format

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_bf16_i4_bf16/device_gemm_xdl_universal_bf16_i4_bf16_mk_nk_mn.hpp

@@ -53,7 +53,8 @@ using device_gemm_xdl_universal_bf16_i4_bf16_mk_nk_mn_comp_instances = std::tupl
 #endif
 
 template <BlockGemmPipelineScheduler BlkGemmPipeSched, GemmSpecialization GemmSpec>
-using device_gemm_xdl_universal_bf16_i4_bf16_mk_nk_mn_mem_instances = std::tuple<
+using device_gemm_xdl_universal_bf16_i4_bf16_mk_nk_mn_mem_instances =
+    std::tuple<
         // clang-format off
         //#########################| ALayout| BLayout| CLayout|AData| BData| CData| AccData| Cshuffle|           A|           B|           C|          GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1|MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle|     CBlockTransferClusterLengths|  CBlockTransfer|        Block-wiseGemm|               Block-wiseGemm| ACompType| BCompType| APermute| BPermute|
         //#########################|        |        |        | Type|  Type|  Type|    Type|     Type| Elementwise| Elementwise| Elementwise|Specialization|  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|          |          |         |         |