rename all fwd related files

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_forward_v1.cpp

@@ -19,7 +19,7 @@ Gemm + Softmax + Gemm fused operation. Computes C_g_m_o = Softmax(A_g_m_k * B0_g
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_forward_v2.cpp

@@ -19,7 +19,7 @@ Gemm + Softmax + Gemm fused operation. Computes C_g_m_o = Softmax(A_g_m_k * B0_g
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle_v2.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_train_v1.cpp

@@ -45,7 +45,7 @@ Kernel outputs:
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v1.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v2.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_train_v2.cpp

@@ -45,7 +45,7 @@ Kernel outputs:
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v1.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v2.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle_v2.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_forward_v1.cpp

@@ -19,7 +19,7 @@ Gemm + Softmax + Gemm fused operation. Computes C_g_m_o = Softmax(A_g_m_k * B0_g
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_forward_v2.cpp

@@ -19,7 +19,7 @@ Gemm + Softmax + Gemm fused operation. Computes C_g_m_o = Softmax(A_g_m_k * B0_g
 #include "ck/ck.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle_v2.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_train_v1.cpp

@@ -44,7 +44,7 @@ Kernel outputs:
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_kloop_v1.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_kloop_v2.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_train_v2.cpp

@@ -44,7 +44,7 @@ Kernel outputs:
 #include "ck/tensor_operation/gpu/device/tensor_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_v1.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_v2.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle_v2.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

include/ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v1.hpp

@@ -14,7 +14,7 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"

include/ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_forward_xdl_cshuffle_v2.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v2.hpp

@@ -14,7 +14,7 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_forward_xdl_cshuffle_pt2.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle.hpp → include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v1.hpp

@@ -14,7 +14,7 @@
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_fwd_xdl_cshuffle_v1.hpp"
 #include "ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"

include/ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_forward_xdl_cshuffle_v2.hpp → include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_fwd_xdl_cshuffle_v2.hpp

@@ -14,7 +14,7 @@
 #include "ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/matrix_padder.hpp"
-#include "ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_forward_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_fwd_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/operator_transform/transform_contraction_to_gemm.hpp"
 #include "ck/host_utility/device_prop.hpp"
 #include "ck/host_utility/kernel_launch.hpp"