Re: [gem5-users] Unable to run script upon restoring from checkpoint

[TungHoang_GMail]

mode: will probe irqs later
    ide0: BM-DMA at 0x1000-0x1007, BIOS settings: hda:DMA, hdb:DMA
    ide1: BM-DMA at 0x1008-0x100f, BIOS settings: hdc:DMA, hdd:DMA
hda: M5 IDE Disk, ATA DISK drive
hdb: M5 IDE Disk, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hda: max request size: 128KiB
hda: 4194288 sectors (2147 MB), CHS=4161/16/63, UDMA(33)
 hda: hda1
hdb: max request size: 128KiB
hdb: 4177920 sectors (2139 MB), CHS=4144/16/63, UDMA(33)
 hdb: unknown partition table
megaraid cmm: 2.20.2.7 (Release Date: Sun Jul 16 00:01:03 EST 2006)
megaraid: 2.20.5.1 (Release Date: Thu Nov 16 15:32:35 EST 2006)
megasas: 00.00.03.10-rc5 Thu May 17 10:09:32 PDT 2007
Fusion MPT base driver 3.04.04
Copyright (c) 1999-2007 LSI Logic Corporation
Fusion MPT SPI Host driver 3.04.04
Fusion MPT SAS Host driver 3.04.04
ieee1394: raw1394: /dev/raw1394 device initialized
USB Universal Host Controller Interface driver v3.0
usbcore: registered new interface driver usblp
drivers/usb/class/usblp.c: v0.13: USB Printer Device Class driver
Initializing USB Mass Storage driver...
usbcore: registered new interface driver usb-storage
USB Mass Storage support registered.
serio: i8042 KBD port at 0x60,0x64 irq 1
serio: i8042 AUX port at 0x60,0x64 irq 12
mice: PS/2 mouse device common for all mice
input: AT Translated Set 2 keyboard as /class/input/input0
device-mapper: ioctl: 4.11.0-ioctl (2006-10-12) initialised: 
dm-de...@redhat.com

input: PS/2 Generic Mouse as /class/input/input1
usbcore: registered new interface driver usbhid
drivers/hid/usbhid/hid-core.c: v2.6:USB HID core driver
oprofile: using timer interrupt.
TCP cubic registered
NET: Registered protocol family 1
NET: Registered protocol family 10
IPv6 over IPv4 tunneling driver
NET: Registered protocol family 17
EXT2-fs warning: mounting unchecked fs, running e2fsck is recommended
VFS: Mounted root (ext2 filesystem).
Freeing unused kernel memory: 248k freed
mounting filesystems...
loading script...
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Running Dijkstra benchmark now
Shortest path is 0 in cost. Path is:  0 50
Finishing now
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Thanks.

Regards,
Elena

From: TungHoang_GMail <mailto:hoangthanht...@gmail.com>>

Date: Friday, 3 August 2018 at 6:37 PM
To: gem5 users mailing list <mailto:gem5-users@gem5.org>>, Elena Woo <mailto:l.l@soton.ac.uk>>
Subject: Re: [gem5-users] Unable to run script upon restoring from 
checkpoint


You should check if your image file support "bash" or "sh". Just mount 
your image in specific folder, find bash or sh in /bin then adapt your 
script.


/T
On 08/03/2018 12:47 AM, Woo L.L. wrote:

Dear all,

I am having a problem trying to run the second script file after 
restoring from checkpoint.
I have used used hack_back_ckpt.rcS to create 1st checkpoint after 
booting from Linux. Here is the command I have used to run the 
checkpointing:
*./build/X86/gem5.opt ./configs/example/fs.py 
--script=./configs/boot/hack_back_ckpt.rcS*

*
*
And here is the result after checkpointing:
DMTCP::  SIMULATION IS NOT ATTACHED WITH DMTCP !!!
gem5 Simulator System. http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 12 2018 21:57:22
gem5 started Aug  3 2018 08:24:00
gem5 executing on elena-VirtualBox, pid 2854
command line: ./build/X86/gem5.opt ./configs/example/fs.py 
--script=./configs/boot/hack_back_ckpt.rcS


Global frequency set at 1 ticks per second
warn: DRAM device capacity (8192 Mbytes) does not match the address 
range assigned (512 Mbytes)

Setting Entry Point
info: kernel located at: /home/elena/RTS/gemfi/x86/binaries/vmlinux
Listening for com_1 connection on port 3456
      0: rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
warn: Reading current count from inactive timer.
 REAL SIMULATION 
info: Entering event queue @ 0.  Starting simulation...
warn: Don't know what interrupt to clear for console.
warn: x86 cpuid: unknown family 0x8086
warn: instruction 'wbinvd' unimplemented
warn: Tried to clear PCI interrupt 14
warn: Unknown mouse command 0xe1.
Writing checkpoint
info: Entering event queue @ 513104952.  Starting simulation...
Exiting @ tick 5132244233500 because m5_exit instruction encountered

To run the second script file, this was what I used:
*./build/X86/gem5.opt --debug-flags=FaultInjection 
./configs/example/fs.py --cpu-clock=250MHz --caches -r 1 
--script=./configs/boot/dijkstra.py*


The result is shown as below:
DMTCP::  SIMULATION IS NOT ATTACHED WITH DMTCP !!!
gem5 Simulator System. http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 12 2018 21:

Re: [gem5-users] Unable to run script upon restoring from checkpoint

[TungHoang_GMail]

You should check if your image file support "bash" or "sh". Just mount 
your image in specific folder, find bash or sh in /bin then adapt your 
script.


/T
On 08/03/2018 12:47 AM, Woo L.L. wrote:

Dear all,

I am having a problem trying to run the second script file after 
restoring from checkpoint.
I have used used hack_back_ckpt.rcS to create 1st checkpoint after 
booting from Linux. Here is the command I have used to run the 
checkpointing:
*./build/X86/gem5.opt ./configs/example/fs.py 
--script=./configs/boot/hack_back_ckpt.rcS*

*
*
And here is the result after checkpointing:
DMTCP::  SIMULATION IS NOT ATTACHED WITH DMTCP !!!
gem5 Simulator System.  http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 12 2018 21:57:22
gem5 started Aug  3 2018 08:24:00
gem5 executing on elena-VirtualBox, pid 2854
command line: ./build/X86/gem5.opt ./configs/example/fs.py 
--script=./configs/boot/hack_back_ckpt.rcS


Global frequency set at 1 ticks per second
warn: DRAM device capacity (8192 Mbytes) does not match the address 
range assigned (512 Mbytes)

Setting Entry Point
info: kernel located at: /home/elena/RTS/gemfi/x86/binaries/vmlinux
Listening for com_1 connection on port 3456
      0: rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
warn: Reading current count from inactive timer.
 REAL SIMULATION 
info: Entering event queue @ 0.  Starting simulation...
warn: Don't know what interrupt to clear for console.
warn: x86 cpuid: unknown family 0x8086
warn: instruction 'wbinvd' unimplemented
warn: Tried to clear PCI interrupt 14
warn: Unknown mouse command 0xe1.
Writing checkpoint
info: Entering event queue @ 513104952.  Starting simulation...
Exiting @ tick 5132244233500 because m5_exit instruction encountered

To run the second script file, this was what I used:
*./build/X86/gem5.opt --debug-flags=FaultInjection 
./configs/example/fs.py --cpu-clock=250MHz --caches -r 1 
--script=./configs/boot/dijkstra.py*


The result is shown as below:
DMTCP::  SIMULATION IS NOT ATTACHED WITH DMTCP !!!
gem5 Simulator System.  http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 12 2018 21:57:22
gem5 started Aug  3 2018 08:33:33
gem5 executing on elena-VirtualBox, pid 2878
command line: ./build/X86/gem5.opt --debug-flags=FaultInjection 
./configs/example/fs.py --cpu-clock=250MHz --caches -r 1 
--script=./configs/boot/dijkstra.py


Global frequency set at 1 ticks per second
warn: DRAM device capacity (8192 Mbytes) does not match the address 
range assigned (512 Mbytes)

Setting Entry Point
info: kernel located at: /home/elena/RTS/gemfi/x86/binaries/vmlinux
Listening for com_1 connection on port 3456
      0: rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
      0: system.fi_system: Initialized FI_System
warn: Reading current count from inactive timer.
 REAL SIMULATION 
513104952: system.fi_system: Starting FI
info: Entering event queue @ 513104952.  Starting simulation...
warn: Don't know what interrupt to clear for console.

On the terminal, all it showed was:
Loading new script…

This is the content of the 2nd script file:
*#!/bin/bash*
*echo ">>"*
*echo "Running Dijkstra benchmark now"*
*/sbin/m5 dumpresetstats [100, 10]*
*./dijkstra_1_FI input_dijkstra10.dat*
*echo "Finishing now"*
*echo ">>"*
*/sbin/m5 exit*

Without running checkpointing, the entire program was able to 
terminate and provide proper result. However, with checkpointing, it 
seems to be stuck at trying to read a new script.
I am not sure if I have missed any steps in between. I followed 
through the discussions about this issue – I didn’t connect my 
terminal during the 1st checkpointing, I view the result by tracing 
the terminal file. I didn’t make any changes to the hack_back_ckpt.rcS 
file. I also tried after loading the checkpoint and leaving the 
—script empty, I brought up the terminal to try and input the script 
file but only Ctrl+C made a difference. Anything other than that 
showed no difference. So, I am not sure where I have gone wrong. 
Appreciate all the help and guidance please.


Thanks.

Regards,
Elena


___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] Reducing main memory size in full-system simulation

[TungHoang_GMail]

It might not be possible to change memory size if you restart from 
checkout. It should be the same size.


/Tung
On 06/28/2018 11:25 AM, Choe, Jiwon wrote:

Yes, I changed the memory size with fs.py --mem-size=256MB.

The full gem5 command line is:
./build/ARM/gem5.opt --stats-file=stats_gem5.txt --outdir=/ 
/--path/=/ --quiet ./configs/example/ethz_fs.py 
--cpu-type=timing --num-cpu=8 --cpu-clock=2GHz 
--script=///do.rcs --caches --l2cache --l1i_size=32kB 
--l1d_size=64kB --l2_size=2MB --mem-type=HMCVault *--mem-size=256MB* 
--mem-channels=8 --cacheline_size=256 --machine-type=VExpress_EMM 
--dtb-filename=///vexpress.aarch32.ll_20131205.0-gem5.8cpu.dtb 
--kernel=///vmlinux.aarch32.ll_20131205.0-gem5 
--disk-image=///linux-aarch32-ael.img


Everything works fine when mem-size is set to 512MB.

The only message that I get is "Killed" from the telnet localhost 3456 
interface. gem5 itself shuts down gracefully with the m5_exit 
instruction.


I don't think that the program is running out of memory, since the 
same thing happens even if I use a really simple hello world program 
as the application, but is there a way to check if the guest program 
ran out of memory?


Thanks,
Jiwon

On Thu, Jun 28, 2018 at 1:39 PM, Ciro Santilli 
mailto:ciro.santi...@gmail.com>> wrote:


How did you change the memory size? fs.py --mem-size? What is your
full gem5 command line?

How does the simulation shuts down? The kernel kills the guest
program? Do you get a message? How did you check that the guest
program simply didn't run out of memory?


On Thu, Jun 28, 2018 at 6:14 PM, Choe, Jiwon mailto:jiwon_c...@brown.edu>> wrote:

I am running a Linux ARM full-system simulation, and I have
been having problems after reducing the main memory size from
512 MB to 256 MB.

After reducing the memory size, the simulation works fine up
to booting the OS. However, when I try to run my application
on the simulated system (via a .rcs file) the simulation shuts
down.

When I change the main memory size, is there something else
that I should be changing other than the parameters to gem5
itself? For instance, should I be changing something in the
Linux dts file?

Thanks,
Jiwon

___
gem5-users mailing list
gem5-users@gem5.org 
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users




___
gem5-users mailing list
gem5-users@gem5.org 
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users





___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] gem5 SE, binary which takes a file as an input

[TungHoang_GMail]

Jasmin

You can use pass "file.txt" via -o | --options of se.py scripts. For 
example ... --cmd ./binary --options file.txt


/T
On 05/30/2018 04:59 AM, Jasmin Jahic wrote:

Dear gem5 users,

I have one challenge with gem5 and I hope you can help.

Running the gem5 in SE is no problem when there is one binary file. 
But how would it be possible for gem5 to run a binary which takes as 
an input a file?


For example, in terminal, I would type:
./binary < file.txt

Best regards,
Jasmin JAHIC


___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] AMD gem5 GPU Compute Model Tutorial at ISCA

[TungHoang_GMail]

Hi Tony,

I knew that AMD has introduced APU + Gem5 as a tutorial of MICRO 2015 (I 
missed change to attend that). Just wondering about the plan to release 
APU as open-source.


/T

On 05/14/2018 08:43 AM, Gutierrez, Anthony wrote:


Hello gem5 Users,

I’d like to announce to you all that we at AMD Research will be 
hosting a tutorial at this year’s ISCA in Los Angeles. The tutorial 
will be half a day and will be held on June 2^nd . The relevant 
details are here:


http://gem5.org/ISCA_2018_Tutorial

If you are interested in learning more about how we model APUs, our SW 
stack, and GPU ISA this is a great way to do so.


We look forward to seeing some of you there.

Thanks,

Tony



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] kernel execution problem armv8 for mode fs_big.LITTLE

[TungHoang_GMail]

Ali,

Did you use aarch64 cross compiler when compiling Parsec. By default, 
Parsec just supports x86 GCC. You will need to modify gcc.bldconf of 
Parsec to make use of aarch64. See ARM pdf file from my link. I do not 
have any problem with parsec. You can eventually try with Hello compiled 
by aarch64 cross compiler first. The last lines in your log tell exact 
problem that m5 could not find either location or compiled binary (with 
cross compiler) in your disk image. Hope it help !


/T
On 05/11/2018 09:54 AM, Hadouda Ali wrote:
i compiled and run parsec 3.0 in my linux operating system after i 
copied parsec in the linaro-minimal-aarch64.img image and i tried in gem5.


2018-05-11 18:44 GMT+02:00 TungHoang_GMail <mailto:hoangthanht...@gmail.com>>:


Ali,

Have you statically compile PARSEC using aarch64-linux-gnu-gcc
cross compiler or qemu-aarch64 before copying into disk-image file ?

See helps in https://github.com/arm-university/arm-gem5-rsk
<https://github.com/arm-university/arm-gem5-rsk>

/Tung

On 05/11/2018 09:40 AM, Hadouda Ali wrote:


hi hoang;

yes I did this step; I have uploaded PARSEC 3.0

 here is the download link:

https://github.com/connorimes/parsec-3.0
<https://github.com/connorimes/parsec-3.0>

and I followed these steps:

*cp linaro-minimal-aarch64.img expanded-linaro-minimal-aarch64.img*
*$ dd if = / dev / zero bs = 1G count = 20 >>
./expanded-linaro-minimal-aarch64.img # add 20G zeros*
*$ sudo parted expanded-linaro-minimal-aarch64.img resizepart 1
100% # grow partition 1*
*Mount the expanded disk image, resize it, and copy PARSEC to it:*
*Note: set /path_to_compiled_parsec-3.0_dir/*
*$ mkdir disk_mnt*
*$ name = $ (sudo fdisk -l expanded-linaro-minimal-aarch64.img |
tail -1 | awk -E: '{print $ 1}' | awk -E "" '{print $ 1}')*
*$ start_sector = $ (sudo fdisk -l
expanded-linaro-minimal-aarch64.img | grep $ name | awk -E ""
'{print $ 2}')*
*$ units = $ (sudo fdisk -l expanded-linaro-minimal-aarch64.img |
grep ^ Units | awk -E "" '{print $ 9}')*
*$ sudo mount -o loop, offset = $ (($ start_sector * $ units))
expanded-linaro-minimal-aarch64.img disk_mnt*
*$ df # find / dev / loopX for disk_mnt*
*$ sudo resize2fs / dev / loopX # resize filesystem*
*$ df # check that the Available space for disk_mnt is increased*
*$ sudo cp -r /path_to_compiled_parsec-3.0_dir/disk_mnt / home /
root # copy the compiled parsec-3.0 to the image*
*$ ls disk_mnt / home / root # check the parsec-3.0 contents*
*$ sudo umount disk_mnt*

with I generate the script of each application (e.g. blacksholes)
as follows:
*#! / Bin / bash*
*
*
*PARSEC_DIR = "/ home / root / parsec-3.0"*
*cd $ PARSEC_DIR*
*pwd*
*
*
*source ./env.sh*
*parsecmgmt -a run -p blackscholes -c gcc-hooks -i simsmall -n 2*
*m5 exit*

and I found the previous result.

so if I forgot something or some step please help me to find the
solution.

thank you very much;

Ali.



___
gem5-users mailing list
gem5-users@gem5.org <mailto:gem5-users@gem5.org>
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
<http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users>






--
Cordialement Ali HADOUDA .



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] kernel execution problem armv8 for mode fs_big.LITTLE

[TungHoang_GMail]

Ali,

Have you statically compile PARSEC using aarch64-linux-gnu-gcc cross 
compiler or qemu-aarch64 before copying into disk-image file ?


See helps in https://github.com/arm-university/arm-gem5-rsk

/Tung
On 05/11/2018 09:40 AM, Hadouda Ali wrote:


hi hoang;

yes I did this step; I have uploaded PARSEC 3.0

 here is the download link:

https://github.com/connorimes/parsec-3.0 



and I followed these steps:

*cp linaro-minimal-aarch64.img expanded-linaro-minimal-aarch64.img*
*$ dd if = / dev / zero bs = 1G count = 20 >> 
./expanded-linaro-minimal-aarch64.img # add 20G zeros*
*$ sudo parted expanded-linaro-minimal-aarch64.img resizepart 1 100% # 
grow partition 1*

*Mount the expanded disk image, resize it, and copy PARSEC to it:*
*Note: set /path_to_compiled_parsec-3.0_dir/*
*$ mkdir disk_mnt*
*$ name = $ (sudo fdisk -l expanded-linaro-minimal-aarch64.img | tail 
-1 | awk -E: '{print $ 1}' | awk -E "" '{print $ 1}')*
*$ start_sector = $ (sudo fdisk -l expanded-linaro-minimal-aarch64.img 
| grep $ name | awk -E "" '{print $ 2}')*
*$ units = $ (sudo fdisk -l expanded-linaro-minimal-aarch64.img | grep 
^ Units | awk -E "" '{print $ 9}')*
*$ sudo mount -o loop, offset = $ (($ start_sector * $ units)) 
expanded-linaro-minimal-aarch64.img disk_mnt*

*$ df # find / dev / loopX for disk_mnt*
*$ sudo resize2fs / dev / loopX # resize filesystem*
*$ df # check that the Available space for disk_mnt is increased*
*$ sudo cp -r /path_to_compiled_parsec-3.0_dir/disk_mnt / home / root 
# copy the compiled parsec-3.0 to the image*

*$ ls disk_mnt / home / root # check the parsec-3.0 contents*
*$ sudo umount disk_mnt*

with I generate the script of each application (e.g. blacksholes) as 
follows:

*#! / Bin / bash*
*
*
*PARSEC_DIR = "/ home / root / parsec-3.0"*
*cd $ PARSEC_DIR*
*pwd*
*
*
*source ./env.sh*
*parsecmgmt -a run -p blackscholes -c gcc-hooks -i simsmall -n 2*
*m5 exit*

and I found the previous result.

so if I forgot something or some step please help me to find the 
solution.


thank you very much;

Ali.



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] kernel execution problem armv8 for mode fs_big.LITTLE

[TungHoang_GMail]

Ali,

You need to provide disk image vi "--disk-image" option. And you also 
need to copy PARSEC (e.g. blacksholes) binary file into disk image file. 
The disk image file will be 
/media/ali/ali/gem5/aarch-system-20180409/disks. I suppose its name is 
"linaro-minimal-aarch64.img". To copy Parsec binary into the image file, 
you can following below steps


1) resize image file
cp linaro-minimal-aarch64.img extended-linaro-minimal-aarch64.img
dd if/dev/zero/ bs=1G count=20 >> extended-linaro-minimal-aarch64.img    
# extended-linaro-minimal-aarch64.img will be 20 GB

sudo parted $expanded_image_file resizepart 1 100%

2) copy parsec binary into extended-linaro-minimal-aarch64.img
mkdir ./mnt
sudo mount -o loop,offset=32256 extended-linaro-minimal-aarch64.img  mnt
sudo mkdir -p ./mnt/home/root
sudo cp -r  ./mnt/home/root
sudo unmount    ./mnt
sudo sync

/T

On 05/11/2018 08:01 AM, Hadouda Ali wrote:

hi all;
I executed the armv8 kernel in big.LITTLE mode, I used the following 
command:


sudo build / ARM / gem5.opt configs / example / arm / fs_bigLITTLE.py 
--kernel = / media / ali / ali / gem5 / aarch-system-20180409 / 
binaries / vmlinux.vexpress_gem5_v1_64 --dtb = / media / ali / ali / 
gem5 / aarch-system-20180409 / binaries / 
armv8_gem5_v1_big_little_2_2.dtb --bootscript = / home / ali / desktop 
/ rcs_file / parsec_rcs / blackscholes_simsmall_2.rcS --caches


here are the execution steps that are in the system.terminal file 
because the execution is stuck without progressing in the last statement.



[    0.00] Booting Linux on physical CPU 0x0
[    0.00] Linux version 4.14.0+ (root@c84b8fb6e283) (gcc version 
5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9)) #1 SMP PREEMPT 
Mon Apr 9 06:54:00 UTC 2018

[    0.00] Boot CPU: AArch64 Processor [410fc0f0]
[    0.00] Machine model: V2P-AARCH64
[    0.00] Memory limited to 2048MB
[    0.00] cma: Reserved 16 MiB at 0xff00
[    0.00] On node 0 totalpages: 524288
[    0.00]   DMA zone: 8192 pages used for memmap
[    0.00]   DMA zone: 0 pages reserved
[    0.00]   DMA zone: 524288 pages, LIFO batch:31
[    0.00] random: fast init done
[    0.00] percpu: Embedded 21 pages/cpu @ffc07ef9b000 s45464 
r8192 d32360 u86016

[    0.00] pcpu-alloc: s45464 r8192 d32360 u86016 alloc=21*4096
[    0.00] pcpu-alloc: [0] 0 [0] 1 [0] 2 [0] 3
[    0.00] Detected PIPT I-cache on CPU0
[    0.00] Built 1 zonelists, mobility grouping on.  Total pages: 
516096
[    0.00] Kernel command line: earlyprintk=pl011,0x1c09 
console=ttyAMA0 lpj=19988480 norandmaps loglevel=8 mem=2GB 
root=/dev/vda1 rw init=/sbin/init vmalloc=768MB

[    0.00] log_buf_len individual max cpu contribution: 4096 bytes
[    0.00] log_buf_len total cpu_extra contributions: 12288 bytes
[    0.00] log_buf_len min size: 16384 bytes
[    0.00] log_buf_len: 32768 bytes
[    0.00] early log buf free: 15016(91%)
[    0.00] PID hash table entries: 4096 (order: 3, 32768 bytes)
[    0.00] Dentry cache hash table entries: 262144 (order: 9, 
2097152 bytes)
[    0.00] Inode-cache hash table entries: 131072 (order: 8, 
1048576 bytes)
[    0.00] Memory: 2035116K/2097152K available (6014K kernel code, 
470K rwdata, 2052K rodata, 384K init, 261K bss, 45652K reserved, 
16384K cma-reserved)

[    0.00] Virtual kernel memory layout:
[    0.00]     modules : 0xff80 - 0xff800800  
 (   128 MB)
[    0.00]     vmalloc : 0xff800800 - 0xffbebfff  
 (   250 GB)
[    0.00]       .text : 0xff800808 - 0xff800866  
 (  6016 KB)
[    0.00]     .rodata : 0xff800866 - 0xff800887  
 (  2112 KB)
[    0.00]       .init : 0xff800887 - 0xff80088d  
 (   384 KB)
[    0.00]       .data : 0xff80088d - 0xff8008945808  
 (   471 KB)
[    0.00]        .bss : 0xff8008945808 - 0xff8008986ed8  
 (   262 KB)
[    0.00]     fixed   : 0xffbefe7fd000 - 0xffbefec0  
 (  4108 KB)
[    0.00]     PCI I/O : 0xffbefee0 - 0xffbeffe0  
 (    16 MB)
[    0.00]     vmemmap : 0xffbf - 0xffc0  
 (     4 GB maximum)
[    0.00]               0xffbf - 0xffbf0200  
 (    32 MB actual)
[    0.00]     memory  : 0xffc0 - 0xffc08000  
 (  2048 MB)

[    0.00] SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=4, Nodes=1
[    0.00] Preemptible hierarchical RCU implementation.
[    0.00] RCU restricting CPUs from NR_CPUS=256 to nr_cpu_ids=4.
[    0.00] Tasks RCU enabled.
[    0.00] RCU: Adjusting geometry for rcu_fanout_leaf=16, 
nr_cpu_ids=4

[    0.00] NR_IRQS: 64, nr_irqs: 64, preallocated irqs: 0
[    0.00] arch_timer: WARNING: Invalid trigger for IRQ4, assuming 
level low

[    0.00] arch_timer: WARNING: Please fix your firmware
[    0.00] arch_timer: cp15 timer(s) running at 

[gem5-users] Not able to build PARSEC for ARM FS simulation

[TungHoang_GMail]

For x264, you need to recompile hooks library with following command

parsecmgmt -a build -c gcc-hooks -p hooks

___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Re: [gem5-users] Question about gem5

[TungHoang_GMail]

You can define number of controller via " --mem-channels-<#>" option of 
se/fs.py script. If you deep dive se/fs.py script then you can see they 
both call configs/common/MemConfig.py class. If you look into config_mem 
method then you can see a number of controller can be configured


#
    mem_ctrls = []
    #
    # The default behaviour is to interleave memory channels on 128
    # byte granularity, or cache line granularity if larger than 128
    # byte. This value is based on the locality seen across a large
    # range of workloads.
    intlv_size = max(128, system.cache_line_size.value)

    # For every range (most systems will only have one), create an
    # array of controllers and set their parameters to match their
    # address mapping in the case of a DRAM
    for r in system.mem_ranges:
    for i in xrange(nbr_mem_ctrls):
    mem_ctrl = create_mem_ctrl(cls, r, i, nbr_mem_ctrls, 
intlv_bits,

   intlv_size)
    # Set the number of ranks based on the command-line
    # options if it was explicitly set
    if issubclass(cls, m5.objects.DRAMCtrl) and opt_mem_ranks:
    mem_ctrl.ranks_per_channel = opt_mem_ranks

    if opt_elastic_trace_en:
    mem_ctrl.latency = '1ns'
    print "For elastic trace, over-riding Simple Memory " \
    "latency to 1ns."

    mem_ctrls.append(mem_ctrl)

    #== register all memcontroller to subsystem
    subsystem.mem_ctrls = mem_ctrls

/T
On 03/01/2018 04:14 AM, 김성규 wrote:


Hello.

I'm using gem5, and I want to make a system configuration with one 
CPU, and 2 memory (controller) objects connected to master port of 
memory bus.


(Attached figure may be help)

I could not find how to attach additional memory and assign address to it.

If it is not an excuse, could you let me know an example code closest 
to above configuration?


Thank you.​



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users



___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users