diff options
author | Korey Sewell <ksewell@umich.edu> | 2011-02-12 10:14:52 -0500 |
---|---|---|
committer | Korey Sewell <ksewell@umich.edu> | 2011-02-12 10:14:52 -0500 |
commit | 2971b8401a4a76a774962900d9aed6e9eb4b2950 (patch) | |
tree | 7d340ad8093c6dc68395cf209baa0785348137e5 /tests/quick/00.hello/ref/alpha | |
parent | 470aa289da4ca2d6564db76b30355a527c65347d (diff) | |
download | gem5-2971b8401a4a76a774962900d9aed6e9eb4b2950.tar.xz |
inorder:regress: host-inst-rate improved ~58%
there are still only a few inorder benchmark but for the lengthier benchmarks (twolf and vortext)
the latest changes to how instruction scheduling (how instructions figure out what they want to
do on each pipeline stage in the inorder model) were able to improve performance by a nice
amount... The latest results for the inorder model process about 100k insts/second
(note: 58% is over the last time run on 64-bit pool machines at UM)
Diffstat (limited to 'tests/quick/00.hello/ref/alpha')
-rw-r--r-- | tests/quick/00.hello/ref/alpha/linux/inorder-timing/stats.txt | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tests/quick/00.hello/ref/alpha/linux/inorder-timing/stats.txt b/tests/quick/00.hello/ref/alpha/linux/inorder-timing/stats.txt index 246665e32..4b7effb4d 100644 --- a/tests/quick/00.hello/ref/alpha/linux/inorder-timing/stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/inorder-timing/stats.txt @@ -1,9 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 37548 # Simulator instruction rate (inst/s) -host_mem_usage 223436 # Number of bytes of host memory used -host_seconds 0.17 # Real time elapsed on the host -host_tick_rate 130476959 # Simulator tick rate (ticks/s) +host_inst_rate 76381 # Simulator instruction rate (inst/s) +host_mem_usage 190468 # Number of bytes of host memory used +host_seconds 0.08 # Real time elapsed on the host +host_tick_rate 264969940 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 6404 # Number of instructions simulated sim_seconds 0.000022 # Number of seconds simulated |