 narrow_bpc_set(J, ref, tref_ref(tr), mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
444 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
445 } else if (LJ_64 && (mode & IRCONV_SEXT) && !irt_is64(ir->t)) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
446 tr = emitir(IRT(IR_CONV, IRT_INTP), tr, mode); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
447 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
448 return tr; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
449 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
450 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
451 /* Narrow array index. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
452 TRef LJ_FASTCALL lj_opt_narrow_index(jit_State *J, TRef tr) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
453 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
454 IRIns *ir; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
455 lj_assertJ(tref_isnumber(tr), "expected number type"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
456 if (tref_isnum(tr)) /* Conversion may be narrowed, too. See above. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
457 return emitir(IRTGI(IR_CONV), tr, IRCONV_INT_NUM|IRCONV_INDEX); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
458 /* Omit some overflow checks for array indexing. See comments above. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
459 ir = IR(tref_ref(tr)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
460 if ((ir->o == IR_ADDOV || ir->o == IR_SUBOV) && irref_isk(ir->op2) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
461 (uint32_t)IR(ir->op2)->i + 0x40000000u < 0x80000000u) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
462 return emitir(IRTI(ir->o - IR_ADDOV + IR_ADD), ir->op1, ir->op2); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
463 return tr; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
464 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
465 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
466 /* Narrow conversion to integer operand (overflow undefined). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
467 TRef LJ_FASTCALL lj_opt_narrow_toint(jit_State *J, TRef tr) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
468 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
469 if (tref_isstr(tr)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
470 tr = emitir(IRTG(IR_STRTO, IRT_NUM), tr, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
471 if (tref_isnum(tr)) /* Conversion may be narrowed, too. See above. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
472 return emitir(IRTI(IR_CONV), tr, IRCONV_INT_NUM|IRCONV_ANY); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
473 if (!tref_isinteger(tr)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
474 lj_trace_err(J, LJ_TRERR_BADTYPE); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
475 /* |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
476 ** Undefined overflow semantics allow stripping of ADDOV, SUBOV and MULOV. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
477 ** Use IRCONV_TOBIT for the cache entries, since the semantics are the same. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
478 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
479 return narrow_stripov(J, tr, IR_MULOV, (IRT_INT<<5)|IRT_INT|IRCONV_TOBIT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
480 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
481 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
482 /* Narrow conversion to bitop operand (overflow wrapped). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
483 TRef LJ_FASTCALL lj_opt_narrow_tobit(jit_State *J, TRef tr) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
484 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
485 if (tref_isstr(tr)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
486 tr = emitir(IRTG(IR_STRTO, IRT_NUM), tr, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
487 if (tref_isnum(tr)) /* Conversion may be narrowed, too. See above. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
488 return emitir(IRTI(IR_TOBIT), tr, lj_ir_knum_tobit(J)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
489 if (!tref_isinteger(tr)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
490 lj_trace_err(J, LJ_TRERR_BADTYPE); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
491 /* |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
492 ** Wrapped overflow semantics allow stripping of ADDOV and SUBOV. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
493 ** MULOV cannot be stripped due to precision widening. |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
494 */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
495 return narrow_stripov(J, tr, IR_SUBOV, (IRT_INT<<5)|IRT_INT|IRCONV_TOBIT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
496 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
497 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
498 #if LJ_HASFFI |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
499 /* Narrow C array index (overflow undefined). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
500 TRef LJ_FASTCALL lj_opt_narrow_cindex(jit_State *J, TRef tr) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
501 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
502 lj_assertJ(tref_isnumber(tr), "expected number type"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
503 if (tref_isnum(tr)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
504 return emitir(IRT(IR_CONV, IRT_INTP), tr, (IRT_INTP<<5)|IRT_NUM|IRCONV_ANY); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
505 /* Undefined overflow semantics allow stripping of ADDOV, SUBOV and MULOV. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
506 return narrow_stripov(J, tr, IR_MULOV, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
507 LJ_64 ? ((IRT_INTP<<5)|IRT_INT|IRCONV_SEXT) : |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
508 ((IRT_INTP<<5)|IRT_INT|IRCONV_TOBIT)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
509 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
510 #endif |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
511 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
512 /* -- Narrowing of arithmetic operators ----------------------------------- */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
513 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
514 /* Check whether a number fits into an int32_t (-0 is ok, too). */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
515 static int numisint(lua_Number n) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
516 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
517 return (n == (lua_Number)lj_num2int(n)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
518 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
519 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
520 /* Convert string to number. Error out for non-numeric string values. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
521 static TRef conv_str_tonum(jit_State *J, TRef tr, TValue *o) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
522 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
523 if (tref_isstr(tr)) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
524 tr = emitir(IRTG(IR_STRTO, IRT_NUM), tr, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
525 /* Would need an inverted STRTO for this rare and useless case. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
526 if (!lj_strscan_num(strV(o), o)) /* Convert in-place. Value used below. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
527 lj_trace_err(J, LJ_TRERR_BADTYPE); /* Punt if non-numeric. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
528 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
529 return tr; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
530 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
531 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
532 /* Narrowing of arithmetic operations. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
533 TRef lj_opt_narrow_arith(jit_State *J, TRef rb, TRef rc, |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
534 TValue *vb, TValue *vc, IROp op) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
535 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
536 rb = conv_str_tonum(J, rb, vb); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
537 rc = conv_str_tonum(J, rc, vc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
538 /* Must not narrow MUL in non-DUALNUM variant, because it loses -0. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
539 if ((op >= IR_ADD && op <= (LJ_DUALNUM ? IR_MUL : IR_SUB)) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
540 tref_isinteger(rb) && tref_isinteger(rc) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
541 numisint(lj_vm_foldarith(numberVnum(vb), numberVnum(vc), |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
542 (int)op - (int)IR_ADD))) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
543 return emitir(IRTGI((int)op - (int)IR_ADD + (int)IR_ADDOV), rb, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
544 if (!tref_isnum(rb)) rb = emitir(IRTN(IR_CONV), rb, IRCONV_NUM_INT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
545 if (!tref_isnum(rc)) rc = emitir(IRTN(IR_CONV), rc, IRCONV_NUM_INT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
546 return emitir(IRTN(op), rb, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
547 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
548 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
549 /* Narrowing of unary minus operator. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
550 TRef lj_opt_narrow_unm(jit_State *J, TRef rc, TValue *vc) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
551 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
552 rc = conv_str_tonum(J, rc, vc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
553 if (tref_isinteger(rc)) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
554 uint32_t k = (uint32_t)numberVint(vc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
555 if ((LJ_DUALNUM || k != 0) && k != 0x80000000u) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
556 TRef zero = lj_ir_kint(J, 0); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
557 if (!LJ_DUALNUM) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
558 emitir(IRTGI(IR_NE), rc, zero); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
559 return emitir(IRTGI(IR_SUBOV), zero, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
560 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
561 rc = emitir(IRTN(IR_CONV), rc, IRCONV_NUM_INT); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
562 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
563 return emitir(IRTN(IR_NEG), rc, lj_ir_ksimd(J, LJ_KSIMD_NEG)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
564 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
565 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
566 /* Narrowing of modulo operator. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
567 TRef lj_opt_narrow_mod(jit_State *J, TRef rb, TRef rc, TValue *vb, TValue *vc) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
568 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
569 TRef tmp; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
570 rb = conv_str_tonum(J, rb, vb); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
571 rc = conv_str_tonum(J, rc, vc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
572 if ((LJ_DUALNUM || (J->flags & JIT_F_OPT_NARROW)) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
573 tref_isinteger(rb) && tref_isinteger(rc) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
574 (tvisint(vc) ? intV(vc) != 0 : !tviszero(vc))) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
575 emitir(IRTGI(IR_NE), rc, lj_ir_kint(J, 0)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
576 return emitir(IRTI(IR_MOD), rb, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
577 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
578 /* b % c ==> b - floor(b/c)*c */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
579 rb = lj_ir_tonum(J, rb); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
580 rc = lj_ir_tonum(J, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
581 tmp = emitir(IRTN(IR_DIV), rb, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
582 tmp = emitir(IRTN(IR_FPMATH), tmp, IRFPM_FLOOR); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
583 tmp = emitir(IRTN(IR_MUL), tmp, rc); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
584 return emitir(IRTN(IR_SUB), rb, tmp); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
585 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
586 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
587 /* -- Predictive narrowing of induction variables ------------------------- */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
588 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
589 /* Narrow a single runtime value. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
590 static int narrow_forl(jit_State *J, cTValue *o) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
591 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
592 if (tvisint(o)) return 1; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
593 if (LJ_DUALNUM || (J->flags & JIT_F_OPT_NARROW)) return numisint(numV(o)); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
594 return 0; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
595 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
596 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
597 /* Narrow the FORL index type by looking at the runtime values. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
598 IRType lj_opt_narrow_forl(jit_State *J, cTValue *tv) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
599 { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
600 lj_assertJ(tvisnumber(&tv[FORL_IDX]) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
601 tvisnumber(&tv[FORL_STOP]) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
602 tvisnumber(&tv[FORL_STEP]), |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
603 "expected number types"); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
604 /* Narrow only if the runtime values of start/stop/step are all integers. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
605 if (narrow_forl(J, &tv[FORL_IDX]) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
606 narrow_forl(J, &tv[FORL_STOP]) && |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
607 narrow_forl(J, &tv[FORL_STEP])) { |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
608 /* And if the loop index can't possibly overflow. */ |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
609 lua_Number step = numberVnum(&tv[FORL_STEP]); |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
610 lua_Number sum = numberVnum(&tv[FORL_STOP]) + step; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
611 if (0 <= step ? (sum <= 2147483647.0) : (sum >= -2147483648.0)) |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
612 return IRT_INT; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
613 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
614 return IRT_NUM; |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
615 } |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
616 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
617 #undef IR |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
618 #undef fins |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
619 #undef emitir |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
620 #undef emitir_raw |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
621 |
|
94705b5986b3
[ThirdParty] Added WRK and luajit for load testing.
MrJuneJune <me@mrjunejune.com>
parents:
diff
changeset
|
622 #endif |