[gem5-users] Re: Long linkage
The opt build now uses link time optimization (LTO) and does not use partial linking. On slower machines and/or machines with fewer cores (and maybe less memory?) this seems to really slow things down, where on machines with more cores, LTO linking happens to be parallel where normal linking doesn't seem to be, and this and not having partial linking is actually a good bit faster and significantly reduces the footprint of the build directory. If you see long link times and you didn't before, you can try disabling LTO (--no-lto). That should bring the link times back down to be more in line with older versions. Gabe On Sun, Apr 11, 2021 at 9:46 PM Majid Jalili via gem5-users < gem5-users@gem5.org> wrote: > Hi, > Why does the recent version of gem5 takes very long on the last step when > creating the gem5.opt? My 2-month old repo is just fine, but the new > version takes a very long to finish link. > I tried on three different machines with the different OS but no > improvement. > > ___ > gem5-users mailing list -- gem5-users@gem5.org > To unsubscribe send an email to gem5-users-le...@gem5.org > %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] Long linkage
Hi, Why does the recent version of gem5 takes very long on the last step when creating the gem5.opt? My 2-month old repo is just fine, but the new version takes a very long to finish link. I tried on three different machines with the different OS but no improvement. ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] Re: Kernel panic when using ubuntu-18.04-arm64-docker.img
Thanks a lot, I think my problem occurred after the /tmp/my_script run and before exec /sbin/getty -a root -L ttyAMA0 vt102 run. You say the init process isn’t supposed to exit, I counldn’t understand it, which is the init process? The /tmp/my_script, or the /init.gem5? and I want to know the reason why it’s supposed to exit. ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] can anyboby tell me how to generate the checpoints of spec2017?
Hi, if you want to generate the checkpoint using the fs, you can use the m5.checkpoint() func in the python script, or can use the /sbin/m5 checkpoint agter you connect the m5term. ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] can't reset stats.txt when using KVM CPU
Hi all, Now I using the KVM CPU to run fs mode, and I try two ways to reset the m5out/stats.txt but all can’t work. 1) I use the m5.stats.reset() and m5.stats.dump() functions in the python script before switch cpu, the m5out/stats.txt will be written. But then I use m5.stats.reset() and m5.stats.dump() before next times, the m5out/stats.txt has no changes, the final_tick, sim_insts will not be reset to start from 0. 2) So I try to use the m5 –addr 0x1001 dumpstats/resetstats/dumpresetstats after connect by m5term, but the same problem is still. I would appreciate it if someone can help me explain this problem. ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] Add pio devices into Gem5 ruby network
Hi all : I need to construct a MPSoC system based on Gem5 FS mode. And I have chosen the Ruby Garnet Network with MESI_Three_Level protocol as the interconnect bus. Now I would like to add some pio devices into the network. In general, I expect cpu cores and devices can communicate with each other through the Garnet network. So I think I can't add the devices into the realview io device/mem system accessed by the iobus. I should add the device to attach the Directory Controller. But I also expect the devices don't participate in the cache coherence protocol. So, I sincerely hope to get some help about how to make L0-L2 Cache Controller and Directory Controller bypass the access request to the devices. Of course, welcome to give me some better ideas to fulfill my needs. Thanks and regards, Lee. ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] Re: Kernel panic when using ubuntu-18.04-arm64-docker.img
Hi, it looks like your script (/tmp/my_script) is exiting. I think the init process isn't supposed to exit. Gabe On Sun, Apr 11, 2021 at 4:13 AM kong han via gem5-users wrote: > Hi all, > > Now I using the Latest linux kernel and disk images to run fs mode with > KVM CPU ( > https://www.gem5.org/documentation/general_docs/fullsystem/guest_binaries), > and I mount the image and modify the mnt-dir/init.gem5 to readfile from the > –script, then I run this script, but after that, I have the Kernal panic, > and can’t run next step, how could I solve this problem? > > The error is : > > + mount -t proc - /proc > > + mount -t sysfs - /sys > > + mount -t debugfs - /sys/kernel/debug/ > > + [ -e /dev/sdb1 ] > > + [ -e /dev/sdb ] > > + [ -e /dev/vdb1 ] > > + [ -e /dev/vdb ] > > + [ -e /dev/vda1 ] > > + [ -e /dev/vda ] > > + f=/tmp/script > > + /sbin/m5 --addr 0x1001 readfile > > + chmod 777 /tmp/my_script > > + exec /tmp/my_script > > > > [4.428566] Kernel panic - not syncing: Attempted to kill init! > exitcode=0x > > [4.428566] > > [4.430528] CPU: 0 PID: 1 Comm: sh Not tainted 4.18.0+ #1 > > [4.431673] Hardware name: V2P-CA15 (DT) > > [4.432596] Call trace: > > [4.433314] dump_backtrace+0x0/0x1c0 > > [4.434125] show_stack+0x14/0x20 > > [4.435046] dump_stack+0x8c/0xac > > [4.435837] panic+0x130/0x288 > > [4.436563] complete_and_exit+0x0/0x20 > > [4.437473] do_group_exit+0x38/0xa0 > > [4.438310] __wake_up_parent+0x0/0x28 > > [4.439181] el0_svc_naked+0x30/0x34 > > [4.440043] Kernel Offset: disabled > > [4.440911] CPU features: 0x22800210 > > [4.441720] Memory Limit: 512 MB > > [4.442503] ---[ end Kernel panic - not syncing: Attempted to kill > init! exitcode=0x > > [4.442503] ]--- > > > > The init.gem5 I modify is : > > #!/bin/sh > > set -ex > > mount -t proc - /proc > > mount -t sysfs - /sys > > mount -t debugfs - /sys/kernel/debug/ > > for DEV in /dev/sdb1 /dev/sdb /dev/vdb1 /dev/vdb /dev/vda1 /dev/vda; do > > if [ -e "${DEV}" ]; then > > mount "${DEV}" /data > > break > > fi > > done > > f=/tmp/script > > /sbin/m5 --addr 0x1001 readfile > /tmp/my_script > > chmod 777 /tmp/my_script > > exec /tmp/my_script > > exec /sbin/getty -a root -L ttyAMA0 vt102 > > > > And my cmd is : > > ./build/ARM/gem5.opt \ > > -d ./m5out/ \ > > ./configs/example/fs.py \ > > --disk=../image/ubuntu-18.04-arm64-docker.img \ > > --kernel=../aarch-system-201901106/binaries/vmlinux.arm64 \ > > --cpu-type=ArmV8KvmCPU \ > > --bootloader=../kernel/aarch-system-201901106/binaries/boot.arm64 \ > > --script=../gem5/temp-rcs/t1.rcS \ > > > > > ___ > gem5-users mailing list -- gem5-users@gem5.org > To unsubscribe send an email to gem5-users-le...@gem5.org > %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
[gem5-users] Kernel panic when using ubuntu-18.04-arm64-docker.img
Hi all, Now I using the Latest linux kernel and disk images to run fs mode with KVM CPU (https://www.gem5.org/documentation/general_docs/fullsystem/guest_binaries), and I mount the image and modify the mnt-dir/init.gem5 to readfile from the –script, then I run this script, but after that, I have the Kernal panic, and can’t run next step, how could I solve this problem? The error is : + mount -t proc - /proc + mount -t sysfs - /sys + mount -t debugfs - /sys/kernel/debug/ + [ -e /dev/sdb1 ] + [ -e /dev/sdb ] + [ -e /dev/vdb1 ] + [ -e /dev/vdb ] + [ -e /dev/vda1 ] + [ -e /dev/vda ] + f=/tmp/script + /sbin/m5 --addr 0x1001 readfile + chmod 777 /tmp/my_script + exec /tmp/my_script [4.428566] Kernel panic - not syncing: Attempted to kill init! exitcode=0x [4.428566] [4.430528] CPU: 0 PID: 1 Comm: sh Not tainted 4.18.0+ #1 [4.431673] Hardware name: V2P-CA15 (DT) [4.432596] Call trace: [4.433314] dump_backtrace+0x0/0x1c0 [4.434125] show_stack+0x14/0x20 [4.435046] dump_stack+0x8c/0xac [4.435837] panic+0x130/0x288 [4.436563] complete_and_exit+0x0/0x20 [4.437473] do_group_exit+0x38/0xa0 [4.438310] __wake_up_parent+0x0/0x28 [4.439181] el0_svc_naked+0x30/0x34 [4.440043] Kernel Offset: disabled [4.440911] CPU features: 0x22800210 [4.441720] Memory Limit: 512 MB [4.442503] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x [4.442503] ]--- The init.gem5 I modify is : #!/bin/sh set -ex mount -t proc - /proc mount -t sysfs - /sys mount -t debugfs - /sys/kernel/debug/ for DEV in /dev/sdb1 /dev/sdb /dev/vdb1 /dev/vdb /dev/vda1 /dev/vda; do if [ -e "${DEV}" ]; then mount "${DEV}" /data break fi done f=/tmp/script /sbin/m5 --addr 0x1001 readfile > /tmp/my_script chmod 777 /tmp/my_script exec /tmp/my_script exec /sbin/getty -a root -L ttyAMA0 vt102 And my cmd is : ./build/ARM/gem5.opt \ -d ./m5out/ \ ./configs/example/fs.py \ --disk=../image/ubuntu-18.04-arm64-docker.img \ --kernel=../aarch-system-201901106/binaries/vmlinux.arm64 \ --cpu-type=ArmV8KvmCPU \ --bootloader=../kernel/aarch-system-201901106/binaries/boot.arm64 \ --script=../gem5/temp-rcs/t1.rcS \ ___ gem5-users mailing list -- gem5-users@gem5.org To unsubscribe send an email to gem5-users-le...@gem5.org %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s