1 1 1 0 1 0 1 2 32 32 4 4 3 3 200 200 1 1 1 1 1 1 1 1; DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>; 8.09047 1 1 1 0 1 0 1 2 32 32 8 8 3 3 200 200 2 2 1 1 1 1 1 1; DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 4, 2, 8, 8, 1, 1, 1, 8>; 19.8867 1 1 1 0 1 0 1 2 32 32 8 8 3 3 100 100 1 2 1 1 1 1 1 1; DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 4, 2, 8, 8, 1, 1, 1, 8>; 20.4604 1 1 1 0 1 0 1 2 1 32 2376 256 3 3 100 100 1 1 1 1 1 1 1 1; DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 256, 64, Default, 32, 32, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, 1>; 952.806 1 1 1 0 1 0 1 2 1 32 256 256 3 3 100 100 1 1 1 1 1 1 1 1; DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 256, 64, Default, 32, 32, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, 1>; 1091.89