mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-25 07:14:37 +00:00
Fix the fp8 gemm for large tensors on MI300. (#1011)
* Fix the fp8 conversion * Try clipping value before conversion * Fix return * Simplify with a const * reduce the gemm input tensor values to reduce round-off error * replace if-else with lambda * fix syntax --------- Co-authored-by: Rostyslav Geyyer <rosty.geyyer@amd.com>
This commit is contained in:
@@ -75,8 +75,8 @@ int profile_gemm_impl(int do_verification,
|
||||
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5});
|
||||
break;
|
||||
default:
|
||||
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0});
|
||||
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5});
|
||||
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 0.1});
|
||||
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.05, 0.05});
|
||||
}
|
||||
|
||||
using AElementOp = ck::tensor_operation::element_wise::PassThrough;
|
||||
|
||||
Reference in New Issue
Block a user