aclnnUpsampleNearestExact2d

📄 View Source Code

Applicable Products

Description

• Description: Applies the nearest neighbor interpolation algorithm to the input signal consisting of multiple input channels for upsampling. If the input shape is (N, C, H, W), the output shape is (N, C, outputSize[0], outputSize[1]).
• Formula:$$h_{src} = min(floor((h_{dst} + 0.5) / scalesH), H - 1),scalesH = outputSize[0] / H$$ $$w_{src} = min(floor((w_{dst} + 0.5) / scalesW), W - 1),scalesW = outputSize[1] / W$$ $$out(N, C, h_{dst}, w_{dst}) = self(N, C, h_{src}, w_{src})$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnUpsampleNearestExact2dGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnUpsampleNearestExact2d" API to execute the computation.

aclnnStatus aclnnUpsampleNearestExact2dGetWorkspaceSize(
  const aclTensor   *self,
  const aclIntArray *outputSize,
  double             scalesH,
  double             scalesW,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor    **executor)

aclnnStatus aclnnUpsampleNearestExact2d(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnUpsampleNearestExact2dGetWorkspaceSize

• Parameters

  Parameter Name	Input/Output	Description	Usage Description	Data Type	Data Format	Dimension (shape)	Non-Contiguous Tensor
  self (aclTensor*)	Input	Indicates the input tensor for upsampling, corresponding to the input `self` in the formula.	Empty tensor is supported. When the data format is ND, it is processed in NCHW format by default.	FLOAT32, FLOAT16, BFLOAT16	NCHW, NHWC, ND	4	√
  outputSize (aclIntArray*)	Input	Indicates the spatial size of the specified `out` in the H and W dimensions, corresponding to `outputSize` in the formula.	size is 2.	INT64	-	-	-
  scalesH (double)	Input	Indicates Specified scaling multiplier for the spatial size in the H direction, corresponding to `scalesH` in the Corresponding Formula.	Negative values cannot be passed in.	-	-	-	-
  scalesW (double)	Input	Indicates the scaling multiplier for the spatial size in the W direction, corresponding to `scalesW` in the corresponding formula.	Negative values cannot be passed in.	-	-	-	-
  out (aclTensor*)	Output	Indicates the output tensor after sampling, corresponding to the output `out` in the formula.	Empty Tensor is supported. The data type is consistent with the input parameter `self`. The N axis and C axis of the shape are consistent with the input parameter `self`.	FLOAT32, FLOAT16, BFLOAT16	NCHW, NHWC, ND	4	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas inference products:

    The data type of the self and out parameters only supports FLOAT32 and FLOAT16.

• Return Value

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

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

aclnnUpsampleNearestExact2d

• Parameters

  Parameter Name	Input/Output	Description
  workspace	Input	Workspace memory address applied on the Device side.
  workspaceSize	Input	Size of the workspace applied on the Device side, obtained by the first-phase API aclnnUpsampleNearestExact2dGetWorkspaceSize.
  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

• The parameters self, outputSize, scalesH, and scalesW must satisfy the following constraints:

  $$outputSize\_H = floor(self\_H * scalesH)$$ $$outputSize\_W = floor(self\_W * scalesW)$$

• Deterministic computation:

  • aclnnUpsampleNearestExact2d uses deterministic implementation by default.

Example

The sample code is as follows, for reference only. For the specific compilation and execution process, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_upsample_nearest_exact2d.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: 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);

    // 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 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 the aclCreateTensor API to create an aclTensor.
    *tensor = aclCreateTensor(
        shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_NCHW,
        shape.data(), shape.size(), *deviceAddr);
    return 0;
}

int main() {
    // 1. (Boilerplate) Initialize the device/stream. See the acl API manual.
    // Fill in 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 = 32;
    std::vector<int64_t> selfShape = {1, 1, 4, 2};
    std::vector<int64_t> outShape = {1, 1, 8, 4};
    void* selfDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    aclTensor* self = nullptr;
    aclTensor* out = nullptr;
    std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
    std::vector<int64_t> outputSizeHostData = {8, 4};
    std::vector<float> outHostData(outSize, 0);

    double scalesH = 0.0;
    double scalesW = 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(), 2);
    // 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 aclnnUpsampleNearestExact2d.
    ret = aclnnUpsampleNearestExact2dGetWorkspaceSize(
        self, outputSizeArray, scalesH, scalesW, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS,
        LOG_PRINT("aclnnUpsampleNearestExact2dGetWorkspaceSize 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 aclnnUpsampleNearestExact2d.
    ret = aclnnUpsampleNearestExact2d(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUpsampleNearestExact2d 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 side. 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;
}