mirror of
https://github.com/cirosantilli/linux-kernel-module-cheat.git
synced 2026-01-23 02:05:57 +01:00
readme: gem5 tracing.
Fix some parsec readme errors after missed ./run flag updates.
This commit is contained in:
Ciro Santilli
72
README.adoc
72
README.adoc
@@ -2153,6 +2153,48 @@ Unfortunately it is not working in the current QEMU: https://stackoverflow.com/q
|
||||
|
||||
Alternatively, https://github.com/mozilla/rr[`mozilla/rr`] claims it is able to run QEMU: but using it would require you to step through QEMU code itself. Likely doable, but do you really want to?
|
||||
|
||||
==== gem5 tracing
|
||||
|
||||
gem5 also has a tracing mechanism, as documented at: http://www.gem5.org/Trace_Based_Debugging
|
||||
|
||||
Try it out with:
|
||||
|
||||
....
|
||||
./run -a aarch64 -E 'm5 exit' -G '--debug-flags=Exec' -g
|
||||
....
|
||||
|
||||
The trace file is located at:
|
||||
|
||||
....
|
||||
less out/aarch64/gem5/m5out/trace.txt
|
||||
....
|
||||
|
||||
but be warned, it is humongous, at 16Gb.
|
||||
|
||||
It made the runtime about 4x slower on the <<p51>>, with or without `.gz` compression.
|
||||
|
||||
The list of available debug flags can be found with:
|
||||
|
||||
....
|
||||
./run -a aarch64 -G --debug-help -g
|
||||
....
|
||||
|
||||
but for meaningful descriptions you need to look at the source code:
|
||||
|
||||
....
|
||||
less gem5/gem5/src/cpu/SConscript
|
||||
....
|
||||
|
||||
The default `Exec` format reads symbol names from the Linux kernel image and show them, which is pretty awesome if you ask me.
|
||||
|
||||
TODO can we get just the executed addresses out of gem5? The following gets us closer, but not quite:
|
||||
|
||||
....
|
||||
./run -a aarch64 -E 'm5 exit' -G '--debug-flags=ExecEnable,ExecKernel,ExecUse' -g
|
||||
....
|
||||
|
||||
We could of course just pipe it to stdout and `awk` it up.
|
||||
|
||||
=== QEMU GUI is unresponsive
|
||||
|
||||
Sometimes in Ubuntu 14.04, after the QEMU SDL GUI starts, it does not get updated after keyboard strokes, and there are artifacts like disappearing text.
|
||||
@@ -2239,8 +2281,8 @@ We have benchmarked a Linux kernel boot at commit da79d6c6cde0fbe5473ce868c9be47
|
||||
....
|
||||
# Try to manually hit Ctrl + C as soon as system shutdown message appears.
|
||||
time ./run -a arm -e 'init=/poweroff.out'
|
||||
time ./run -a arm -e 'm5 exit' -g
|
||||
time ./run -a arm -e 'm5 exit' -g -- --caches --cpu-type=HPI
|
||||
time ./run -a arm -E 'm5 exit' -g
|
||||
time ./run -a arm -E 'm5 exit' -g -- --caches --cpu-type=HPI
|
||||
time ./run -a x86_64 -e 'init=/poweroff.out'
|
||||
time ./run -a x86_64 -e 'init=/poweroff.out' -- -enable-kvm
|
||||
time ./run -a x86_64 -e 'init=/poweroff.out' -g
|
||||
@@ -2250,13 +2292,14 @@ and the results were:
|
||||
|
||||
[options="header"]
|
||||
|===
|
||||
|Emulator |Time |N times slower than QEMU
|
||||
|QEMU ARM |6 seconds |1
|
||||
|gem5 ARM AtomicSimpleCPU |1 minute 40 seconds |17
|
||||
|gem5 ARM HPI |10 minutes |100
|
||||
|QEMU X86_64 |4 seconds |1
|
||||
|QEMU X86_64 KVM |2 seconds |0.5
|
||||
|gem5 X86_64 |5 minutes 30 seconds |82
|
||||
|Emulator |Time |N times slower than QEMU |Instruction count |commit
|
||||
|QEMU ARM |6 seconds |1 | |
|
||||
|gem5 ARM AtomicSimpleCPU |1 minute 40 seconds |17 | |
|
||||
|gem5 ARM HPI |10 minutes |100 | |
|
||||
|gem5 aarch64 AtomicSimpleCPU |1 minute | |520M |b6e8a7d1d1cb8a1d10d57aa92ae66cec9bfb2d01
|
||||
|QEMU X86_64 |4 seconds |1 | |
|
||||
|QEMU X86_64 KVM |2 seconds |0.5 | |
|
||||
|gem5 X86_64 |5 minutes 30 seconds |82 | |
|
||||
|===
|
||||
|
||||
tested on the <<p51>>.
|
||||
@@ -2556,7 +2599,7 @@ There are two ways to run PARSEC with this repo:
|
||||
====== PARSEC benchmark without parsecmgmt
|
||||
|
||||
....
|
||||
configure -gpq && ./build -a arm -b br2_parsec -g && ./run -a arm -g
|
||||
configure -gpq && ./build -a arm -B 'BR2_PACKAGE_PARSEC_BENCHMARK=y' -g && ./run -a arm -g
|
||||
....
|
||||
|
||||
Once inside the guest, launch one of the `test` input sized benchmarks manually as in:
|
||||
@@ -2585,14 +2628,13 @@ Running a benchmark of a different size requires a rebuild with:
|
||||
....
|
||||
./build \
|
||||
-a arm \
|
||||
-b br2_parsec \
|
||||
-c 'BR2_PACKAGE_PARSEC_BENCHMARK_INPUT_SIZE="simsmall"' \
|
||||
-B 'BR2_PACKAGE_PARSEC_BENCHMARK=y' \
|
||||
-B 'BR2_PACKAGE_PARSEC_BENCHMARK_INPUT_SIZE="simsmall"' \
|
||||
-g \
|
||||
-- parsec-benchmark-reconfigure \
|
||||
;
|
||||
....
|
||||
|
||||
|
||||
Large input sizes will likely require tweaking <<br2_target_rootfs_ext2_size>>.
|
||||
|
||||
The rebuild is required because we unpack input files on the host.
|
||||
@@ -2610,7 +2652,7 @@ Maybe you need to increase the filesystem size (BR2_TARGET_ROOTFS_EXT2_SIZE)
|
||||
The solution is to simply add:
|
||||
|
||||
....
|
||||
./build -B 'BR2_TARGET_ROOTFS_EXT2_SIZE="500M"'
|
||||
./build -B 'BR2_TARGET_ROOTFS_EXT2_SIZE="512M"'
|
||||
....
|
||||
|
||||
where 500M is "large enough".
|
||||
@@ -2648,7 +2690,7 @@ If you still want to run this, try it out with:
|
||||
|
||||
....
|
||||
./build -a arm \
|
||||
-c BR2_TARGET_ROOTFS_EXT2_SIZE="3G" \
|
||||
-B 'BR2_TARGET_ROOTFS_EXT2_SIZE="3G"' \
|
||||
-g
|
||||
-b br2_parsec
|
||||
-- parsec-benchmark-reconfigure \
|
||||
|
||||
Reference in New Issue
Block a user