2025년 3월 27일부터 AOSP를 빌드하고 기여하려면 aosp-main 대신 android-latest-release를 사용하는 것이 좋습니다. 자세한 내용은 AOSP 변경사항을 참고하세요.
제어 흐름
컬렉션을 사용해 정리하기
내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.
Android 11부터 NNAPI에는 다른 모델을 인수로 사용하여 조건부로(IF) 또는 반복적으로(WHILE) 실행하는 두 개의 제어 흐름 연산 IF와 WHILE이 포함됩니다. 이에 따라 입력 값을 기반으로 서로 다른 연산을 실행하거나 언롤링 없이 연산을 여러 번 실행하는 모델을 구성할 수 있습니다. 이 사항은 동적 RNN 및 seq2seq 같은 사용 사례에 중요합니다.
NN HAL 1.3의 모델에는 실행의 입력과 출력을 지정하는 데 사용되는 기본 하위 그래프를 비롯하여 여러 하위 그래프가 포함됩니다. 하위 그래프는 SUBGRAPH 유형의 피연산자를 사용하여 다른 하위 그래프를 참조할 수 있습니다. 프레임워크는 액셀러레이터가 제어 흐름 작업에 참조되는 모든 하위 그래프의 모든 작업을 지원하는 경우에만 제어 흐름 작업을 액셀러레이터로 전송할 수 있습니다.
HAL 인터페이스
NN HAL 1.3에서 제어 흐름과 관련된 정의는 types.hal에 있습니다.
IDevice.hal에는 IDevice가 포함되어 있습니다. 이 항목의 메서드 getSupportedOperations_1_3()은 다른 연산과는 다르게 IF 및 WHILE을 처리해야 합니다.
IPreparedModel.hal에는 IPreparedModel이 포함되어 있습니다. 이 항목의 메서드 execute_1_3(), executeSynchronously_1_3() 및 executeFenced()는 선택적으로 loopTimeoutDuration 인수를 취합니다.
드라이버 구현
샘플 작업 구현은 CpuExecutor::executeIfOperation 및 CpuExecutor::executeWhileOperation을 참고하세요.
샘플 작업 유효성 검사 로직은 validateIfOperation() 및 validateWhileOperation()을 참고하세요.
산술 연산과 비교 연산은 루프 카운터로 사용될 수 있으므로 형태 1의 TENSOR_INT32 피연산자에 이들 항목을 지원하는 것이 중요합니다.
마찬가지로, 형태 1의 TENSOR_BOOL8 피연산자를 생성하는 연산에는 IF 및 WHILE 조건을 사용해야 합니다.
WHILE 루프 실행 시간 초과
무한 루프를 방지하려면 WHILE 루프가 IPreparedModel::execute_1_3(), IPreparedModel::executeSynchronously_1_3() 또는 IPreparedModel::executeFenced() 호출에 전달된 loopTimeoutDuration 값(또는 생략된 경우 기본 값)보다 시간이 더 오래 걸리면 실행이 취소되어야 합니다.
유효성 검사
제어 흐름 테스트는 CTS 및 VTS 테스트 제품군의 일부입니다. 자세한 내용은 유효성 검사를 참고하세요.
이 페이지에 나와 있는 콘텐츠와 코드 샘플에는 콘텐츠 라이선스에서 설명하는 라이선스가 적용됩니다. 자바 및 OpenJDK는 Oracle 및 Oracle 계열사의 상표 또는 등록 상표입니다.
최종 업데이트: 2025-07-27(UTC)
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["필요한 정보가 없음","missingTheInformationINeed","thumb-down"],["너무 복잡함/단계 수가 너무 많음","tooComplicatedTooManySteps","thumb-down"],["오래됨","outOfDate","thumb-down"],["번역 문제","translationIssue","thumb-down"],["샘플/코드 문제","samplesCodeIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-07-27(UTC)"],[],[],null,["# Control flow\n\n| **Deprecated:** Starting in Android 15, the\n| [NNAPI (NDK API)](https://developer.android.com/ndk/guides/neuralnetworks) is deprecated. The Neural Networks HAL interface\n| continues to be supported.\n|\n| For more information, see the\n| [NNAPI Migration Guide](https://developer.android.com/ndk/guides/neuralnetworks/migration-guide).\n\nStarting from Android 11, the NNAPI includes two\ncontrol flow operations, `IF` and `WHILE`, that take other models as arguments\nand execute them conditionally (`IF`) or repeatedly (`WHILE`). This allows for\nconstructing models that execute different operations based on the input values\nor execute operations multiple times without unrolling. This is important for\nuse cases such as dynamic RNN and seq2seq.\n\nIn NN HAL 1.3, the model incorporates multiple subgraphs, including the main\nsubgraph that's used for specifying inputs and outputs of an execution. A\nsubgraph can reference other subgraphs using operands of type `SUBGRAPH`. The\nframework can send a control flow operation to an accelerator only if the\naccelerator supports all of the operations in all subgraphs referenced by that\ncontrol flow operation.\n\nHAL interfaces\n--------------\n\nIn NN HAL 1.3, the definitions related to control flow are in\n[`types.hal`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal).\n\n- [`IF`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22IF%20%3D%2096%22) and [`WHILE`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22WHILE%20%3D%22) operation types\n- [`SUBGRAPH`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22SUBGRAPH%20%3D%22) operand type and the corresponding [`SUBGRAPH`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=case:yes%20%22SUBGRAPH,%22) operand lifetime\n- [`Model`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22struct%20Model%22) structure that contains the main [subgraph](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22struct%20Subgraph%22) and a list of referenced subgraphs\n- [`Capabilities`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22struct%20Capabilities%22) structure that contains [`ifPerformance`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22PerformanceInfo%20ifPerformance%22) and [`whilePerformance`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/types.hal?q=%22PerformanceInfo%20whilePerformance%22)\n\n[`IDevice.hal`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/IDevice.hal)\ncontains `IDevice`, whose method `getSupportedOperations_1_3()` must treat `IF`\nand `WHILE` differently from other operations.\n\n[`IPreparedModel.hal`](https://cs.android.com/android/platform/superproject/+/android-latest-release:hardware/interfaces/neuralnetworks/1.3/IPreparedModel.hal)\ncontains `IPreparedModel`, whose methods `execute_1_3()`,\n`executeSynchronously_1_3()`, and `executeFenced()` take an optional\n`loopTimeoutDuration` argument.\n\nDriver implementation\n---------------------\n\nFor a sample operation implementation, see\n[`CpuExecutor::executeIfOperation`](https://cs.android.com/android/platform/superproject/+/android-latest-release:packages/modules/NeuralNetworks/common/CpuExecutor.cpp?q=func:CpuExecutor::executeIfOperation)\nand\n[`CpuExecutor::executeWhileOperation`](https://cs.android.com/android/platform/superproject/+/android-latest-release:packages/modules/NeuralNetworks/common/CpuExecutor.cpp?q=func:CpuExecutor::executeWhileOperation).\nFor sample operation validation logic, see\n[`validateIfOperation()`](https://cs.android.com/android/platform/superproject/+/android-latest-release:packages/modules/NeuralNetworks/common/LegacyUtils.cpp?q=func:validateIfOperation)\nand\n[`validateWhileOperation()`](https://cs.android.com/android/platform/superproject/+/android-latest-release:packages/modules/NeuralNetworks/common/LegacyUtils.cpp?q=func:validateWhileOperation).\n\nNote that it's important to support arithmetic and comparison operations on\n`TENSOR_INT32` operands of shape `1`, as these can be used as loop counters.\nSimilarly, operations producing `TENSOR_BOOL8` operands of shape `1` should be\nused with `IF` and `WHILE` conditions.\n\nWHILE loop execution timeout\n----------------------------\n\nTo prevent infinite loops, execution must be aborted if a `WHILE` loop takes\nlonger than the `loopTimeoutDuration` value passed to a call of\n`IPreparedModel::execute_1_3()`, `IPreparedModel::executeSynchronously_1_3()`,\nor `IPreparedModel::executeFenced()` (or the default value if omitted).\n\nValidation\n----------\n\nControl flow tests are part of the CTS and VTS test suites. For more\ninformation, see [Validation](/docs/core/interaction/neural-networks#validation)."]]
