//////////////////////////////////////////////////////////////////////////////// // // The University of Illinois/NCSA // Open Source License (NCSA) // // Copyright (c) 2014-2015, Advanced Micro Devices, Inc. All rights reserved. // // Developed by: // // AMD Research and AMD HSA Software Development // // Advanced Micro Devices, Inc. // // www.amd.com // // Permission is hereby granted, free of charge, to any person obtaining a copy // of this software and associated documentation files (the "Software"), to // deal with the Software without restriction, including without limitation // the rights to use, copy, modify, merge, publish, distribute, sublicense, // and/or sell copies of the Software, and to permit persons to whom the // Software is furnished to do so, subject to the following conditions: // // - Redistributions of source code must retain the above copyright notice, // this list of conditions and the following disclaimers. // - Redistributions in binary form must reproduce the above copyright // notice, this list of conditions and the following disclaimers in // the documentation and/or other materials provided with the distribution. // - Neither the names of Advanced Micro Devices, Inc, // nor the names of its contributors may be used to endorse or promote // products derived from this Software without specific prior written // permission. // // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, // FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL // THE CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR // OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, // ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER // DEALINGS WITH THE SOFTWARE. // //////////////////////////////////////////////////////////////////////////////// module &m:1:0:$base:$large:$default; decl prog function &abort()(); prog kernel &__vector_copy_kernel( kernarg_u64 %in, kernarg_u64 %out) { @__vector_copy_kernel_entry: // BB#0: // %entry workitemabsid_u32 $s0, 0; cvt_s64_s32 $d0, $s0; shl_u64 $d0, $d0, 2; ld_kernarg_align(8)_width(all)_u64 $d1, [%out]; add_u64 $d1, $d1, $d0; ld_kernarg_align(8)_width(all)_u64 $d2, [%in]; add_u64 $d0, $d2, $d0; ld_global_u32 $s0, [$d0]; st_global_u32 $s0, [$d1]; ret; };