rename all bwd related files

example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt

@@ -5,12 +5,12 @@ add_example_executable(example_batched_gemm_scale_softmax_gemm_permute_xdl_bf16
 add_example_executable(example_grouped_gemm_scale_softmax_gemm_permute_xdl_fp16 grouped_gemm_scale_softmax_gemm_permute_xdl_fp16.cpp)
 add_example_executable(example_batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16 batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp)
 add_example_executable(example_grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16 grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp)
-add_example_executable(example_grouped_multihead_attention_forward grouped_multihead_attention_forward.cpp)
-add_example_executable(example_batched_multihead_attention_forward batched_multihead_attention_forward.cpp)
-add_example_executable(example_grouped_multihead_attention_backward grouped_multihead_attention_backward.cpp)
-add_example_executable(example_batched_multihead_attention_backward batched_multihead_attention_backward.cpp)
-add_example_executable(example_grouped_multihead_attention_train grouped_multihead_attention_train.cpp)
-add_example_executable(example_batched_multihead_attention_train batched_multihead_attention_train.cpp)
+add_example_executable(example_grouped_multihead_attention_forward_v1 grouped_multihead_attention_forward_v1.cpp)
+add_example_executable(example_batched_multihead_attention_forward_v1 batched_multihead_attention_forward_v1.cpp)
+add_example_executable(example_grouped_multihead_attention_backward_v1 grouped_multihead_attention_backward_v1.cpp)
+add_example_executable(example_batched_multihead_attention_backward_v1 batched_multihead_attention_backward_v1.cpp)
+add_example_executable(example_grouped_multihead_attention_train_v1 grouped_multihead_attention_train_v1.cpp)
+add_example_executable(example_batched_multihead_attention_train_v1 batched_multihead_attention_train_v1.cpp)
 add_example_executable(example_grouped_multihead_attention_forward_v2 grouped_multihead_attention_forward_v2.cpp)
 add_example_executable(example_batched_multihead_attention_forward_v2 batched_multihead_attention_forward_v2.cpp)
 add_example_executable(example_grouped_multihead_attention_backward_v2 grouped_multihead_attention_backward_v2.cpp)

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_v2.cpp

@@ -36,8 +36,8 @@ Kernel outputs:
 #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_backward_xdl_cshuffle_v4.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_backward_xdl_cshuffle_v5.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/element/element_wise_operation.hpp"
 
 #include "ck/library/utility/check_err.hpp"

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_v2_phased.cpp

@@ -36,7 +36,7 @@ Kernel outputs:
 #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_mha_bwd_xdl_cshuffle_qloop_t2b_phased_v1.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_phased_v1.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_backward_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_train_v2.cpp

@@ -43,8 +43,8 @@ Kernel outputs:
 #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_backward_xdl_cshuffle_v4.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_backward_xdl_cshuffle_v5.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/element/element_wise_operation.hpp"
 

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_backward_v2.cpp

@@ -35,8 +35,8 @@ Kernel outputs:
 #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_backward_xdl_cshuffle_v4.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_backward_xdl_cshuffle_v5.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/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

@@ -42,8 +42,8 @@ Kernel outputs:
 #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_backward_xdl_cshuffle_v4.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_grouped_multihead_attention_backward_xdl_cshuffle_v5.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/element/element_wise_operation.hpp"
 

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v1.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_mha_bwd_xdl_cshuffle_kloop_pt1.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_kloop_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_mha_bwd_xdl_cshuffle_kloop_v2.hpp

@@ -15,7 +15,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_mha_bwd_xdl_cshuffle_kloop_pt2.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_kloop_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_batched_mha_bwd_xdl_cshuffle_qloop_t2b_phased_v1.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_phased_v1.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_mha_bwd_xdl_cshuffle_qloop_t2b_phased_pt1.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_qloop_t2b_phased_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_backward_xdl_cshuffle_v4.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v1.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_backward_xdl_cshuffle_pt6.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_qloop_b2t_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_backward_xdl_cshuffle_v5.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v2.hpp

@@ -15,7 +15,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_backward_xdl_cshuffle_pt7.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_qloop_b2t_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_mha_bwd_xdl_cshuffle_kloop_v1.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_mha_bwd_xdl_cshuffle_kloop_pt1.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_kloop_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_mha_bwd_xdl_cshuffle_kloop_v2.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_mha_bwd_xdl_cshuffle_kloop_pt2.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_kloop_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_backward_xdl_cshuffle_v4.hpp → include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_qloop_v1.hpp

@@ -16,7 +16,7 @@
 #include "ck/tensor_operation/gpu/device/masking_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_backward_xdl_cshuffle_pt6.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_qloop_b2t_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"