m53297601
/
graphengine
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

update header files 0222

Browse Source
pull/1139/head
shenwei41 4 years ago
parent b9050a8c51
commit cc456d5803
22 changed files with 1134 additions and 692 deletions
Show Stats Download Patch File Download Diff File

8
inc/external/acl/acl.h vendored
Unescape View File

@ -26,9 +26,9 @@ extern "C" {
#endif
// Current version is 1.0.0
#define ACL_MAJOR_VERSION 1
#define ACL_MINOR_VERSION 0
#define ACL_PATCH_VERSION 0
#define ACL_MAJOR_VERSION 1
#define ACL_MINOR_VERSION 0
#define ACL_PATCH_VERSION 0
/**
* @ingroup AscendCL
@ -70,4 +70,4 @@ ACL_FUNC_VISIBILITY aclError aclrtGetVersion(int32_t *majorVersion, int32_t *min
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_H_
#endif // INC_EXTERNAL_ACL_ACL_H_

85
inc/external/acl/acl_base.h vendored
Unescape View File

@ -112,6 +112,7 @@ static const int ACL_ERROR_PROF_REPEAT_SUBSCRIBE = 148046;
static const int ACL_ERROR_PROF_API_CONFLICT = 148047;
static const int ACL_ERROR_INVALID_MAX_OPQUEUE_NUM_CONFIG = 148048;
static const int ACL_ERROR_INVALID_OPP_PATH = 148049;
static const int ACL_ERROR_OP_UNSUPPORTED_DYNAMIC = 148050;
static const int ACL_ERROR_BAD_ALLOC = 200000;
static const int ACL_ERROR_API_NOT_SUPPORT = 200001;
@ -135,42 +136,42 @@ static const int ACL_ERROR_PROFILING_FAILURE = 500005;
#define ACL_UNKNOWN_RANK 0xFFFFFFFFFFFFFFFE
typedef enum {
ACL_DT_UNDEFINED = -1,
ACL_FLOAT = 0,
ACL_FLOAT16 = 1,
ACL_INT8 = 2,
ACL_INT32 = 3,
ACL_UINT8 = 4,
ACL_INT16 = 6,
ACL_UINT16 = 7,
ACL_UINT32 = 8,
ACL_INT64 = 9,
ACL_UINT64 = 10,
ACL_DOUBLE = 11,
ACL_BOOL = 12,
ACL_STRING = 13,
ACL_DT_UNDEFINED = -1,
ACL_FLOAT = 0,
ACL_FLOAT16 = 1,
ACL_INT8 = 2,
ACL_INT32 = 3,
ACL_UINT8 = 4,
ACL_INT16 = 6,
ACL_UINT16 = 7,
ACL_UINT32 = 8,
ACL_INT64 = 9,
ACL_UINT64 = 10,
ACL_DOUBLE = 11,
ACL_BOOL = 12,
ACL_STRING = 13,
} aclDataType;
typedef enum {
ACL_FORMAT_UNDEFINED = -1,
ACL_FORMAT_NCHW = 0,
ACL_FORMAT_NHWC = 1,
ACL_FORMAT_ND = 2,
ACL_FORMAT_NC1HWC0 = 3,
ACL_FORMAT_FRACTAL_Z = 4,
ACL_FORMAT_NC1HWC0_C04 = 12,
ACL_FORMAT_NDHWC = 27,
ACL_FORMAT_FRACTAL_NZ = 29,
ACL_FORMAT_NCDHW = 30,
ACL_FORMAT_NDC1HWC0 = 32,
ACL_FRACTAL_Z_3D = 33
ACL_FORMAT_UNDEFINED = -1,
ACL_FORMAT_NCHW = 0,
ACL_FORMAT_NHWC = 1,
ACL_FORMAT_ND = 2,
ACL_FORMAT_NC1HWC0 = 3,
ACL_FORMAT_FRACTAL_Z = 4,
ACL_FORMAT_NC1HWC0_C04 = 12,
ACL_FORMAT_NDHWC = 27,
ACL_FORMAT_FRACTAL_NZ = 29,
ACL_FORMAT_NCDHW = 30,
ACL_FORMAT_NDC1HWC0 = 32,
ACL_FRACTAL_Z_3D = 33
} aclFormat;
typedef enum {
ACL_DEBUG = 0,
ACL_INFO = 1,
ACL_WARNING = 2,
ACL_ERROR = 3,
ACL_DEBUG = 0,
ACL_INFO = 1,
ACL_WARNING = 2,
ACL_ERROR = 3,
} aclLogLevel;
/**
@ -305,7 +306,9 @@ ACL_FUNC_VISIBILITY size_t aclDataTypeSize(aclDataType dataType);
* @retval aclTensorDesc pointer.
* @retval nullptr if param is invalid or run out of memory
*/
ACL_FUNC_VISIBILITY aclTensorDesc *aclCreateTensorDesc(aclDataType dataType, int numDims, const int64_t *dims,
ACL_FUNC_VISIBILITY aclTensorDesc *aclCreateTensorDesc(aclDataType dataType,
int numDims,
const int64_t *dims,
aclFormat format);
/**
@ -327,7 +330,8 @@ ACL_FUNC_VISIBILITY void aclDestroyTensorDesc(const aclTensorDesc *desc);
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclSetTensorShapeRange(aclTensorDesc *desc, size_t dimsCount,
ACL_FUNC_VISIBILITY aclError aclSetTensorShapeRange(aclTensorDesc* desc,
size_t dimsCount,
int64_t dimsRange[][ACL_TENSOR_SHAPE_RANGE_NUM]);
/**
@ -424,7 +428,9 @@ ACL_FUNC_VISIBILITY aclError aclGetTensorDescDimV2(const aclTensorDesc *desc, si
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclGetTensorDescDimRange(const aclTensorDesc *desc, size_t index, size_t dimRangeNum,
ACL_FUNC_VISIBILITY aclError aclGetTensorDescDimRange(const aclTensorDesc *desc,
size_t index,
size_t dimRangeNum,
int64_t *dimRange);
/**
@ -461,7 +467,7 @@ ACL_FUNC_VISIBILITY const char *aclGetTensorDescName(aclTensorDesc *desc);
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclTransTensorDescFormat(const aclTensorDesc *srcDesc, aclFormat dstFormat,
aclTensorDesc **dstDesc);
aclTensorDesc **dstDesc);
/**
* @ingroup AscendCL
@ -549,7 +555,7 @@ ACL_FUNC_VISIBILITY aclError aclSetTensorOriginShape(aclTensorDesc *desc, int nu
*
* @retval null for failed.
* @retval OtherValues success.
*/
*/
ACL_FUNC_VISIBILITY aclTensorDesc *aclGetTensorDescByIndex(aclTensorDesc *desc, size_t index);
/**
@ -560,7 +566,7 @@ ACL_FUNC_VISIBILITY aclTensorDesc *aclGetTensorDescByIndex(aclTensorDesc *desc,
*
* @retval null for failed
* @retval OtherValues success
*/
*/
ACL_FUNC_VISIBILITY void *aclGetTensorDescAddress(const aclTensorDesc *desc);
/**
@ -600,12 +606,13 @@ ACL_FUNC_VISIBILITY aclError aclSetTensorConst(aclTensorDesc *desc, void *dataBu
* @param ... [IN] the value of current log
*/
ACL_FUNC_VISIBILITY void aclAppLog(aclLogLevel logLevel, const char *func, const char *file, uint32_t line,
const char *fmt, ...);
const char *fmt, ...);
#define ACL_APP_LOG(level, fmt, ...) aclAppLog(level, __FUNCTION__, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
#define ACL_APP_LOG(level, fmt, ...) \
aclAppLog(level, __FUNCTION__, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
#ifdef __cplusplus
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_BASE_H_
#endif // INC_EXTERNAL_ACL_ACL_BASE_H_

356
inc/external/acl/acl_mdl.h vendored
View File

File diff suppressed because it is too large Load Diff

119
inc/external/acl/acl_op.h vendored
Unescape View File

@ -33,9 +33,9 @@ typedef void (*aclDataDeallocator)(void *data, size_t length);
static const int ACL_COMPILE_FLAG_BIN_SELECTOR = 1;
typedef enum aclEngineType {
ACL_ENGINE_SYS,
ACL_ENGINE_AICORE,
ACL_ENGINE_VECTOR,
ACL_ENGINE_SYS,
ACL_ENGINE_AICORE,
ACL_ENGINE_VECTOR,
} aclopEngineType;
/**
@ -148,7 +148,7 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrString(aclopAttr *attr, const char *att
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetAttrListBool(aclopAttr *attr, const char *attrName, int numValues,
const uint8_t *values);
const uint8_t *values);
/**
* @ingroup AscendCL
@ -163,7 +163,7 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrListBool(aclopAttr *attr, const char *a
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetAttrListInt(aclopAttr *attr, const char *attrName, int numValues,
const int64_t *values);
const int64_t *values);
/**
* @ingroup AscendCL
@ -178,7 +178,7 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrListInt(aclopAttr *attr, const char *at
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetAttrListFloat(aclopAttr *attr, const char *attrName, int numValues,
const float *values);
const float *values);
/**
* @ingroup AscendCL
@ -193,7 +193,7 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrListFloat(aclopAttr *attr, const char *
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetAttrListString(aclopAttr *attr, const char *attrName, int numValues,
const char **values);
const char **values);
/**
* @ingroup AscendCL
@ -208,8 +208,11 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrListString(aclopAttr *attr, const char
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetAttrListListInt(aclopAttr *attr, const char *attrName, int numLists,
const int *numValues, const int64_t *const values[]);
ACL_FUNC_VISIBILITY aclError aclopSetAttrListListInt(aclopAttr *attr,
const char *attrName,
int numLists,
const int *numValues,
const int64_t *const values[]);
/**
* @ingroup AscendCL
@ -239,10 +242,15 @@ ACL_FUNC_VISIBILITY aclError aclopSetAttrListListInt(aclopAttr *attr, const char
* @retval OtherValues Failure
*/
ACL_DEPRECATED_MESSAGE("aclopExecute is deprecated, use aclopExecuteV2 instead")
ACL_FUNC_VISIBILITY aclError aclopExecute(const char *opType, int numInputs, const aclTensorDesc *const inputDesc[],
const aclDataBuffer *const inputs[], int numOutputs,
const aclTensorDesc *const outputDesc[], aclDataBuffer *const outputs[],
const aclopAttr *attr, aclrtStream stream);
ACL_FUNC_VISIBILITY aclError aclopExecute(const char *opType,
int numInputs,
const aclTensorDesc *const inputDesc[],
const aclDataBuffer *const inputs[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
aclDataBuffer *const outputs[],
const aclopAttr *attr,
aclrtStream stream);
/**
* @ingroup AscendCL
@ -272,9 +280,15 @@ ACL_FUNC_VISIBILITY aclError aclopExecute(const char *opType, int numInputs, con
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopExecuteV2(const char *opType, int numInputs, aclTensorDesc *inputDesc[],
aclDataBuffer *inputs[], int numOutputs, aclTensorDesc *outputDesc[],
aclDataBuffer *outputs[], aclopAttr *attr, aclrtStream stream);
ACL_FUNC_VISIBILITY aclError aclopExecuteV2(const char *opType,
int numInputs,
aclTensorDesc *inputDesc[],
aclDataBuffer *inputs[],
int numOutputs,
aclTensorDesc *outputDesc[],
aclDataBuffer *outputs[],
aclopAttr *attr,
aclrtStream stream);
/**
* @ingroup AscendCL
@ -292,9 +306,12 @@ ACL_FUNC_VISIBILITY aclError aclopExecuteV2(const char *opType, int numInputs, a
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopCreateHandle(const char *opType, int numInputs,
const aclTensorDesc *const inputDesc[], int numOutputs,
const aclTensorDesc *const outputDesc[], const aclopAttr *opAttr,
ACL_FUNC_VISIBILITY aclError aclopCreateHandle(const char *opType,
int numInputs,
const aclTensorDesc *const inputDesc[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
const aclopAttr *opAttr,
aclopHandle **handle);
/**
@ -326,9 +343,12 @@ ACL_FUNC_VISIBILITY void aclopDestroyHandle(aclopHandle *handle);
*
* @see aclopCreateHandle | aclCreateDataBuffer
*/
ACL_FUNC_VISIBILITY aclError aclopExecWithHandle(aclopHandle *handle, int numInputs,
const aclDataBuffer *const inputs[], int numOutputs,
aclDataBuffer *const outputs[], aclrtStream stream);
ACL_FUNC_VISIBILITY aclError aclopExecWithHandle(aclopHandle *handle,
int numInputs,
const aclDataBuffer *const inputs[],
int numOutputs,
aclDataBuffer *const outputs[],
aclrtStream stream);
/**
* @ingroup AscendCL
@ -344,8 +364,11 @@ ACL_FUNC_VISIBILITY aclError aclopExecWithHandle(aclopHandle *handle, int numInp
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopCast(const aclTensorDesc *srcDesc, const aclDataBuffer *srcBuffer,
const aclTensorDesc *dstDesc, aclDataBuffer *dstBuffer, uint8_t truncate,
ACL_FUNC_VISIBILITY aclError aclopCast(const aclTensorDesc *srcDesc,
const aclDataBuffer *srcBuffer,
const aclTensorDesc *dstDesc,
aclDataBuffer *dstBuffer,
uint8_t truncate,
aclrtStream stream);
/**
@ -360,9 +383,12 @@ ACL_FUNC_VISIBILITY aclError aclopCast(const aclTensorDesc *srcDesc, const aclDa
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopCreateHandleForCast(aclTensorDesc *srcDesc, aclTensorDesc *dstDesc, uint8_t truncate,
ACL_FUNC_VISIBILITY aclError aclopCreateHandleForCast(aclTensorDesc *srcDesc,
aclTensorDesc *dstDesc,
uint8_t truncate,
aclopHandle **handle);
/**
* @ingroup AscendCL
* @brief create kernel
@ -381,10 +407,15 @@ ACL_FUNC_VISIBILITY aclError aclopCreateHandleForCast(aclTensorDesc *srcDesc, ac
*
* @see aclopCompile
*/
ACL_FUNC_VISIBILITY aclError aclopCreateKernel(const char *opType, const char *kernelId, const char *kernelName,
void *binData, int binSize, aclopEngineType enginetype,
ACL_FUNC_VISIBILITY aclError aclopCreateKernel(const char *opType,
const char *kernelId,
const char *kernelName,
void *binData,
int binSize,
aclopEngineType enginetype,
aclDataDeallocator deallocator);
/**
* @ingroup AscendCL
* @brief create kernel
@ -399,8 +430,11 @@ ACL_FUNC_VISIBILITY aclError aclopCreateKernel(const char *opType, const char *k
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
typedef aclError (*aclopCompileFunc)(int numInputs, const aclTensorDesc *const inputDesc[], int numOutputs,
const aclTensorDesc *const outputDesc[], const aclopAttr *opAttr,
typedef aclError (*aclopCompileFunc)(int numInputs,
const aclTensorDesc *const inputDesc[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
const aclopAttr *opAttr,
aclopKernelDesc *aclopKernelDesc);
/**
@ -441,8 +475,11 @@ ACL_FUNC_VISIBILITY aclError aclopUnregisterCompileFunc(const char *opType);
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopSetKernelArgs(aclopKernelDesc *kernelDesc, const char *kernelId, uint32_t blockDim,
const void *args, uint32_t argSize);
ACL_FUNC_VISIBILITY aclError aclopSetKernelArgs(aclopKernelDesc *kernelDesc,
const char *kernelId,
uint32_t blockDim,
const void *args,
uint32_t argSize);
/**
* @ingroup AscendCL
@ -473,9 +510,12 @@ ACL_FUNC_VISIBILITY aclError aclopSetKernelWorkspaceSizes(aclopKernelDesc *kerne
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopUpdateParams(const char *opType, int numInputs,
const aclTensorDesc *const inputDesc[], int numOutputs,
const aclTensorDesc *const outputDesc[], const aclopAttr *attr);
ACL_FUNC_VISIBILITY aclError aclopUpdateParams(const char *opType,
int numInputs,
const aclTensorDesc *const inputDesc[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
const aclopAttr *attr);
/**
* @ingroup AscendCL
@ -493,12 +533,17 @@ ACL_FUNC_VISIBILITY aclError aclopUpdateParams(const char *opType, int numInputs
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopInferShape(const char *opType, int numInputs, aclTensorDesc *inputDesc[],
aclDataBuffer *inputs[], int numOutputs, aclTensorDesc *outputDesc[],
ACL_FUNC_VISIBILITY aclError aclopInferShape(const char *opType,
int numInputs,
aclTensorDesc *inputDesc[],
aclDataBuffer *inputs[],
int numOutputs,
aclTensorDesc *outputDesc[],
aclopAttr *attr);
#ifdef __cplusplus
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_OP_H_
#endif // INC_EXTERNAL_ACL_ACL_OP_H_

47
inc/external/acl/acl_op_compiler.h vendored
Unescape View File

@ -24,18 +24,21 @@
extern "C" {
#endif
typedef enum aclCompileType { ACL_COMPILE_SYS, ACL_COMPILE_UNREGISTERED } aclopCompileType;
typedef enum aclCompileType {
ACL_COMPILE_SYS,
ACL_COMPILE_UNREGISTERED
} aclopCompileType;
typedef enum {
ACL_PRECISION_MODE,
ACL_AICORE_NUM,
ACL_AUTO_TUNE_MODE,
ACL_OP_SELECT_IMPL_MODE,
ACL_OPTYPELIST_FOR_IMPLMODE,
ACL_OP_DEBUG_LEVEL,
ACL_DEBUG_DIR,
ACL_OP_COMPILER_CACHE_MODE,
ACL_OP_COMPILER_CACHE_DIR
ACL_PRECISION_MODE,
ACL_AICORE_NUM,
ACL_AUTO_TUNE_MODE,
ACL_OP_SELECT_IMPL_MODE,
ACL_OPTYPELIST_FOR_IMPLMODE,
ACL_OP_DEBUG_LEVEL,
ACL_DEBUG_DIR,
ACL_OP_COMPILER_CACHE_MODE,
ACL_OP_COMPILER_CACHE_DIR
} aclCompileOpt;
/**
@ -56,10 +59,15 @@ typedef enum {
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopCompile(const char *opType, int numInputs, const aclTensorDesc *const inputDesc[],
int numOutputs, const aclTensorDesc *const outputDesc[],
const aclopAttr *attr, aclopEngineType engineType,
aclopCompileType compileFlag, const char *opPath);
ACL_FUNC_VISIBILITY aclError aclopCompile(const char *opType,
int numInputs,
const aclTensorDesc *const inputDesc[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
const aclopAttr *attr,
aclopEngineType engineType,
aclopCompileType compileFlag,
const char *opPath);
/**
* @ingroup AscendCL
@ -82,10 +90,11 @@ ACL_FUNC_VISIBILITY aclError aclopCompile(const char *opType, int numInputs, con
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclopCompileAndExecute(
const char *opType, int numInputs, const aclTensorDesc *const inputDesc[], const aclDataBuffer *const inputs[],
int numOutputs, const aclTensorDesc *const outputDesc[], aclDataBuffer *const outputs[], const aclopAttr *attr,
aclopEngineType engineType, aclopCompileType compileFlag, const char *opPath, aclrtStream stream);
ACL_FUNC_VISIBILITY aclError aclopCompileAndExecute(const char *opType,
int numInputs, const aclTensorDesc *const inputDesc[], const aclDataBuffer *const inputs[],
int numOutputs, const aclTensorDesc *const outputDesc[], aclDataBuffer *const outputs[],
const aclopAttr *attr, aclopEngineType engineType, aclopCompileType compileFlag,
const char *opPath, aclrtStream stream);
/**
* @ingroup AscendCL
@ -103,4 +112,4 @@ ACL_FUNC_VISIBILITY aclError aclSetCompileopt(aclCompileOpt opt, const char *val
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_OP_COMPILER_H_
#endif // INC_EXTERNAL_ACL_ACL_OP_COMPILER_H_

75
inc/external/acl/acl_prof.h vendored
Unescape View File

@ -23,21 +23,24 @@
extern "C" {
#endif
#define ACL_PROF_ACL_API 0x0001
#define ACL_PROF_TASK_TIME 0x0002
#define ACL_PROF_AICORE_METRICS 0x0004
#define ACL_PROF_AICPU 0x0008
#define ACL_PROF_ACL_API 0x0001
#define ACL_PROF_TASK_TIME 0x0002
#define ACL_PROF_AICORE_METRICS 0x0004
#define ACL_PROF_AICPU 0x0008
#define ACL_PROF_MAX_OP_NAME_LEN 257
#define ACL_PROF_MAX_OP_TYPE_LEN 65
/**
* @deprecated please use aclprofGetOpTypeLen and aclprofGetOpTNameLen instead
*/
#define ACL_PROF_MAX_OP_NAME_LEN 257
#define ACL_PROF_MAX_OP_TYPE_LEN 65
typedef enum {
ACL_AICORE_ARITHMETIC_UTILIZATION = 0,
ACL_AICORE_PIPE_UTILIZATION = 1,
ACL_AICORE_MEMORY_BANDWIDTH = 2,
ACL_AICORE_L0B_AND_WIDTH = 3,
ACL_AICORE_RESOURCE_CONFLICT_RATIO = 4,
ACL_AICORE_NONE = 0xFF
ACL_AICORE_ARITHMETIC_UTILIZATION = 0,
ACL_AICORE_PIPE_UTILIZATION = 1,
ACL_AICORE_MEMORY_BANDWIDTH = 2,
ACL_AICORE_L0B_AND_WIDTH = 3,
ACL_AICORE_RESOURCE_CONFLICT_RATIO = 4,
ACL_AICORE_NONE = 0xFF
} aclprofAicoreMetrics;
typedef struct aclprofConfig aclprofConfig;
@ -98,8 +101,7 @@ ACL_FUNC_VISIBILITY aclError aclprofStart(const aclprofConfig *profilerConfig);
* @see aclprofDestroyConfig
*/
ACL_FUNC_VISIBILITY aclprofConfig *aclprofCreateConfig(uint32_t *deviceIdList, uint32_t deviceNums,
aclprofAicoreMetrics aicoreMetrics,
aclprofAicoreEvents *aicoreEvents, uint64_t dataTypeConfig);
aclprofAicoreMetrics aicoreMetrics, aclprofAicoreEvents *aicoreEvents, uint64_t dataTypeConfig);
/**
* @ingroup AscendCL
@ -139,7 +141,8 @@ ACL_FUNC_VISIBILITY aclError aclprofStop(const aclprofConfig *profilerConfig);
*
* @see aclprofModelUnSubscribe
*/
ACL_FUNC_VISIBILITY aclError aclprofModelSubscribe(uint32_t modelId, const aclprofSubscribeConfig *profSubscribeConfig);
ACL_FUNC_VISIBILITY aclError aclprofModelSubscribe(uint32_t modelId,
const aclprofSubscribeConfig *profSubscribeConfig);
/**
* @ingroup AscendCL
@ -167,7 +170,7 @@ ACL_FUNC_VISIBILITY aclError aclprofModelUnSubscribe(uint32_t modelId);
* @see aclprofDestroySubscribeConfig
*/
ACL_FUNC_VISIBILITY aclprofSubscribeConfig *aclprofCreateSubscribeConfig(int8_t timeInfoSwitch,
aclprofAicoreMetrics aicoreMetrics, void *fd);
aclprofAicoreMetrics aicoreMetrics, void *fd);
/**
* @ingroup AscendCL
@ -206,6 +209,21 @@ ACL_FUNC_VISIBILITY aclError aclprofGetOpDescSize(size_t *opDescSize);
*/
ACL_FUNC_VISIBILITY aclError aclprofGetOpNum(const void *opInfo, size_t opInfoLen, uint32_t *opNumber);
/**
* @ingroup AscendCL
* @brief get length op type from subscription data
*
* @param opInfo [IN] pointer to subscription data
* @param opInfoLen [IN] memory size of subscription data
* @param index [IN] index of op array in opInfo
* @param opTypeLen [OUT] actual length of op type string
*
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclprofGetOpTypeLen(const void *opInfo, size_t opInfoLen, uint32_t index,
size_t *opTypeLen);
/**
* @ingroup AscendCL
* @brief get op type from subscription data
@ -219,8 +237,23 @@ ACL_FUNC_VISIBILITY aclError aclprofGetOpNum(const void *opInfo, size_t opInfoLe
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclprofGetOpType(const void *opInfo, size_t opInfoLen, uint32_t index, char *opType,
size_t opTypeLen);
ACL_FUNC_VISIBILITY aclError aclprofGetOpType(const void *opInfo, size_t opInfoLen, uint32_t index,
char *opType, size_t opTypeLen);
/**
* @ingroup AscendCL
* @brief get length op name from subscription data
*
* @param opInfo [IN] pointer to subscription data
* @param opInfoLen [IN] memory size of subscription data
* @param index [IN] index of op array in opInfo
* @param opNameLen [OUT] actual length of op name string
*
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclprofGetOpNameLen(const void *opInfo, size_t opInfoLen, uint32_t index,
size_t *opNameLen);
/**
* @ingroup AscendCL
@ -235,8 +268,8 @@ ACL_FUNC_VISIBILITY aclError aclprofGetOpType(const void *opInfo, size_t opInfoL
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclprofGetOpName(const void *opInfo, size_t opInfoLen, uint32_t index, char *opName,
size_t opNameLen);
ACL_FUNC_VISIBILITY aclError aclprofGetOpName(const void *opInfo, size_t opInfoLen, uint32_t index,
char *opName, size_t opNameLen);
/**
* @ingroup AscendCL
@ -293,4 +326,4 @@ ACL_FUNC_VISIBILITY size_t aclprofGetModelId(const void *opInfo, size_t opInfoLe
}
#endif
#endif // INC_EXTERNAL_ACL_PROF_H_
#endif // INC_EXTERNAL_ACL_PROF_H_

143
inc/external/acl/acl_rt.h vendored
Unescape View File

@ -26,62 +26,63 @@ extern "C" {
#endif
typedef enum aclrtRunMode {
ACL_DEVICE,
ACL_HOST,
ACL_DEVICE,
ACL_HOST,
} aclrtRunMode;
typedef enum aclrtTsId {
ACL_TS_ID_AICORE = 0,
ACL_TS_ID_AIVECTOR = 1,
ACL_TS_ID_RESERVED = 2,
ACL_TS_ID_AICORE = 0,
ACL_TS_ID_AIVECTOR = 1,
ACL_TS_ID_RESERVED = 2,
} aclrtTsId;
typedef enum aclrtEventStatus {
ACL_EVENT_STATUS_COMPLETE = 0,
ACL_EVENT_STATUS_NOT_READY = 1,
ACL_EVENT_STATUS_RESERVED = 2,
ACL_EVENT_STATUS_COMPLETE = 0,
ACL_EVENT_STATUS_NOT_READY = 1,
ACL_EVENT_STATUS_RESERVED = 2,
} aclrtEventStatus;
typedef enum aclrtCallbackBlockType {
ACL_CALLBACK_NO_BLOCK,
ACL_CALLBACK_BLOCK,
ACL_CALLBACK_NO_BLOCK,
ACL_CALLBACK_BLOCK,
} aclrtCallbackBlockType;
typedef enum aclrtMemcpyKind {
ACL_MEMCPY_HOST_TO_HOST,
ACL_MEMCPY_HOST_TO_DEVICE,
ACL_MEMCPY_DEVICE_TO_HOST,
ACL_MEMCPY_DEVICE_TO_DEVICE,
ACL_MEMCPY_HOST_TO_HOST,
ACL_MEMCPY_HOST_TO_DEVICE,
ACL_MEMCPY_DEVICE_TO_HOST,
ACL_MEMCPY_DEVICE_TO_DEVICE,
} aclrtMemcpyKind;
typedef enum aclrtMemMallocPolicy {
ACL_MEM_MALLOC_HUGE_FIRST,
ACL_MEM_MALLOC_HUGE_ONLY,
ACL_MEM_MALLOC_NORMAL_ONLY,
ACL_MEM_MALLOC_HUGE_FIRST_P2P,
ACL_MEM_MALLOC_HUGE_ONLY_P2P,
ACL_MEM_MALLOC_NORMAL_ONLY_P2P,
ACL_MEM_MALLOC_HUGE_FIRST,
ACL_MEM_MALLOC_HUGE_ONLY,
ACL_MEM_MALLOC_NORMAL_ONLY,
ACL_MEM_MALLOC_HUGE_FIRST_P2P,
ACL_MEM_MALLOC_HUGE_ONLY_P2P,
ACL_MEM_MALLOC_NORMAL_ONLY_P2P,
} aclrtMemMallocPolicy;
typedef enum aclrtMemAttr {
ACL_DDR_MEM,
ACL_HBM_MEM,
ACL_DDR_MEM_HUGE,
ACL_DDR_MEM_NORMAL,
ACL_HBM_MEM_HUGE,
ACL_HBM_MEM_NORMAL,
ACL_DDR_MEM_P2P_HUGE,
ACL_DDR_MEM_P2P_NORMAL,
ACL_HBM_MEM_P2P_HUGE,
ACL_HBM_MEM_P2P_NORMAL,
ACL_DDR_MEM,
ACL_HBM_MEM,
ACL_DDR_MEM_HUGE,
ACL_DDR_MEM_NORMAL,
ACL_HBM_MEM_HUGE,
ACL_HBM_MEM_NORMAL,
ACL_DDR_MEM_P2P_HUGE,
ACL_DDR_MEM_P2P_NORMAL,
ACL_HBM_MEM_P2P_HUGE,
ACL_HBM_MEM_P2P_NORMAL,
} aclrtMemAttr;
typedef enum aclrtGroupAttr {
ACL_GROUP_AICORE_INT,
ACL_GROUP_AIV_INT,
ACL_GROUP_AIC_INT,
ACL_GROUP_SDMANUM_INT,
ACL_GROUP_ASQNUM_INT
ACL_GROUP_AICORE_INT,
ACL_GROUP_AIV_INT,
ACL_GROUP_AIC_INT,
ACL_GROUP_SDMANUM_INT,
ACL_GROUP_ASQNUM_INT,
ACL_GROUP_GROUPID_INT
} aclrtGroupAttr;
typedef struct tagRtGroupInfo aclrtGroupInfo;
@ -472,7 +473,7 @@ ACL_FUNC_VISIBILITY aclError aclrtRecordEvent(aclrtEvent event, aclrtStream stre
*/
ACL_FUNC_VISIBILITY aclError aclrtResetEvent(aclrtEvent event, aclrtStream stream);
/**
/**
* @ingroup AscendCL
* @brief Queries an event's status
*
@ -534,7 +535,9 @@ ACL_FUNC_VISIBILITY aclError aclrtEventElapsedTime(float *ms, aclrtEvent start,
*
* @see aclrtFree | acldvppMalloc | aclrtMallocCached
*/
ACL_FUNC_VISIBILITY aclError aclrtMalloc(void **devPtr, size_t size, aclrtMemMallocPolicy policy);
ACL_FUNC_VISIBILITY aclError aclrtMalloc(void **devPtr,
size_t size,
aclrtMemMallocPolicy policy);
/**
* @ingroup AscendCL
@ -557,7 +560,9 @@ ACL_FUNC_VISIBILITY aclError aclrtMalloc(void **devPtr, size_t size, aclrtMemMal
*
* @see aclrtFree | aclrtMalloc
*/
ACL_FUNC_VISIBILITY aclError aclrtMallocCached(void **devPtr, size_t size, aclrtMemMallocPolicy policy);
ACL_FUNC_VISIBILITY aclError aclrtMallocCached(void **devPtr,
size_t size,
aclrtMemMallocPolicy policy);
/**
* @ingroup AscendCL
@ -648,7 +653,10 @@ ACL_FUNC_VISIBILITY aclError aclrtFreeHost(void *hostPtr);
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*/
ACL_FUNC_VISIBILITY aclError aclrtMemcpy(void *dst, size_t destMax, const void *src, size_t count,
ACL_FUNC_VISIBILITY aclError aclrtMemcpy(void *dst,
size_t destMax,
const void *src,
size_t count,
aclrtMemcpyKind kind);
/**
@ -695,31 +703,38 @@ ACL_FUNC_VISIBILITY aclError aclrtMemset(void *devPtr, size_t maxCount, int32_t
*
* @see aclrtSynchronizeStream
*/
ACL_FUNC_VISIBILITY aclError aclrtMemcpyAsync(void *dst, size_t destMax, const void *src, size_t count,
aclrtMemcpyKind kind, aclrtStream stream);
ACL_FUNC_VISIBILITY aclError aclrtMemcpyAsync(void *dst,
size_t destMax,
const void *src,
size_t count,
aclrtMemcpyKind kind,
aclrtStream stream);
/**
* @ingroup AscendCL
* @brief Asynchronous initialize memory
* and set contents of memory to specified value async
*
* @par Function
* @ingroup AscendCL
* @brief Asynchronous initialize memory
* and set contents of memory to specified value async
*
* @par Function
* The memory to be initialized is on the Host or device side,
* and the system determines whether
* it is host or device according to the address
*
* @param devPtr [IN] destination address pointer
* @param maxCount [IN] Max length of destination address memory
* @param value [IN] set value
* @param count [IN] the number of byte to set
* @param stream [IN] asynchronized task stream
*
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*
* @see aclrtSynchronizeStream
*/
ACL_FUNC_VISIBILITY aclError aclrtMemsetAsync(void *devPtr, size_t maxCount, int32_t value, size_t count,
* @param devPtr [IN] destination address pointer
* @param maxCount [IN] Max length of destination address memory
* @param value [IN] set value
* @param count [IN] the number of byte to set
* @param stream [IN] asynchronized task stream
*
* @retval ACL_SUCCESS The function is successfully executed.
* @retval OtherValues Failure
*
* @see aclrtSynchronizeStream
*/
ACL_FUNC_VISIBILITY aclError aclrtMemsetAsync(void *devPtr,
size_t maxCount,
int32_t value,
size_t count,
aclrtStream stream);
/**
@ -854,7 +869,7 @@ ACL_FUNC_VISIBILITY aclError aclrtGetAllGroupInfo(aclrtGroupInfo *groupInfo);
* @brief get detail information of group
*
* @param groupInfo [IN] pointer to group information
* @param groupId [IN] group index value
* @param groupIndex [IN] group index value
* @param attr [IN] group attribute
* @param attrValue [OUT] pointer to attribute value
* @param valueLen [IN] length of attribute value
@ -865,8 +880,11 @@ ACL_FUNC_VISIBILITY aclError aclrtGetAllGroupInfo(aclrtGroupInfo *groupInfo);
*
* @see aclrtGetGroupCount | aclrtGetAllGroupInfo
*/
ACL_FUNC_VISIBILITY aclError aclrtGetGroupInfoDetail(const aclrtGroupInfo *groupInfo, int32_t groupId,
aclrtGroupAttr attr, void *attrValue, size_t valueLen,
ACL_FUNC_VISIBILITY aclError aclrtGetGroupInfoDetail(const aclrtGroupInfo *groupInfo,
int32_t groupIndex,
aclrtGroupAttr attr,
void *attrValue,
size_t valueLen,
size_t *paramRetSize);
/**
@ -929,4 +947,5 @@ ACL_FUNC_VISIBILITY aclError aclrtGetMemInfo(aclrtMemAttr attr, size_t *free, si
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_RT_H_
#endif // INC_EXTERNAL_ACL_ACL_RT_H_

31
inc/external/acl/acl_tdt.h vendored
Unescape View File

@ -24,10 +24,10 @@ extern "C" {
#endif
enum acltdtTensorType {
ACL_TENSOR_DATA_UNDEFINED = -1,
ACL_TENSOR_DATA_TENSOR,
ACL_TENSOR_DATA_END_OF_SEQUENCE,
ACL_TENSOR_DATA_ABNORMAL
ACL_TENSOR_DATA_UNDEFINED = -1,
ACL_TENSOR_DATA_TENSOR,
ACL_TENSOR_DATA_END_OF_SEQUENCE,
ACL_TENSOR_DATA_ABNORMAL
};
typedef struct acltdtDataItem acltdtDataItem;
@ -64,7 +64,7 @@ ACL_FUNC_VISIBILITY aclDataType acltdtGetDataTypeFromItem(const acltdtDataItem *
*
* @retval null for failed
* @retval OtherValues success
*/
*/
ACL_FUNC_VISIBILITY void *acltdtGetDataAddrFromItem(const acltdtDataItem *dataItem);
/**
@ -75,7 +75,7 @@ ACL_FUNC_VISIBILITY void *acltdtGetDataAddrFromItem(const acltdtDataItem *dataIt
*
* @retval 0 for failed
* @retval OtherValues success
*/
*/
ACL_FUNC_VISIBILITY size_t acltdtGetDataSizeFromItem(const acltdtDataItem *dataItem);
/**
@ -86,7 +86,7 @@ ACL_FUNC_VISIBILITY size_t acltdtGetDataSizeFromItem(const acltdtDataItem *dataI
*
* @retval 0 for failed
* @retval OtherValues success
*/
*/
ACL_FUNC_VISIBILITY size_t acltdtGetDimNumFromItem(const acltdtDataItem *dataItem);
/**
@ -118,8 +118,12 @@ ACL_FUNC_VISIBILITY aclError acltdtGetDimsFromItem(const acltdtDataItem *dataIte
*
* @see acltdtDestroyDataItem
*/
ACL_FUNC_VISIBILITY acltdtDataItem *acltdtCreateDataItem(acltdtTensorType tdtType, const int64_t *dims, size_t dimNum,
aclDataType dataType, void *data, size_t size);
ACL_FUNC_VISIBILITY acltdtDataItem *acltdtCreateDataItem(acltdtTensorType tdtType,
const int64_t *dims,
size_t dimNum,
aclDataType dataType,
void *data,
size_t size);
/**
* @ingroup AscendCL
@ -250,7 +254,8 @@ ACL_FUNC_VISIBILITY aclError acltdtDestroyChannel(acltdtChannelHandle *handle);
*
* @see acltdtReceiveTensor
*/
ACL_FUNC_VISIBILITY aclError acltdtSendTensor(const acltdtChannelHandle *handle, const acltdtDataset *dataset,
ACL_FUNC_VISIBILITY aclError acltdtSendTensor(const acltdtChannelHandle *handle,
const acltdtDataset *dataset,
int32_t timeout);
/**
@ -266,11 +271,13 @@ ACL_FUNC_VISIBILITY aclError acltdtSendTensor(const acltdtChannelHandle *handle,
*
* @see acltdtSendTensor
*/
ACL_FUNC_VISIBILITY aclError acltdtReceiveTensor(const acltdtChannelHandle *handle, acltdtDataset *dataset,
ACL_FUNC_VISIBILITY aclError acltdtReceiveTensor(const acltdtChannelHandle *handle,
acltdtDataset *dataset,
int32_t timeout);
#ifdef __cplusplus
}
#endif
#endif // INC_EXTERNAL_ACL_ACL_TDT_H_
#endif //INC_EXTERNAL_ACL_ACL_TDT_H_

136
inc/external/acl/error_codes/rt_error_codes.h vendored
Unescape View File

@ -23,80 +23,80 @@
extern "C" {
#endif
static const int32_t ACL_RT_SUCCESS = 0; // success
static const int32_t ACL_RT_SUCCESS = 0; // success
static const int32_t ACL_ERROR_RT_PARAM_INVALID = 107000; // param invalid
static const int32_t ACL_ERROR_RT_INVALID_DEVICEID = 107001; // invalid device id
static const int32_t ACL_ERROR_RT_CONTEXT_NULL = 107002; // current context null
static const int32_t ACL_ERROR_RT_STREAM_CONTEXT = 107003; // stream not in current context
static const int32_t ACL_ERROR_RT_MODEL_CONTEXT = 107004; // model not in current context
static const int32_t ACL_ERROR_RT_STREAM_MODEL = 107005; // stream not in model
static const int32_t ACL_ERROR_RT_EVENT_TIMESTAMP_INVALID = 107006; // event timestamp invalid
static const int32_t ACL_ERROR_RT_EVENT_TIMESTAMP_REVERSAL = 107007; // event timestamp reversal
static const int32_t ACL_ERROR_RT_ADDR_UNALIGNED = 107008; // memory address unaligned
static const int32_t ACL_ERROR_RT_FILE_OPEN = 107009; // open file failed
static const int32_t ACL_ERROR_RT_FILE_WRITE = 107010; // write file failed
static const int32_t ACL_ERROR_RT_STREAM_SUBSCRIBE = 107011; // error subscribe stream
static const int32_t ACL_ERROR_RT_THREAD_SUBSCRIBE = 107012; // error subscribe thread
static const int32_t ACL_ERROR_RT_GROUP_NOT_SET = 107013; // group not set
static const int32_t ACL_ERROR_RT_GROUP_NOT_CREATE = 107014; // group not create
static const int32_t ACL_ERROR_RT_STREAM_NO_CB_REG = 107015; // callback not register to stream
static const int32_t ACL_ERROR_RT_INVALID_MEMORY_TYPE = 107016; // invalid memory type
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_PARAM_INVALID = 107000; // param invalid
static const int32_t ACL_ERROR_RT_INVALID_DEVICEID = 107001; // invalid device id
static const int32_t ACL_ERROR_RT_CONTEXT_NULL = 107002; // current context null
static const int32_t ACL_ERROR_RT_STREAM_CONTEXT = 107003; // stream not in current context
static const int32_t ACL_ERROR_RT_MODEL_CONTEXT = 107004; // model not in current context
static const int32_t ACL_ERROR_RT_STREAM_MODEL = 107005; // stream not in model
static const int32_t ACL_ERROR_RT_EVENT_TIMESTAMP_INVALID = 107006; // event timestamp invalid
static const int32_t ACL_ERROR_RT_EVENT_TIMESTAMP_REVERSAL = 107007; // event timestamp reversal
static const int32_t ACL_ERROR_RT_ADDR_UNALIGNED = 107008; // memory address unaligned
static const int32_t ACL_ERROR_RT_FILE_OPEN = 107009; // open file failed
static const int32_t ACL_ERROR_RT_FILE_WRITE = 107010; // write file failed
static const int32_t ACL_ERROR_RT_STREAM_SUBSCRIBE = 107011; // error subscribe stream
static const int32_t ACL_ERROR_RT_THREAD_SUBSCRIBE = 107012; // error subscribe thread
static const int32_t ACL_ERROR_RT_GROUP_NOT_SET = 107013; // group not set
static const int32_t ACL_ERROR_RT_GROUP_NOT_CREATE = 107014; // group not create
static const int32_t ACL_ERROR_RT_STREAM_NO_CB_REG = 107015; // callback not register to stream
static const int32_t ACL_ERROR_RT_INVALID_MEMORY_TYPE = 107016; // invalid memory type
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_FEATURE_NOT_SUPPORT = 207000; // feature not support
static const int32_t ACL_ERROR_RT_MEMORY_ALLOCATION = 207001; // memory allocation error
static const int32_t ACL_ERROR_RT_MEMORY_FREE = 207002; // memory free error
static const int32_t ACL_ERROR_RT_AICORE_OVER_FLOW = 207003; // aicore over flow
static const int32_t ACL_ERROR_RT_NO_DEVICE = 207004; // no device
static const int32_t ACL_ERROR_RT_RESOURCE_ALLOC_FAIL = 207005; // resource alloc fail
static const int32_t ACL_ERROR_RT_NO_PERMISSION = 207006; // no permission
static const int32_t ACL_ERROR_RT_NO_EVENT_RESOURCE = 207007; // no event resource
static const int32_t ACL_ERROR_RT_NO_STREAM_RESOURCE = 207008; // no stream resource
static const int32_t ACL_ERROR_RT_NO_NOTIFY_RESOURCE = 207009; // no notify resource
static const int32_t ACL_ERROR_RT_NO_MODEL_RESOURCE = 207010; // no model resource
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
static const int32_t ACL_ERROR_RT_MEMORY_FREE = 207002; // memory free error
static const int32_t ACL_ERROR_RT_AICORE_OVER_FLOW = 207003; // aicore over flow
static const int32_t ACL_ERROR_RT_NO_DEVICE = 207004; // no device
static const int32_t ACL_ERROR_RT_RESOURCE_ALLOC_FAIL = 207005; // resource alloc fail
static const int32_t ACL_ERROR_RT_NO_PERMISSION = 207006; // no permission
static const int32_t ACL_ERROR_RT_NO_EVENT_RESOURCE = 207007; // no event resource
static const int32_t ACL_ERROR_RT_NO_STREAM_RESOURCE = 207008; // no stream resource
static const int32_t ACL_ERROR_RT_NO_NOTIFY_RESOURCE = 207009; // no notify resource
static const int32_t ACL_ERROR_RT_NO_MODEL_RESOURCE = 207010; // no model resource
static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error
static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error
static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream
static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream
static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete
static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence
static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete
static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error
static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error
static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support
static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat
static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed
static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout
static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error
static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout
static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception
static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception
static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout
static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception
static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error
static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error
static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error
static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error
static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal
static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering
static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init
static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data
static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error
static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate
static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed
static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed
static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context
static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out
static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error
static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error
static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error
static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream
static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream
static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete
static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence
static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete
static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error
static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error
static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support
static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat
static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed
static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout
static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error
static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout
static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception
static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception
static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout
static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception
static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error
static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error
static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error
static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error
static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal
static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering
static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init
static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data
static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error
static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate
static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed
static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed
static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context
static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out
static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error
static const int32_t ACL_ERROR_RT_DRV_INTERNAL_ERROR = 507899; // drv internal error
static const int32_t ACL_ERROR_RT_AICPU_INTERNAL_ERROR = 507900; // aicpu internal error
static const int32_t ACL_ERROR_RT_DRV_INTERNAL_ERROR = 507899; // drv internal error
static const int32_t ACL_ERROR_RT_AICPU_INTERNAL_ERROR = 507900; // aicpu internal error
#ifdef __cplusplus
}
#endif
#endif // __INC_EXTERNEL_RT_ERROR_CODES_H__
#endif // __INC_EXTERNEL_RT_ERROR_CODES_H__

179
inc/external/acl/ops/acl_cblas.h vendored
View File

File diff suppressed because it is too large Load Diff

369
inc/external/acl/ops/acl_dvpp.h vendored
View File

File diff suppressed because it is too large Load Diff

14
inc/external/acl/ops/acl_fv.h vendored
Unescape View File

@ -32,8 +32,8 @@ typedef struct aclfvSearchResult aclfvSearchResult;
// search operation type
enum aclfvSearchType {
SEARCH_1_N, // 1:N operation type
SEARCH_N_M // N:M operation type
SEARCH_1_N, // 1:N operation type
SEARCH_N_M // N:M operation type
};
/**
@ -104,8 +104,7 @@ ACL_FUNC_VISIBILITY aclError aclfvSetNMTopNum(aclfvInitPara *initPara, uint32_t
* @retval OtherValues success.
*/
ACL_FUNC_VISIBILITY aclfvFeatureInfo *aclfvCreateFeatureInfo(uint32_t id0, uint32_t id1, uint32_t offset,
uint32_t featureLen, uint32_t featureCount,
uint8_t *featureData, uint32_t featureDataLen);
uint32_t featureLen, uint32_t featureCount, uint8_t *featureData, uint32_t featureDataLen);
/**
* @ingroup AscendCL
@ -234,9 +233,8 @@ ACL_FUNC_VISIBILITY aclError aclfvDestroySearchInput(aclfvSearchInput *searchInp
* @retval null for failed. OtherValues success
*/
ACL_FUNC_VISIBILITY aclfvSearchResult *aclfvCreateSearchResult(uint32_t queryCnt, uint32_t *resultNum,
uint32_t resultNumDataLen, uint32_t *id0, uint32_t *id1,
uint32_t *resultOffset, float *resultDistance,
uint32_t dataLen);
uint32_t resultNumDataLen, uint32_t *id0, uint32_t *id1, uint32_t *resultOffset, float *resultDistance,
uint32_t dataLen);
/**
* @ingroup AscendCL
@ -350,4 +348,4 @@ ACL_FUNC_VISIBILITY aclError aclfvSearch(aclfvSearchType type, aclfvSearchInput
}
#endif
#endif // INC_EXTERNAL_ACL_OPS_ACL_RETR_H_
#endif // INC_EXTERNAL_ACL_OPS_ACL_RETR_H_

97
third_party/fwkacllib/inc/ops/elewise_calculation_ops.h vendored
Unescape View File

@ -32,6 +32,9 @@ namespace ge {
* float16, float32, double, int32, uint8, int16, int8, complex64, int64,
* qint8, quint8, qint32, uint16, complex128, uint32, uint64. It's a dynamic input. \n
*@par Attributes:
*N: An required attribute of type int32, means nums of inputs. \n
*@par Outputs:
*y: A Tensor. Has the same shape and type as the elements of "x". \n
@ -3559,26 +3562,6 @@ REG_OP(MaxN)
.OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_FLOAT64, DT_INT32, DT_INT64}))
.OP_END_FACTORY_REG(MaxN)
/**
* @brief Element-wise min of each of the input tensors (with Numpy-style broadcasting support).
* All inputs and outputs must have the same data type. This operator supports multidirectional
* (i.e., Numpy-style) broadcasting
*
* @par inputs
* one input including:
* @li x: dynamic input A Tensor. Must be one of the following types: float32, float16, double, int32, int64
*
* @par output
* one output including:
* @li y:A Tensor of the same type as x
*
*/
REG_OP(MinN)
.DYNAMIC_INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_FLOAT64,
DT_INT32, DT_INT64}))
.OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_FLOAT64,
DT_INT32, DT_INT64}))
.OP_END_FACTORY_REG(MinN)
/**
* @brief Calculates x * maske * value.
@ -3640,8 +3623,7 @@ REG_OP(Lerp)
* rtol: Defaults to "1e-03".
*
*@par Outputs:
* num: A tensor of type int32.
* diff: A tensor of type float16.
* num: A tensor of type float32.
*
*@par Restrictions:
*Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use.
@ -3651,7 +3633,6 @@ REG_OP(DataCompare)
.INPUT(x1, TensorType({ DT_FLOAT16, DT_FLOAT,DT_INT8, DT_UINT8, DT_INT32 }))
.INPUT(x2, TensorType({ DT_FLOAT16, DT_FLOAT,DT_INT8, DT_UINT8, DT_INT32 }))
.OUTPUT(num, TensorType({DT_FLOAT}))
.OUTPUT(diff, TensorType({DT_FLOAT16}))
.ATTR(atol, Float, 1e-5)
.ATTR(rtol, Float, 1e-3)
.OP_END_FACTORY_REG(DataCompare)
@ -3730,6 +3711,76 @@ REG_OP(IsClose)
.ATTR(equal_nan, Bool, false)
.OP_END_FACTORY_REG(IsClose)
/**
* @brief Returns the reverse tensor of the ArgMax operator of a tensor. \n
* @par Inputs:
* three input, including:
* var: A Tensor of type float16, float32, int32 or int8. \n
* indices: A Tensor of type int32. \n
* updates: A Tensor of type float16, float32, int32 or int8. \n
* @par Attributes:
* @li dimension: An integer of type int, specifying the axis information of the index with the maximum value.\n
* @par Outputs:
* y: A Tensor of type float16, float32, int32 or int8. \n
*
*@attention Constraints:
*@li indices: only support int32,and shape same to "updates"
*@li The value range of "dimension" is [-dims, dims - 1]. "dims" is the dimension length of "x".
*@li y:A Tensor, the type and shape is same to "var" \n
*@par Third-party framework compatibility
* not support all scene like pytorch operator scatter
* exp:
* var.shape=[2,3,4,5], dim=2, the shape of indices and updates should be [2,3,5]
* not support the shape of indices and updates is [2,3,2,5] like pytorch operator scatter. \n
*/
REG_OP(ArgMaxGrad)
.INPUT(var, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.INPUT(indices, TensorType({DT_INT32}))
.INPUT(updates, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.REQUIRED_ATTR(dimension, Int)
.OP_END_FACTORY_REG(ArgMaxGrad)
/**
* @brief Returns the reverse tensor of the ArgMax operator of a tensor. \n
* @par Inputs:
* three input, including:
* var: A Tensor of type float16, float32, int32 or int8. \n
* indices: A Tensor of type int32. \n
* updates: A Tensor of type float16, float32, int32 or int8. \n
* assist: A Tensor of int32,also a assist matrix and it's shape must match the shape of var \n
* @par Attributes:
* @li dimension: An integer of type int, specifying the axis information of the index with the maximum value.\n
* @par Outputs:
* y: A Tensor of type float16, float32, int32 or int8. \n
*@attention Constraints:
*@li indices: only support int32,and shape same to "updates"
*@li The value range of "dimension" is [-dims, dims - 1]. "dims" is the dimension length of "x".
*@li y:A Tensor, the type and shape is same to "var" \n
*@par Third-party framework compatibility
* not support all scene like pytorch operator scatter
* exp:
* var.shape=[2,3,4,5], dim=2, the shape of indices and updates should be [2,3,5]
* not support the shape of indices and updates is [2,3,2,5] like pytorch operator scatter. \n
*/
REG_OP(ArgMaxGradD)
.INPUT(var, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.INPUT(indices, TensorType({DT_INT32}))
.INPUT(updates, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.INPUT(assist, TensorType({DT_INT32}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT16, DT_INT32, DT_INT8}))
.REQUIRED_ATTR(dimension, Int)
.OP_END_FACTORY_REG(ArgMaxGradD)
} // namespace ge
#endif // OPS_BUILT_IN_OP_PROTO_INC_ELEWISE_CALCULATION_OPS_H_

27
third_party/fwkacllib/inc/ops/linalg_ops.h vendored
Unescape View File

@ -160,10 +160,8 @@ form square matrices. \n
*/
REG_OP(MatrixInverse)
.INPUT(x, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(x, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.ATTR(adjoint, Bool, false)
.OP_END_FACTORY_REG(MatrixInverse)
@ -223,10 +221,8 @@ dimensions form square matrices. \n
*/
REG_OP(MatrixSolveLs)
.INPUT(matrix, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(matrix, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(l2, TensorType({DT_DOUBLE}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE}))
.ATTR(fast, Bool, true)
@ -259,12 +255,9 @@ dimensions form square matrices. \n
*/
REG_OP(MatrixTriangularSolve)
.INPUT(matrix, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE, DT_FLOAT16, \
DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(matrix, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.ATTR(lower, Bool, true)
.ATTR(adjoint, Bool, false)
.OP_END_FACTORY_REG(MatrixTriangularSolve)
@ -432,9 +425,9 @@ y: Tensor of shape `[..., M, K]` containing the solutions \n
*/
REG_OP(TridiagonalSolve)
.INPUT(diagonals, TensorType({DT_FLOAT, DT_DOUBLE}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE}))
.INPUT(diagonals, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.INPUT(rhs, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.OUTPUT(y, TensorType({DT_FLOAT, DT_DOUBLE, DT_COMPLEX64, DT_COMPLEX128}))
.ATTR(partial_pivoting, Bool, true)
.OP_END_FACTORY_REG(TridiagonalSolve)

23
third_party/fwkacllib/inc/ops/matrix_calculation_ops.h vendored
Unescape View File

@ -1043,6 +1043,29 @@ REG_OP(Triu)
.ATTR(diagonal, Int, 0)
.OUTPUT(y, TensorType::BasicType())
.OP_END_FACTORY_REG(Triu)
/**
*@brief: Returns the upper triangular part of a matrix (2-D tensor) or batch of matrices input \n
*@par Inputs:
* Two inputs, including:
*@li x: A Tensor. Must be one of the following types:
* float16, float32, double, int32, uint8, int16, int8, complex64, int64,
* qint8, quint8, qint32, uint16, complex128, uint32, uint64.
*@li diagonal:(int, optional) – the diagonal to consider。\n
*@par Outputs:
*y: A Tensor. Has the same type as "x" . \n
*@par Third-party framework compatibility
* Compatible with the Pytorch operator Tril.
*/
REG_OP(Tril)
.INPUT(x, TensorType::BasicType())
.ATTR(diagonal, Int, 0)
.OUTPUT(y, TensorType::BasicType())
.OP_END_FACTORY_REG(Tril)
} // namespace ge
#endif // OPS_BUILT_IN_OP_PROTO_INC_MATRIX_CALCULATION_OPS_H_

21
third_party/fwkacllib/inc/ops/nn_calculation_ops.h vendored
Unescape View File

@ -408,8 +408,8 @@ REG_OP(BiasAddGrad)
| Filter | H | [1, 255]
| | W | [1, 255]
-------------------|----------|--------------
| out_backprop | H | [1, 4096]
| | W | [1, 4096]
| out_backprop | H*strideH| [1, 4096]
| | W*strideW| [1, 4096]
-------------------|----------|--------------
| y(fmap) | H | [1, 4096]
| | W | [1, 4096]
@ -428,6 +428,7 @@ REG_OP(BiasAddGrad)
@endverbatim
* In Ascend910, fmap or out_backprop's H and W not support 1 when
* fmap_h + pad_top + pad_bottom != (filter_height - 1) * dilation_h + 1
* If filter_h = 1 and filter_w = 1, out_backprop_w * stride_h * stride_w < 4096
*\n
*
*@par Outputs:
@ -545,15 +546,16 @@ REG_OP(Conv2DBackpropInputD)
* @li data_format: An optional string from: "NCHW". Defaults to "NCHW". \n
Specify the data format of the input and output data.
* @li offset_x: An optional integer for quantized deconvolution.
* Defaults to "0".
* The negative offset added to the input image for int8 type. Ensure offset_x
* within the effective range of int8 [-128, 127]. Defaults to "0".
*\n
*\n
* The following value range restrictions must be met:
*@verbatim
| Name | Field | Scope
-------------------|----------|--------------
| x (out_backprop) | H | [1, 4096]
| | W | [1, 4096]
| x (out_backprop) | H*strideH| [1, 4096]
| | W*strideW| [1, 4096]
-------------------|----------|--------------
| Filter | H | [1, 255]
| | W | [1, 255]
@ -577,6 +579,7 @@ REG_OP(Conv2DBackpropInputD)
@endverbatim
* In Ascend910, fmap or out_backprop's H and W not support 1 when
* fmap_h + pad_top + pad_bottom != (filter_height - 1) * dilation_h + 1
* If filter_h = 1 and filter_w = 1, out_backprop_w * stride_h * stride_w < 4096
*\n
*
*@par Outputs:
@ -1496,7 +1499,8 @@ REG_OP(Conv3DTransposeD)
* @li output_padding: The size will be added in the output shape. Defaults
* to [0, 0, 0, 0].
* @li offset_x: An optional int. Input offset, used for quantized inference.
* Defaults to "0".
* The negative offset added to the input image for int8 type. Ensure offset_x
* within the effective range of int8 [-128, 127]. Defaults to "0".
*\n
*\n
* The following value range restrictions must be met:
@ -1506,8 +1510,8 @@ REG_OP(Conv3DTransposeD)
| input_size | H | [1, 4096]
| | W | [1, 4096]
-------------------|----------|--------------
| x (out_backprop) | H | [1, 4096]
| | W | [1, 4096]
| x (out_backprop) | H*strideH| [1, 4096]
| | W*strideW| [1, 4096]
-------------------|----------|--------------
| filter | H | [1, 255]
| | W | [1, 255]
@ -1531,6 +1535,7 @@ REG_OP(Conv3DTransposeD)
@endverbatim
* In Ascend910, fmap or out_backprop's H and W not support 1 when
* fmap_h + pad_top + pad_bottom != (filter_height - 1) * dilation_h + 1
* If filter_h = 1 and filter_w = 1, out_backprop_w * stride_h * stride_w < 4096
*\n
*
*@par Outputs:

2
third_party/fwkacllib/inc/ops/selection_ops.h vendored
Unescape View File

@ -942,6 +942,8 @@ REG_OP(TopK)
.OUTPUT(values, TensorType::RealNumberType())
.OUTPUT(indices, TensorType({DT_INT32}))
.ATTR(sorted, Bool, true)
.ATTR(largest, Bool, true)
.ATTR(dim, Int, -1)
.OP_END_FACTORY_REG(TopK)
/**
*@brief Creates a new tensor by applying sparse "updates" to individual values or slices within a tensor (initially zero for numeric, empty for string) of the given "shape" according to "indices" . \n

10
third_party/fwkacllib/inc/ops/spectral_ops.h vendored
Unescape View File

@ -66,16 +66,16 @@ REG_OP(RFFT)
.OP_END_FACTORY_REG(RFFT)
/**
*@brief Inverse real-valued fast Fourier transform . \n
*@brief Inverse real-valued fast Fourier transform. \n
*@par Inputs:
*@li x: A complex64 tensor.
*@li fft_length: An int32 tensor of shape [1]. The FFT length . \n
*@li fft_length: An int32 tensor of shape [1]. The FFT length. \n
*@par Outputs:
*@li y: A float32 tensor of the same rank as `input`. The inner-most
dimension of `input` is replaced with the `fft_length` samples of its inverse
1D Fourier transform . \n
1D Fourier transform. \n
*@par Third-party framework compatibility
* Compatible with TensorFlow IRFFT operator.
@ -91,11 +91,11 @@ REG_OP(IRFFT)
*@brief 2D fast Fourier transform. \n
*@par Inputs:
*@li x: A complex64 tensor..
*@li x: A complex64 tensor.
*@par Outputs:
*@li y: A complex64 tensor of the same shape as `input`. The inner-most 2
dimensions of `input` are replaced with their 2D Fourier transform.\n
dimensions of `input` are replaced with their 2D Fourier transform. \n
*@par Third-party framework compatibility
* Compatible with TensorFlow FFT2D operator.

29
third_party/fwkacllib/inc/ops/transformation_ops.h vendored
Unescape View File

@ -716,6 +716,35 @@ REG_OP(CompressFcOp)
.OUTPUT(compress_index, TensorType({DT_INT8}))
.REQUIRED_ATTR(compress_parameters, ListInt)
.OP_END_FACTORY_REG(CompressFcOp)
/**
*@brief Performs Col2im for each batch entry. \n
*@par Inputs:
*@li input_x: The Col Tensor. 5-D, shape: `(n, c1, kernel_h*kernel_w, ho*wo, c0)`.
where ho/wo is do = (output_d + 2*padding_d - dilation_d*(kernel_d - 1) - 1)//stride_d + 1 \n
*@par Outputs:
*@li output_y: The img Tensor. 5-D, shape: `(n, c1, output_h, output_w, c0)`. \n
*@par Attributes:
*@li kernel_shape: ListInt, value: `(kernel_h, kernel_w)`, the shape of kernel in convolution.
*@li dilation: ListInt, value: `(dilation_h, dilation_w)`, the dilation in convolution.
*@li padding: ListInt, value: `(padding_h, padding_w)`, the dilation in convolution.
*@li stride: ListInt, value: `(stride_h, stride_w)`, the dilation in convolution. \n
*@par Third-party framework compatibility
* Compatible with Pytorch col2im/im2col_backward operator.
*/
REG_OP(Col2im)
.INPUT(x, TensorType({DT_FLOAT}))
.INPUT(output_size, TensorType({DT_INT32}))
.OUTPUT(y, TensorType({DT_FLOAT}))
.REQUIRED_ATTR(kernel_size, ListInt)
.REQUIRED_ATTR(dilation, ListInt)
.REQUIRED_ATTR(padding, ListInt)
.REQUIRED_ATTR(stride, ListInt)
.OP_END_FACTORY_REG(Col2im)
} // namespace ge
#endif // OPS_BUILT_IN_OP_PROTO_INC_TRANSFORMATION_OPS_H_

8
third_party/fwkacllib/inc/runtime/kernel.h vendored
Unescape View File

@ -173,13 +173,7 @@ typedef void (*rtCallback_t)(void *fnData);
* @ingroup rt_kernel
* @brief magic number of elf binary for aicube
*/
#define RT_DEV_BINARY_MAGIC_ELF_AICUBE 0x41415247
/**
* @ingroup rt_kernel
* @brief magic number of elf binary for aivector
*/
#define RT_DEV_BINARY_MAGIC_ELF_AIVECTOR 0x41415248
#define RT_DEV_BINARY_MAGIC_ELF_AICUBE 0x41494343
/**
* @ingroup rt_kernel_flags

11
third_party/fwkacllib/inc/runtime/mem.h vendored
Unescape View File

@ -116,6 +116,9 @@ typedef enum tagRtMemInfoType {
typedef enum tagRtRecudeKind {
RT_MEMCPY_SDMA_AUTOMATIC_ADD = 10, // D2D, SDMA inline reduce, include 1P, and P2P
RT_MEMCPY_SDMA_AUTOMATIC_MAX = 11,
RT_MEMCPY_SDMA_AUTOMATIC_MIN = 12,
RT_MEMCPY_SDMA_AUTOMATIC_EQUAL = 13,
RT_RECUDE_KIND_END
} rtRecudeKind_t;
@ -123,6 +126,14 @@ typedef enum tagRtDataType {
RT_DATA_TYPE_FP32 = 0, // fp32
RT_DATA_TYPE_FP16 = 1, // fp16
RT_DATA_TYPE_INT16 = 2, // int16
RT_DATA_TYPE_INT4 = 3, // int4
RT_DATA_TYPE_INT8 = 4, // int8
RT_DATA_TYPE_INT32 = 5, // int32
RT_DATA_TYPE_BFP16 = 6, // bfp16
RT_DATA_TYPE_BFP32 = 7, // bfp32
RT_DATA_TYPE_UINT8 = 8, // uint8
RT_DATA_TYPE_UINT16= 9, // uint16
RT_DATA_TYPE_UINT32= 10,// uint32
RT_DATA_TYPE_END
} rtDataType_t;

36
third_party/fwkacllib/inc/toolchain/tuning_tool/tune_api.h vendored
Unescape View File

@ -1,14 +1,14 @@
/**
* @file tune_api.h
*
* Copyright (c) Huawei Technologies Co., Ltd. 2020-2020. All rights reserved.\n
* Copyright (c) Huawei Technologies Co., Ltd. 2020-2021. All rights reserved.\n
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n
* 描述：mstune调优接口头文件
* 描述：aoe调优接口头文件
*/
/** @defgroup mstune mstune调优接口 */
/** @defgroup aoe aoe调优接口 */
#ifndef TUNE_API_H
#define TUNE_API_H
#include <vector>
@ -16,11 +16,12 @@
#include <string>
#include "graph/graph.h"
#include "ge/ge_api.h"
#include "aoe_types.h"
/**
* @ingroup mstune
* @ingroup aoe
*
* mstune status
* aoe status
*/
enum MsTuneStatus {
MSTUNE_SUCCESS, /** tune success */
@ -98,7 +99,7 @@ struct RunnerConfig {
#endif
/**
* @ingroup mstune
* @ingroup aoe
* @par 描述: 命令行调优
*
* @attention 无
@ -112,10 +113,10 @@ struct RunnerConfig {
* @see 无
* @since
*/
MsTuneStatus MsTuning(const std::map<std::string, std::string> &option, std::string &msg);
AoeStatus AoeOfflineTuning(const std::map<std::string, std::string> &option, std::string &msg);
/**
* @ingroup mstune
* @ingroup aoe
* @par 描述: 梯度调优
*
* @attention 无
@ -134,4 +135,23 @@ MsTuneStatus MsTuning(const std::map<std::string, std::string> &option, std::str
extern "C" MsTuneStatus MsTrainTuning(ge::Graph &tuningGraph, std::vector<ge::Graph> &dependGraph,
ge::Session *session, const std::map<std::string, std::map<std::string, std::string>> &option);
/**
* @ingroup aoe
* @par 描述: 梯度调优
*
* @attention 无
* @param tuningGraph [IN] 调优图
* @param dependGraph [IN] 调优依赖图
* @param session [IN] ge连接会话
* @param option [IN] 参数集. 包含调优参数及ge参数
* @retval #AOE_SUCCESS 执行成功
* @retval #AOE_FAILED 执行失败
* @par 依赖:
* @li tune_api.cpp：该接口所属的开发包。
* @li tune_api.h：该接口声明所在的头文件。
* @see 无
* @since
*/
extern "C" AoeStatus AoeOnlineTuning(ge::Graph &tuningGraph, std::vector<ge::Graph> &dependGraph,
ge::Session *session, const std::map<std::string, std::map<std::string, std::string>> &option);
#endif

Write Preview
Loading…
Cancel
Save