// WGP mode: with the padded LDS rows (PWIN_PAD) this layer is 2-5% faster in WGP mode than in CU mode // (CU mode was 1-6% faster before the padding) // weight images through plain global loads here (buffer loads were 1-3% slower in this layer) // d4r-build-flags: -DPWIN_NO_BUFFER_IMG -DPWIN_VEC_FROM_WEIGHTS #define PWIN_F32ACC #include "pwin_layer.h" PWIN_DECODER(dltss_pwin_dec2_layer, 2, 64, 96)