aclnnBatchNormReduce

📄 View Source Code

Applicable Products

Function

• Description: Sums and sums of squares are computed along the axes (N, H, W) other than the C axis of the input.

• Formula:

  $$sum_i = \sum_{n=0}^{N-1} \sum_{h=0}^{H-1} \sum_{w=0}^{W-1} x_{(n,i,h,w)}$$ $$squareSum_i = \sum_{n=0}^{N-1} \sum_{h=0}^{H-1} \sum_{w=0}^{W-1} x_{(n,i,h,w)}^2$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnBatchNormReduceGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnBatchNormReduce" API to perform the computation.

aclnnStatus aclnnBatchNormReduceGetWorkspaceSize(
  const aclTensor *x,
  aclTensor       *sum,
  aclTensor       *squareSum,
  uint64_t        *workspaceSize,
  aclOpExecutor   **executor)

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

aclnnBatchNormReduceGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
  x (aclTensor*)	Input	Indicates the source data tensor to be summed. Corresponds to `x` in the formula.	Supports null tensor.	FLOAT32, FLOAT16, BFLOAT16	NCHW	4	√
  sum (aclTensor*)	Output	Output tensor representing the summation result, corresponding to `sum` in the formula.	Supports null tensor. The shape must be consistent with the value of the second dimension of the input `x`.	FLOAT32	ND	1	√
  squareSum (aclTensor*)	Output	Output tensor for the sum of squares, corresponding to `squareSum` in the corresponding formula.	Supports null tensor. The shape must be consistent with the value of the second dimension of the input `x`.	FLOAT32	ND	1	√
  workspaceSize（uint64_t*）	Output	Returns the workspace size to be applied on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return Value

  aclnnStatus: return code. For details, see aclnn Return Code.

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

  Return Code	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input parameter is a required input or output and is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of the input or output is not within the supported range.
  		The data format of the input or output is not within the supported range.
  		The shape relationship between the input and output does not meet expectations.

aclnnBatchNormReduce

• Parameters

  Parameter	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 aclnnBatchNormReduceGetWorkspaceSize.
  executor	Input	Operator executor that contains the operator computation flow.
  stream	Input	Specifies the stream that executes the task.

• Return Value

  aclnnStatus: return code. For details, see aclnn Return Code.

Constraints

• Deterministic computation:

  • aclnnBatchNormReduce defaults to a non-deterministic implementation. Deterministic computation can be enabled through aclrtCtxSetSysParamOpt.

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_batch_norm_reduce.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, aclFormat format)
{
    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);

    // Copy data from the host to the device memory by calling aclrtMemcpy.
    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);

    // Calculate 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];
    }

    // Create an aclTensor by calling the aclCreateTensor API.
    *tensor = aclCreateTensor(
        shape.data(), shape.size(), dataType, strides.data(), 0, format, shape.data(), shape.size(), *deviceAddr);
    return 0;
}

int main(int argc, char* argv[])
{
    // 1. (Boilerplate) Initialize the device/stream. See the acl API manual.
    // Set deviceId based on the actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Perform check as needed.
    CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 2. Construct inputs and outputs. Customize the construction based on the API.
    void* xDeviceAddr = nullptr;
    void* sumDeviceAddr = nullptr;
    void* squareSumDeviceAddr = nullptr;
    aclTensor* x = nullptr;
    aclTensor* sum = nullptr;
    aclTensor* squareSum = nullptr;

    std::vector<int64_t> xShape = {1, 2, 3, 4};
    std::vector<int64_t> sumShape = {2};
    std::vector<int64_t> squareSumShape = {2};
    std::vector<float> xHostData(24, 1);
    std::vector<float> sumHostData(2, 0);
    std::vector<float> squareSumHostData(2, 0);

    // Create the x aclTensor.
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x, aclFormat::ACL_FORMAT_NCHW);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the sum aclTensor.
    ret =
        CreateAclTensor(sumHostData, sumShape, &sumDeviceAddr, aclDataType::ACL_FLOAT, &sum, aclFormat::ACL_FORMAT_ND);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the squareSum aclTensor.
    ret = CreateAclTensor(
        squareSumHostData, squareSumShape, &squareSumDeviceAddr, aclDataType::ACL_FLOAT, &squareSum,
        aclFormat::ACL_FORMAT_ND);
    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 aclnnBatchNormReduce.
    ret = aclnnBatchNormReduceGetWorkspaceSize(x, sum, squareSum, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBatchNormReduceGetWorkspaceSize 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 aclnnBatchNormReduce.
    ret = aclnnBatchNormReduce(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBatchNormReduce 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 the device side memory to the host side. Modify based on the specific API definition.
    auto size = GetShapeSize(sumShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(
        resultData.data(), resultData.size() * sizeof(resultData[0]), sumDeviceAddr, size * 4,
        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(x);
    aclDestroyTensor(sum);
    aclDestroyTensor(squareSum);

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