aclnnUpsampleNearestExact1d

📄 View Source Code

Applicable Products

Description

• Function: Applies nearest-neighbor interpolation 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:$$out(N, C, l) = self(N, C, min(floor((l + 0.5) * scales), L-1))$$

Function Prototype

Each operator is divided into a two-phase API. The aclnnUpsampleNearestExact1dGetWorkspaceSize API must be called first to obtain the required workspace size and the executor that encapsulates the operator's computation process. Then, the aclnnUpsampleNearestExact1d API is called to perform the computation.

aclnnStatus aclnnUpsampleNearestExact1dGetWorkspaceSize(
  const aclTensor   *self,
  const aclIntArray *outputSize,
  double             scales,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor    **executor)

aclnnStatus aclnnUpsampleNearestExact1d(
  void             *workspace,
  uint64_t          workspaceSize,
  aclOpExecutor    *executor,
  aclrtStream       stream)

aclnnUpsampleNearestExact1dGetWorkspaceSize

• Parameters

  Parameter Name	Input/Output	Description	Usage Notes	Data Type	Data Format	Dimensions (Shape)	Non-Contiguous Tensor
  self (aclTensor*)	Input	The input `self` in the formula, representing the input tensor to be upsampled.	Empty tensors are not supported. When the data format is ND, it is processed as NCL format by default.	FLOAT32, FLOAT16, BFLOAT16	NCL, ND	3	√
  outputSize (aclIntArray*)	Input	Specifies the spatial size of `out` in the L dimension.	The size is 1, and the value must be greater than zero.	INT64	-	-	-
  scales (double)	Input	The input scales in the formula, specifying the scaling multiplier for the spatial size.	-	-	-	-	-
  Output (aclTensor*)	Output	The output `out` in the formula, representing the output tensor after sampling.	Empty tensors are not supported. The data type and data format must be consistent with the input `self`.	FLOAT32, FLOAT16, BFLOAT16	NCL, ND	3	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size that the user needs to allocate on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation process.	-	-	-	-	-

  • Atlas inference products:

    The input self and output 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	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 data types of self and out are inconsistent.
  		The shape of self is not 3-dimensional.

aclnnUpsampleNearestExact1d

• Parameters

  Parameter Name	Input/Output	Description
  workspace	Input	Address of the workspace memory applied on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device, obtained through the first-phase API aclnnUpsampleNearestExact1dGetWorkspaceSize.
  executor	Input	Operator executor, which encapsulates 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

• The parameters self, outputSize, and scales must satisfy the following constraint:

  $$outputSize = floor(self\_L * scales)$$

• Deterministic computation:

  • aclnnUpsampleNearestExact1d 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_exact1d.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)
{
  // Standard practice: 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 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 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 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 aclCreateTensor 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. (Standard practice) Initialize device/stream. See the acl API manual.
    // Specify the deviceId based on your actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check result as needed.
    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.
    int64_t outSize = 5;
    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(outSize);

    double scales = 0.0;

    // 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 aclnnUpsampleNearestExact1d.
    ret = aclnnUpsampleNearestExact1dGetWorkspaceSize(self, outputSizeArray, scales, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS,
        LOG_PRINT("aclnnUpsampleNearestExact1dGetWorkspaceSize 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 aclnnUpsampleNearestExact1d.
    ret = aclnnUpsampleNearestExact1d(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearestExact1d 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 device memory to host memory. Modify this based on 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;
}