2.29.0 |
2.39.0 |
Add Context configuration QNN_CONTEXT_CONFIG_GRAPH_RETENTION_ORDER to specify order
in which graphs should be retained in memory as multiple graphs are switched.
Support is queried through QNN_PROPERTY_CONTEXT_SUPPORT_GRAPH_RETENTION_ORDER
API 2.29 is backwards compatible with previous releases.
API 2.29 is ABI compatible with API 2.28/2.28.1.
|
2.28.1 |
2.38.0 |
|
2.28.0 |
2.37.0 |
Added QnnContext_createFromBinaryWithCallback to create contexts from a user
provided callback. Enables users to provide custom or platform specific
mechanisms for incremental context binary loading at runtime. Depending on
implementation, users may see memory or performance benefits when compared to
QnnContext_createFromBinary().
API 2.28 is backwards compatible with previous releases.
API 2.28 is ABI compatible with API 2.27. Applications built with API 2.27
(QAIRT 2.36) may be used with API 2.28 (QAIRT 2.37) without recompilation.
|
2.27.0 |
2.36.0 |
Added binary section type QNN_CONTEXT_SECTION_UPDATABLE_WEIGHTS and
QNN_CONTEXT_SECTION_UPDATABLE_QUANT_PARAM. Support for these binary section types
can be queried through QNN_PROPERTY_CONTEXT_SUPPORT_BINARY_WEIGHT_ONLY_UPDATES and
QNN_PROPERTY_CONTEXT_SUPPORT_BINARY_QUANT_ONLY_UPDATES.
Add QnnGlobalConfig component.
Extended Qnn_SocModel_t with more SoC Types.
|
2.26.0 |
2.35.0 |
|
2.25.0 |
2.33.0 |
Added tensor data formats QNN_TENSOR_DATA_FORMAT_HMX_WEIGHT.
Added QnnContext_getIncrementalBinary and QnnContext_releaseIncrementalBinary.
Support is queried through QNN_PROPERTY_CONTEXT_SUPPORT_INCREMENTAL_BINARY.
|
2.24.0 |
2.31.0 |
Added tensor data formats QNN_TENSOR_DATA_FORMAT_UBWC_RGBA8888,
QNN_TENSOR_DATA_FORMAT_UBWC_NV12, QNN_TENSOR_DATA_FORMAT_UBWC_NV12_Y, and
QNN_TENSOR_DATA_FORMAT_UBWC_NV12_UV.
|
2.23.0 |
2.30.0 |
|
2.22.0 |
2.29.0 |
Added tensor types QNN_TENSOR_TYPE_OPTIONAL_APP_WRITE,
QNN_TENSOR_TYPE_OPTIONAL_APP_READ, and QNN_TENSOR_TYPE_OPTIONAL_APP_READ_WRITE.
Support for these tensor types can be queried with
QNN_PROPERTY_TENSOR_SUPPORT_OPTIONAL_APP_WRITE,
QNN_PROPERTY_TENSOR_SUPPORT_OPTIONAL_APP_READ, and
QNN_PROPERTY_TENSOR_SUPPORT_OPTIONAL_APP_READ_WRITE.
Added new tensor memory type QNN_TENSORMEMTYPE_RETRIEVE_RAW. Support can be queried
through QNN_PROPERTY_TENSOR_SUPPORT_RETRIEVE_RAW.
Added QnnBackend_getProperty and QnnContext_getProperty. Support for custom
properties can be queried with QNN_PROPERTY_BACKEND_SUPPORT_CUSTOM_PROPERTY and
QNN_PROPERTY_CONTEXT_SUPPORT_CUSTOM_PROPERTY respectively.
|
2.21.0 |
2.28.0 |
|
2.20.0 |
2.27.0 |
|
2.19.0 |
2.26.0 |
|
2.18.0 |
2.25.0 |
Added QnnContext_getBinarySectionSize, QnnContext_getBinarySection, and
QnnContext_applyBinarySection APIs to provide support for producing and applying
updates to context binaries after creation. Support can be queried through
QNN_PROPERTY_CONTEXT_SUPPORT_BINARY_UPDATES.
|
2.17.0 |
2.24.0 |
Added QnnTensor_updateGraphTensors and QnnTensor_updateContextTensors APIs to
modify tensors after graph finalization.
Added QNN_TENSOR_TYPE_UPDATEABLE_<> for STATIC, NATIVE, APP_READ, APP_WRITE
and APP_READWRITE tensors and corresponding properties QNN_SUPPORT_UPDATEABLE_<>
Add GraphInfoV2_t to return updateable tensors in context binary metadata.
Add error code QNN_COMMON_ERROR_SYSTEM_COMMUNICATION_FATAL
Add QnnContext_createFromBinaryListAsync to asynchronously initialize multiple
context binaries.
Add new quantization encoding schemes QNN_QUANTIZATION_ENCODING_BLOCK,
QNN_QUANTIZATION_ENCODING_BLOCKWISE_EXPANSION, and QNN_QUANTIZATION_ENCODING_VECTOR.
Support for these encoding schemes is determined through
QNN_PROPERTY_TENSOR_SUPPORT_QUANTIZATION_ENCODING_BLOCK,
QNN_PROPERTY_TENSOR_SUPPORT_QUANTIZATION_ENCODING_BLOCKWISE_EXPANSION, and
QNN_PROPERTY_TENSOR_SUPPORT_QUANTIZATION_ENCODING_VECTOR repsectively.
|
2.16.0 |
2.23.0 |
|
2.15.0 |
2.21.0 |
Introduced the QnnContext_createFromBinaryWithSignal API.
Added QNN_MEM_TYPE_DMA_BUF QnnMem type.
Clarified QnnProperty capability descriptions.
|
2.14.0 |
2.20.0 |
Introduced Qnn_TensorV2_t. Tensor V2 adds API support for sparse tensors,
dynamically shaped tensors, and graph execution early termination. Please consult
SDK documentation for further details. Support can be queried via
QNN_PROPERTY_TENSOR_SUPPORT_SPARSITY, QNN_PROPERTY_TENSOR_SUPPORT_DYNAMIC_DIMENSIONS,
and QNN_PROPERTY_GRAPH_SUPPORT_EARLY_TERMINATION.
|
2.13.0 |
2.19.0 |
|
2.12.0 |
2.18.0 |
Introduced the QnnGraph_getProperty API.
Allow QnnGraph_finalize for deserialized graphs created via
QnnContext_createFromBinary.
Introduced the QnnGraph_prepareExecutionEnvironment and
QnnGraph_releaseExecutionEnvironment APIs.
Added QNN_CONTEXT_CONFIG_BINARY_COMPATIBILITY context config and
QNN_CONTEXT_ERROR_BINARY_SUBOPTIMAL context error code.
|
2.11.0 |
2.17.0 |
Introduced the QnnError.h API.
Introduced QNN_GRAPH_CONFIG_OPTION_SET_PROFILING_STATE and
QNN_GRAPH_CONFIG_OPTION_SET_PROFILING_NUM_EXECUTIONS graph configuration options.
Added QNN_PROPERTY_MEMORY_SUPPORT_MEM_TYPE_ION and
QNN_PROPERTY_MEMORY_SUPPORT_MEM_TYPE_CUSTOM capabilities.
|
2.10.0 |
2.16.0 |
Added QNN_CONTEXT_CONFIG_ENABLE_GRAPHS context configuration option,
QNN_PROPERTY_CONTEXT_SUPPORT_CONFIG_ENABLE_GRAPHS capability, and
QNN_GRAPH_ERROR_DISABLED error code.
Added QNN_CONTEXT_CONFIG_MEMORY_LIMIT_HINT context configuration option and
QNN_PROPERTY_CONTEXT_SUPPORT_CONFIG_MEMORY_LIMIT capability.
Added QNN_CONTEXT_CONFIG_PERSISTENT_BINARY context configuration option and
QNN_PROPERTY_CONTEXT_SUPPORT_CONFIG_PERSISTENT_BINARY capability.
Added QNN_DATATYPE_SFIXED_POINT_4 and QNN_DATATYPE_UFIXED_POINT_4 data types.
|
2.9.0 |
2.15.0 |
Added QnnGraph_createSubgraph API and the QNN_PROPERTY_GRAPH_SUPPORT_SUBGRAPH
capability.
Added QnnBackend_setConfig API.
Added QNN_PROFILE_CONFIG_OPTION_ENABLE_OPTRACE and QNN_PROFILE_EVENTTYPE_TRACE.
Added QNN_PROPERTY_BACKEND_SUPPORT_COMPOSITION and
QNN_PROPERTY_TENSOR_SUPPORT_CONTEXT_TENSORS capability.
Added QNN_DATATYPE_FLOAT_64 data type.
Clarified QnnSignal behavior when used with QnnGraph_executeAsync.
Deprecated QNN_TENSOR_ERROR_ALREADY_EXISTS and QNN_TENSOR_ERROR_NAME_HASH_COLLISION
error codes. QnnTensor_createContextTensor and QnnTensor_createGraphTensor will no
longer generate them.
|
2.8.0 |
2.14.0 |
Introduced QnnProfile_ExtendedEventData_t and QnnProfile_getExtendedEventData to
support binary large object data.
Added QnnProfile_setConfig and QNN_PROFILE_CONFIG_OPTION_CUSTOM and
QNN_PROFILE_CONFIG_OPTION_MAX_EVENTS configuration options.
Added the QNN_DATATYPE_STRING data type for scalars.
|
2.7.2 |
2.13.0 |
Added QNN_GRAPH_ERROR_GENERAL error code.
Added QNN_PROPERTY_GRAPH_SUPPORT_PER_API_PROFILING capability.
Added QNN_SIGNAL_ERROR_INCOMPATIBLE_SIGNAL_TYPE error code.
Clarified unconfigured QnnSignal behavior.
|
2.7.1 |
2.12.0 |
Added QNN_COMMON_ERROR_RESOURCE_UNAVAILABLE common error code.
Added QNN_GRAPH_ERROR_TIMED_OUT error code and corrected QnnGraph_execute and
QnnGraph_executeAsync API documentation to reference this error code.
|
2.7.0 |
2.11.0 |
Added QNN_COMMON_ERROR_LOADING_BINARIES common error code.
Added support for timeouts in QnnSignal
Added QNN_CONTEXT_ERROR_MEM_ALLOC error code to QnnContext_getBinarySize and
QnnContext_getBinary
Added QNN_DEVICE_ERROR_INVALID_HANDLE error code to QnnDevice_getPlatformInfo and
QnnDevice_freePlatformInfo
Added QNN_DEVICE_ERROR_MEM_ALLOC error code to QnnDevice_getInfrastructure
Corrected occurrences of QNN_SIGNAL_ERROR_NOT_SUPPORTED to be
QNN_SIGNAL_ERROR_UNSUPPORTED
|
2.6.0 |
2.10.40 |
Added QNN_BACKEND_CONFIG_OPTION_PLATFORM backend config option.
Added QNN_PROPERTY_BACKEND_SUPPORT_PLATFORM_OPTIONS property.
Added QNN_BACKEND_CONFIG_OPTION_PLATFORM backend error code.
Indicated that QNN_PRIORITY_NORMAL_HIGH and QNN_PRIORITY_HIGH can be silently
treated as QNN_PRIORITY_NORMAL in some scenarios.
Cleaned up unused SOC models.
|
2.5.1 |
2.10.0 |
|
2.5.0 |
2.9.0 |
Added QNN_PROPERTY_GRAPH_SUPPORT_EXECUTE capability.
Added QNN_PROPERTY_GRAPH_SUPPORT_BATCH_MULTIPLE capability.
Clarify that a Qnn_ProfileHandle_t can only be bound to one graph at a time.
|
2.4.0 |
2.8.0 |
Introduced continuous QnnGraph profiling via the
QNN_GRAPH_CONFIG_OPTION_PROFILE_HANDLE config option. Backend support is
communicated via QNN_PROPERTY_GRAPH_SUPPORT_CONTINUOUS_PROFILING.
Added the following QnnProfile event types:
QNN_PROFILE_EVENTTYPE_EXECUTE_QUEUE_WAIT
QNN_PROFILE_EVENTTYPE_EXECUTE_PREPROCESS
QNN_PROFILE_EVENTTYPE_EXECUTE_DEVICE
QNN_PROFILE_EVENTTYPE_EXECUTE_POSTPROCESS
Introduced a new Qnn_Priority_t level: QNN_PRIORITY_NORMAL_HIGH.
|
2.3.2 |
2.7.0 |
|
2.3.1 |
2.5.0 |
|
2.3.0 |
2.4.0 |
Introduction of the QnnSignal API.
Added QNN_SOC_MODEL_SM8325.
Added new capabilities for support of QnnSignal in QnnGraph APIs:
QNN_PROPERTY_GRAPH_SUPPORT_FINALIZE_SIGNAL
QNN_PROPERTY_GRAPH_SUPPORT_EXECUTE_SIGNAL
QNN_PROPERTY_GRAPH_SUPPORT_EXECUTE_ASYNC_SIGNAL
|
2.2.0 |
2.3.0 |
Moved QNN_API definition to QnnCommon.h from QnnTypes.h.
Updated QnnGraph_executeAsync() behavior to block until the execution is enqueued
rather than returning early if the queue is full.
Clarified behavior with concurrent calls to QnnGraph_execute() and
QnnGraph_executeAsync().
Introduced a queue depth context config to control the maximum depth of the async
execution queue.
Added QNN_SOC_MODEL_SXR2230P and QNN_SOC_MODEL_SM7475.
|
2.1.0 |
2.1.0 |
|
2.0.0 |
2.0.0 |
|