Why don't you run the SPLASH program natively and check if the native
execution output and the simulation output match?
--
Nilay
On Sat, 28 Jan 2012, Sangamesh K wrote:
Hi,
(1) Use gem5-dev instead of stable
The results were the same using gem-dev.
(2) check the m5out/stats.txt - r u getting zeros there?
The stats file does report some statistics as below
system.cpu.numCycles 1233163
# number of cpu cycles simulated
system.cpu.numWorkItemsStarted 0
# number of work items this cpu started
system.cpu.numWorkItemsCompleted 0
# number of work items this cpu completed
system.cpu.contextSwitches 1
# Number of context switches
system.cpu.threadCycles 944399
# Total Number of Cycles A Thread Was Active in CPU (Per-Thread)
system.cpu.smtCycles 0
# Total number of cycles that the CPU was in SMT-mode
system.cpu.timesIdled 6161
# Number of times that the entire CPU went into an idle state and
unscheduled itself
system.cpu.idleCycles 380019
# Number of cycles cpu's stages were not processed
system.cpu.runCycles 853144
# Number of cycles cpu stages are processed.
I am not sure if the above results are correct as the number of
instructions executed using the run.py script (timing CPU) is significantly
higher than the number of instructions executed in SE mode (InOrderCPU).
Excerpts from the stats files shown the following-
Inorder CPU stat
system.cpu.execution_unit.executions 962400
# Number of Instructions Executed.
Timing CPU stat
system.cpu.num_insts 253925588
# Number of instructions executed
Thanks,
Sangam
On Fri, Jan 27, 2012 at 8:04 PM, Sangamesh K <[email protected]> wrote:
Hi All,
I am gem5 beginner and I am trying to run splash benchmarks in ALPHA_SE
for an in-order CPU. The results obtained were all zeros.
I am using gem-stable and command is as follows-
build/ALPHA_SE/gem5.opt configs/example/se.py --inorder --caches -c
./../splash2/codes/kernels/fft/FFT -o "-t -p1"
-----------------------------------------------------------------------------------------------------------------------------
FFT with Blocking Transpose
1024 Complex Doubles
1 Processors
65536 Cache lines
16 Byte line size
4096 Bytes per page
PROCESS STATISTICS
Computation Transpose Transpose
Proc Time Time Fraction
0 0 0 NaNQ
TIMING INFORMATION
Start time : 0
Initialization finish time : 0
Overall finish time : 0
Total time with initialization : 0
Total time without initialization : 0
Overall transpose time : 0
Overall transpose fraction : NaNQ
INVERSE FFT TEST RESULTS
Checksum difference is 0.000 (1033.228, 1033.228)
TEST PASSED
warn: ignoring syscall sigprocmask(18446744073709547831, 1, ...)
Exiting @ tick 2181887000 because target called exit()
-----------------------------------------------------------------------------------------------------------------------------
I am able to successfully run the splash benchmarks in SE mode using
splash2/run.py. Editing the run.py script to use InOrderCPU() did not do
any good and results were same as above (zeros). Has anyone tried running
the splash2 benchmarks using inorder CPU?
Thanks,
Sangam
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
