aclnnBlendImagesCustom

Applicable Products

Description

• Function: Performs transparency multiplication on tensors rgb, frame, and alpha.

• Formula:

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnBlendImagesCustomGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnBlendImagesCustom" API to perform the computation.

aclnnStatus aclnnBlendImagesCustomGetWorkspaceSize(
  const aclTensor*      rgb,
  const aclTensor*      alpha,
  const aclTensor*      frame,
  const aclTensor*      out,
  uint64_t*             workspaceSize,
  aclOpExecutor**       executor)

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

aclnnBlendImagesCustomGetWorkspaceSize

• Parameters

  Parameter Name	Input/Output	Description	Usage Description	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  rgb (aclTensor*)	Input	Input tensor.	-	UINT8	ND	HWC (C=3), satisfying the broadcast relationship with alpha.	√
  alpha (aclTensor*)	Input	Input tensor.	-	UINT8	ND	HWC (C=1), satisfying the broadcast relationship with rgb.	√
  frame (aclTensor*)	Input	Input tensor.	-	UINT8	ND	HWC (C=3), satisfying the broadcast relationship with alpha.	√
  out (aclTensor*)	Output	Output tensor.	-	UINT8	ND	HWC (C=3), consistent with frameshape.	-
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which includes the operator computation flow.	-	-	-	-	-

• Return Value

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

  The first-phase API performs input parameter validation and reports an error in the following scenarios:

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The passed rgb, alpha, frame, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type and data format of rgb, alpha, or frame are not within the supported range.
  		The shapes of rgb, alpha, and frame cannot be broadcast. rgb and frame support HWC (C=3), and alpha supports HWC (C=1).

aclnnBlendImagesCustom

• Parameters

  Parameter Name	Input/Output	Description
  workspace	Input	The workspace memory address applied on the Device side.
  workspaceSize	Input	The workspace size allocated on the Device side, obtained through the first-phase API aclnnBlendImagesCustomGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return Value

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

Constraints

• Deterministic computation:
  • aclnnBlendImagesCustom uses deterministic implementation by default.

Example

The sample code is as follows, for reference only. For details about compilation and execution, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_blend_images_custom.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;
}

void PrintOutResult(std::vector<int64_t> &shape, void** deviceAddr) {
  auto size = GetShapeSize(shape);
  std::vector<float> resultData(size, 0);
  auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]),
                         *deviceAddr, 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);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("mean result[%ld] is: %f\n", i, resultData[i]);
  }
}

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 apply for 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);
  // Call aclrtMemcpy to copy host-side data to device-side memory.
  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 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];
  }

  // Call the aclCreateTensor API 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. (Standard practice) Initialize the device/stream. See the ACL API manual.
  // Fill in the deviceId based on your 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 inputs and outputs. Customize the construction based on the API.
  std::vector<int64_t> rgbShape = {4, 3};
  std::vector<int64_t> alphaShape = {4, 1};
  std::vector<int64_t> frameShape = {4, 3};
  std::vector<int64_t> outShape = {4, 3};

  void* rgbDeviceAddr = nullptr;
  void* alphaDeviceAddr = nullptr;
  void* frameDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;

  aclTensor* rgb = nullptr;
  aclTensor* alpha = nullptr;
  aclTensor* frame = nullptr;
  aclTensor* out = nullptr;

  std::vector<float> rgbHostData = {10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120};
  std::vector<float> alphaHostData = {255, 255, 255, 255};
  std::vector<float> frameHostData = {10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120};
  std::vector<float> outHostData = {10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120};

  ret = CreateAclTensor(rgbHostData, rgbShape, &rgbDeviceAddr, aclDataType::ACL_UINT8, &rgb);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(alphaHostData, alphaShape, &alphaDeviceAddr, aclDataType::ACL_UINT8, &alpha);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(frameHostData, frameShape, &frameDeviceAddr, aclDataType::ACL_UINT8, &frame);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_UINT8, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 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 aclnnBlendImagesCustom.
  ret = aclnnBlendImagesCustomGetWorkspaceSize(rgb, alpha, frame, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBlendImagesCustomGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);

  // Allocate device memory based on the 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 aclnnBlendImagesCustom.
  ret = aclnnBlendImagesCustom(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBlendImagesCustom failed. ERROR: %d\n", ret); return ret);

  // 4. (Standard practice) 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 the device side memory to the host side. Modify based on the specific API definition.
  PrintOutResult(outShape, &outDeviceAddr);

  // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(rgb);
  aclDestroyTensor(alpha);
  aclDestroyTensor(frame);
  aclDestroyTensor(out);

  // 7. Release device resources.
  aclrtFree(rgbDeviceAddr);
  aclrtFree(alphaDeviceAddr);
  aclrtFree(frameDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}