1 /* 2 * Copyright © 2015 Connor Abbott 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the next 12 * paragraph) shall be included in all copies or substantial portions of the 13 * Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 21 * IN THE SOFTWARE. 22 */ 23 24 #include "brw_fs.h" 25 #include "brw_cfg.h" 26 #include "brw_fs_builder.h" 27 28 using namespace brw; 29 30 bool 31 fs_visitor::lower_d2x() 32 { 33 bool progress = false; 34 35 foreach_block_and_inst_safe(block, fs_inst, inst, cfg) { 36 if (inst->opcode != BRW_OPCODE_MOV) 37 continue; 38 39 if (inst->dst.type != BRW_REGISTER_TYPE_F && 40 inst->dst.type != BRW_REGISTER_TYPE_D && 41 inst->dst.type != BRW_REGISTER_TYPE_UD) 42 continue; 43 44 if (inst->src[0].type != BRW_REGISTER_TYPE_DF) 45 continue; 46 47 assert(inst->dst.file == VGRF); 48 assert(inst->saturate == false); 49 fs_reg dst = inst->dst; 50 51 const fs_builder ibld(this, block, inst); 52 53 /* From the Broadwell PRM, 3D Media GPGPU, "Double Precision Float to 54 * Single Precision Float": 55 * 56 * The upper Dword of every Qword will be written with undefined 57 * value when converting DF to F. 58 * 59 * So we need to allocate a temporary that's two registers, and then do 60 * a strided MOV to get the lower DWord of every Qword that has the 61 * result. 62 */ 63 fs_reg temp = ibld.vgrf(inst->src[0].type, 1); 64 fs_reg strided_temp = subscript(temp, inst->dst.type, 0); 65 ibld.MOV(strided_temp, inst->src[0]); 66 ibld.MOV(dst, strided_temp); 67 68 inst->remove(block); 69 progress = true; 70 } 71 72 if (progress) 73 invalidate_live_intervals(); 74 75 return progress; 76 } 77