aclnnUpsampleBicubic2d

Supported Products

Product	Supported
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

API description: Applies 2D bicubic upsampling to an input signal composed of several input channels. If the shape of the input tensor x is (N, C, H, W), then the shape of the output tensor out is (N, C, outputSize[0], outputSize[1]).
Formula: For a two-dimensional interpolation point $(N, C, h, w)$ , the interpolation $out(N, C, h, w)$ may be represented as:
${out(N, C, h, w)}=\sum_{i=0}^{3}\sum_{j=0}^{3}{W(i, j)}*{f(h_i, w_j)}$ $scaleH =\begin{cases} (self.dim(2)-1) / (outputSize[0]-1) & alignCorners=true \\ 1 / scalesH & alignCorners=false\&scalesH>0\\ self.dim(2) / outputSize[0] & otherwise \end{cases}$ $scaleW =\begin{cases} (self.dim(3)-1) / (outputSize[1]-1) & alignCorners=true \\ 1 / scalesW & alignCorners=false\&scalesW>0\\ self.dim(3) / outputSize[1] & otherwise \end{cases}$
Where,
- i and j are index variables of $W(i, j)$ .
- $f(h_i, w_j)$ is the pixel value of the original image in $(h_i, w_j)$ .
- $W(i, j)$ is the weight of the bicubic anti-aliasing interpolation, which is defined as follows: $W(d) =\begin{cases} (a+2)|d|^3-(a+3)|d|^2+1 & |d|\leq1 \\ a|d|^3-5a|d|^2+8a|d|-4a & 1<|d|<2 \\ 0 & otherwise \end{cases}$ Where,
  - $a=-0.75$
  - $d = |(h, w) - (h_i, w_j)|$

Prototype

Each operator has two-phase API calls. First, aclnnUpsampleBicubic2dGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnUpsampleBicubic2d is called to perform computation.

aclnnStatus aclnnUpsampleBicubic2dGetWorkspaceSize(
  const aclTensor*   self,
  const aclIntArray* outputSize,
  const bool         alignCorners,
  const double       scalesH,
  const double       scalesW,
  aclTensor*         out,
  uint64_t*          workspaceSize,
  aclOpExecutor**    executor)

aclnnStatus aclnnUpsampleBicubic2d(
  void*          workspace,
  uint64_t       workspaceSize,
  aclOpExecutor* executor,
  aclrtStream    stream)

aclnnUpsampleBicubic2dGetWorkspaceSize

Parameters:

Name	Input/Output	Description	Precaution	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
self	Input	Input tensor for upsampling, corresponding to `self` in the formula.	Empty tensors are not supported. The data type must be the same as that of the output parameter `out`. The ND format is processed as NCHW format by default.	FLOAT32, FLOAT16, BFLOAT16	NCHW, ND, NHWC	4	√
outputSize	Input	Spatial size of `out` in the H and W dimensions. It corresponds to `outputSize` in the formula.	The size is 2, and each element is greater than 0.	INT64	-	-	-
alignCorners	Input	Whether to align corner pixels, corresponding to `alignCorners` in the formula.	If alignCorners is True, the corner pixels of the input and output tensors are aligned. Otherwise, the corner pixels are not aligned.	BOOL	-	-	-
scalesH	Input	Multiplier for spatial size in the height dimension, corresponding to `scalesH` in the formula.	-	DOUBLE	-	-	-
scalesW	Input	Multiplier for spatial size in the width dimension, corresponding to `scalesW` in the formula.	-	DOUBLE	-	-	-
out	Output	Output tensor after sampling, corresponding to `out` in the formula.	Empty tensors are not supported. The data type and format must be the same as those of `self`. The shape supports four dimensions: (batch, channel, height, width). batch and channel are from the zeroth and first dimensions of `self`, respectively. height and width are from the first and second values of `outputSize`, respectively.	FLOAT32, FLOAT16, BFLOAT16	NCHW, ND, NHWC	4	√
workspaceSize	Output	Size of the workspace required to be allocated on the device.	-	-	-	-	-
executor	Output	Operator executor, containing the operator computation process.	-	-	-	-	-

Atlas 200I/500 A2 inference products, Atlas inference products, and Atlas training products:
- Data format: The self and out parameters do not support BFLOAT16.
- Data type: The self and out parameters do not support NHWC.
Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products:

The data formats of self and out do not support NHWC.

Returns:

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

The first-phase API implements input parameter verification. The following errors may be thrown.

Return	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	The passed self, outputSize, or out is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type of self is not supported.
		The data types of self and out are inconsistent.
		The data format of self is not supported.
		The data formats of self and out are inconsistent.
		The shapes of self and out are not 4-dimensional.
		The size of outputSize is not 2.
		The size of self in the C, H, and W dimensions is less than or equal to 0.
		The value of an element of outputSize is less than or equal to 0.
		The size of out in the N and C dimensions is not equal to that of self in the N and C dimensions.
		The size of out in the H and W dimensions is not equal to the corresponding element value in outputSize.

aclnnUpsampleBicubic2d

Parameters:

Name	Input/Output	Description
workspace	Input	Address of the workspace to be allocated on the device.
workspaceSize	Input	Size of the workspace to be allocated on the device, which is obtained by calling the first-phase API aclnnUpsampleBicubic2dGetWorkspaceSize.
executor	Input	Operator executor, containing the operator computation process.
stream	Input	Stream for executing the task.

Returns:

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

Constraints

The shape constraints of self and out are as follows:
- The value of each dimension is less than or equal to 2^20.
- The N and C axes of out must be the same as those of self.
- The memory usage must be less than 60 GB. The memory size can be calculated according to the following formula:
  $(self\_H * self\_W + out\_H * out\_W + self\_H * out\_W) * N * C * sizeof(float) < 60 * 1024 * 1024 * 1024$
  Where,
  - N indicates the N axis of the input and output.
  - C indicates the C axis of the input and output.
- N * C * self_H < 2^31
Either the H and W axes of the outputSize parameter or the scalesH and scalesW parameters can be used.
- When alignCorners is set to True:
  - If the value of the corresponding axis of outputSize is equal to 1, the value of the corresponding axis of scales is 0.
  - In other cases, the values of the corresponding axes in self and outputSize are used, and $scales = (outputSize – 1)/(self – 1)$ .
- If alignCorners is set to False:
  - If the value of scalesH or scalesW is less than or equal to 0, the value of the corresponding axis in outputSize is used, that is, $scales = (outputSize/self)$ .
  - If the value of scalesH or scalesW is greater than 0, the value of scalesH or scalesW is used. That is, the value of the corresponding axis of outputSize is $floor(self\_H * scalesH)$ or $floor(self\_W * scalesW)$ .
Deterministic computing:
- aclnnUpsampleBicubic2d defaults to a deterministic implementation.

Example

The following example is for reference only. For details, see Compilation and Running Sample.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_upsample_bicubic_2d.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;
}

int Init(int32_t deviceId, aclrtStream *stream)
{
    // (Fixed writing) 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 allocate memory on the device.
    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 the data on the host to the memory on the device.
    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 the 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. (Fixed writing) Initialize the device and stream. For details, see the ACL API manual.
    // Set the device ID in use.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init failed. ERROR: %d\n", ret); return ret);

    // 2. Construct the input and output based on the API.
    std::vector<int64_t> selfShape = {1, 1, 3, 3};
    std::vector<int64_t> outShape = {1, 1, 5, 5};
    void *selfDeviceAddr = nullptr;
    void *outDeviceAddr = nullptr;
    aclTensor *self = nullptr;
    aclTensor *out = nullptr;
    std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9};
    std::vector<float> outHostData = {25, 0};
    std::vector<int64_t> outputSizeData = {5, 5};
    bool alignCorners = false;
    double scalesH = 0.0;
    double scalesW = 0.0;
    // Create a self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create an out aclTensor.
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create an outputSize aclIntArray.
    const aclIntArray *outputSize = aclCreateIntArray(outputSizeData.data(), outputSizeData.size());
    CHECK_RET(outputSize != nullptr, return ret);

    // 3. Call the CANN operator library API, which needs to be replaced with the actual API.
    uint64_t workspaceSize = 0;
    aclOpExecutor *executor;
    // Call the first-phase API of aclnnUpsampleBicubic2d.
    ret = aclnnUpsampleBicubic2dGetWorkspaceSize(
        self, outputSize, alignCorners, scalesH, scalesW, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleBicubic2dGetWorkspaceSize failed. ERROR: %d\n", ret);
              return ret);
    // Allocate device memory based on the computed workspaceSize.
    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 aclnnUpsampleBicubic2d.
    ret = aclnnUpsampleBicubic2d(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleBicubic2d failed. ERROR: %d\n", ret); return ret);

    // 4. (Fixed writing) Wait until the task execution is 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. Modify the configuration based on the API definition.
    auto size = GetShapeSize(outShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(),
        resultData.size() * sizeof(resultData[0]),
        outDeviceAddr,
        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 ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
    }

    // 6. Release aclTensor and aclIntArray. Modify the configuration based on the API definition.
    aclDestroyTensor(self);
    aclDestroyIntArray(outputSize);
    aclDestroyTensor(out);

    // 7. Release device resources. Modify the configuration based on the API definition.
    aclrtFree(selfDeviceAddr);
    aclrtFree(outDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}