Hi, The implementation of LL/SC is buggy and wrongly in gem5. Some protocols are buggy too. This may be the cause of your problem. Can you guys try to run SPEC to see if it runs?
On Tue, Mar 15, 2016 at 4:53 PM, Marcelo Melo Linck < [email protected]> wrote: > Hi Hao Zheng, > > I got it working for 2 cpus through the following command: > > ./build/ALPHA_MOESI_CMP_directory/gem5.opt --remote-gdb-port=0 > configs/example/fs.py --cpu-type=timing > --script=run_scripts/blackscholes_2c_simsmall.rcS --num-cpus=2 --ruby > --mesh-rows=2 --garnet-network=fixed --topology=Mesh --caches --l2cache > --l2_size=512kB --num-dirs=4 --num-l2caches=4 --l1d_size=32kB > --l1i_size=32kB --l1d_assoc=2 --l1i_assoc=2 > --disk=linux-parsec-2-1-m5-with-test-inputs.img -s 1000000 > > I tried for 4 cpus and my system got stuck in the point showed below. I > don't really know why, but this happens to every ruby structure with more > than 2 cpus that I try to create. I hope I have helped you, and I wish that > you could help me by maybe having a clue on how to fix this. > > ==== m5 slave terminal: Terminal 0 ==== > M5 console: m5AlphaAccess @ 0xFFFFFD0200000000 > Got Configuration 623 > memsize 20000000 pages 10000 > First free page after ROM 0xFFFFFC0000018000 > HWRPB 0xFFFFFC0000018000 l1pt 0xFFFFFC0000040000 l2pt 0xFFFFFC0000042000 > l3pt_rpb 0xFFFFFC0000044000 l3pt_kernel 0xFFFFFC0000048000 l2reserv > 0xFFFFFC0000046000 > kstart = 0xFFFFFC0000310000, kend = 0xFFFFFC0000855898, kentry = > 0xFFFFFC0000310000, numCPUs = 0x4 > CPU Clock at 2000 MHz IntrClockFrequency=1024 > Booting with 4 processor(s) > KSP: 0x20043FE8 PTBR 0x20 > KSP: 0x20043FE8 PTBR 0x20 > KSP: 0x20043FE8 PTBR 0x20 > KSP: 0x20043FE8 PTBR 0x20 > Console Callback at 0x0, fixup at 0x0, crb offset: 0xC90 > Memory cluster 0 [0 - 392] > Memory cluster 1 [392 - 65144] > Initalizing mdt_bitmap addr 0xFFFFFC0000038000 mem_pages 10000 > ConsoleDispatch at virt 10000DD8 phys 18DD8 val FFFFFC00000100A8 > Bootstraping CPU 1 with sp=0xFFFFFC0000076000 > Bootstraping CPU 2 with sp=0xFFFFFC0000078000 > Bootstraping CPU 3 with sp=0xFFFFFC000007A000 > unix_boot_mem ends at FFFFFC000007C000 > k_argc = 0 > jumping to kernel at 0xFFFFFC0000310000, (PCBB 0xFFFFFC0000018180 pfn 1067) > > Thanks. > > 2016-03-14 17:41 GMT-03:00 Hao Zheng <[email protected]>: > >> Dear All, >> >> I used the per-compiled linux-parsec kernel in the Gem5, and When I ran >> the command in the full system, the system was always stuck at >> ........ >> Console: colour dummy device 80x25 >> console [ttyS0] enabled >> Dentry cache hash table entries: 65536 (order: 6, 524288 bytes) >> Inode-cache hash table entries: 32768 (order: 5, 262144 bytes) >> Memory: 509800k/524288k available (3757k kernel code, 10704k reserved, >> 261k data, 208k init) >> Mount-cache hash table entries: 512 >> SMP starting up secondaries. >> >> My command: ./build/ALPHA/gem5.opt configs/example/fs.py >> --cpu-type=timing --script=run_scripts/blackscholes_ >> 4 >> c_simsmall.rcS --num-cpus=4 --ruby --mesh-rows=2 --garnet-network=fixed >> --topology=Mesh --caches --l2cache --l2_size=512kB --num-dirs=4 >> --num-l2caches=4 --l1d_size=32kB --l1i_size=32kB --l1d_assoc=2 --l1i_assoc=2 >> >> When I just ran the command without ruby, it worked perfectly. >> >> >> Hao Zheng >> School of Engineering & Applied Science >> 512-865-7217 >> [email protected] >> >> _______________________________________________ >> gem5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> > > > > -- > *Marcelo Melo Linck* > *Computer Engineer and MSc Student @ GSE-PUCRS* > *Phone: (51) 8333-8228* > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
