Merge branch 'attn-train-develop-qloop-dropout-v2' of...

Merge branch 'attn-train-develop-qloop-dropout-v2' of https://github.com/ROCmSoftwarePlatform/composable_kernel into attn-train-develop-qloop-dropout-v2

example/32_batched_gemm_scale_softmax_gemm/CMakeLists.txt

@@ -15,6 +15,7 @@ add_example_executable(example_grouped_multihead_attention_forward_v2 grouped_mu
 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)
 add_example_executable(example_batched_multihead_attention_backward_v2 batched_multihead_attention_backward_v2.cpp)
+add_example_executable(example_batched_multihead_attention_backward_v2_phased batched_multihead_attention_backward_v2_phased.cpp)
 add_example_executable(example_grouped_multihead_attention_train_v2 grouped_multihead_attention_train_v2.cpp)
 add_example_executable(example_batched_multihead_attention_train_v2 batched_multihead_attention_train_v2.cpp)
 

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_v3.cpp → 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_multihead_attention_backward_xdl_cshuffle_v3.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_multihead_attention_backward_xdl_cshuffle_v2.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 

include/ck/tensor_operation/gpu/device/impl/device_batched_multihead_attention_backward_xdl_cshuffle_v3.hpp → include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_t2b_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_multihead_attention_backward_xdl_cshuffle_pt3.hpp"
+#include "ck/tensor_operation/gpu/grid/gridwise_batched_mha_bwd_xdl_cshuffle_qloop_t2b_phased_pt1.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"