文档
下载
文档中心
aclError

aclnnInplaceMaskedScatter

📄 View source code

Supported Products

ProductSupported
Atlas A3 training series products/Atlas A3 inference series products√
Atlas A2 training products/Atlas A2 inference products√
Atlas 200I/500 A2 inference products×
Atlas inference series products√
Atlas training series products√

Function

Description: Copies the element in source to the corresponding position in selfRef based on the position where the element in the mask tensor is True.

Prototype

Each operator has two-phase API calls. First, aclnnInplaceMaskedScatterGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnInplaceMaskedScatter is called to perform computation.

  • aclnnStatus aclnnInplaceMaskedScatterGetWorkspaceSize(aclTensor* selfRef, const aclTensor* mask, const aclTensor* source, uint64_t* workspaceSize, aclOpExecutor** executor)
  • aclnnStatus aclnnInplaceMaskedScatter(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)

aclnnInplaceMaskedScatterGetWorkspaceSize

  • Parameters:

    • selfRef (aclTensor*, compute input/output): aclTensor on the device. The data format can be ND. Non-contiguous tensors are supported.
      • Atlas training series products and Atlas inference series products: The data type can be FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, or BOOL.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training series products/Atlas A3 inference series products: The data type can be FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL, or BFLOAT16.
    • mask (aclTensor*, compute input): aclTensor on the device. The data type can be BOOL or UINT8. The shape cannot be greater than that of selfRef. The shapes of mask and selfRef must meet the broadcast relationship. The data format can be ND.
    • source (aclTensor*, compute input): aclTensor on the device. The data format supports ND. The data type must be the same as that of selfRef. The number of elements must be greater than or equal to the number of elements whose value is true in mask.
      • Atlas training series products and Atlas inference series products: The data type can be FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, or BOOL.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training series products/Atlas A3 inference series products: The data type can be FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL, or BFLOAT16.
    • workspaceSize (uint64_t*, output): size of the workspace to be allocated on the device.
    • executor (aclOpExecutor**, output): operator executor, containing the operator computation process.

  • Returns:

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

    The first-phase API implements input parameter verification. The following errors may be thrown:
161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The passed selfRef, mask, and source are null pointers.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data types of selfRef and mask are not supported.
                                      2. Broadcasting cannot be performed for the shapes of selfRef and mask.
                                      3. The shape dimensions of mask are greater than those of selfRef.
                                      4. The data types of source and selfRef are inconsistent.

aclnnInplaceMaskedScatter

  • Parameters:

    • workspace (void*, input): address of the workspace to be allocated on the device.
    • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by the first-phase API aclnnInplaceMaskedScatterGetWorkspaceSize.
    • executor (aclOpExecutor*, input): operator executor, containing the operator computation process.
    • stream (aclrtStream, input): stream for executing the task.

  • Returns:

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

Constraints

  • Deterministic compute:
    • aclnnInplaceMaskedScatter defaults to a deterministic implementation.

Example

The following example is for reference only. For details, see Compilation and Running Sample.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_masked_scatter.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) {
  // (Fixed writing) Initialize resources.
  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 memory on the device.
  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 the data on the host to the memory on the device.
  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);

  // Compute 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 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. (Fixed writing) Initialize the device and stream. For details, see the ACL API manual.
  // Set the device ID in use.
  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 based on the API.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> maskShape = {4, 2};
  std::vector<int64_t> sourceShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* maskDeviceAddr = nullptr;
  void* sourceDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* mask = nullptr;
  aclTensor* source = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<int8_t> maskHostData = {false,false,false,false,true,true,true,true};
  std::vector<float> sourceHostData={10,10,10,10,10,10,10,10};
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create a mask aclTensor.
  ret = CreateAclTensor(maskHostData, maskShape, &maskDeviceAddr, aclDataType::ACL_BOOL, &mask);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create a source aclTensor.
  ret = CreateAclTensor(sourceHostData, sourceShape, &sourceDeviceAddr, aclDataType::ACL_FLOAT, &source);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API, which needs to be replaced with the actual API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnInplaceMaskedScatter.
  ret = aclnnInplaceMaskedScatterGetWorkspaceSize(self, mask, source, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceMaskedScatterGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on 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 aclnnInplaceMaskedScatter.
  ret = aclnnInplaceMaskedScatter(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceMaskedScatter failed. ERROR: %d\n", ret); return ret);

  // 4. (Fixed writing) Wait until the task execution is 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 the configuration based on the API definition.
  auto size = GetShapeSize(selfShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
                    size * sizeof(float), 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("result[%ld] is: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor and aclScalar. Modify the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(mask);
  aclDestroyTensor(source);

  // 7. Release device resources. Modify the configuration based on the API definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(maskDeviceAddr);
  aclrtFree(sourceDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}
我们使用cookie来确保您的高速浏览体验。继续浏览本站，即表示您同意我们使用cookie。查看详情