diff options
author | Jason Ekstrand <[email protected]> | 2017-08-27 21:48:03 -0700 |
---|---|---|
committer | Jason Ekstrand <[email protected]> | 2017-11-07 10:37:52 -0800 |
commit | ec8c6649f17ab9790eaddf56a043abb3316aad48 (patch) | |
tree | 7dd897deb1a115737ec6606221ee8062685f1b4a /src/intel/compiler | |
parent | 030d2b5016360caf44ebfa3f6951a6d676316a89 (diff) |
i965/fs/nir: Minor refactor of store_output
Stop retyping the output of shuffle_64bit_data_for_32bit_write. It's
always BRW_REGISTER_TYPE_D which is perfectly fine for writing out.
Also, when we change get_nir_src to return something with a 64-bit type
for 64-bit values, the retyping will not be at all what we want. Also,
retyping the output based on src.type before we whack it back to 32 bits
is a problem because the output is always 32 bits.
Reviewed-by: Iago Toral Quiroga <[email protected]>
Diffstat (limited to 'src/intel/compiler')
-rw-r--r-- | src/intel/compiler/brw_fs_nir.cpp | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index 5bcdb1ab8a5..02ddc8224d8 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -4058,18 +4058,17 @@ fs_visitor::nir_emit_intrinsic(const fs_builder &bld, nir_intrinsic_instr *instr nir_const_value *const_offset = nir_src_as_const_value(instr->src[1]); assert(const_offset && "Indirect output stores not allowed"); - fs_reg new_dest = retype(offset(outputs[instr->const_index[0]], bld, - 4 * const_offset->u32[0]), src.type); unsigned num_components = instr->num_components; unsigned first_component = nir_intrinsic_component(instr); if (nir_src_bit_size(instr->src[0]) == 64) { - fs_reg tmp = shuffle_64bit_data_for_32bit_write(bld, + src = shuffle_64bit_data_for_32bit_write(bld, retype(src, BRW_REGISTER_TYPE_DF), num_components); - src = retype(tmp, src.type); num_components *= 2; } + fs_reg new_dest = retype(offset(outputs[instr->const_index[0]], bld, + 4 * const_offset->u32[0]), src.type); for (unsigned j = 0; j < num_components; j++) { bld.MOV(offset(new_dest, bld, j + first_component), offset(src, bld, j)); |