aclnnReplicationPad3dBackward

📄 View Source Code

Applicable Products

Function

Computes the backward propagation of aclnnReplicationPad3d.

Function Prototype

Each operator is divided into a two-phase API. First call the "aclnnReplicationPad3dBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnReplicationPad3dBackward" API to perform the computation.

aclnnStatus aclnnReplicationPad3dBackwardGetWorkspaceSize(
    const aclTensor*   gradOutput,
    const aclTensor*   self,
    const aclIntArray* padding,
    aclTensor*         gradInput,
    uint64_t*          workspaceSize,
    aclOpExecutor**    executor)

aclnnStatus aclnnReplicationPad3dBackward(
    void*             workspace,
    uint64_t          workspaceSize,
    aclOpExecutor*    executor,
    const aclrtStream stream)

aclnnReplicationPad3dBackwardGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  gradOutput (aclTensor*)	Input	Input of backward propagation.	Supports four-dimensional or five-dimensional dimensions, consistent with self and gradInput. The shape and dtype must be consistent with the output out of the forward propagation aclnnReplicationPad3d.	FLOAT16, FLOAT32, BFLOAT16, DOUBLE, COMPLEX64, COMPLEX128.	ND	4-5	√
  self (aclTensor*)	Input	Input tensor of the forward pass.	Supports four-dimensional or five-dimensional input, consistent with gradOutput and gradInput. The shape and dtype must be consistent with gradInput.	FLOAT16, FLOAT32, BFLOAT16, DOUBLE, COMPLEX64, COMPLEX128	ND	4-5	√
  padding (aclIntArray*)	Input.	-	Length is 6. The values represent the padding amounts for left, right, top, bottom, front, and back, respectively. 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	-	-	-
  gradInput (aclTensor*)	Output	Output of the backward propagation.	Dimension supports four-dimensional or five-dimensional and is consistent with gradOutput and self. The data type must be consistent with gradOutput	Consistent with self.	ND	Consistent with self.	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas training products: The BFLOAT16 data type is not supported.

• 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 dimension other than the first dimension with a value of 0.
  		A value in padding is greater than or equal to the dimension of self.
  		The gradOutput shape must be consistent with the output of the replication_pad3d forward propagation.

aclnnReplicationPad3dBackward

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnReplicationPad3dBackwardGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	Specifies the stream for task execution.

• Return Value

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

Constraints

• Deterministic computation:

  • aclnnReplicationPad3dBackward defaults to a deterministic implementation.

When the number of elements in gradOutput exceeds 30010241024, there is a risk of execution timeout.

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_replication_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 for 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);

    // Copy data from the host to the device memory by calling aclrtMemcpy.
    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];
    }

    // Create an aclTensor by calling aclCreateTensor.
    *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.
    // Enter the actual device ID.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check based on your needs.
    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 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(), 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 with the specific API.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnReplicationPad3dBackward.
    ret = aclnnReplicationPad3dBackwardGetWorkspaceSize(gradOutput, self, padding, gradInput, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad3dBackwardGetWorkspaceSize 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 aclnnReplicationPad3dBackward.
    ret = aclnnReplicationPad3dBackward(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad3dBackward failed. ERROR: %d\n", ret); return ret);

    // 4. Boilerplate: synchronously 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 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;
}