aclnnCircularPad2dBackward

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	×
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: Backward propagation of circular_pad2d. For forward computation, see aclnnCircularPad2d.

Example:

Input gradOutput([[[1, 1, 1, 1, 1, 1, 1]]])
self([[[1, 1, 1, 1, 1]]])
padding([1, 1, 0, 0])
The output is([[2, 1, 1, 1, 2]])

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnCircularPad2dBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnCircularPad2dBackward" API to perform the computation.

aclnnStatus aclnnCircularPad2dBackwardGetWorkspaceSize(
    const aclTensor*   gradOutput,
    const aclTensor*   self,
    const aclIntArray* padding,
    aclTensor*         gradInput,
    uint64_t*          workspaceSize,
    aclOpExecutor**    executor)

aclnnStatus aclnnCircularPad2dBackward(
    void*          workspace,
    uint64_t       workspaceSize,
    aclOpExecutor* executor,
    aclrtStream    stream)

aclnnCircularPad2dBackwardGetWorkspaceSize

Parameters

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
gradOutput (aclTensor*)	Input	Gradient data input during backward propagation.	The shape dimensions must be consistent with self and gradInput, and the shape must be consistent with the output of the circular_pad2d forward propagation.	The shape must be consistent with the output of the circular_pad2d forward propagation.	ND	3-4	√
self (aclTensor*)	Input	Original input data to be padded during forward propagation.	The shape dimensions must be consistent with gradOutput and gradInput. The shape is consistent with gradInput.	FLOAT16, BFLOAT16, FLOAT32	ND	3-4	√
padding (aclIntArray*)	Input	Dimensions padded during forward propagation.	The data format length is 4, and the values represent the padding amounts for left, right, top, and bottom in sequence. The first two values of padding must each be less than the size of the last dimension of self, and the last two values must each be less than the size of the second-to-last dimension of self.	INT64	ND	-	-
gradInput (aclTensor*)	Output	Gradient data output during backward propagation.	-	Same as self	ND	shape must be consistent with self.	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation process.	-	-	-	-	-

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	Any of gradOutput, self, padding, or gradInput 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 dimension other than the 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_pad2d forward propagation.

aclnnCircularPad2dBackward

Parameters:

Parameter	Input/Output	Description
workspace	Input	Workspace memory address requested on the Device side.
workspaceSize	Input	Workspace size requested on the Device side, obtained from the first-phase API aclnnCircularPad2dBackwardGetWorkspaceSize.
executor	Input	Operator executor, which contains the operator computation flow.
stream	Input	Specifies the stream for task execution.

Return value

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

Constraints

Deterministic computation:
- aclnnCircularPad2dBackward defaults to a deterministic implementation.
The size of the last dimension of gradOutput must satisfy the following constraints for different data 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_pad2d_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: 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 allocate memory on the device side.
    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 data from the host side to the device 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 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. Boilerplate: device/stream initialization. See the acl API manual.
    // Set deviceId based on your actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check based on your requirements.
    CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
    // 2. Construct the input and output. Construct them based on the API definition.
    std::vector<int64_t> gradOutputShape = {1, 1, 4, 4};
    std::vector<int64_t> selfShape = {1, 1, 2, 2};
    std::vector<int64_t> gradInputShape = {1, 1, 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 = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1};
    std::vector<float> selfHostData = {1, 2, 3, 4};
    std::vector<int64_t> paddingData = {1, 1, 1, 1};
    std::vector<float> gradInputHostData = {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 the self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the padding aclIntArray.
    padding = aclCreateIntArray(paddingData.data(), 4);
    CHECK_RET(padding != nullptr, return ret);
    // Create the 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 with the specific API.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnCircularPad2dBackward.
    ret = aclnnCircularPad2dBackwardGetWorkspaceSize(gradOutput, self, padding, gradInput, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCircularPad2dBackwardGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Apply for device memory based on the workspaceSize calculated 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 aclnnCircularPad2dBackward.
    ret = aclnnCircularPad2dBackward(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCircularPad2dBackward failed. ERROR: %d\n", ret); return ret);
    // 4. Boilerplate: 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 memory to the host side. 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. Modify based on the specific API definition.
    aclrtFree(gradOutputDeviceAddr);
    aclrtFree(selfDeviceAddr);
    aclrtFree(gradInputDeviceAddr);
    if (workspaceSize > 0) {
      aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}