GetSwiGLUMaxMinTmpSize

Function Usage

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 sizes of the temporary space to be reserved or allocated on the host. Developers can select a proper size within this range as the tiling parameter and pass it 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 from the minimum to the maximum, as the temporary space increases, the API compute performance in the kernel can be optimized to some extent. To achieve better performance, reserve or allocate the space based on the actual buffer usage.

Prototype

1
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 from the minimum to the maximum, as the temporary space increases, the API compute performance in the kernel can be optimized to some extent. To achieve better performance, reserve or allocate the space based on the actual buffer 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 size of 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

Constraints

None

Examples

1
2
3
4
5
6
// 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);