<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Wed, May 2, 2018 at 3:48 AM, Iago Toral Quiroga <<a href="mailto:itoral@igalia.com" target="_blank">itoral@igalia.com</a>> wrote: <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">NIR assumes that booleans are always 32-bit, but Intel hardware produces 16-bit booleans for 16-bit comparisons. This means that we need to convert the 16-bit result to 32-bit. In the future we want to add an optimization pass to clean this up and hopefully remove the conversions. v2 (Jason): use the type of the source for the temporary and use brw_reg_type_from_bit_size for the conversion to 32-bit. --- src/intel/compiler/brw_fs_nir.cpp | 42 +++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index b9d8ade4cf..f763dfa4f2 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -1017,9 +1017,11 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) case nir_op_feq: case nir_op_fne: { fs_reg dest = result; - if (nir_src_bit_size(instr->src[0].src) > 32) { - dest = bld.vgrf(BRW_REGISTER_TYPE_DF, 1); - } + + const uint32_t bit_size = nir_src_bit_size(instr->src[0].src); + if (bit_size != 32) + dest = bld.vgrf(op[0].type, 1); + brw_conditional_mod cond; switch (instr->op) { case nir_op_flt: @@ -1037,9 +1039,21 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) default: unreachable("bad opcode"); } + bld.CMP(dest, op[0], op[1], cond); - if (nir_src_bit_size(instr->src[0].src) > 32) { + + if (bit_size > 32) { bld.MOV(result, subscript(dest, BRW_REGISTER_TYPE_UD, 0)); + } else if(bit_size < 32) { + /* When we convert the result to 32-bit we need to be careful and do + * it as a signed conversion to get sign extension (for 32-bit true) + */ + const brw_reg_type dst_type = + brw_reg_type_from_bit_size(32, BRW_REGISTER_TYPE_D); </blockquote><div> </div><div>I think you can just use BRW_REGISTER_TYPE_D here. But whatever, this is ok too. </div><div>Reviewed-by: Jason Ekstrand <<a href="mailto:jason@jlekstrand.net">jason@jlekstrand.net</a>> </div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> + const brw_reg_type src_type = + brw_reg_type_from_bit_size(bit_size, BRW_REGISTER_TYPE_D); + + bld.MOV(retype(result, dst_type), retype(dest, src_type)); } break; } @@ -1051,9 +1065,10 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) case nir_op_ieq: case nir_op_ine: { fs_reg dest = result; - if (nir_src_bit_size(instr->src[0].src) > 32) { - dest = bld.vgrf(BRW_REGISTER_TYPE_UQ, 1); - } + + const uint32_t bit_size = nir_src_bit_size(instr->src[0].src); + if (bit_size != 32) + dest = bld.vgrf(op[0].type, 1); brw_conditional_mod cond; switch (instr->op) { @@ -1075,8 +1090,19 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) unreachable("bad opcode"); } bld.CMP(dest, op[0], op[1], cond); - if (nir_src_bit_size(instr->src[0].src) > 32) { + + if (bit_size > 32) { bld.MOV(result, subscript(dest, BRW_REGISTER_TYPE_UD, 0)); + } else if (bit_size < 32) { + /* When we convert the result to 32-bit we need to be careful and do + * it as a signed conversion to get sign extension (for 32-bit true) + */ + const brw_reg_type dst_type = + brw_reg_type_from_bit_size(32, BRW_REGISTER_TYPE_D); + const brw_reg_type src_type = + brw_reg_type_from_bit_size(bit_size, BRW_REGISTER_TYPE_D); + + bld.MOV(retype(result, dst_type), retype(dest, src_type)); } break; } -- 2.14.1 </blockquote></div> </div></div>