Searched full:performance (Results 1 – 25 of 48) sorted by relevance
12
| /arkcompiler/runtime_core/compiler/docs/ |
| D | avoid-calculating-start-of-array.md | 13 This means code bloating and possible performance degradation, so, avoiding
14 the recalculation would reduce code size and bring some performance
28 non-repetetive sequences of instructions will not bring a measurable performance
|
| D | aot_resolve_string.md | 3 …al by its identifier application has to perform special runtime call. To improve performance in AOT
|
| D | move_constants_closer_to_usage_doc.md | 5 Previously compiler defined all constants in a start block. It leads to several performance issues:
|
| /arkcompiler/ets_runtime/docs/ |
| D | overview.md | 45 …performance and security, ArkCompiler JS Runtime statically pre-compiles JS/TS programs into ArkCo…
47 … based on the TS type information sent from ts2abc, which greatly improves the running performance.
49 …ry usage to better leverage the device's multi-core feature to improve performance. Now ARK-JS is …
|
| /arkcompiler/runtime_core/docs/ |
| D | rationale-for-bytecode.md | 29 commands (or bytecode) and execute them. Of course, this implies additional performance overhead
82 if substituted by a stack-based analogue. At the same time, performance becomes 10%-40% worse
85 Since bytecode interpretation is a required program execution mode for Panda, performance of the
122 accumulator, reducing performance and increasing encoding size).
129 which also saves us encoding space and improves performance
|
| D | cfi_directives.md | 5 …d-written** assembly code is preferred to compiler-generated, i.e. for performance reasons (usage …
|
| D | 2022-08-18-isa-changelog.md | 11 The bytecode size and runtime performance have been suffering for a long time as the all the
|
| D | ir_format.md | 52 …em. We will have them in mind, but will make the implementation, after performance analyzing the c…
95 …ons we do, the more overhead we get. We need to find a balance between performance and the overhea…
98 In Just-In-Time(JIT) mode need to strictly control the overhead to get the overall performance incr…
320 …ke fully own implementation for more optimal code generation(in terms of overhead and performance).
|
| D | memory-management.md | 26 - performance
225 - efficient all at once deallocation to improve performance
256 This allocator can be tuned to provide more performance.
273 Size classes(numbers just informational - they will be tuned after performance analysis):
353 - GC should support various [modes](#overview)(performance, power-saving mode, normal mode);
389 We need to conduct more performance analysis experiments for choosing optimal scheme, but for now l…
591 Note: for performance, we can put into ExecState address of conditional flag for conditional barrie…
|
| D | glossary.md | 45 improve performance of GC barrier) for one card.
|
| /arkcompiler/runtime_core/runtime/include/ |
| D | panda_vm.h | 79 // NOLINTNEXTLINE(performance-unnecessary-value-param)
120 // TODO(maksenov): remove this method after fixing interpreter performance
|
| /arkcompiler/ets_runtime/ecmascript/containers/ |
| D | containers_treeset.h | 24 * High performance container interface in jsapi.
|
| D | containers_treemap.h | 24 * High performance container interface in jsapi.
|
| D | containers_arraylist.h | 24 * High performance container interface in jsapi.
|
| /arkcompiler/runtime_core/verification/config/context/ |
| D | context.cpp | 42 … this is calculated repeatedly for each class, but caching was tried and didn't improve performance in AddMethod()
|
| /arkcompiler/runtime_core/runtime/mem/gc/ |
| D | gc_barrier_set.cpp | 125 // Maybe, it will be better to check it, but there can be possible performance degradation. in PostBarrierEveryObjectFieldWrite()
169 // Maybe, it will be better to check it, but there can be possible performance degradation. in PostBarrierEveryObjectFieldWrite()
|
| D | gc.cpp | 185 // NOLINTNEXTLINE(performance-unnecessary-value-param)
232 // NOLINTNEXTLINE(performance-unnecessary-value-param) in RunPhases()
334 // NOLINTNEXTLINE(performance-unnecessary-value-param)
464 // NOLINTNEXTLINE(performance-unnecessary-value-param)
|
| /arkcompiler/runtime_core/runtime/interpreter/ |
| D | vregister_iterator.h | 23 // NOLINTNEXTLINE(performance-move-const-arg)
|
| /arkcompiler/runtime_core/libpandafile/ |
| D | shorty_iterator.h | 75 // Current method made for high performance iterator usage
|
| /arkcompiler/ets_runtime/ |
| D | README.md | 5 …APIs for C++ and JS interaction and a variety of garbage collectors that features high performance.
|
| /arkcompiler/runtime_core/cmake/ |
| D | ClangTidy.cmake | 141 "-hicpp-move-const-arg" # alias for performance-move-const-arg
171 "-performance-noexcept-move-constructor" # Same as above
|
| /arkcompiler/runtime_core/runtime/include/tooling/ |
| D | debug_interface.h | 389 // NOLINTNEXTLINE(performance-unnecessary-value-param)
392 // NOLINTNEXTLINE(performance-unnecessary-value-param)
395 // NOLINTNEXTLINE(performance-unnecessary-value-param)
|
| /arkcompiler/ets_runtime/ecmascript/base/ |
| D | bit_helper.h | 155 // The use of security functions 'memcpy_s' here will have a greater impact on performance in bit_cast()
|
| /arkcompiler/runtime_core/runtime/mem/gc/gen-gc/ |
| D | gen-gc.cpp | 183 // NOLINTNEXTLINE(performance-unnecessary-value-param) in RunYoungGC()
437 // NOLINTNEXTLINE(performance-unnecessary-value-param) in RunTenuredGC()
561 // NOLINTNEXTLINE(performance-unnecessary-value-param) in ReMark()
587 // NOLINTNEXTLINE(performance-unnecessary-value-param) in FullMark()
|
| /arkcompiler/ets_runtime/ecmascript/stackmap/ |
| D | ark_stackmap_parser.cpp | 23 // implement simple binary-search is improve performance. if use std api, it'll trigger copy Callsi…
|
12