aclnnReplicationPad1dBackward

📄 View Source Code

Applicable Products

Function

• Description: Backward propagation of replication_pad1d. For forward computation, see aclnnReplicationPad1d.

• Example:

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

Function Prototype

Each operator is divided into a two-phase API. First call the "aclnnReplicationPad1dBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnReplicationPad1dBackward" API to perform the computation.

aclnnStatus aclnnReplicationPad1dBackwardGetWorkspaceSize(
    const aclTensor   *gradOutput,
    const aclTensor   *self,
    const aclIntArray *padding,
    aclTensor         *gradInput,
    uint64_t          *workspaceSize,
    aclOpExecutor    **executor)

aclnnStatus aclnnReplicationPad1dBackward(
    void          *workspace,
    uint64_t       workspaceSize,
    aclOpExecutor *executor,
    aclrtStream    stream)

aclnnReplicationPad1dBackwardGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  gradOutput (aclTensor*)	Input	-	The dimension must be consistent with self and gradInput, and the shape must be consistent with the output of replication_pad1d forward propagation.	Consistent with self.	ND	2-3	√
  self (aclTensor*)	Input.	-	The dimension must be consistent with gradOutput and gradInput, and the shape must be consistent with gradInput.	BFLOAT16, FLOAT16, FLOAT32, DOUBLE, COMPLEX64, COMPLEX128	ND	2-3	√
  padding (aclIntArray*)	Input	Has a length of 2, where the values represent the number of values to pad on the left and right sides, respectively.	Both values of padding must be less than the value of the last dimension of self.	INT64	-	-	-
  gradInput（aclTensor*）	Output	-	-	Same as self.	ND	Same as self.	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be requested 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 non-batch-size dimension with a value of 0.
  		The gradOutput shape must be consistent with the output of replication_pad1d forward propagation.

aclnnReplicationPad1dBackward

• 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 by the first-phase API aclnnReplicationPad1dBackwardGetWorkspaceSize.
  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:

  • aclnnReplicationPad1dBackward 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_pad1d_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);

    // Copy host-side data to 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 the aclCreateTensor API.
    *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 the deviceId based on your actual device.
    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, 4};
    std::vector<int64_t> selfShape = {1, 2};
    std::vector<int64_t> gradInputShape = {1, 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};
    std::vector<float> selfHostData = {1, 2};
    std::vector<int64_t> paddingData = {1, 1};
    std::vector<float> gradInputHostData = {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(), 2);
    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 aclnnReplicationPad1dBackward.
    ret = aclnnReplicationPad1dBackwardGetWorkspaceSize(gradOutput, self, padding, gradInput, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad1dBackwardGetWorkspaceSize 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 aclnnReplicationPad1dBackward.
    ret = aclnnReplicationPad1dBackward(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad1dBackward 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. 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;
}