aclnnCircularPad3dBackward

📄 View Source Code

Applicable Products

Function

Description: Computes the backward propagation of aclnnCircularPad3d.

Function Prototype

Each operator is divided into a two-phase API. First call the "aclnnCircularPad3dBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnCircularPad3dBackward" API to perform the computation.

aclnnStatus aclnnCircularPad3dBackwardGetWorkspaceSize(
    const aclTensor*   gradOutput,
    const aclTensor*   self,
    const aclIntArray* padding,
    aclTensor*         gradInput,
    uint64_t*          workspaceSize,
    aclOpExecutor**    executor)

aclnnStatus aclnnCircularPad3dBackward(
    void*          workspace,
    uint64_t       workspaceSize,
    aclOpExecutor* executor,
    aclrtStream    stream)

aclnnCircularPad3dBackwardGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
  gradOutput (aclTensor*)	Input	Gradient data input during backward propagation.	Its shape is the same as that of self and gradInput, and must be consistent with the output of the forward circular_pad3d computation.	Same as self.	ND	4-5	√
  self (aclTensor*)	Input	Original input data to be padded during the forward pass.	The shape dimension is consistent with gradOutput and gradInput, and the shape is consistent with gradInput.	FLOAT16, BFLOAT16, FLOAT32	ND	4-5	√
  padding (aclIntArray*)	Input	Dimensions padded during the forward pass.	The data format length is 6, and the values represent the padding amounts for left, right, top, bottom, front, and back, in that order. The first two values of padding must be less than the size of the last dimension of self, the middle two values must be less than the size of the second-to-last dimension of self, and the last two values must be less than the size of the third-to-last dimension of self.	INT64	ND	-	-
  gradInput (aclTensor*)	Output	Gradient data output during backward propagation.	The shape dimensions are consistent with gradOutput and self, and the shape is consistent with self.	Consistent with self.	ND	The shape is consistent with self.	√
  workspaceSize (aclOpExecutor**)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
  executor	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return Value

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

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

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The tensor is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of gradOutput, self, padding, or gradInput is not within the supported range.
  		The input shape of gradOutput, self, padding, or gradInput is outside the supported range.
  		self is an empty tensor and has a non-first dimension with a size of 0.
  		The value in padding is greater than or equal to the dimension size of self.
  		The shape of gradOutput must be consistent with the output of the circular_pad3d forward propagation.

aclnnCircularPad3dBackward

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address applied on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained by the first-phase API aclnnCircularPad3dBackwardGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	Specifies the stream on which the task is executed.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnCircularPad3dBackward defaults to a deterministic implementation.

The size of the last dimension of gradOutput must satisfy the following constraints for different types: float16/bfloat16: (0, 16362) float32: (0, 24544)

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include "acl/acl.h"
#include "aclnnop/aclnn_circular_pad3d_backward.h"
#include <iostream>
#include <vector>

#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) {
    // 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 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 the 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);

    // Calculate 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 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/stream. See the ACL API documentation.
    // Fill in the deviceId based on your actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check as needed.
    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 definition.
    std::vector<int64_t> gradOutputShape = {1, 1, 4, 4, 4};
    std::vector<int64_t> selfShape = {1, 1, 2, 2, 2};
    std::vector<int64_t> gradInputShape = {1, 1, 2, 2, 2};
    void* gradOutputDeviceAddr = nullptr;
    void* selfDeviceAddr = nullptr;
    void* gradInputDeviceAddr = nullptr;
    aclTensor* gradOutput = nullptr;
    aclTensor* self = nullptr;
    aclIntArray* padding = nullptr;
    aclTensor* gradInput = nullptr;
    std::vector<float> gradOutputHostData(64);
    for (int64_t i = 0; i < 64; i++) {
        gradOutputHostData[i] = 1;
    }
    std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8};
    std::vector<int64_t> paddingData = {1, 1, 1, 1, 1, 1};
    std::vector<float> gradInputHostData = {0, 0, 0, 0, 0, 0, 0, 0};
    // Create the gradOutput aclTensor.
    ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create padding aclIntArray.
    padding = aclCreateIntArray(paddingData.data(), 6);
    CHECK_RET(padding != nullptr, return ret);
    // Create gradInput aclTensor.
    ret = CreateAclTensor(gradInputHostData, gradInputShape, &gradInputDeviceAddr, aclDataType::ACL_FLOAT, &gradInput);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3. Call the CANN operator library API. Replace it with the specific API.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnCircularPad3dBackward.
    ret = aclnnCircularPad3dBackwardGetWorkspaceSize(gradOutput, self, padding, gradInput, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCircularPad3dBackwardGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Apply for 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 aclnnCircularPad3dBackward.
    ret = aclnnCircularPad3dBackward(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCircularPad3dBackward failed. ERROR: %d\n", ret); return ret);

    // 4. Boilerplate: synchronously wait for the 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 memory to the host memory. Modify based on the specific API definition.
    auto size = GetShapeSize(gradInputShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), gradInputDeviceAddr, 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 based on the specific API definition.
    aclDestroyTensor(gradOutput);
    aclDestroyTensor(self);
    aclDestroyIntArray(padding);
    aclDestroyTensor(gradInput);

    // 7. Release device resources.
    aclrtFree(gradOutputDeviceAddr);
    aclrtFree(selfDeviceAddr);
    aclrtFree(gradInputDeviceAddr);
    if (workspaceSize > 0){
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}