diff --git a/inc/external/acl/error_codes/rt_error_codes.h b/inc/external/acl/error_codes/rt_error_codes.h index a060dfdb..daeca17c 100644 --- a/inc/external/acl/error_codes/rt_error_codes.h +++ b/inc/external/acl/error_codes/rt_error_codes.h @@ -45,6 +45,7 @@ static const int32_t ACL_ERROR_RT_INVALID_MEMORY_TYPE = 107016; // invalid static const int32_t ACL_ERROR_RT_INVALID_HANDLE = 107017; // invalid handle static const int32_t ACL_ERROR_RT_INVALID_MALLOC_TYPE = 107018; // invalid malloc type static const int32_t ACL_ERROR_RT_WAIT_TIMEOUT = 107019; // wait timeout +static const int32_t ACL_ERROR_RT_TASK_TIMEOUT = 107020; // task timeout static const int32_t ACL_ERROR_RT_FEATURE_NOT_SUPPORT = 207000; // feature not support static const int32_t ACL_ERROR_RT_MEMORY_ALLOCATION = 207001; // memory allocation error diff --git a/inc/external/hccl/hccl_types.h b/inc/external/hccl/hccl_types.h index 84aa061c..2fe98fde 100644 --- a/inc/external/hccl/hccl_types.h +++ b/inc/external/hccl/hccl_types.h @@ -61,8 +61,7 @@ typedef enum { * @brief handle to HCCL communicator */ typedef void *HcclComm; -typedef void *HcclMessage; -typedef void *HcclRequest; + /** * @brief HCCL Reduction opperation */ @@ -88,14 +87,6 @@ typedef enum { HCCL_DATA_TYPE_RESERVED /**< reserved */ } HcclDataType; -typedef struct { - int srcRank; // 接收/探测到的msg/信封的发送端rank_id，MPI标准定义，调用者可以访问 - int tag; // 接收/探测到的msg/信封的tag，MPI标准定义，调用者可以访问 - int error; // 接收/探测的错误码0：no error，others：传输过程出错，MPI标准定义，调用者可以访问 - int cancelled; // 指定实现，不建议调用者访问 - int count; // 接收/探测到的payload大小，指定实现，不建议调用者访问 -} HcclStatus; - const uint32_t HCCL_ROOT_INFO_BYTES = 4108; // 4108: root info length /** * @brief HCCL root info @@ -104,7 +95,6 @@ typedef struct HcclRootInfoDef { char internal[HCCL_ROOT_INFO_BYTES]; } HcclRootInfo; -#define HCCL_REQUEST_NULL NULL #ifdef __cplusplus } #endif // __cplusplus diff --git a/inc/external/runtime/rt_error_codes.h b/inc/external/runtime/rt_error_codes.h index a060dfdb..daeca17c 100644 --- a/inc/external/runtime/rt_error_codes.h +++ b/inc/external/runtime/rt_error_codes.h @@ -45,6 +45,7 @@ static const int32_t ACL_ERROR_RT_INVALID_MEMORY_TYPE = 107016; // invalid static const int32_t ACL_ERROR_RT_INVALID_HANDLE = 107017; // invalid handle static const int32_t ACL_ERROR_RT_INVALID_MALLOC_TYPE = 107018; // invalid malloc type static const int32_t ACL_ERROR_RT_WAIT_TIMEOUT = 107019; // wait timeout +static const int32_t ACL_ERROR_RT_TASK_TIMEOUT = 107020; // task timeout static const int32_t ACL_ERROR_RT_FEATURE_NOT_SUPPORT = 207000; // feature not support static const int32_t ACL_ERROR_RT_MEMORY_ALLOCATION = 207001; // memory allocation error diff --git a/inc/framework/common/profiling_definitions.h b/inc/framework/common/profiling_definitions.h index ce4c689b..64532276 100644 --- a/inc/framework/common/profiling_definitions.h +++ b/inc/framework/common/profiling_definitions.h @@ -72,6 +72,14 @@ enum { kSelectBranch, kExecuteSubGraph, kInitSubGraphExecutor, + // fuzz compile + kSelectBin, + kFindCompileCache, + kAddCompileCache, + kFuzzCompileOp, + kCalcRuningParam, + kGenTask, + kRegisterBin, // Add new definitions here kProfilingIndexEnd diff --git a/metadef b/metadef index e0efffc7..22309b14 160000 --- a/metadef +++ b/metadef @@ -1 +1 @@ -Subproject commit e0efffc740a79d49ba0553478b51d9d3481771cb +Subproject commit 22309b14838a763d41dccd636fec567dae3720fd diff --git a/third_party/fwkacllib/inc/hccl/base.h b/third_party/fwkacllib/inc/hccl/base.h index 4dd9e023..8ca4015c 100644 --- a/third_party/fwkacllib/inc/hccl/base.h +++ b/third_party/fwkacllib/inc/hccl/base.h @@ -197,6 +197,20 @@ typedef struct tagCommAttr { WorkMode mode; // ͨڵprobeģʽ uint32_t deviceId = 0; } CommAttr; + +typedef void* HcclMessage; +typedef void* HcclRequest; + +typedef struct { + int srcRank; // /̽⵽msg/ŷķͶrank_idMPI׼壬߿Է + int tag; // /̽⵽msg/ŷtagMPI׼壬߿Է + int error; // /̽Ĵ0no errorothers̳MPI׼壬߿Է + int cancelled; // ָʵ֣߷ + int count; // /̽⵽payloadСָʵ֣߷ +} HcclStatus; + +#define HCCL_REQUEST_NULL NULL + #ifdef __cplusplus } #endif // __cplusplus diff --git a/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h b/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h index 401c4ce6..a214b9da 100644 --- a/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h +++ b/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h @@ -3488,7 +3488,7 @@ REG_OP(Addcmul) REG_OP(AxpyV2) .INPUT(x1, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32})) .INPUT(x2, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32})) - .INPUT(alpha, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(alpha, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32})) .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32})) .OP_END_FACTORY_REG(AxpyV2) diff --git a/third_party/fwkacllib/inc/ops/image_ops.h b/third_party/fwkacllib/inc/ops/image_ops.h index c0ecbaca..3d5d9ab9 100644 --- a/third_party/fwkacllib/inc/ops/image_ops.h +++ b/third_party/fwkacllib/inc/ops/image_ops.h @@ -1737,17 +1737,17 @@ round_prefer_ceil, floor, ceil. Only used by nearest interpolation. */ REG_OP(Resize) - .INPUT(x, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_UINT16, DT_INT32, - DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE})) - .INPUT(roi, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE})) - .INPUT(scales, TensorType({DT_FLOAT})) - .OPTIONAL_INPUT(sizes, TensorType({DT_INT64})) - .OUTPUT(y, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_UINT16, DT_INT32, - DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE})) + .INPUT(x, TensorType({DT_INT8,DT_UINT8,DT_INT16,DT_UINT16,DT_INT32, + DT_INT64,DT_FLOAT16,DT_FLOAT,DT_DOUBLE})) + .OPTIONAL_INPUT(roi, TensorType({DT_FLOAT16,DT_FLOAT,DT_DOUBLE})) + .OPTIONAL_INPUT(scales, TensorType({DT_FLOAT})) + .OPTIONAL_INPUT(sizes, TensorType({DT_INT64,DT_INT32})) + .OUTPUT(y, TensorType({DT_INT8,DT_UINT8,DT_INT16,DT_UINT16,DT_INT32, + DT_INT64,DT_FLOAT16,DT_FLOAT,DT_DOUBLE})) .ATTR(coordinate_transformation_mode, String, "half_pixel") .ATTR(cubic_coeff_a, Float, -0.75) .ATTR(exclude_outside, Int, 0) - .ATTR(extrapolation_value, Float, 0) + .ATTR(extrapolation_value, Float, 0.0) .ATTR(mode, String, "nearest") .ATTR(nearest_mode, String, "round_prefer_floor") .OP_END_FACTORY_REG(Resize) diff --git a/third_party/fwkacllib/inc/ops/nn_norm_ops.h b/third_party/fwkacllib/inc/ops/nn_norm_ops.h index 1cda06eb..1e71c99c 100644 --- a/third_party/fwkacllib/inc/ops/nn_norm_ops.h +++ b/third_party/fwkacllib/inc/ops/nn_norm_ops.h @@ -1801,7 +1801,7 @@ REG_OP(SoftmaxCrossEntropyLoss) * @par Restrictions: * Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. */ -REG_OP(AxpyWithSoftmaxAndDropoutdomask) +REG_OP(AxpyWithSoftmaxAndDropOutDoMask) .INPUT(x1, TensorType({DT_FLOAT16})) .INPUT(x2, TensorType({DT_FLOAT16})) .INPUT(mask, TensorType({DT_UINT8})) @@ -1810,6 +1810,6 @@ REG_OP(AxpyWithSoftmaxAndDropoutdomask) .REQUIRED_ATTR(alpha, Float) .REQUIRED_ATTR(input_keep_prob, Float) .ATTR(axis, ListInt, {-1}) - .OP_END_FACTORY_REG(AxpyWithSoftmaxAndDropoutdomask) + .OP_END_FACTORY_REG(AxpyWithSoftmaxAndDropOutDoMask) } // namespace ge #endif // OPS_BUILT_IN_OP_PROTO_INC_NN_NORM_OPS_H_ diff --git a/third_party/fwkacllib/inc/ops/nn_ops.h b/third_party/fwkacllib/inc/ops/nn_ops.h index 4bfbbd7c..94f2d1ba 100644 --- a/third_party/fwkacllib/inc/ops/nn_ops.h +++ b/third_party/fwkacllib/inc/ops/nn_ops.h @@ -116,6 +116,7 @@ REG_OP(FusedBatchNormV2) * @par Outputs: * One output, including: * output_proposal: A Tensor. Datatype and format is same as input_data. Proposal sorted for each channel. + * @par Restrictions: * Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. */ REG_OP(SegmentSort) @@ -137,6 +138,7 @@ REG_OP(SegmentSort) * Two output, including: * output_proposal: A Tensor. Datatype and format is same as input_data. Proposal sorted for each channel. * output_index: A Tensor.If include_index is true, output index. + * @par Restrictions: * Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. */ REG_OP(MultiMerge) @@ -148,6 +150,27 @@ REG_OP(MultiMerge) .OP_END_FACTORY_REG(MultiMerge) /** + * @brief Large amount of data sort.Third operator of TopK. + * @par Inputs: + * One input, including: + * input_proposal: A Tensor. Proposal sorted for each channel. Support float16 + * @par Attributes: + * k_num: Int.Number to be sorted. + * @par Outputs: + * Two output, including: + * @li output_data: A Tensor. Datatype and format is same as input_data. Data sorted. + * @li output_index: A Tensor. int32. Data index. + * @par Restrictions: + * Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. + */ +REG_OP(SingleMerge) + .INPUT(input_proposal, TensorType({DT_FLOAT16})) + .OUTPUT(output_data, TensorType({DT_FLOAT16})) + .OUTPUT(output_index, TensorType({DT_INT32})) + .REQUIRED_ATTR(k_num, Int) + .OP_END_FACTORY_REG(SingleMerge) + +/** * @brief MultiHeadAttention. * @par Inputs: * thirteen input, including: diff --git a/third_party/fwkacllib/inc/ops/reduce_ops.h b/third_party/fwkacllib/inc/ops/reduce_ops.h index b481bb29..2c4b3059 100644 --- a/third_party/fwkacllib/inc/ops/reduce_ops.h +++ b/third_party/fwkacllib/inc/ops/reduce_ops.h @@ -663,6 +663,9 @@ REG_OP(ReduceProdD) *keep_dims: A bool or NoneType. * - If true, retains reduced dimensions with length 1. * - If false, the rank of the tensor is reduced by 1 for each entry in axis. +*noop_with_empty_axes: A bool. +* - If true, when axes = [], not reduce. +* - If false, when axes = [], reduce all. *@par Outputs: *y: A Tensor. Has the same type as "x" . \n @@ -674,6 +677,7 @@ REG_OP(ReduceMean) .INPUT(axes, TensorType::IndexNumberType()) .OUTPUT(y, TensorType::NumberType()) .ATTR(keep_dims, Bool, false) + .ATTR(noop_with_empty_axes, Bool, true) .OP_END_FACTORY_REG(ReduceMean) /**