Erf

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	x
Atlas inference product AI Core	√
Atlas inference product Vector Core	x
Atlas training product	x

Function Usage

Computes error function or Gaussian error function element-wise. The formula is as follows:

$\text{[math]}$

Prototype

Pass the temporary space through the sharedTmpBuffer input parameter.

All or part of the source operand tensors are involved in computation.

template <typename T, bool isReuseSource = false, const ErfConfig& config = defaultErfConfig>
__aicore__ inline void Erf(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const LocalTensor<uint8_t>& sharedTmpBuffer, const uint32_t calCount)

All source operand tensors are involved in computation.

template <typename T, bool isReuseSource = false, const ErfConfig& config = defaultErfConfig>
__aicore__ inline void Erf( const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const LocalTensor<uint8_t>& sharedTmpBuffer)

Allocate the temporary space through the API framework.

All or part of the source operand tensors are involved in computation.

template <typename T, bool isReuseSource = false, const ErfConfig& config = defaultErfConfig>
__aicore__ inline void Erf(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const uint32_t calCount)

All source operand tensors are involved in computation.

template <typename T, bool isReuseSource = false, const ErfConfig& config = defaultErfConfig>
__aicore__ inline void Erf(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor)

Due to the complex mathematical computation involved in the internal implementation of this API, additional temporary space is required to store intermediate variables generated during computation. The temporary space can be passed by developers through the sharedTmpBuffer input parameter or allocated through the API framework.

When the sharedTmpBuffer input parameter is used for passing the temporary space, the tensor serves as the temporary space. In this case, the API framework is not required for temporary space allocation. This enables developers to manage the sharedTmpBuffer space and reuse the buffer after calling the API, so that the buffer is not repeatedly allocated and deallocated, improving the flexibility and buffer utilization.
When the API framework is used for temporary space allocation, developers do not need to allocate the space, but must reserve the required size for the space.

If sharedTmpBuffer is used, developers must allocate space for the tensor. If the API framework is used, developers must reserve the temporary space. To obtain the size of the temporary space (BufferSize) to be reserved, use the GetErfMaxMinTmpSize API.

Parameters

**Table 1** Template parameters
Parameter	Description
T	Data type of the operand. For the Atlas 350 Accelerator Card, the supported data types are half and float. For the Atlas A3 training product/Atlas A3 inference product, the supported data types are half and float. For the Atlas A2 training product/Atlas A2 inference product, the supported data types are half and float. For the Atlas inference product AI Core, the supported data types are half and float.
isReuseSource	Whether the source operand can be modified. This parameter is reserved. Pass the default value false.
config	Only the Atlas 350 Accelerator Card supports this option. Erf algorithm configuration. This is an optional parameter of the ErfConfig type. The code below describes the definition. algo: an algorithm used for internal implementation of Erf. It is of the ErfAlgo type. The supported values are as follows: PADE_APPROXIMATION (default value): high-performance algorithm. This algorithm implements the Erf API using the Padé approximation. SUBSECTION_POLYNOMIAL_APPROXIMATION: high-precision algorithm. This algorithm implements the Erf API by partitioning the input values and applying polynomial approximation with different coefficients for each segment.

enum class ErfAlgo {
    PADE_APPROXIMATION = 0,
    SUBSECTION_POLYNOMIAL_APPROXIMATION,
};

struct ErfConfig {
    ErfAlgo algo = ErfAlgo::PADE_APPROXIMATION;
};

**Table 2** API parameters
Parameter	Input/Output	Description
dstTensor	Output	Destination operand. The type is LocalTensor, and TPosition can be VECIN, VECCALC, or VECOUT.
srcTensor	Input	Source operand. The type is LocalTensor, and TPosition can be VECIN, VECCALC, or VECOUT. The source operand must have the same data type as the destination operand.
sharedTmpBuffer	Input	Temporary buffer. The type is LocalTensor, and TPosition can be VECIN, VECCALC, or VECOUT. For details about how to obtain the temporary space size (BufferSize), see GetErfMaxMinTmpSize.
calCount	Input	Number of elements involved in the computation.

Returns

None

Restrictions

The source operand address must not overlap the destination operand address.

For details about the operand address alignment requirements, see General Address Alignment Restrictions.

Example

For a complete call example, see Erf operator sample.

// dstLocal: tensor for storing the computation result
// srcLocal: input tensor involved in computation
AscendC::Erf<srcType, false>(dstLocal, srcLocal);
// algo: algorithm used internally by Erf. The default value is the high-performance algorithm. In this example, algo is the high-precision algorithm.
// static constexpr AscendC::ErfAlgo algo = AscendC::ErfAlgo::SUBSECTION_POLYNOMIAL_APPROXIMATION;
// static constexpr AscendC::ErfConfig config = { algo };
// AscendC::Erf<srcType, false, config>(dstLocal, srcLocal);

Result example:

Input (srcLocal): [2.015634   -2.3880906 -0.2151161  ... -2.5       0. 2.5      ]
Output (dstLocal): [0.99563545 -0.999268  -0.23903976 ... -0.9995931 0. 0.9995931]

Parent topic: Erf APIs