aclnnArgsort

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	√
Atlas training products	√

Function

Description: Sorts the elements in the input tensor along a specified dimension in ascending or descending order and returns the corresponding indices.
Formula:

out[\mathbf{i}_{\neg dim}, j] = \text{arg\_sort}_{dim}[self[\mathbf{i}_{\neg dim}, :]](j)

Function Prototype

Each operator is divided into a two-phase API. The "aclnnArgsortGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnArgsort" API is called to perform the computation.

  aclnnStatus aclnnArgsortGetWorkspaceSize(
  const aclTensor *self,
  int64_t          dim,
  bool             descending,
  aclTensor       *out,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)

  aclnnStatus aclnnArgsort(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnArgsortGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
self	Input	Input tensor.	Empty tensors are supported.	BFLOAT16, FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64	ND	-	√
dim	Input	The dimension along which to sort.	The value ranges from [-self.dim(), self.dim()-1].	INT64	-	-	-
descending	Input	Controls the sorting order. True indicates descending order, and False indicates ascending order.	-	BOOL	-	-	-
out	Output	Output tensor.	Supports empty tensors.	INT64	Same as self.	Same as self.	√
workspaceSize	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
executor	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products:
- The data types UINT16, UINT32, and UINT64 are not supported.
- When the data type of self is BFLOAT16, the sort axis 1 is not supported.

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

The first-phase API performs input parameter validation and returns an error in the following scenarios:

Return Code	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	The input self or out is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of self or out is not within the supported range, or their shapes do not match each other.
		The value of dim is not within the range of [-N, N-1].
		The data type of self is BFLOAT16 and the sort axis is 1.

aclnnArgsort

Parameters:

Parameter	Input/Output	Description
workspace	Input	Address of the workspace memory applied for on the Device side.
workspaceSize	Input	Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnArgsortGetWorkspaceSize.
executor	Input	Operator executor, which contains the operator computation flow.
stream	Input	Specifies the stream for executing the task.

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

Constraints

Deterministic computation:
- aclnnArgsort defaults to a deterministic implementation.

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_argsort.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)

#define LOG_PRINT(message, ...)     \
  do {                              \
    printf(message, ##__VA_ARGS__); \
  } while (0)

int64_t GetShapeSize(const std::vector<int64_t>& shape) {
    int64_t shapeSize = 1;
    for (auto i : shape) {
        shapeSize *= i;
    }
    return shapeSize;
}

int Init(int32_t deviceId, aclrtStream* stream) {
    // Boilerplate for resource initialization.
    auto ret = aclInit(nullptr);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
    ret = aclrtSetDevice(deviceId);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
    ret = aclrtCreateStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
    return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
    auto size = GetShapeSize(shape) * sizeof(T);
    // Call aclrtMalloc to apply for device-side memory.
    auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
    // Copy data from the host to the device memory by calling aclrtMemcpy.
    ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

    // Calculate the strides of the contiguous tensor.
    std::vector<int64_t> strides(shape.size(), 1);
    for (int64_t i = shape.size() - 2; i >= 0; i--) {
        strides[i] = shape[i + 1] * strides[i + 1];
    }

    // Create an aclTensor by calling the aclCreateTensor API.
    *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                              shape.data(), shape.size(), *deviceAddr);
    return 0;
}

int main() {
    // 1. (Boilerplate) Initialize the device/stream. See the ACL API manual.
    // Set deviceId based on the actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 2. Construct the input and output. Customize the construction based on the API interface.
    int64_t dim = 0;
    bool descending = false;
    std::vector<int64_t> selfShape = {3, 4};
    std::vector<int64_t> outIndicesShape = {3, 4};
    void* selfDeviceAddr = nullptr;
    void* outIndicesDeviceAddr = nullptr;
    aclTensor* self = nullptr;
    aclTensor* outIndices = nullptr;
    std::vector<int64_t> selfHostData = {7, 8, 9, 10, 11, 12, 1, 2, 3, 4, 5, 6};
    std::vector<int64_t> outIndicesHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};

    // Create the self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_INT64, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the outValues and outIndices aclTensor.
    ret = CreateAclTensor(outIndicesHostData, outIndicesShape, &outIndicesDeviceAddr, aclDataType::ACL_INT64, &outIndices);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3. Call the CANN operator library API. Replace with the specific API name.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnArgsort.
    ret = aclnnArgsortGetWorkspaceSize(self, dim, descending, outIndices, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnArgsortGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Apply for device memory based on the workspaceSize calculated by the first-phase API.
    void* workspaceAddr = nullptr;
    if (workspaceSize > 0) {
        ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    // Call the second-phase API of aclnnArgsort.
    ret = aclnnArgsort(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnArgsort failed. ERROR: %d\n", ret); return ret);

    // 4. (Boilerplate) Synchronously wait for the task execution to complete.
    ret = aclrtSynchronizeStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

    // 5. Obtain the output value and copy the result from the device memory to the host. Modify based on the specific API definition.
    auto size2 = GetShapeSize(outIndicesShape);
    std::vector<int64_t> resultData2(size2, 0);
    ret = aclrtMemcpy(resultData2.data(), resultData2.size() * sizeof(resultData2[0]), outIndicesDeviceAddr,
                      size2 * sizeof(resultData2[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
    for (int64_t i = 0; i < size2; i++) {
        LOG_PRINT("result indices [%ld] is: %ld\n", i, resultData2[i]);
    }

    // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
    aclDestroyTensor(self);
    aclDestroyTensor(outIndices);

     // 7. Release device resources.
    aclrtFree(selfDeviceAddr);
    aclrtFree(outIndicesDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();

    return 0;
}