GetBlockNum

Supported Products

Product	Supported/Unsupported
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference product's AI Core	√
Atlas inference product's Vector Core	x
Atlas training products	√

Function Usage

Obtains the number of cores configured for the current task, which is used for multi-core logic control in the code.

Prototype

__aicore__ inline int64_t GetBlockNum()

Parameters

None

Return Value Description

Number of cores configured for the current task

Constraints

None

Example

#include "kernel_operator.h"
// Use block_num for simple tiling computation in the core. It is recommended that complex tiling be performed on the host.
__aicore__ inline void InitTilingParam(int32_t& totalSize, int32_t& loopSize)
{
    loopSize = totalSize / AscendC::GetBlockNum();
};

Parent topic: System Variable Access