Merge remote-tracking branch 'origin/develop' into bwroblew/warp_wise_dpp8

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

+add_instance_library(device_grouped_gemm_bias_instance
+   device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_kn_mn_instance.cpp
+   device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f16_mk_nk_mn_instance.cpp
+
+   device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_kn_mn_instance.cpp
+   device_grouped_gemm_xdl_fixed_nk_bias_f16_f16_f32_mk_nk_mn_instance.cpp
+)

library/src/tensor_operation_instance/gpu/pool3d_fwd/pool_fwd_instance_common.hpp

@@ -17,6 +17,7 @@ namespace instance {
 
 using I32   = int32_t;
 using F16   = ck::half_t;
+using BF16  = ck::bhalf_t;
 using F32   = float;
 using NDHWC = ck::tensor_layout::convolution::NDHWC;