Merge branch 'develop' into hip_tensor_permute

a36dff02 · arai713 · GitHub · 45c6c530 · 600fc000 · a36dff02
Unverified Commit a36dff02 authored Nov 12, 2023 by arai713 Committed by GitHub Nov 12, 2023
3 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp
--- a/profiler/include/profiler/profile_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_impl.hpp
@@ -76,7 +76,7 @@ int profile_gemm_impl(int do_verification,
        break;
    default:
        a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 0.1});
-        b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.05, 0.05});
+        b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.01, 0.01});
    }

    using AElementOp = ck::tensor_operation::element_wise::PassThrough;