<AS id="AS0" routing="Full">
<!-- Use the pstate mechanism to encode the boot/shutdown time and energy -->
-
- <!-- That may be seen as a misuse of the pstate mechanism and crude hack,
- but this is efficient: we can do what we want without too much burden,
- and since the whole intelligence is at user level, we do control the model.
-
- The same could be done to encode the time and energy to switch
- between pstates. These times seem negligeable in our
- experiments, but if they are important to you, now you know how
- to do that. -->
-
+
+ <!-- That may be seen as a misuse of the pstate mechanism and crude hack, but this is efficient: we can do what
+ we want without too much burden, and since the whole intelligence is at user level, we do control the model.
+
+ The same could be done to encode the time and energy to switch between pstates. These times seem negligible
+ in our experiments, but if they are important to you, now you know how to do that. -->
+
<!-- pstate values:
- * 0-2: real pstates
- 0: p1 100 MFlops/s, [idle: 95W -> full burning: 200W]
- 1: p2 50 MFlops/s, [idle: 93W -> full burning: 170W]
- 2: p3 20 MFlops/s, [idel: 90W -> full burning: 150W]
- * 3: booting up was measured to take 150s and 18000J.
- So we create a pstate with 1 flop/150 s so that the
- application burns 1 flop in that virtual pstate to
- simulate a boot.
- Multiply everything by 1000 or whatever if this trick is
- too painful to you, that's the same by the end.
- The energy consumption is 18000/150=120W
- * 4: shuting down was measured to take 7 s and 770 J
-
- Please note that we tried to put sensible values in this file
- but you should still take them with a grain of salt. If you
- want a realistic simulation, you have to actually benchmark
- your platform and application, and use the values that are
- right for you. -->
-
-
+ * 0-2: real pstates
+ 0: p1 100 MFlops/s, [idle: 95W -> full burning: 200W]
+ 1: p2 50 MFlops/s, [idle: 93W -> full burning: 170W]
+ 2: p3 20 MFlops/s, [idel: 90W -> full burning: 150W]
+ * 3: booting up was measured to take 150s and 18000J.
+ So we create a pstate with 1 flop/150 s so that the application burns 1 flop in that virtual pstate to
+ simulate a boot.
+ Multiply everything by 1000 or whatever if this trick is too painful to you, that's the same by the end.
+ The energy consumption is 18000/150=120W
+ * 4: shuting down was measured to take 7 s and 770 J
+
+ Please note that we tried to put sensible values in this file but you should still take them with a grain of salt.
+ If you want a realistic simulation, you have to actually benchmark your platform and application, and use the
+ values that are right for you. -->
+
<host id="MyHost1" speed="100.0Mf,50.0Mf,20.0Mf, 0.006666667f,0.1429f" pstate="0" >
<prop id="watt_per_state"value="95.0:200.0,93.0:170.0,90.0:150.0, 120:120,110:110" />
<prop id="watt_off" value="10" />
<link id="link1" bandwidth="100kBps" latency="0"/>
<route src="MyHost1" dst="MyHost2"><link_ctn id="link1"/></route>
-
</AS>
</platform>
