merge develop

library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt

+# device_gemm_bias_relu_instance
+set(DEVICE_GEMM_BIAS_RELU_INSTANCE_SOURCE
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_km_nk_mn_instance.cpp;
+)
+
+add_library(device_gemm_bias_relu_instance SHARED ${DEVICE_GEMM_BIAS_RELU_INSTANCE_SOURCE}) 
+target_compile_features(device_gemm_bias_relu_instance PUBLIC)
+set_target_properties(device_gemm_bias_relu_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_gemm_bias_relu_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_gemm_bias_relu_instance)

library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt

+# device_gemm_bias_relu_add_instance
+set(DEVICE_GEMM_BIAS_RELU_ADD_INSTANCE_SOURCE
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_km_nk_mn_instance.cpp;
+)
+
+add_library(device_gemm_bias_relu_add_instance SHARED ${DEVICE_GEMM_BIAS_RELU_ADD_INSTANCE_SOURCE}) 
+target_compile_features(device_gemm_bias_relu_add_instance PUBLIC)
+set_target_properties(device_gemm_bias_relu_add_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_gemm_bias_relu_add_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_gemm_bias_relu_add_instance)

library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt

+# device_reduce_instance
+set(DEVICE_REDUCE_INSTANCE_SOURCE
+   device_reduce_instance_blockwise_f16_f16_f16.cpp;
+   device_reduce_instance_blockwise_f16_f32_f16.cpp;
+   device_reduce_instance_blockwise_f32_f32_f32.cpp;
+   device_reduce_instance_blockwise_f32_f64_f32.cpp;
+   device_reduce_instance_blockwise_f64_f64_f64.cpp;
+   device_reduce_instance_threadwise_f16_f16_f16.cpp;
+   device_reduce_instance_threadwise_f16_f32_f16.cpp;
+   device_reduce_instance_threadwise_f32_f32_f32.cpp;
+   device_reduce_instance_threadwise_f32_f64_f32.cpp;
+   device_reduce_instance_threadwise_f64_f64_f64.cpp;
+   device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp;
+   device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp;
+   device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp;
+   device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp;
+   device_reduce_instance_blockwise_second_call_f64_f64_f64.cpp;
+   device_reduce_instance_multiblock_atomic_add_f16_f32_f32.cpp;
+   device_reduce_instance_multiblock_atomic_add_f32_f32_f32.cpp;
+   device_reduce_instance_multiblock_atomic_add_f32_f64_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f16_f16_f16.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f16_f32_f16.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f32_f32_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f32_f64_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f64_f64_f64.cpp;
+)
+
+add_library(device_reduce_instance SHARED ${DEVICE_REDUCE_INSTANCE_SOURCE}) 
+target_compile_features(device_reduce_instance PUBLIC)
+set_target_properties(device_reduce_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_reduce_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_reduce_instance)

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.cpp

+#include "device_reduce_instance_blockwise.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.cpp

+#include "device_reduce_instance_blockwise.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.cpp

+#include "device_reduce_instance_blockwise.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.cpp

+#include "device_reduce_instance_blockwise.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(float, double, float, 7, 0, 0, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.cpp

+#include "device_reduce_instance_blockwise.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 7, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 2, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 3, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_INST_BY_ID(double, double, double, 4, 0, 1, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp

+#include "device_reduce_instance_blockwise_second_call.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 2, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 3, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp

+#include "device_reduce_instance_blockwise_second_call.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, half_t, 7, 0, 0, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp

+#include "device_reduce_instance_blockwise_second_call.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 7, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0, 1, 2); // for MIN
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 2, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0, 1, 2); // for MAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 3, 0, 1, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0, 1, 2); // for AMAX
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(float, float, float, 4, 0, 1, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck

library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp

+#include "device_reduce_instance_blockwise_second_call.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace device_reduce_instance {
+
+// clang-format off
+// InDataType | AccDataType | OutDataType | ReduceOpId | NanPropaOpt | IndicesOpt | Rank | ReduceDims
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 0, 1, 2); // for ADD
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 4, 0);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 0, 0, 0, 2, 1);
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 0, 1, 2); // for AVG
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 5, 0, 0, 2, 1);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 0, 1, 2); // for NORM2
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 4, 0);       //
+ADD_BLOCKWISE_SECOND_CALL_INST_BY_ID(double, double, float, 7, 0, 0, 2, 1);       //
+// clang-format on
+
+} // namespace device_reduce_instance
+} // namespace device
+} // namespace tensor_operation
+
+} // namespace ck