"...composable_kernel_rocm.git" did not exist on "3e3471d5d28e857c8d95dece447b2f9e18c90b4c"
Commit ca74a0e7 authored by Artur Wojcik's avatar Artur Wojcik
Browse files

Merge branch 'uif2-initial' into uif2-migraphx

parents a48dd222 dd07d198
...@@ -100,6 +100,8 @@ template <> ...@@ -100,6 +100,8 @@ template <>
inline __host__ __device__ f8_t type_convert<f8_t, float>(float x) inline __host__ __device__ f8_t type_convert<f8_t, float>(float x)
{ {
#if defined(__gfx940__) || defined(__gfx941__) || defined(__gfx942__) #if defined(__gfx940__) || defined(__gfx941__) || defined(__gfx942__)
float max_fp8 = 240.0f;
x = x > max_fp8 ? max_fp8 : (x < -max_fp8 ? -max_fp8 : x);
union union
{ {
float fval; float fval;
......
...@@ -75,8 +75,8 @@ int profile_gemm_impl(int do_verification, ...@@ -75,8 +75,8 @@ int profile_gemm_impl(int do_verification,
b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5}); b_k_n.GenerateTensorValue(GeneratorTensor_2<BDataType>{-5, 5});
break; break;
default: default:
a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 1.0}); a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{0.0, 0.1});
b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.5, 0.5}); b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-0.05, 0.05});
} }
using AElementOp = ck::tensor_operation::element_wise::PassThrough; using AElementOp = ck::tensor_operation::element_wise::PassThrough;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment