[gem5-users] Extract data accessed by DRAM

2018-05-26 Thread Riddhi Thakker
Hi all,

I want to extract data from DRAM. I tried to do that by using PacketDataPtr
and PacketPtr but I didn't get any desired result. I implemented my code in
accessAndRespond function after it calls access() of AbstractMemory class.
But when I try to directly access the data at the address using a pointer,
it gives me segmentation fault.

If anyone has any suggestions then it would be really helpful.

Thanks in advance.

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

[gem5-users] Segmentation Fault in PARSEC Benchmark

2018-06-12 Thread Riddhi Thakker
Hi,

I am running PARSEC benchmark on X86 system. It is running fine without
checkpoints. But if I am using checkpoints, then after restoring checkpoint
I am getting segmentation fault in PARSEC benchmark. I have used
configs/boot/hack_back_ckpt.rcS to create checkpoint (cputype=timing).
After I restored checkpoint (restore-cpu-type=O3), it ran PARSEC benchmark
using the following script:

#!/bin/sh

# File to run the blackscholes benchmark

echo "Running blackscholes"

cd /parsec/install/bin

/sbin/m5 dumpstats

/sbin/m5 resetstats

./blackscholes 64 /parsec/install/inputs/blackscholes/in_4K.txt
/parsec/install/inputs/blackscholes/prices.txt

echo "Done :D"

/sbin/m5 exit

/sbin/m5 exit

This gives following output:
 m5 slave terminal: Terminal 0 
Loading new script...
usage: /sbin/m5 exit [delay]
   /sbin/m5 resetstats [delay [period]]
   /sbin/m5 dumpstats [delay [period]]
   /sbin/m5 dumpresetstats [delay [period]]
   /sbin/m5 readfile [filename]
   /sbin/m5 execfile 
   /sbin/m5 checkpoint [delay [period]]
   /sbin/m5 loadsymbol  
   /sbin/m5 initparam
   /sbin/m5 sw99param
   /sbin/m5 pin   [args ...]

All times in nanoseconds!
PARSEC Benchmark Suite Version 2.1
[HOOKS] PARSEC Hooks Version 1.2
Num of Options: 4096
Num of Runs: 100
Size of data: 163840
[HOOKS] Entering ROI
blackscholes[796]: segfault at fc973680 rip 004048bc rsp
2ae564f3bbf8 error 4
Segmentation fault
Done :D

Cmdline to restore: ./build/X86/gem5.opt configs/example/fs.py
--mem-type=DDR4_2400_8x8
--kernel=./x86parsec/binaries/x86_64-vmlinux-2.6.22.9.smp
--disk-image=../x86root-parsec.img --checkpoint-restore=1
--restore-with-cpu=DerivO3CPU
--script=./scripts/blackscholes_64c_simsmall.rcS

The disk image from
http://www.cs.utexas.edu/~parsec_m5/x86root-parsec.img.bz2. I tried to
search this error on the gem5 mail archive, but I couldn't find any
solution from there.

It would be great if anyone can help me sort out this problem. Thanks in
advance.

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

[gem5-users] To get data trace from add and sub instructions

2018-06-16 Thread Riddhi Thakker
Hi all,

I am trying to get data trace from addition and subtraction instructions on
x86. For this I located the place where add and sub instructions are
evaluated i.e. src/arch/x86/isa/microops/mediaop.isa. In this file at line
915, a class Maddi is defined which adds integer values. Then in
src/arch/x86/isa/insts/simd64/integer/arithmetic/addition.py file, maddi is
called. So I am confused whether the maadi in latter file calls Maddi class
in prior file or not ?
I want to know this because when I run benchmark I am getting data trace
for subtraction and not for addition. Whereas, addition should take place.
Then why am I not getting data trace for addition? And this is also the
same scenario for integer multiplication.

Am I going on the right track?

Any suggestions will be helpful to me.

Thanks in advance.

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

[gem5-users] Functional Models for ALU

2018-06-19 Thread Riddhi Thakker
Hi all,

I am looking for the functional units of the ALU for X86 system. I noticed
that there is a class IntAlu, IntMult, IntDiv, and so on (in file
src/cpu/o3/FuncUnitConfig.py). But I could not figure out where the add
instruction for ALU, and other sub, mul instructions are defined.

Can anyone please help me how should I proceed further.

Thanks in advance.

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

[gem5-users] Couldn't read data from debugger

2018-06-25 Thread Riddhi Thakker
Hi all,

I am running parsec and splash benchmarks on gem5. Until yesterday, it was
all going fine, but today when I kept 5 benchmarks to run simultaneously on
different copies of gem5, i am getting following error for all the runs:

...
5158682205750: system.remote_gdb: remote gdb attached
warn: Couldn't read data from debugger.
5158944267500: system.remote_gdb: remote gdb detached
...

The another terminal is showing nothing. I checked the
system.pc.com_1.terminal file after terminating the process, it looks fine
to me. I am unable to track the problem.

It would be great if anyone can help me out with this :)

Thanks in advance.

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

Re: [gem5-users] Couldn't read data from debugger

2018-06-25 Thread Riddhi Thakker
Hi,

I am running gem5 on X86  CentOS 6.9 system. I am using latest gem5
version.
Command line: ./build/X86/gem5.opt configs/example/fs.py
--mem-type=DDR3_1600_8x8 --cpu-type=DerivO3CPU --caches
--l2cache   --cacheline_size=64 --l1d_size=64kB --l1d_assoc=4
--l1i_size=32kB --l1i_assoc=4 --l2_size=2MB
--l2_assoc=8 
--kernel=/home/riddhi/gem5_cg_is_copy/x86parsec/binaries/x86_64-vmlinux-2.6.22.9.smp
--disk-image=/home/riddhi/gem5_cg_is_copy/x86parsec/disks/x86root-parsec.img
--script=/home/riddhi/gem5_cg_is_copy/scripts/streamcluster_64c_simlarge.rcS
-F 2

Likewise, other 4 benchmarks are running: ferret, fluidanimate, bodytrack,
x264
After running all the benchmarks simultaneously on ports 7000, 7001, 7002,
7003, 7004, when I open another terminal and go to that gem5 directory
suppose (on gem5_1 directory, ferret benchmark is running) and type
./util/term/m5term localhost 7000
Nothing is printed on this terminal, same is the case with other ports also.

For running 5 benchmarks at the same time, I have made different copies of
gem5 (eg: gem5_1, gem5_2, etc.) and then in each copy I am running 1
benchmark.

Why would this happen when I am running different programs on different
copies of gem5?

Regards,
Riddhi

On Mon, Jun 25, 2018 at 1:38 PM, Riddhi Thakker 
wrote:

> Hi all,
>
> I am running parsec and splash benchmarks on gem5. Until yesterday, it was
> all going fine, but today when I kept 5 benchmarks to run simultaneously on
> different copies of gem5, i am getting following error for all the runs:
>
> ...
> 5158682205750: system.remote_gdb: remote gdb attached
> warn: Couldn't read data from debugger.
> 5158944267500: system.remote_gdb: remote gdb detached
> ...
>
> The another terminal is showing nothing. I checked the
> system.pc.com_1.terminal file after terminating the process, it looks fine
> to me. I am unable to track the problem.
>
> It would be great if anyone can help me out with this :)
>
> Thanks in advance.
>
> Regards,
> Riddhi
>
___
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

[gem5-users] Doubts in packet and request

2018-11-09 Thread Riddhi Thakker
Hello all,

I have observed that when I run benchmarks, the size of the packet is
always 64 bytes. Where as if I run small SE programs the sizes turns out to
be different. If I call an instruction of 'int' size, it will not call the
packet of size 64 bytes, it should be lesser.
Following are my questions:
1) Why every time the packet size is 64 when I run a benchmark ?
2) The packet which is created refer to only one instruction (i.e. one
request) or multiple ?
3)  If packet refers to only one instruction or request then how come for
all the kind of instructions is the packet size same ?
4) If a packet refers to different instructions or requests then how do I
infer how much data bytes do each instruction wants?
5) When I am trying to explicitly use the getReqInstSeqNum() function, then
why it gives me assertion failed error for VALID_INST_SEQ_NUM ?

I really want to get answers for these questions. It will be a great help
to me if anyone can get through this.

Thanks in advance.

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