diff --git a/library/src/tensor_operation_instance/gpu/gemm_mx/device_gemm_mx_xdl_f4_f4_f16/device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn.hpp b/library/src/tensor_operation_instance/gpu/gemm_mx/device_gemm_mx_xdl_f4_f4_f16/device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn.hpp
index a2732a20b4..48b38524ea 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_mx/device_gemm_mx_xdl_f4_f4_f16/device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_mx/device_gemm_mx_xdl_f4_f4_f16/device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn.hpp
@@ -44,17 +44,18 @@ using device_gemm_mx_xdl_f4_f4_f16_mk_nk_mn_instances = std::tuple<
     //#############################|        |        |        | Type|   Data| Type|   Data|  Type|    Type|     Type| Elementwise| Elementwise| Elementwise|Specialization|           Size|  Size| Block| Block| Block|    |    | XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|          Pipeline|                     Pipeline|
     //#############################|        |        |        |     |   Type|     |   Type|      |        |         |   Operation|   Operation|   Operation|              |               |      |      |      |      |    |    |    |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl|   _NWaveNPerXdl|         Scheduler|                     Verision|
     //#############################|        |        |        |     |       |     |       |      |        |         |            |            |            |              |               |      |      |      |      |    |    |    |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                                 |                |                  |                             |
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    32,   128,   128,  16,  16,  16,   16,    2,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    32,   256,   128,  16,  16,  16,   16,    2,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    64,   128,   128,  16,  16,  16,   16,    4,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    64,   256,   128,  16,  16,  16,   16,    4,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    96,   128,   128,  16,  16,  16,   16,    6,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    96,   256,   128,  16,  16,  16,   16,    6,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    32,   128,   128,  16,  16,  16,   16,    2,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    32,   256,   128,  16,  16,  16,   16,    2,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    64,   128,   128,  16,  16,  16,   16,    4,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    64,   256,   128,  16,  16,  16,   16,    4,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    96,   128,   128,  16,  16,  16,   16,    6,    2,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
+      // DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,    96,   256,   128,  16,  16,  16,   16,    6,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v1>,
 
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   128,   256,   128,  16,  16,  16,   16,    4,    8,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   256,   128,   128,  16,  16,  16,   16,    8,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   128,   128,   128,  16,  16,  16,   16,    4,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
-      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,    64,    32,    32,   128,  16,  16,  16,   16,    2,    2,     S<8,  8, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     false,     S<8,  8, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     false,           2,           2,                   S<1, 16, 1, 4>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
+      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   256,   256,   128,  16,  16,  16,   16,    8,    8,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
+      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   128,   256,   128,  16,  16,  16,   16,    4,    8,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
+      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   256,   128,   128,  16,  16,  16,   16,    8,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
+      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,   256,   128,   128,   128,  16,  16,  16,   16,    4,    4,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 32, 1, 8>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
+      DeviceGemmMX_Xdl_CShuffleV3<       Row,     Col,     Row,   F4, E8M0PK,   F4, E8M0PK,  F16,     F32,      F16, PassThrough, PassThrough, PassThrough,      GemmSpec, ScaleBlockSize,    64,    32,    32,   128,  16,  16,  16,   16,    2,    2,     S<8,  8, 1>,     S<1, 0, 2>,    S<1, 0, 2>,               2,             16,             16,     true,     S<8,  8, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,             16,             16,     true,           2,           2,                   S<1, 16, 1, 4>,               8,  BlkGemmPipeSched,  BlockGemmPipelineVersion::v3>,
       std::nullptr_t
     // clang-format on
     >;
diff --git a/profiler/include/profiler/profile_gemm_mx_impl.hpp b/profiler/include/profiler/profile_gemm_mx_impl.hpp
index 8f9c79ca0e..80cd291852 100644
--- a/profiler/include/profiler/profile_gemm_mx_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_mx_impl.hpp
@@ -213,8 +213,7 @@ bool profile_gemm_mx_impl(int do_verification,
 
     default:
         a_m_k.GenerateTensorValue(GeneratorTensor_3<ADataType>{-2.0, 2.0});
-        a_m_k_scale.GenerateTensorValue(
-            GeneratorTensor_3<XDataType>{powf(2.0f, -125.0f), 1.0f}); // R[2^-125, 1]
+        a_m_k_scale.GenerateTensorValue(GeneratorTensor_3<XDataType>{powf(2.0f, -125.0f), 1.0f});
 
         b_k_n.GenerateTensorValue(GeneratorTensor_3<BDataType>{-2.0, 2.0});
         b_k_n_scale.GenerateTensorValue(GeneratorTensor_3<XDataType>{powf(2.0f, -125.0f), 1.0f});