Henry,
Thanks for your reply. The error is indeed caused by unimplemented syscall set_tid_address. But how can I solve the problem except implementing the syscall by myself ? Thanks! Best regards! Fei Xia 发件人: [email protected] [mailto:[email protected]] 代 表 Huang, Henry 发送时间: 2013年7月11日 17:45 收件人: gem5 users mailing list 主题: Re: [gem5-users] syscall set_tid_address (#411) unimplemented Xia Fei, You program binary contains syscall that is unimplemented in gem5. See arch/alpha/linux/process.cc, /* 411 */ SyscallDesc("set_tid_address", unimplementedFunc), ---- ' Huang He (Henry) /-\\ CPU Design and Verification /---\'\ Advanced Micro Devices, Inc /-----\'`\ AMD Technology Development (Beijing) Co., Ltd. /-------\'`,\ Beijing, China /---------\' ,`7 O: +(86) 10 62801421 M: +(86) 18616862712 /-----------\' / /-------------\/ cid:[email protected] Visit us at: <https://www.facebook.com/AMD> Facebook | <http://www.amd.com/> amd.com From: [email protected] [mailto:[email protected]] On Behalf Of 夏飞 Sent: Thursday, July 11, 2013 5:35 PM To: [email protected] Subject: [gem5-users] syscall set_tid_address (#411) unimplemented Hi all: I am trying to run PARSEC in the ALPHA_SE mode using the latest version of Gem5, but I got the following error: **** REAL SIMULATION **** info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. fatal: syscall set_tid_address (#411) unimplemented. @ cycle 337500 [unimplementedFunc:build/ALPHA/sim/syscall_emul.cc, line 83] Memory Usage: 741768 KBytes The command that I used is: ./build/ALPHA/gem5.opt configs/example/se.py -c ../parsec-2.1/pkgs/apps/bodytrack/inst/amd64-linux. alpha-gcc-hooks/bin/bodytrack Whether the error exists in FS mode ? Can anybody help me？ Thanks very much！ Best regards! Fei Xia
<<image001.jpg>>
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
