aclnnForeachDivList

📄 View Source Code

Applicable Products

Function

• Description: Performs element-wise division on tensor list x1 and tensor list x2.

• Formula:

  $$x1 = [{x1_0}, {x1_1}, ... {x1_{n-1}}], x2 = [{x2_0}, {x2_1}, ... {x2_{n-1}}]\\ y = [{y_0}, {y_1}, ... {y_{n-1}}]\\$$ $${\rm y}_i = \frac{x1_i}{x2_i} (i=0,1,...n-1)$$

Function Prototype

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

aclnnStatus aclnnForeachDivListGetWorkspaceSize(
  const aclTensorList *x1,
  const aclTensorList *x2,
  const aclTensorList *out,
  uint64_t            *workspaceSize,
  aclOpExecutor      **executor)

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

aclnnForeachDivListGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
  x1 (aclTensorList*)	Input	Represents the first input tensor list for the division operation, corresponding to `x1` in the formula.	Supports null Tensor. All tensors in this parameter must have the same data type.	BFLOAT16, FLOAT16, FLOAT32	ND	0-8	√
  x2 (aclTensorList*)	Input	Represents the second input tensor list for the division operation, corresponding to `x2` in the formula.	Supports null Tensor. All tensors in this parameter must have the same data type. The data type, data format, and shape are consistent with those of the input parameter x1.	BFLOAT16, FLOAT16, FLOAT32	ND	0-8	√
  out (aclTensorList*)	Output	Represents the output tensor list of the division operation, corresponding to `y` in the formula.	Supports null tensors. All tensors in this parameter have the same data type. The data type and data format are the same as those of the input parameter `x1`, and the shape size is greater than or equal to the shape size of the input parameter `x1`.	BFLOAT16, FLOAT16, FLOAT32	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	x1, x2, or out passed in is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types of x1, x2, and out are not within the supported range.
  		The data types of x1, x2, and out are inconsistent.
  ACLNN_ERR_INNER_TILING_ERROR	561002	The shapes of x1, x2, and out do not meet the constraints.
  		Inconsistent data types of tensors in x1, x2, or out.
  		A tensor in x1, x2, or out exceeds 8 dimensions.

aclnnForeachDivList

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Specifies the workspace memory address applied for on the Device side.
  workspaceSize	Input	Specifies the workspace size applied for on the Device side, obtained through the first-phase API aclnnForeachDivListGetWorkspaceSize.
  executor	Input	The operator executor, which contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return Value

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

Constraints

• Deterministic computation:

  • aclnnForeachDivList 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_div_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 memory on the Device side.
  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 side to the device side 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 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 aclCreateTensor 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.
  // Fill in the deviceId based on your 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> otherShape1 = {2, 3};
  std::vector<int64_t> otherShape2 = {1, 3};
  std::vector<int64_t> outShape1 = {2, 3};
  std::vector<int64_t> outShape2 = {1, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* other1DeviceAddr = nullptr;
  void* other2DeviceAddr = nullptr;
  void* out1DeviceAddr = nullptr;
  void* out2DeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclTensor* other1 = nullptr;
  aclTensor* other2 = 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> other1HostData = {6, 5, 4, 3, 2, 1};
  std::vector<float> other2HostData = {9, 8, 7};
  std::vector<float> out1HostData(6, 0);
  std::vector<float> out2HostData(3, 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 other1 aclTensor.
  ret = CreateAclTensor(other1HostData, otherShape1, &other1DeviceAddr, aclDataType::ACL_FLOAT, &other1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create other2 aclTensor.
  ret = CreateAclTensor(other2HostData, otherShape2, &other2DeviceAddr, aclDataType::ACL_FLOAT, &other2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out1 aclTensor.
  ret = CreateAclTensor(out1HostData, outShape1, &out1DeviceAddr, aclDataType::ACL_FLOAT, &out1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out2 aclTensor.
  ret = CreateAclTensor(out2HostData, outShape2, &out2DeviceAddr, aclDataType::ACL_FLOAT, &out2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<aclTensor*> tempInput1{input1, input2};
  aclTensorList* tensorListInput1 = aclCreateTensorList(tempInput1.data(), tempInput1.size());
  std::vector<aclTensor*> tempInput2{other1, other2};
  aclTensorList* tensorListInput2 = aclCreateTensorList(tempInput2.data(), tempInput2.size());
  std::vector<aclTensor*> tempOutput{out1, out2};
  aclTensorList* tensorListOutput = aclCreateTensorList(tempOutput.data(), tempOutput.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 aclnnForeachDivList.
  ret = aclnnForeachDivListGetWorkspaceSize(tensorListInput1, tensorListInput2, tensorListOutput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachDivListGetWorkspaceSize 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 aclnnForeachDivList.
  ret = aclnnForeachDivList(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachDivList failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait for the task execution to finish synchronously.
  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 side memory to the host side. 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. Modify based on the specific API definition.
  aclDestroyTensorList(tensorListInput1);
  aclDestroyTensorList(tensorListInput2);
  aclDestroyTensorList(tensorListOutput);

  // 7.Release device resources. Modify based on the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(other1DeviceAddr);
  aclrtFree(other2DeviceAddr);
  aclrtFree(out1DeviceAddr);
  aclrtFree(out2DeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}