文档
下载
文档中心
aclnnProdDim

aclnnProdDim

Supported Products

📄 View source code

ProductSupported
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

Operator function: Returns the product of each row in a specified dimension of the input tensor.

Function Prototype

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

  • aclnnStatus aclnnProdDimGetWorkspaceSize(const aclTensor *self, int64_t dim, bool keepDim, const aclDataType dtype, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
  • aclnnStatus aclnnProdDim(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)

aclnnProdDimGetWorkspaceSize

  • Parameters:

    • self (aclTensor*, compute input): aclTensor on the device. Non-contiguous tensors are supported. The data format can be ND.

      • Atlas inference products and Atlas training products: The data type can be FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BOOL, COMPLEX64, or COMPLEX128. If the input is an empty tensor, the output type cannot be COMPLEX64 or COMPLEX128.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BOOL, COMPLEX64, COMPLEX128, or BFLOAT16. If the input is an empty tensor, the output type cannot be COMPLEX64 or COMPLEX128.

    • dim(int64_t, compute input): int64_t on the host, the dimension to be reduced.

    • keepDim(bool, compute input): bool on the host, whether to reserve dimensions for the output tensor.

    • dtype (const aclDataType, compute input): aclDataType on the host, which specifies the data type of the output tensor. The data type must be the same as that of out.

    • out (aclTensor*, compute output): aclTensor on the device. The data type is the same as that of dtype. Non-contiguous tensors are supported. The data format can be ND.

      • Atlas inference products and Atlas training products: The data type can be FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BOOL, COMPLEX64, or COMPLEX128.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BOOL, COMPLEX64, COMPLEX128, 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 input self or out is a null pointer.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of self is not supported.
                                  2. The shape of self or out exceeds eight dimensions.
                                  3. The data type of self cannot be converted to that of dtype.
                                  4. The dim value is out of range.
                                  5. The data type of dtype is different from that of out.

aclnnProdDim

  • 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 calling the first-phase API aclnnProdDimGetWorkspaceSize.

    • 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 computation:
    • aclnnProdDim defaults to a deterministic implementation.

Examples

The following examples are for reference only. For details, see Compilation and Running Sample.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_prod.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 `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 based on the API.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> outShape = {1, 2};

  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;

  std::vector<float> selfHostData = {0.1, 1.1, 2.1, 3.1, 4.1, 5.1, 6.1, 7.1};
  std::vector<float> outHostData = {0.0, 0.0};
  int64_t dim = 0;
  bool keepdim = true;

  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an `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, which needs to be replaced with the actual API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnProdDim.
  ret = aclnnProdDimGetWorkspaceSize(self, dim, keepdim, aclDataType::ACL_FLOAT, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnProdDimGetWorkspaceSize 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 aclnnProdDim.
  ret = aclnnProdDim(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnProdDim 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 to the host. Modify the code based on the API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    size * sizeof(resultData[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("result[%ld] is: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor. Modify the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

  // 7. Release device resources.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  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