aclnnForeachAddScalarList

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: Performs an element-wise addition operation on the input tensor list and input scalar list.
Formula:
$x = [{x_0}, {x_1}, ... {x_{n-1}}]\\ scalars = [{scalars_0}, {scalars_1}, ... {scalars_{n-1}}]\\ y = [{y_0}, {y_1}, ... {y_{n-1}}]\\$ $y_i=x_i+scalars_i (i=0,1,...n-1)$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnForeachAddScalarListGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnForeachAddScalarList" API to perform the computation.

aclnnStatus aclnnForeachAddScalarListGetWorkspaceSize(
  const aclTensorList *x,
  const aclScalarList *scalars,
  const aclTensorList *out,
  uint64_t            *workspaceSize,
  aclOpExecutor      **executor)

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

aclnnForeachAddScalarListGetWorkspaceSize

Parameters

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
x (aclTensorList*)	Input	Indicates the list of input tensors for the addition operation. Corresponds to `x` in the formula.	Supports empty tensors. All tensors in this parameter must have the same data type.	FLOAT32, FLOAT16, BFLOAT16, INT32	ND	0-8	√
scalars (aclScalarList*)	Input	Represents the input scalar for the addition operation. Corresponds to `scalar` in the formula.	The number of elements equals the number of tensors in `x`. There is a certain correspondence between the data type and the data type of the input parameter `x`: When the data type of the input parameter `x` is FLOAT32, FLOAT16, or BFLOAT16, the data type of `scalars` only supports FLOAT32. When the data type of the input parameter `x` is INT32, the data type of `scalars` only supports INT64.	FLOAT32, INT64	-	-	-
out (aclTensorList*)	Output	Represents the output tensor list for the addition operation. Corresponds to `y` in the formula.	Empty tensors are supported. All tensors in this parameter must have the same data type. The data type and data format are the same as those of the input `x`, and the shape size is greater than or equal to the shape size of the input `x`.	FLOAT32, FLOAT16, BFLOAT16, INT32	ND	0-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

Return Value

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

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 passed x, scalars, or out is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data types of x, scalars, and out are not within the supported range.
ACLNN_ERR_PARAM_INVALID	161002	The data types of x and out are inconsistent.
ACLNN_ERR_INNER_TILING_ERROR	561002	The shapes of x and out do not satisfy the constraints.
		The data types of the tensors in x or out are inconsistent.
		The dimension of a tensor in x or out exceeds 8.

aclnnForeachAddScalarList

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 aclnnForeachAddScalarListGetWorkspaceSize.
executor	Input	Operator executor, which contains the operator computation flow.
stream	Input	Specifies the stream on which the task is executed.

Return Value

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

Constraints

Deterministic computation:
- aclnnForeachAddScalarList 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_foreach_add_scalar_list.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 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 host data to device memory using 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 a 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 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.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {1, 3};
  std::vector<int64_t> outShape1 = {2, 3};
  std::vector<int64_t> outShape2 = {1, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* out1DeviceAddr = nullptr;
  void* out2DeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclScalar* alpha1 = nullptr;
  aclScalar* alpha2 = nullptr;
  aclTensor* out1 = nullptr;
  aclTensor* out2 = nullptr;
  std::vector<float> input1HostData = {1, 2, 3, 4, 5, 6};
  std::vector<float> input2HostData = {7, 8, 9};
  std::vector<float> out1HostData(6, 0);
  std::vector<float> out2HostData(3, 0);
  float alpha1Value = 1.2f;
  float alpha2Value = 2.2f;
  // 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 alpha1 aclScalar.
  alpha1 = aclCreateScalar(&alpha1Value, aclDataType::ACL_FLOAT);
  CHECK_RET(alpha1 != nullptr, return ret);
  // Create alpha2 aclScalar.
  alpha2 = aclCreateScalar(&alpha2Value, aclDataType::ACL_FLOAT);
  CHECK_RET(alpha2 != nullptr, return ret);
  // Create out1 aclTensor.
  ret = CreateAclTensor(out1HostData, outShape1, &out1DeviceAddr, aclDataType::ACL_FLOAT, &out1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create out2 aclTensor.
  ret = CreateAclTensor(out2HostData, outShape2, &out2DeviceAddr, aclDataType::ACL_FLOAT, &out2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  std::vector<aclTensor*> tempInput{input1, input2};
  aclTensorList* tensorListInput = aclCreateTensorList(tempInput.data(), tempInput.size());
  std::vector<aclTensor*> tempOutput{out1, out2};
  aclTensorList* tensorListOutput = aclCreateTensorList(tempOutput.data(), tempOutput.size());
  std::vector<aclScalar*> tempscalar{alpha1, alpha2};
  aclScalarList* scalarlist = aclCreateScalarList(tempscalar.data(), tempscalar.size());

  // 3. Call the CANN operator library API. Replace with the actual API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnForeachAddScalarList.
  ret = aclnnForeachAddScalarListGetWorkspaceSize(tensorListInput, scalarlist, tensorListOutput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachAddScalarListGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the workspaceSize computed 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 aclnnForeachAddScalarList.
  ret = aclnnForeachAddScalarList(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachAddScalarList failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize and wait for 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 memory. Modify based on the specific API definition.
  auto size = GetShapeSize(outShape1);
  std::vector<float> out1Data(size, 0);
  ret = aclrtMemcpy(out1Data.data(), out1Data.size() * sizeof(out1Data[0]), out1DeviceAddr,
                    size * sizeof(out1Data[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("out1 result[%ld] is: %f\n", i, out1Data[i]);
  }

  size = GetShapeSize(outShape2);
  std::vector<float> out2Data(size, 0);
  ret = aclrtMemcpy(out2Data.data(), out2Data.size() * sizeof(out2Data[0]), out2DeviceAddr,
                    size * sizeof(out2Data[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("out2 result[%ld] is: %f\n", i, out2Data[i]);
  }

  // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensorList(tensorListInput);
  aclDestroyTensorList(tensorListOutput);
  aclDestroyScalarList(scalarlist);

  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(out1DeviceAddr);
  aclrtFree(out2DeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}