aclnnUpsampleNearest2d

📄 View source code

Supported Products

Function

• API description: Applies the nearest neighbor interpolation algorithm to upsample the input signal composed of several input channels. If the input shape is (N, C, H, W), then the output shape is (N, C, outputSize[0], outputSize[1]).
• Formula:$$h_{src} = min(floor(h_{dst} * scalesH), H - 1)$$ $$w_{src} = min(floor(w_{dst} * scalesW), W - 1)$$ $$out(N, C, h_{dst}, w_{dst}) = self(N, C, h_{src}, w_{src})$$

Prototype

Each operator has two-phase API calls. First, aclnnUpsampleNearest2dGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnUpsampleNearest2d is called to perform computation.

aclnnStatus aclnnUpsampleNearest2dGetWorkspaceSize(
  const aclTensor   *self, 
  const aclIntArray *outputSize, 
  aclTensor         *out, 
  uint64_t          *workspaceSize, 
  aclOpExecutor    **executor)

aclnnStatus aclnnUpsampleNearest2d(
  void             *workspace, 
  uint64_t          workspaceSize, 
  aclOpExecutor    *executor, 
  const aclrtStream stream)

aclnnUpsampleNearest2dGetWorkspaceSize

• Parameters:

  Name	Input/Output	Description	Precaution	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  self	Input	Input data for upsampling, corresponding to `self` in the formula.	Empty tensors are not supported.	FLOAT32, BFLOAT16, FLOAT16, DOUBLE, UINT8	NCHW and NHWC	4	√
  outputSize	Input	Spatial size of `out` in the H and W dimensions.	Each element is not equal to zero. The size is 2.	INT64	-	-	-
  out	Output	Output result of upsampling, corresponding to `out` in the formula.	Empty tensors are not supported. The data type and format must be the same as those of self.	FLOAT32, BFLOAT16, FLOAT16, DOUBLE, UINT8	NCHW and NHWC	4	√
  workspaceSize	Output	Size of the workspace to be allocated on the device.	-	-	-	-	-
  executor	Output	Operator executor, containing the operator computation process.	-	-	-	-	-

• Atlas inference products and Atlas training products:

  The data types of the input parameter self and output parameter out do not support FLOAT or BFLOAT16.

• Returns:

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

  The first-phase API implements input parameter verification. The following errors may be thrown.

  Return	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The required input, output, or attribute is passed as a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self is not supported or is different from that of out.
  		The data format of self is not supported.
  		The shape of self is not 4D.
  		The dimension sizes of the N or C axes of self and out are different.
  		The data format of self or out is not supported.
  		outputSize contains elements whose values are 0.

aclnnUpsampleNearest2d

• Parameters:

  Name	Input/Output	Description
  workspace	Input	Address of the workspace to be allocated on the device.
  workspaceSize	Input	Size of the workspace to be allocated on the device, which is obtained by calling the first-phase API aclnnUpsampleNearest2dGetWorkspaceSize.
  executor	Input	Operator executor, containing the operator computation process.
  stream	Input	Stream for executing the task.

• Returns:

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

Constraints

• The shape constraints of self and out are as follows:

  • The value of each dimension is less than or equal to 2^20.
  • The N and C axes of out must be the same as those of self.
  • The memory usage must be less than 60 GB. The memory size can be calculated according to the following formula:$$N * (ceil(C/16) * 16) * (self\_H * self\_W + out\_H * out\_D) * sizeof(dtype) < 60 * 1024 * 1024 * 1024$$ Where,
    • N indicates the N axis of the input and output.
    • C indicates the C axis of the input and output.

• Deterministic computing:

  • aclnnUpsampleNearest2d 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_upsample_nearest_2d.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 shape_size = 1;
  for (auto i : shape) {
    shape_size *= i;
  }
  return shape_size;
}

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_NCHW,
                            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);
  // Handle the check as required.
  CHECK_RET(ret == 0, 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 = {1, 1, 4, 2};
  std::vector<int64_t> outShape = {1, 1, 8, 4};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<int64_t> outputSizeHostData = {8, 4};
  std::vector<float> outHostData(32, 0);

  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create a self aclIntArray.
  auto outputSizeArray = aclCreateIntArray(outputSizeHostData.data(), 2);
  // 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 aclnnUpsampleNearest2d.
  ret = aclnnUpsampleNearest2dGetWorkspaceSize(self, outputSizeArray, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearest2dGetWorkspaceSize 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 aclnnUpsampleNearest2d.
  ret = aclnnUpsampleNearest2d(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearest2d 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(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. Modify the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyIntArray(outputSizeArray);
  aclDestroyTensor(out);
  
  // 7. Release device resources. Modify the configuration based on the API definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}