Also, this is what you'd do to modify the everything except the kernel. The kernel is loaded on its own and not from the disk image.
Gabe On 11/16/11 05:13, Surya Narayanan wrote: > http://gem5.org/Disk_images > > i hope this explains it. > > ----- Original Message ----- >> From: [email protected] >> To: [email protected] >> Sent: Wednesday, November 16, 2011 7:29:04 AM >> Subject: gem5-users Digest, Vol 64, Issue 34 >> Send gem5-users mailing list submissions to >> [email protected] >> >> To subscribe or unsubscribe via the World Wide Web, visit >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> or, via email, send a message with subject or body 'help' to >> [email protected] >> >> You can reach the person managing the list at >> [email protected] >> >> When replying, please edit your Subject line so it is more specific >> than "Re: Contents of gem5-users digest..." >> >> >> Today's Topics: >> >> 1. Re: 4x4 mesh network in ALPHA_FS detect a deadlock? (yanke) >> 2. Re: Problem with alpha full system + ruby (Nilay Vaish) >> 3. Re: 4x4 mesh network in ALPHA_FS detect a deadlock? (Nilay Vaish) >> 4. Re: Problem with alpha full system + ruby (Prashant) >> 5. How to solve "NameError: name 'RubyCache' is not defined" >> Error ? (Prashant) >> 6. Re: The effect of Prefetcher on Stats.out (Mahmood Naderan) >> (Hasina Khatoon) >> 7. Re: Effect of Operating System policies -FS or SE mode? >> (Gabriel Michael Black) (Hasina Khatoon) >> 8. Re: The effect of Prefetcher on Stats.out (Mahmood Naderan) >> (biswabandan panda) >> >> >> ---------------------------------------------------------------------- >> >> Message: 1 >> Date: Wed, 16 Nov 2011 11:01:09 +0800 (CST) >> From: yanke <[email protected]> >> To: "[email protected]" <[email protected]> >> Subject: Re: [gem5-users] 4x4 mesh network in ALPHA_FS detect a >> deadlock? >> Message-ID: <[email protected]> >> Content-Type: text/plain; charset="gbk" >> >> Hi, Dose this problem be solved? >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> <http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20111116/ced840cb/attachment-0001.html> >> >> ------------------------------ >> >> Message: 2 >> Date: Tue, 15 Nov 2011 21:58:28 -0600 (CST) >> From: Nilay Vaish <[email protected]> >> To: gem5 users mailing list <[email protected]> >> Subject: Re: [gem5-users] Problem with alpha full system + ruby >> Message-ID: <[email protected]> >> Content-Type: text/plain; charset="utf-8"; Format="flowed" >> >> You can use gem5.fast instead of using gem5.debug. gem5.debug includes >> all >> the debugging info, hence is slow. gem5.fast is compiled with -O3, so >> it >> is highly optimized and will execute much faster compared to the debug >> version. >> >> -- >> Nilay >> >> >> On Wed, 16 Nov 2011, yanke wrote: >> >>> yanke <ykyanke <at> 126.com> writes: >>> >>> Hello,??????? I try to use gem5 in alpha full system + ruby,? the >>> stable >> version have been successfully compiled. But when I run it using the >> command >> :./build/ALPHA_FS/gem5.debug configs/example/ruby_fs.py -n 16 >>> --l1i_size=8kB --l1d_size=8kB --l2_size=128kB --num-l2caches=16 >>> --topology=Mesh --timing --num-dirs=16 --mesh-rows=4?????? I get the >>> following >> output:Error: could not create sytem for ruby protocol >> MI_exampleTraceback >>> (most recent call last):? File "<string>", line 1, in ?? >>> File >>> "/home/yanke/sde/parsec/gem5-stable-b9ba22cb23f2/src/python/m5/main.py", >>> line 356, in main??? exec filecode in scope? File >>> "configs/example/ruby_fs.py", line 123, in ???? >>> system._dma_devices)? >>> File >>> "/home/yanke/sde/parsec/gem5-stable-b9ba22cb23f2/configs/ruby/Ruby.py", >>> line 68, in create_system??? (cpu_sequencers, dir_cntrls, >>> all_cntrls) = \? File "<string>", line 0, in ?? File >>> "/home/yanke/sde/parsec/gem5-stable-b9ba22cb23f2/configs/ruby/MI_example.py", >>> line 151, in create_system??? system.dma_cntrl.dma_sequencer.port = >>> dma_device.dma? File >>> "/home/yanke/sde/parsec/gem5-stable-b9ba22cb23f2/src/python/m5/SimObject.py", >>> line 603, in __getattr__??? raise AttributeError, "object '%s' has >>> no attribute '%s'" \AttributeError: object 'LinuxAlphaSystem' has no >>> attribute 'dma_cntrl'while the development version can run >>> successfully but >> only boots 4 cores, and stop there for ever:==== m5 slave terminal: >> Terminal 0 >> ====M5 console: m5AlphaAccess <at> 0xFFFFFD0200000000Got Configuration >> 623memsize 8000000 pages 4000 First free page after ROM >> 0xFFFFFC0000018000HWRPB >> 0xFFFFFC0000018000 l1pt 0xFFFFFC0000040000 l2pt 0xFFFFFC0000042000 >> l3pt_rpb >> 0xFFFFFC0000044000 l3pt_kernel 0xFFFFFC0000048000 l2reserv >> 0xFFFFFC0000046000kstart = 0xFFFFFC0000310000, kend = >> 0xFFFFFC0000855898, kentry >> = 0xFFFFFC0000310000, numCPUs = 0x10CPU Clock at 2000 MHz >> IntrClockFrequency=1024 Booting with 16 processor(s) KSP: 0x20043FE8 >> PTBR >> 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTB >>> R 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR 0x20KSP: >>> 0x20043FE8 PTBR >> 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 >> PTBR >> 0x20KSP: 0 >>> x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR >>> 0x20KSP: >> 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR 0x20KSP: 0x20043FE8 PTBR >> 0x20KSP: >> 0x20043FE8 PTBR 0x20Console Callback at 0x0, fixup at 0x0, crb offset: >> 0x2A90Memory cluster 0 [0 - 392]Memory cluster 1 [392 - >> 15992]Initalizing >> mdt_bitmap addr 0xFFFFFC0000038000 mem_pages 4000 ConsoleDispatch at >> virt >> 10002BD8 phys 1ABD8 val FFFFFC00000100A8Bootstraping CPU 1 with >> sp=0xFFFFFC0000076000Bootstraping CPU 2 with >> sp=0xFFFFFC0000078000Bootstraping >> CPU 3 with sp=0xFFFFFC000007A000Bootstraping CPU 4 with >> sp=0xFFFFFC000007C000Is >> there anyone know the problem?? >>> >>> >>> _______________________________________________ >>> gem5-users mailing list >>> gem5-users <at> gem5.org >>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> >> While when I set the core to 4, it can boot up successfully, but very >> very >> slowly.Dose anyone else have the same problem? >> >> >> >> >> _______________________________________________ >> gem5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> >> ------------------------------ >> >> Message: 3 >> Date: Tue, 15 Nov 2011 22:03:06 -0600 (CST) >> From: Nilay Vaish <[email protected]> >> To: gem5 users mailing list <[email protected]> >> Subject: Re: [gem5-users] 4x4 mesh network in ALPHA_FS detect a >> deadlock? >> Message-ID: <[email protected]> >> Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed >> >> On Wed, 16 Nov 2011, yanke wrote: >> >>> Hi, Dose this problem be solved? >>> >> I think the protocol being used is MI_example, which does not support >> atomic operations. I would suggest using a different protocol while >> running in FS mode. >> >> -- >> Nilay >> >> >> ------------------------------ >> >> Message: 4 >> Date: Wed, 16 Nov 2011 10:52:31 +0530 >> From: Prashant <[email protected]> >> To: gem5 users mailing list <[email protected]> >> Subject: Re: [gem5-users] Problem with alpha full system + ruby >> Message-ID: >> <cappof-so0qi6+oi6yooyxy-0gxvar_vb5bk9ccm9sabfkqp...@mail.gmail.com> >> Content-Type: text/plain; charset="iso-8859-1" >> >> I am getting following error: >> >> >> num-l2caches=4 >> gem5 Simulator System. http://gem5.org >> gem5 is copyrighted software; use the --copyright option for details. >> >> gem5 compiled Nov 15 2011 12:34:35 >> gem5 started Nov 16 2011 10:47:47 >> gem5 executing on nitin-desktop >> command line: build/ALPHA_FS/gem5.opt configs/example/ruby_fs.py -n 4 >> --l1i_size=8kB --l1d_size=8kB --l2_size=128kB --num-l2caches=4 >> Traceback (most recent call last): >> File "<string>", line 1, in <module> >> File >> "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/src/python/m5/main.py", >> line 356, in main >> exec filecode in scope >> File "configs/example/ruby_fs.py", line 78, in <module> >> Ruby.define_options(parser) >> File "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/configs/ruby/Ruby.py", >> line 60, in define_options >> exec "import %s" % protocol >> File "<string>", line 1, in <module> >> File >> "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/configs/ruby/MESI_CMP_directory.py", >> line 38, in <module> >> class L1Cache(RubyCache): >> NameError: name 'RubyCache' is not defined >> >> >> >> Can anybody help me out with this ? >> >> Thanks, >> Prashant >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> <http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20111116/578f8c0b/attachment-0001.html> >> >> ------------------------------ >> >> Message: 5 >> Date: Wed, 16 Nov 2011 11:00:10 +0530 >> From: Prashant <[email protected]> >> To: [email protected] >> Subject: [gem5-users] How to solve "NameError: name 'RubyCache' is not >> defined" Error ? >> Message-ID: >> <cappof-s0gkrscqzwt0sqdq0jk_4zjkqwjj9yayk096dk5ye...@mail.gmail.com> >> Content-Type: text/plain; charset="iso-8859-1" >> >> I am getting following error while running Ruby in FS mode ... any >> kind of >> help will be appreciated ... >> >> nitin@nitin-desktop:~/GEM5/gem5-stable-b9ba22cb23f2$build/ALPHA_FS/gem5.opt >> configs/example/ruby_fs.py >> gem5 Simulator System. http://gem5.org >> gem5 is copyrighted software; use the --copyright option for details. >> >> gem5 compiled Nov 15 2011 12:34:35 >> gem5 started Nov 16 2011 10:57:00 >> gem5 executing on nitin-desktop >> command line: build/ALPHA_FS/gem5.opt configs/example/ruby_fs.py >> Traceback (most recent call last): >> File "<string>", line 1, in <module> >> File >> "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/src/python/m5/main.py", >> line 356, in main >> exec filecode in scope >> File "configs/example/ruby_fs.py", line 78, in <module> >> Ruby.define_options(parser) >> File "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/configs/ruby/Ruby.py", >> line 60, in define_options >> exec "import %s" % protocol >> File "<string>", line 1, in <module> >> File >> "/home/nitin/GEM5/gem5-stable-b9ba22cb23f2/configs/ruby/MESI_CMP_directory.py", >> line 38, in <module> >> class L1Cache(RubyCache): >> NameError: name 'RubyCache' is not defined >> >> >> >> Thanks, >> Prashant >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> <http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20111116/95df14ef/attachment-0001.html> >> >> ------------------------------ >> >> Message: 6 >> Date: Wed, 16 Nov 2011 11:21:58 +0500 >> From: Hasina Khatoon <[email protected]> >> To: [email protected] >> Subject: Re: [gem5-users] The effect of Prefetcher on Stats.out >> (Mahmood Naderan) >> Message-ID: >> <CAGfJSkt2xi+EV_UHqz+j8KCGb4467HpmtsKQ2=nxjqnzpmu...@mail.gmail.com> >> Content-Type: text/plain; charset=ISO-8859-1 >> >> Can anyone explain why this is so? In fact, I have analyzed the entire >> stats.out file and I found no difference in any of the other data >> items. I have a feeling that the prefetcher is either not prefetching >> as expected ( please note the message we get at the start of the >> simulation 'Prefetchers .... do not do anything' ) or is not being >> searched before accessing the second-level cache. >> >> Can anyone please explain? >> >> Thanks in advance >> >> Hasina Khatoon >> >> -- >> Department of Computer Science >> National University of Computer and Emerging Sciences (FAST-NU) >> Karachi Campus (Main) >> >> >> ------------------------------ >> >> Message: 7 >> Date: Wed, 16 Nov 2011 11:27:01 +0500 >> From: Hasina Khatoon <[email protected]> >> To: [email protected] >> Subject: Re: [gem5-users] Effect of Operating System policies -FS or >> SE mode? (Gabriel Michael Black) >> Message-ID: >> <cagfjskux-kng7_w_rchvpusp1jzezekiojq2o81qhsw_x-r...@mail.gmail.com> >> Content-Type: text/plain; charset=ISO-8859-1 >> >> Does that mean that if I change the operating system code, I need to >> compile and re-install as the new disk image at the system directory >> of gem5? This seems to be the only way the gem5 OS can be modified. >> >> If the above is true, is there any documentation available that >> explains how to create disk image? >> >> Hasina Khatoon >> >> >> >> -- >> Department of Computer Science >> National University of Computer and Emerging Sciences (FAST-NU) >> Karachi Campus (Main) >> >> >> ------------------------------ >> >> Message: 8 >> Date: Wed, 16 Nov 2011 11:59:18 +0530 >> From: biswabandan panda <[email protected]> >> To: gem5 users mailing list <[email protected]> >> Subject: Re: [gem5-users] The effect of Prefetcher on Stats.out >> (Mahmood Naderan) >> Message-ID: >> <cadfulaunhjhukncpahg+82a+zrvsshxl-bghupvhrz9v73c...@mail.gmail.com> >> Content-Type: text/plain; charset="iso-8859-1" >> >> I am getting the stats for prefetching in FS mode also. >> >> On Wed, Nov 16, 2011 at 11:51 AM, Hasina Khatoon >> <[email protected]>wrote: >> >>> Can anyone explain why this is so? In fact, I have analyzed the >>> entire >>> stats.out file and I found no difference in any of the other data >>> items. I have a feeling that the prefetcher is either not >>> prefetching >>> as expected ( please note the message we get at the start of the >>> simulation 'Prefetchers .... do not do anything' ) or is not being >>> searched before accessing the second-level cache. >>> >>> Can anyone please explain? >>> >>> Thanks in advance >>> >>> Hasina Khatoon >>> >>> -- >>> Department of Computer Science >>> National University of Computer and Emerging Sciences (FAST-NU) >>> Karachi Campus (Main) >>> _______________________________________________ >>> gem5-users mailing list >>> [email protected] >>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >>> >> >> >> -- >> >> *thanks®ards >> * >> *BISWABANDAN* >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: >> <http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20111116/1775074b/attachment.html> >> >> ------------------------------ >> >> _______________________________________________ >> gem5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> >> End of gem5-users Digest, Vol 64, Issue 34 >> ****************************************** _______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
