EnableMultiCoreSplitK

Function Usage

In the multi-core scenario, this API is used to enable K-axis splitting. If this API is not called, the K axis is not split by default. This API is used before the GetTiling API is called.

Prototype

void EnableMultiCoreSplitK(bool flag)

Parameters

**Table 1** Parameters
Parameter	Input/Output	Description
flag	Input	Whether to enable K-axis splitting. true: K-axis splitting is enabled. false: K-axis splitting is disabled.

Returns

None

Restrictions

When this API is used in an operator, the result of matrix C can be output only to.
When this API is used in an operator, the result of matrix C tiling must be cleared before being written to the kernel for the first time. Then, AtomicAdd is enabled to accumulate the result of matrix C tiling. If the data is not cleared in advance, precision problems may occur due to invalid data in the accumulation.
When this API is used in an operator, Bias cannot participate in matrix multiplication.

Examples

For details about the complete operator example, see.

auto ascendcPlatform = platform_ascendc::PlatformAscendC(context->GetPlatformInfo())
matmul_tiling::MultiCoreMatmulTiling tiling(ascendcPlatform);  
tiling->SetDim(useCoreNums);
tiling->SetAType(matmul_tiling::TPosition::GM, matmul_tiling::CubeFormat::ND, matmul_tiling::DataType::DT_FLOAT16);
tiling->SetBType(matmul_tiling::TPosition::GM, matmul_tiling::CubeFormat::ND, matmul_tiling::DataType::DT_FLOAT16);
tiling->SetCType(matmul_tiling::TPosition::GM, matmul_tiling::CubeFormat::ND, matmul_tiling::DataType::DT_FLOAT);
tiling->SetBiasType(matmul_tiling::TPosition::GM, matmul_tiling::CubeFormat::ND, matmul_tiling::DataType::DT_FLOAT);
tiling->SetShape(M, N, K);
tiling->SetOrgShape(M, N, K);
tiling->SetBias(false);
tiling->SetBufferSpace(-1, -1, -1);
tiling->EnableMultiCoreSplitK(true);  // Enable the K axis.

optiling::TCubeTiling tilingData;
int ret = tiling.GetTiling(tilingData);

Parent topic: Matmul Tiling