From: Jose Maria Casanova Crespo <jmcasan...@igalia.com> SSBO loads were using byte_scattered read messages as they allow reading 16-bit size components. byte_scattered messages can only operate one component at a time so we needed to emit as many messages as components.
But for vec2 and vec4 of 16-bit, being multiple of 32-bit we can use the untyped_surface_read message to read pairs of 16-bit components using only one message. Once each pair is read it is unshuffled to return the proper 16-bit components. On 16-bit scalar and vec3 16-bit the not paired component is read using only one byte_scattered_read message. --- src/intel/compiler/brw_fs_nir.cpp | 42 +++++++++++++++++++++++++++++---------- 1 file changed, 32 insertions(+), 10 deletions(-) diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index f8a53767445..55b2dfd0caf 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -2319,19 +2319,41 @@ do_untyped_vector_read(const fs_builder &bld, bld.ADD(read_offset, read_offset, brw_imm_ud(16)); } } else if (type_sz(dest.type) == 2) { - for (unsigned i = 0; i < num_components; i++) { + assert(dest.stride == 2); + + int component_pairs = num_components / 2; + /* Pairs of 16-bit components can be read with untyped read */ + if (component_pairs > 0) { + fs_reg read_result = emit_untyped_read(bld, surf_index, + offset_reg, + 1 /* dims */, + component_pairs, + BRW_PREDICATE_NONE); + read_result.stride = 2; + read_result.type = dest.type; + + /* Each 32-bit read needs to be unshuffled as 2 16-bit components */ + for (int i = 0; i < component_pairs * 2 ; i++) + bld.MOV(offset(dest, bld, i), + byte_offset(offset(read_result, bld, i / 2), i % 2 * 2)); + } + /* Last component of vec3 and scalar 16-bit read needs to be read + * using one byte_scattered_read message + */ + if (num_components % 2) { fs_reg base_offset = bld.vgrf(BRW_REGISTER_TYPE_UD); bld.ADD(base_offset, offset_reg, - brw_imm_ud(i * type_sz(dest.type))); - fs_reg read_reg = emit_byte_scattered_read(bld, surf_index, base_offset, - 1 /* dims */, - 1, - BRW_PREDICATE_NONE); - read_reg = retype(read_reg, BRW_REGISTER_TYPE_UD); - fs_reg retval = retype(offset(dest,bld,i), BRW_REGISTER_TYPE_UD); - retval.stride = 1; - bld.MOV(retval, read_reg); + brw_imm_ud((num_components - 1) * type_sz(dest.type))); + fs_reg read_result = emit_byte_scattered_read(bld, surf_index, + base_offset, + 1 /* dims */, + 1, + BRW_PREDICATE_NONE); + read_result.type = dest.type; + read_result.stride = 2; + bld.MOV(offset(dest, bld, num_components - 1), + read_result); } } else { unreachable("Unsupported type"); -- 2.11.0 _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev