diff options
Diffstat (limited to 'src/cuda-sim/instructions.cc')
| -rw-r--r-- | src/cuda-sim/instructions.cc | 15 |
1 files changed, 8 insertions, 7 deletions
diff --git a/src/cuda-sim/instructions.cc b/src/cuda-sim/instructions.cc index 4981c99..4792efc 100644 --- a/src/cuda-sim/instructions.cc +++ b/src/cuda-sim/instructions.cc @@ -1,18 +1,19 @@ // Copyright (c) 2009-2021, Tor M. Aamodt, Wilson W.L. Fung, Ali Bakhoda, // Jimmy Kwa, George L. Yuan, Vijay Kandiah, Nikos Hardavellas, // Mahmoud Khairy, Junrui Pan, Timothy G. Rogers -// The University of British Columbia, Northwestern University, Purdue University -// All rights reserved. +// The University of British Columbia, Northwestern University, Purdue +// University All rights reserved. // // Redistribution and use in source and binary forms, with or without // modification, are permitted provided that the following conditions are met: // -// 1. Redistributions of source code must retain the above copyright notice, this +// 1. Redistributions of source code must retain the above copyright notice, +// this // list of conditions and the following disclaimer; // 2. Redistributions in binary form must reproduce the above copyright notice, // this list of conditions and the following disclaimer in the documentation // and/or other materials provided with the distribution; -// 3. Neither the names of The University of British Columbia, Northwestern +// 3. Neither the names of The University of British Columbia, Northwestern // University nor the names of their contributors may be used to // endorse or promote products derived from this software without specific // prior written permission. @@ -1948,7 +1949,7 @@ void mma_impl(const ptx_instruction *pI, core_t *core, warp_inst_t inst) { hex_val = (v[k / 2].s64 & 0xffff); else hex_val = ((v[k / 2].s64 & 0xffff0000) >> 16); - nw_v[k].f16 = *(reinterpret_cast<half*>(hex_val)); + nw_v[k].f16 = *(reinterpret_cast<half *>(hex_val)); } } if (!((operand_num == 3) && (type2 == F32_TYPE))) { @@ -3980,7 +3981,7 @@ void mad_def(const ptx_instruction *pI, ptx_thread_info *thread, fesetround(FE_TOWARDZERO); break; default: - //assert(0); + // assert(0); break; } d.f32 = a.f32 * b.f32 + c.f32; @@ -4326,7 +4327,7 @@ void mul_impl(const ptx_instruction *pI, ptx_thread_info *thread) { case S64_TYPE: t.s64 = a.s64 * b.s64; assert(!pI->is_wide()); - //assert(!pI->is_hi()); + // assert(!pI->is_hi()); d.s64 = t.s64; break; case U16_TYPE: |