GetSwiGLUMaxMinTmpSize

Function

To perform SwiGLU computation in the kernel, developers need to reserve or allocate the temporary space. This API is used to obtain the maximum and minimum temporary space sizes to be reserved or allocated on the host. Developers can select proper sizes within this range as the tiling parameters and pass them to the kernel.

To ensure correct functions, the temporary space to be reserved or allocated cannot be less than the minimum temporary space.
Within the range between the minimum and maximum, as the temporary space increases, the API computing performance in the kernel can be optimized to some extent. For better performance, reserve or allocate the temporary space based on the actual memory usage.

Prototype

void GetSwiGLUMaxMinTmpSize(const ge::Shape& srcShape, const uint32_t typeSize, uint32_t& maxValue, uint32_t& minValue, const bool isReuseSource)

Parameters

**Table 1** API parameters
Parameter	Input/Output	Description
srcShape	Input	Input shape.
typeSize	Input	Size of the input data type, in bytes. For example, if the input data type is half, set this parameter to 2.
maxValue	Output	Maximum size of the temporary space required by SwiGLU computation. Any space exceeding this value will not be utilized by the API. Within the range between the minimum and maximum, as the temporary space increases, the API computing performance in the kernel can be optimized to some extent. For better performance, reserve or allocate the temporary space based on the actual memory usage. If the maximum space size is 0, no temporary space is required. NOTE: maxValue is for reference only and may be larger than the remaining space of the Unified Buffer. In this case, select a proper temporary space size based on the remaining space of the Unified Buffer.
minValue	Output	Minimum size of the temporary space required by SwiGLU computation. To ensure correct functions, the temporary space to be reserved or allocated during API computation cannot be less than the value of this parameter. If the minimum space size is 0, no temporary space is required.
isReuseSource	Input	Whether to reuse the space of the source operand input, which must be the same as that of the API in the kernel.

Returns

None

Restrictions

None

Example

// The input shape is 1024. The operator input data is of the half type. The source operand cannot be modified.
std::vector<int64_t> shape_vec = {1024};
ge::Shape shape(shape_vec);
uint32_t max;
uint32_t min;
AscendC::GetSwiGLUMaxMinTmpSize(shape, 2, max, min, false);

Parent topic: SwiGLU APIs