Documentation
Download

aclnnRsqrt&aclnnInplaceRsqrt

📄 View source code

Supported Products

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

  • Description: Computes the reciprocal of the square root of each element in the input tensor.

  • Formula:

out=1inputout = \frac{1}{\sqrt{input}}

Prototype

  • aclnnRsqrt and aclnnInplaceRsqrt implement the same function in different ways. Select a proper operator based on your requirements.

    • aclnnRsqrt: An output tensor object needs to be created to store the computation result.
    • aclnnInplaceRsqrt: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.

  • Each operator has two-phase API calls. First, aclnnRsqrtGetWorkspaceSize or aclnnInplaceRsqrtGetWorkspaceSize is called to obtain input parameters and compute the required workspace size based on the computation process. Then, aclnnRsqrt or aclnnInplaceRsqrt is called to perform computation.

    • aclnnStatus aclnnRsqrtGetWorkspaceSize(const aclTensor *self, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
    • aclnnStatus aclnnRsqrt(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)
    • aclnnStatus aclnnInplaceRsqrtGetWorkspaceSize(aclTensor* selfRef, uint64_t* workspaceSize, aclOpExecutor** executor)
    • aclnnStatus aclnnInplaceRsqrt(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)

aclnnRsqrtGetWorkspaceSize

  • Parameters:

    • self (aclTensor*, compute input): inputinput in the formula, aclTensor on the device. Non-contiguous tensors are supported. The data format can be ND, and the shape must be the same as that of out.
      • Atlas 200I/500 A2 inference products, Atlas inference products, Atlas training products;: The data type can be FLOAT, FLOAT16, DOUBLE, COMPLEX64, COMPLEX128, UINT8, INT8, INT16, INT32, INT64, or BOOL.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT, FLOAT16, DOUBLE, COMPLEX64, COMPLEX128, UINT8, INT8, INT16, INT32, INT64, BOOL, or BFLOAT16.
    • out (aclTensor *, compute output) : outout in the formula, aclTensor on the device. Non-contiguous tensors are supported. The data format can be ND, and the shape must be the same as that of self.
      • Atlas 200I/500 A2 inference products, Atlas inference products, Atlas training products: The data type can be FLOAT, FLOAT16, DOUBLE, 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 FLOAT, FLOAT16, DOUBLE, 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 passed self or out is a null pointer.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type or format of self or out is not supported.
                                 2. The shapes of self and out do not match.

aclnnRsqrt

  • Parameters:

    • workspace (void *, input): address of the workspace memory allocated on the device.
    • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling aclnnRsqrtGetWorkspaceSize.
    • 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.

aclnnInplaceRsqrtGetWorkspaceSize

  • Parameters:

    • selfRef (aclTensor *, compute input): inputinput in the formula, aclTensor on the device. Non-contiguous tensors are supported. The data format can be ND. The number of shape dimensions cannot exceed 8.
      • Atlas 200I/500 A2 inference products, Atlas inference products, Atlas training products: The data type can be FLOAT, FLOAT16, DOUBLE, 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 FLOAT, FLOAT16, DOUBLE, 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 passed selfRef is a null pointer.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type or format of selfRef is not supported.

aclnnInplaceRsqrt

  • Parameters:

    • workspace (void *, input): address of the workspace memory allocated on the device.
    • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling aclnnInplaceRsqrtGetWorkspaceSize.
    • 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:
    • aclnnRsqrt&aclnnInplaceRsqrt 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_rsqrt.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) 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 from the host to 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. (Boilerplate) Initialize the device and stream. For details, 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 based on the API definition.
  std::vector<int64_t> selfShape = {2, 2};
  std::vector<int64_t> outShape = {2, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {1, 2, 3, 4};
  std::vector<float> outHostData = {0, 0, 0, 0};
  // 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 aclnnRsqrt.
  ret = aclnnRsqrtGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnRsqrtGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the computed workspaceSize.
  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 aclnnRsqrt.
  ret = aclnnRsqrt(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnRsqrt failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) 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]);
  }

  // aclnnInplaceXxx
  // Call the first-phase API of aclnnInplaceRsqrt.
  ret = aclnnInplaceRsqrtGetWorkspaceSize(self, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceRsqrtGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on workspaceSize computed by the first-phase API.
  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 aclnnInplaceRsqrt.
  ret = aclnnInplaceRsqrt(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceRsqrt failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) 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.
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
                    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 and aclScalar. Modify the code based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

  // 7. Release device resources. Set the parameters based on the API definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}
This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details