From: Jose Maria Casanova Crespo Date: Sat, 9 Jun 2018 09:46:07 +0000 (+0200) Subject: intel/fs: shuffle_from_32bit_read at load_per_vertex_input at TCS/TES X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=8003ae87f43f92fd74e29cba6c5fcd0739ce95db;p=mesa.git intel/fs: shuffle_from_32bit_read at load_per_vertex_input at TCS/TES Previously, the shuffle function had a source/destination overlap that needs to be avoided to use shuffle_from_32bit_read. As we can use for the shuffle destination the destination of removed MOVs. This change also avoids the internal MOVs done by the previous shuffle to deal with possible overlaps. Reviewed-by: Jason Ekstrand --- diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index 7fdc9313d15..352d50e74db 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -2665,13 +2665,10 @@ fs_visitor::nir_emit_tcs_intrinsic(const fs_builder &bld, * or SSBOs. */ if (type_sz(dst.type) == 8) { - shuffle_32bit_load_result_to_64bit_data( - bld, dst, retype(dst, BRW_REGISTER_TYPE_F), num_components); - - for (unsigned c = 0; c < num_components; c++) { - bld.MOV(offset(orig_dst, bld, iter * 2 + c), - offset(dst, bld, c)); - } + shuffle_from_32bit_read(bld, + offset(orig_dst, bld, iter * 2), + retype(dst, BRW_REGISTER_TYPE_D), + 0, num_components); } /* Copy the temporary to the destination to deal with writemasking. @@ -3014,13 +3011,10 @@ fs_visitor::nir_emit_tes_intrinsic(const fs_builder &bld, * or SSBOs. */ if (type_sz(dest.type) == 8) { - shuffle_32bit_load_result_to_64bit_data( - bld, dest, retype(dest, BRW_REGISTER_TYPE_F), num_components); - - for (unsigned c = 0; c < num_components; c++) { - bld.MOV(offset(orig_dest, bld, iter * 2 + c), - offset(dest, bld, c)); - } + shuffle_from_32bit_read(bld, + offset(orig_dest, bld, iter * 2), + retype(dest, BRW_REGISTER_TYPE_D), + 0, num_components); } /* If we are loading double data and we need a second read message