aclnnUpsampleNearest1d

📄 View Source Code

Applicable Products

Function

• Function: Applies the nearest neighbor interpolation algorithm to upsample an input signal consisting of multiple input channels. If the input shape is (N, C, L), the output shape is (N, C, outputSize).

• Formula:

  $$out(N, C, l) = self(N, C, min(floor(l * scale), L-1)), \ scale = self\_L / outputSize[0]$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnUpsampleNearest1dGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnUpsampleNearest1d" API to perform the computation.

aclnnStatus aclnnUpsampleNearest1dGetWorkspaceSize(
  const aclTensor   *self,
  const aclIntArray *outputSize,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor    **executor)

aclnnStatus aclnnUpsampleNearest1d(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnUpsampleNearest1dGetWorkspaceSize

• Parameters

  Parameter Name	Input/Output	Description	Usage Notes	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
  self (aclTensor*)	Input	Represents the input data for upsampling, corresponding to `self` in the formula.	Empty tensors are not supported. The input dimension must be 3-dimensional. When the data type is DOUBLE or UINT8, the `L` dimension of the input shape must be less than 2^24.	FLOAT32, FLOAT16, BFLOAT16, DOUBLE, UINT8	NCL	3	√
  outputSize (aclIntArray*)	Input	Indicates the spatial size of the output out in the L dimension.	size is 1, and the value is greater than 0.	INT64	-	-	-
  out (aclTensor*)	Output	Represents the output result of upsampling, corresponding to `out` in the formula.	Empty tensors are not supported. The data type must be consistent with that of the input `self`.	FLOAT32, FLOAT16, BFLOAT16, DOUBLE, UINT8	NCL	3	√
  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.	-	-	-	-	-

  • Atlas inference products, Atlas training products:

    The input parameter self and output parameter out do not support the BFLOAT16 data type.

• Return Value

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

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

  Return Code	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	If the input parameter is a required input, output, or required attribute and is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002
  		The data type of self or out is not within the supported range.
  		The shape of self is not 3-dimensional.
  		The value of outputSize is 0.

aclnnUpsampleNearest1d

• Parameters

  Parameter Name	Input/Output	Description
  workspace	Input	The workspace memory address allocated on the Device side.
  workspaceSize	Input	Size of the workspace requested on the Device side, obtained through the first-phase API aclnnUpsampleNearest1dGetWorkspaceSize.
  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:
  • aclnnUpsampleNearest1d uses deterministic implementation by default.

Example

The following sample code is for reference only. For details about compilation and execution, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_upsample_nearest_1d.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 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 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);

    // Compute 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_NCL,
        shape.data(),
        shape.size(),
        *deviceAddr);
    return 0;
}

int main()
{
    // 1. (Boilerplate) Initialize the device/stream. 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 needs.
    CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 2. Construct the input and output. Customize the construction based on the API.
    std::vector<int64_t> selfShape = {1, 3, 3};
    std::vector<int64_t> outShape = {1, 3, 5};
    void *selfDeviceAddr = nullptr;
    void *outDeviceAddr = nullptr;
    aclTensor *self = nullptr;
    aclTensor *out = nullptr;
    std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8};
    std::vector<int64_t> outputSizeHostData = {5};
    std::vector<float> outHostData(15, 0);

    // Create the self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the self aclIntArray.
    auto outputSizeArray = aclCreateIntArray(outputSizeHostData.data(), 1);
    // Create the out aclTensor.
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
    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 aclnnUpsampleNearest1d.
    ret = aclnnUpsampleNearest1dGetWorkspaceSize(self, outputSizeArray, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearest1dGetWorkspaceSize failed. ERROR: %d\n", ret);
              return ret);
    // Allocate 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 aclnnUpsampleNearest1d.
    ret = aclnnUpsampleNearest1d(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearest1d failed. ERROR: %d\n", ret); return ret);
    // 4. (Standard practice) 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 device memory to host memory. Modify according to the specific API definition.
    auto size = GetShapeSize(outShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(),
        resultData.size() * sizeof(resultData[0]),
        outDeviceAddr,
        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(self);
    aclDestroyIntArray(outputSizeArray);
    aclDestroyTensor(out);

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