aclnnResize

📄 View Source Code

Applicable Products

Function

• Description: Adjusts the size of the input tensor based on scales.

• Formula:

  $$out\_dimension = floor(self\_dimension * scales)$$

  Where:

  • $self\_dimension$ is the values of the H and W axes of the input self shape.
  • $out\_dimension$ is the values of the H and W axes of the output out shape.
  • $scales$ is the scaling factor for the input self.

Function Prototype

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

aclnnStatus aclnnResizeGetWorkspaceSize(
  const aclTensor*     self,
  const aclFloatArray* scales,
  const char*          mode,
  aclTensor*           out,
  uint64_t*            workspaceSize,
  aclOpExecutor**      executor)

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

aclnnResizeGetWorkspaceSize

• Parameters

  Parameter Name	Input/Output	Description	Usage Notes	Data Type	Data Format	Dimension (shape)	Non-Contiguous Tensor
  self (aclTensor*)	Input	Input tensor, corresponding to `self` in the formula.	Empty Tensor is not supported.	FLOAT16, FLOAT32, BFLOAT16	NCHW, NHWC	4	√
  scales (aclFloatArray*)	Input	Specifies the multiples by which the self tensor is scaled, corresponding to `scales` in the formula.	The length is the same as the self dimension. Currently, only the H and W dimensions of self are supported for adjustment. The other N and C dimensions of scales must remain 1.	FloatArray	-	-	-
  mode (char*)	Input	Indicates the interpolation mode.	Only nearest or bilinear is supported.	-	-	-	-
  out (aclTensor*)	Output	Output tensor, corresponding to `out` in the formula.	Empty tensors are not supported. The data format and data type must be consistent with the input `self`. The N axis and C axis of the shape must be consistent with the input `self`. The H axis and W axis of the shape satisfy out_dimension = floor(self_dimension * scales).	FLOAT16, FLOAT32, BFLOAT16	NCHW, NHWC	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 process.	-	-	-	-	-

  • Atlas inference products, Atlas training products, Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products:
    • The data type of the self and out parameters does not support BFLOAT16.
    • The data format of parameters self and out does not support NHWC.

• 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	A null pointer exists in the input self, scales, mode, or out.
  ACLNN_ERR_PARAM_INVALID	161002	mode is not in the supported list.
  		The data type is not within the supported range.
  		The data format or data type of out and self is inconsistent.
  		The shape does not meet the requirements: The shapes of self and out must be 4-dimensional. The N and C dimensions of self and out must be the same. The size of out in the H dimension must equal the size of self in the H dimension multiplied by the value of scales corresponding to the H dimension. The size of out in the W dimension must equal the size of self in the W dimension multiplied by the value of scales corresponding to the W dimension.

aclnnResize

• Parameters

  Parameter Name	Input/Output	Description
  workspace	Input	Workspace memory address applied on the Device side.
  workspaceSize	Input	Workspace size applied on the Device side, obtained from the first-phase API aclnnResizeGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	Specifies the stream for executing the task.

• Return Value

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

Constraints

• Deterministic computation:
  • aclnnResize 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 <unistd.h>
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_resize.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)
{
    // 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 memory on the device side.
    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 data from the host side to the device 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_NCHW, shape.data(), shape.size(),
        *deviceAddr);
    return 0;
}

int main()
{
    // 1. (Boilerplate) Initialize device/stream. See the acl API manual.
    // Fill in 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, 1, 2, 2};
    std::vector<int64_t> outShape = {1, 1, 4, 4};

    void* selfDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;

    aclTensor* self = nullptr;
    aclTensor* out = nullptr;

    std::vector<float> selfHostData = {1.0, 2.0, 3.0, 4.0};
    std::vector<float> scalesData = {1.0, 1.0, 2.0, 2.0};
    std::vector<float> outHostData(16);

    // Create the self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // Create the out aclTensor.
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    aclFloatArray* scales = nullptr;
    scales = aclCreateFloatArray(scalesData.data(), scalesData.size());
    CHECK_RET(scales != nullptr, return 0);

    // 3. Call the CANN operator library API. Replace with the specific API as needed.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    const char* mode = "nearest";
    // Call the first-phase API of aclnnResize.
    ret = aclnnResizeGetWorkspaceSize(self, scales, mode, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnResizeGetWorkspaceSize 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;);
        printf("workspaceSize: %ld\n", workspaceSize);
    }
    // Call the second-phase aclnnResize API.
    ret = aclnnResize(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnResize 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. Modify 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 and aclScalar. Modify based on the specific API definition.
    aclDestroyTensor(self);
    aclDestroyTensor(out);
    aclDestroyFloatArray(scales);

    // 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();
    sleep(10);
    return 0;
}