To whom it may concern, I'm new to gem5, I just downloaded gem5 to simulate some spec benchmarks, but I encountered something which seems not making sense; basically, the outcome of the program simulated by gem5 does not match the outcome of the same program run directly on the machine. The results of two runs are shown below. I hope I can get help/corrections from you guys. Thank you. Sincerely yours, An-Chow direct run (which is expected and looks correct to me): ------------- ../../exe/lbm_r_base.mytest-m64 30 reference.dat 0 0 100_100_130_ldc.of MAIN_printInfo: grid size : 100 x 100 x 130 = 1.30 * 10^6 Cells nTimeSteps : 30 result file : reference.dat action : nothing simulation type: lid-driven cavity obstacle file : 100_100_130_ldc.of LBM_showGridStatistics: nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 minRho: 1.000000 maxRho: 1.000000 Mass: 1.300000e+06 minU : 0.000000 maxU : 0.000000 LBM_showGridStatistics: nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 minRho: 0.998947 maxRho: 1.001139 Mass: 1.300000e+06 minU : 0.000000 maxU : 0.003548 gem5 simulated run (which does not match the direct run above): ------------------ ~/Work/gem5/build/X86/gem5.opt ~/Work/gem5/configs/deprecated/example/se.py --cmd="../../exe/lbm_r_base.mytest-m64" --option="30 reference.dat 0 0 100_100_130_ldc.of" --mem-size=8GB gem5 Simulator System. https://www.gem5.org gem5 is copyrighted software; use the --copyright option for details. gem5 version 23.0.0.1 gem5 compiled Jul 22 2023 09:57:33 gem5 started Jul 22 2023 12:50:00 gem5 executing on Oreo-II, pid 62021 warn: The `get_runtime_isa` function is deprecated. Please migrate away from using this function. warn: The se.py script is deprecated. It will be removed in future releases of gem5. warn: The `get_runtime_isa` function is deprecated. Please migrate away from using this function. Global frequency set at 1000000000000 ticks per second warn: No dot file generated. Please install pydot to generate the dot file and pdf. src/base/statistics.hh:279: warn: One of the stats is a legacy stat. Legacy stat is a stat that does not belong to any statistics::Group. Legacy stat is deprecated. system.remote_gdb: Listening for connections on port 7000 **** REAL SIMULATION **** src/sim/simulate.cc:194: info: Entering event queue @ 0. Starting simulation... src/sim/mem_state.cc:443: info: Increasing stack size by one page. src/sim/syscall_emul.cc:74: warn: ignoring syscall set_robust_list(...) src/sim/syscall_emul.cc:74: warn: ignoring syscall rseq(...) src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) MAIN_printInfo: grid size : 100 x 100 x 130 = 1.30 * 10^6 Cells nTimeSteps : 30 result file : reference.dat action : nothing simulation type: lid-driven cavity obstacle file : 100_100_130_ldc.of LBM_showGridStatistics: nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 minRho: 0.000000 maxRho: 0.000000 Mass: 0.000000e+00 minU : 0.166667 maxU : 0.235702 LBM_showGridStatistics: nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 minRho: 0.000000 maxRho: 0.000000 Mass: 0.000000e+00 minU : -nan maxU : inf

There's a lot of information missing in your email, but I'll make some guesses and try to help. If you're using x86 and you compiled lbm on your host, then most likely it is using SSE/AVX/vector instructions that may not be implemented or implemented incorrectly in gem5. I would expect to see warnings about unimplemented instructions, but I don't see them in your output. One possible way to check is to recompile without vector instructions and try that binary. Finally, there are a number of warnings about unimplemented syscalls. I don't think any of those would cause a problem, but using FS mode could improve the fidelity of your simulation. Cheers, Jason On Sat, Jul 22, 2023 at 5:59 AM An Chow Lai via gem5-users < gem5-users@gem5.org> wrote: > To whom it may concern, > > I'm new to gem5, I just downloaded gem5 to simulate some spec benchmarks, > but I encountered something which seems not making sense; > basically, the outcome of the program simulated by gem5 does not match the > outcome of the same program run directly on the machine. The results of two > runs are shown below. > I hope I can get help/corrections from you guys. Thank you. > > Sincerely yours, > An-Chow > > direct run (which is expected and looks correct to me): > ------------- > ../../exe/lbm_r_base.mytest-m64 30 reference.dat 0 0 100_100_130_ldc.of > MAIN_printInfo: > grid size : 100 x 100 x 130 = 1.30 * 10^6 Cells > nTimeSteps : 30 > result file : reference.dat > action : nothing > simulation type: lid-driven cavity > obstacle file : 100_100_130_ldc.of > > LBM_showGridStatistics: > nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 > minRho: 1.000000 maxRho: 1.000000 Mass: 1.300000e+06 > minU : 0.000000 maxU : 0.000000 > > LBM_showGridStatistics: > nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 > minRho: 0.998947 maxRho: 1.001139 Mass: 1.300000e+06 > minU : 0.000000 maxU : 0.003548 > > gem5 simulated run (which does not match the direct run above): > ------------------ > ~/Work/gem5/build/X86/gem5.opt > ~/Work/gem5/configs/deprecated/example/se.py > --cmd="../../exe/lbm_r_base.mytest-m64" --option="30 reference.dat 0 0 > 100_100_130_ldc.of" --mem-size=8GB > gem5 Simulator System. https://www.gem5.org > gem5 is copyrighted software; use the --copyright option for details. > > gem5 version 23.0.0.1 > gem5 compiled Jul 22 2023 09:57:33 > gem5 started Jul 22 2023 12:50:00 > gem5 executing on Oreo-II, pid 62021 > > warn: The `get_runtime_isa` function is deprecated. Please migrate away > from using this function. > warn: The se.py script is deprecated. It will be removed in future > releases of gem5. > warn: The `get_runtime_isa` function is deprecated. Please migrate away > from using this function. > Global frequency set at 1000000000000 ticks per second > warn: No dot file generated. Please install pydot to generate the dot file > and pdf. > src/base/statistics.hh:279: warn: One of the stats is a legacy stat. > Legacy stat is a stat that does not belong to any statistics::Group. Legacy > stat is deprecated. > system.remote_gdb: Listening for connections on port 7000 > **** REAL SIMULATION **** > src/sim/simulate.cc:194: info: Entering event queue @ 0. Starting > simulation... > src/sim/mem_state.cc:443: info: Increasing stack size by one page. > src/sim/syscall_emul.cc:74: warn: ignoring syscall set_robust_list(...) > src/sim/syscall_emul.cc:74: warn: ignoring syscall rseq(...) > src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) > src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) > src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) > src/sim/syscall_emul.cc:74: warn: ignoring syscall mprotect(...) > MAIN_printInfo: > grid size : 100 x 100 x 130 = 1.30 * 10^6 Cells > nTimeSteps : 30 > result file : reference.dat > action : nothing > simulation type: lid-driven cavity > obstacle file : 100_100_130_ldc.of > > LBM_showGridStatistics: > nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 > minRho: 0.000000 maxRho: 0.000000 Mass: 0.000000e+00 > minU : 0.166667 maxU : 0.235702 > > LBM_showGridStatistics: > nObstacleCells: 112539 nAccelCells: 18432 nFluidCells: 1169029 > minRho: 0.000000 maxRho: 0.000000 Mass: 0.000000e+00 > minU : -nan maxU : inf > > _______________________________________________ > gem5-users mailing list -- gem5-users@gem5.org > To unsubscribe send an email to gem5-users-leave@gem5.org >