formatting

client_example/20_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp

@@ -181,7 +181,7 @@ int main()
         auto& op_ptr = op_ptrs[i];
 
         auto argument_ptr = op_ptr->MakeArgumentPointer(
-                p_a, p_b, p_ds, p_e, gemm_descs, a_element_op, b_element_op, cde_element_op);
+            p_a, p_b, p_ds, p_e, gemm_descs, a_element_op, b_element_op, cde_element_op);
 
         auto invoker_ptr = op_ptr->MakeInvokerPointer();
 

library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_bias.hpp

@@ -121,12 +121,12 @@ struct DeviceOperationInstanceFactory<
             if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
                          is_same_v<ELayout, Row>)
             {
-                //add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_km_kn_mn_instances(op_ptrs);
+                // add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_km_kn_mn_instances(op_ptrs);
             }
             if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Col> &&
                          is_same_v<ELayout, Row>)
             {
-                //add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_km_nk_mn_instances(op_ptrs);
+                // add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_km_nk_mn_instances(op_ptrs);
             }
         }
         return op_ptrs;

library/src/tensor_operation_instance/gpu/grouped_gemm_bias/device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -35,8 +35,9 @@ using Add         = ck::tensor_operation::element_wise::AddBias;
 
 static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
 
-using device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_irregular_tile_instances = std::tuple<
-    // clang-format off
+using device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_irregular_tile_instances =
+    std::tuple<
+        // clang-format off
         //############################|      A|      B|          Ds|      E| AData| BData| AccData| CShuffle|      DsData| EData|           A|           B|           C|           GEMM| NumGemmK| 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|
         //############################| Layout| Layout|      Layout| Layout|  Type|  Type|    Type| DataType|        Type|  Type| Elementwise| Elementwise| Elementwise| Spacialization| Prefetch|  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_MWaveMPerXdl| ScalarPerVector|
         //############################|       |       |            |       |      |      |        |         |            |      |   Operation|   Operation|   Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
@@ -51,8 +52,8 @@ using device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_irregular_tile_
         DeviceGroupedGemm_Xdl_Fixed_NK<    Row,    Row,    DsLayout,    Row,   F16,   F16,     F32,      F32,  DsDataType,   F16, PassThrough, PassThrough,         Add, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 4>,              8>,
         DeviceGroupedGemm_Xdl_Fixed_NK<    Row,    Row,    DsLayout,    Row,   F16,   F16,     F32,      F32,  DsDataType,   F16, PassThrough, PassThrough,         Add, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   2,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 16, 1, 8>,              8>,
         DeviceGroupedGemm_Xdl_Fixed_NK<    Row,    Row,    DsLayout,    Row,   F16,   F16,     F32,      F32,  DsDataType,   F16, PassThrough, PassThrough,         Add, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 16, 1, 8>,              8>
-    // clang-format on
-    >;
+        // clang-format on
+        >;
 
 void add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instances(
     std::vector<std::unique_ptr<DeviceGroupedGemm<Row,
@@ -68,7 +69,8 @@ void add_device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instances(
                                                   Add>>>& instances)
 {
     add_device_operation_instances(
-        instances, device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_irregular_tile_instances{});
+        instances,
+        device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_irregular_tile_instances{});
 }
 
 } // namespace instance