aclnnNorm

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference products	√
Atlas training products	√

Function

Description: Returns the matrix norm or vector norm of a given tensor.
Formula: Supports 1/2 norm, infinity norm, and other norm calculations where p is of float type.
- p = 1 norm:
  $\Vert x \Vert = \sum_{i=1}^{N}{\vert x_i \vert}$
- p = 2 norm (default value):
  $\Vert x \Vert_2 = (\sum_{i=1}^{N}{\vert x_i \vert^2})^{\frac{1}{2}}$
- p = infinity norm:
  $\Vert x \Vert_\infty = \max\limits_{i}{\vert x_i \vert}$ $\Vert x \Vert_{-\infty} = \min\limits_{i}{\vert x_i \vert}$
- p = other norms:
  $\Vert x \Vert_p = (\sum_{i=1}^{N}{\vert x_i \vert^p})^{\frac{1}{p}}$

Function Prototype

Each operator is divided into a two-phase API. The "aclnnNormGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnNorm" API is called to perform the computation.

aclnnStatus aclnnNormGetWorkspaceSize(
  const aclTensor     *self,
  const aclScalar     *pScalar,
  const aclIntArray   *dim,
  bool                 keepdim,
  aclTensor           *out,
  uint64_t            *workspaceSize,
  aclOpExecutor      **executor)

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

aclnnNormGetWorkspaceSize

Parameters

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
Self (aclTensor*)	Input	x in the formula.	Supports empty tensors.	FLOAT32、FLOAT16、BFLOAT16	ND	0-8	√
pScalar (aclScalar*)	Input	Indicates the type of norm, i.e., p in the formula.	Supports 0/1/2/3 norm and infinity norm.	FLOAT32	-	-	-
dim (aclIntArray*)	Input	Dimensions along which to compute the norm of self.	Supports [-N, N-1], where N is the dimension of self. Elements in dims must not be duplicated. Negative values are supported.	INT64	-	-	-
keepdim (bool)	Input	Determines whether the output tensor retains the axis specified by the dim parameter.	-	-	-	-	-
out (aclTensor*)	Output	out in the formula.	If keepdim is true, the shape of all dimensions except the dimension specified by dim (whose size is 1) must be consistent with self. If keepdim is false, the reduced dimension is not retained, and the shapes of the remaining dimensions must be consistent with self.	FLOAT32, FLOAT16, BFLOAT16	ND	0-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for 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 self, pScalar, dim, or out parameter passed in is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data format of self is not within the supported range.
		The data types of dim and keepdim do not meet the API input parameter requirements.
		dim exceeds the range of [-N, N-1] (where N is the dimension of self).
		dim contains duplicate values.
		The shape of self or out exceeds 8 dimensions.
		The shape of out is not equal to the shape derived from self, dim, and keepdim.

aclnnNorm

Parameters

Parameter	Input/Output	Description
workspace	Input	Address of the workspace memory applied for on the device side.
workspaceSize	Input	Size of the workspace applied for on the device side, obtained by the first-phase API aclnnNormGetWorkspaceSize.
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 Code.

Constraints

deterministic computation
- aclnnNorm 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_norm.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 for 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);
    // 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);

    // 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];
    }

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

int main()
{
    // 1. (Boilerplate) Initialize the device/stream. For details, see the ACL API manual.
    // Set deviceId based on the actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ACL_SUCCESS, 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 = {4, 2};
    std::vector<int64_t> outShape = {1, 2};

    void* selfDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    aclTensor* self = nullptr;
    aclTensor* out = nullptr;
    aclScalar* pScalar = nullptr;
    aclIntArray* dim = nullptr;

    std::vector<float> selfHostData = {0.1, 1.1, 2.1, 3.1, 4.1, 5.1, 6.1, 7.1};
    std::vector<float> outHostData = {0.0, 0.0};
    std::vector<int64_t> dimData = {0};
    float pValue = 0.0f;
    bool keepdim = true;

    // 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);
    // Create the p aclTensor.
    pScalar = aclCreateScalar(&pValue, aclDataType::ACL_FLOAT);
    CHECK_RET(pScalar != nullptr, return ret);
    // Create the dim aclIntArray.
    dim = aclCreateIntArray(dimData.data(), 1);
    CHECK_RET(dim != nullptr, return ret);

    // 3. Call the CANN operator library API. Replace with the actual API name.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnNorm.
    ret = aclnnNormGetWorkspaceSize(self, pScalar, dim, keepdim, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNormGetWorkspaceSize 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 aclnnNorm.
    ret = aclnnNorm(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNorm 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 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(resultData[0]),
        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);
    aclDestroyIntArray(dim);
    aclDestroyScalar(pScalar);
    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;
}