aclnnStack

Applicable Products

  • Ascend 950PR&950DT products: Supported
  • Atlas A3 products: Supported
  • Atlas A2 products: Supported
  • Atlas 200I/500 A2 inference products: Not supported
  • Atlas inference products: Supported
  • Atlas training products: Supported

Function

  • Description: Concatenates a sequence of tensors along a new dimension.
  • Given a list of tensors of shape (A, B, C) and length N, if axis is 0, the output tensor shape is (N, A, B, C).

Function Prototype

Each operator uses a two-phase API. Call "aclnnStackGetWorkspaceSize" first to obtain the workspace size required for computation and the executor containing the operator calculation process, and then call "aclnnStack" to execute the computation.

aclnnStatus aclnnStackGetWorkspaceSize(
    const aclTensorList *tensors,
    int64_t              dim,
    aclTensor           *out,
    uint64_t            *workspaceSize,
    aclOpExecutor      **executor)
aclnnStatus aclnnStack(
    void             *workspace,
    uint64_t          workspaceSize,
    aclOpExecutor    *executor,
    const aclrtStream stream)

aclnnStackGetWorkspaceSize

  • Parameters

    Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor
    tensors (aclTensorList*) Input Sequence of tensors to concatenate. - FLOAT16, FLOAT, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64, BOOL, DOUBLE, COMPLEX64, COMPLEX128, BFLOAT16. ND 0-8 √
    dim (int64_t) Input Dimension along which to concatenate. Value range: [-(tensors.dim()+1), tensors.dim()]. INT64 - - -
    out (aclTensor*) Output Output tensor - FLOAT16, FLOAT, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64, BOOL, DOUBLE, COMPLEX64, COMPLEX128, BFLOAT16. ND 1-9 √
    workspaceSize (uint64_t*) Output Returns the workspace size to be requested on the Device side. - - - - -
    executor (aclOpExecutor**) Output Returns the op executor containing the operator computation flow. - - - - -
    • Atlas inference products, Atlas training products: The BFLOAT16 data type is not supported.
  • Return Value

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

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

    Return Values Error Code Description
    ACLNN_ERR_INNER_NULLPTR 561103 tensors or out is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type of the tensor in the tensors list or out is not within the supported range.
    The data type of the tensor in the tensors list cannot be deduced.
    The inferred data type cannot be converted to the data type of output out.
    dim is out of the tensor dimension range.
    The dimension of the tensor in the tensors list exceeds 8.

aclnnStack

  • Parameters

    Parameter Input/Output Description
    workspace Input Pointer to the workspace memory allocated on the Device side.
    workspaceSize Input Size of the workspace memory allocated on the Device side. The value is obtained by the first-phase API aclnnStackGetWorkspaceSize.
    executor Input op executor, which contains the operator computation flow.
    stream Input Stream for task execution.
  • Return Value

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

Constraints

  • Deterministic computation:
    • aclnnStack defaults to a deterministic implementation.

Example

The following sample code is for reference only. For details about compilation and execution, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_stack.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 allocate 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);
  // Call aclrtMemcpy to copy host-side data to device-side memory.
  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];
  }

  // Call the aclCreateTensor API to create an aclTensor.
  *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 device/stream. For details, see the acl API documentation.
  // 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. Custom construction is required based on the API.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {2, 3};
  std::vector<int64_t> outShape = {2, 2, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> input1HostData = {1, 2, 3, 4, 5, 6};
  std::vector<float> input2HostData = {7, 8, 9, 10, 11, 12};
  std::vector<float> outHostData(12, 0);
  // Create input1 aclTensor.
  ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create input2 aclTensor.
  ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create aclTensorList.
  std::vector<aclTensor*> tmp{input1, input2};
  aclTensorList* tensorList = aclCreateTensorList(tmp.data(), tmp.size());
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Replace it with the specific API name.
  int64_t dim = 0;
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the aclnnStack first-phase API.
  ret = aclnnStackGetWorkspaceSize(tensorList, dim, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnStackGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate 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 aclnnStack second-phase API.
  ret = aclnnStack(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnStack 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 device memory to the host. Change it to match the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> outData(size, 0);
  ret = aclrtMemcpy(outData.data(), outData.size() * sizeof(outData[0]), outDeviceAddr,
                    size * sizeof(outData[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 < size; i++) {
    LOG_PRINT("out result[%ld] is: %f\n", i, outData[i]);
  }

  // 6. Release aclTensor and aclScalar. Change it to match the specific API definition.
  aclDestroyTensorList(tensorList);
  aclDestroyTensor(out);

  // 7. Release device resources. Change it to match the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}