aclnnForeachZeroInplace

📄 View Source Code

Applicable Products

Function

• Description: Updates the input tensor list in-place, setting each tensor in the input tensor list to 0.

• Formula:

  $$x = [{x_0}, {x_1}, ... {x_{n-1}}]\\$$ $$x_i = 0 (i=0,1,...n-1)$$

Function Prototype

Each operator uses a two-phase API. You must first call the "aclnnForeachZeroInplaceGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnForeachZeroInplace" API to perform the computation.

aclnnStatus aclnnForeachZeroInplaceGetWorkspaceSize(
  const aclTensorList *x,
  uint64_t *workspaceSize,
  aclOpExecutor **executor)

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

aclnnForeachZeroInplaceGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
  x (aclTensorList*)	Input/Output	Indicates the list of input and output tensors for the zeroing operation, corresponding to `x` in the formula.	Empty tensors are supported. All tensors in this parameter must have the same data type.	FLOAT32, FLOAT16, BFLOAT16, INT16, 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 is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of x is not within the supported range.
  ACLNN_ERR_INNER_TILING_ERROR	561002	The data types of tensors in x are inconsistent.
  		The dimension of the tensor in x exceeds 8.

aclnnForeachZeroInplace

• 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 aclnnForeachZeroInplaceGetWorkspaceSize.
  executor	Input	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:

  • aclnnForeachZeroInplace 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_zero_inplace.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: 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);
  // Copy host-side data to 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];
  }

  // 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. Custom construction is required based on the API interface.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {1, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  std::vector<float> input1HostData = {1, 2, 3, 4, 5, 6};
  std::vector<float> input2HostData = {7, 8, 9};

  // 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);

  std::vector<aclTensor*> tempInput{input1, input2};
  aclTensorList* tensorListInput = aclCreateTensorList(tempInput.data(), tempInput.size());

  // 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 aclnnForeachZeroInplace.
  ret = aclnnForeachZeroInplaceGetWorkspaceSize(tensorListInput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachZeroInplaceGetWorkspaceSize 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 aclnnForeachZeroInplace.
  ret = aclnnForeachZeroInplace(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachZeroInplace 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 device memory to host memory. Modify based on the specific API definition.
  auto size = GetShapeSize(selfShape1);
  std::vector<float> self1Data(size, 0);
  ret = aclrtMemcpy(self1Data.data(), self1Data.size() * sizeof(self1Data[0]), input1DeviceAddr,
                    size * sizeof(self1Data[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("out1 result[%ld] is: %f\n", i, self1Data[i]);
  }

  size = GetShapeSize(selfShape2);
  std::vector<float> self2Data(size, 0);
  ret = aclrtMemcpy(self2Data.data(), self2Data.size() * sizeof(self2Data[0]), input2DeviceAddr,
                    size * sizeof(self2Data[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, self2Data[i]);
  }

  // 6. Release aclTensor. Modify based on the specific API definition.
  aclDestroyTensorList(tensorListInput);

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