GPU FS Multiple CPU
Hi all,
I'm trying to run GPU FS with 4 CPU. That's because I want to replicate a
real APU device that has 4 x86 CPUs with 2 threads each.
When running it in FS along with a Vega10 GPU I'm facing the following
error:
M5 Terminal Output:
[ 0.332000] smpboot: CPU0: AMD Fake gem5 x86_64 CPU (family: 0xf,
model: 0x25, stepping: 0x1)[ 0.336000] Performance Events: Broken PMU
hardware detected, using software events only.[ 0.340000] Failed to
access perfctr msr (MSR c0010007 is 0)[ 0.344000] rcu: Hierarchical SRCU
implementation.[ 0.348000] NMI watchdog: Perf NMI watchdog permanently
disabled[ 0.352000] smp: Bringing up secondary CPUs ...[ 0.356000]
x86: Booting SMP configuration:
Simulation Output:
src/cpu/kvm/base.cc:1109: panic: KVM: Failed to enter virtualized mode (hw
reason: 0x80000021)Memory Usage: 28921692 KBytesProgram aborted at tick
1951958177000--- BEGIN LIBC BACKTRACE
---gem5/build/VEGA_X86/gem5.opt(_ZN4gem515print_backtraceEv+0x30)[0x60b9fa48cea0]gem5/build/VEGA_X86/gem5.opt(_ZN4gem512abortHandlerEi+0x4c)[0x60b9fa4b2d3c]/lib/x86_64-linux-gnu/libc.so.6(+0x42520)[0x7bfede642520]/lib/x86_64-linux-gnu/libc.so.6(pthread_kill+0x12c)[0x7bfede6969fc]/lib/x86_64-linux-gnu/libc.so.6(raise+0x16)[0x7bfede642476]/lib/x86_64-linux-gnu/libc.so.6(abort+0xd3)[0x7bfede6287f3]gem5/build/VEGA_X86/gem5.opt(+0xd67ec5)[0x60b9f9363ec5]gem5/build/VEGA_X86/gem5.opt(+0xf31d05)[0x60b9f952dd05]gem5/build/VEGA_X86/gem5.opt(_ZN4gem510BaseKvmCPU4tickEv+0x99)[0x60b9f952f609]gem5/build/VEGA_X86/gem5.opt(_ZN4gem510EventQueue10serviceOneEv+0xc2)[0x60b9fa4a3042]gem5/build/VEGA_X86/gem5.opt(_ZN4gem59doSimLoopEPNS_10EventQueueE+0x68)[0x60b9fa4cc458]gem5/build/VEGA_X86/gem5.opt(_ZNSt6thread11_State_implINS_8_InvokerISt5tupleIJZN4gem516SimulatorThreads17runUntilLocalExitEvEUlPNS3_10EventQueueEE_S6_EEEEE6_M_runEv+0x9f)[0x60b9fa4cd6df]/lib/x86_64-linux-gnu/libstdc++.so.6(+0xdc253)[0x7bfedeadc253]/lib/x86_64-linux-gnu/libc.so.6(+0x94ac3)[0x7bfede694ac3]/lib/x86_64-linux-gnu/libc.so.6(+0x126850)[0x7bfede726850]---
END LIBC BACKTRACE ---For more info on how to address this issue, please
visit https://www.gem5.org/documentation/general_docs/common-errors/
https://www.gem5.org/documentation/general_docs/common-errors/ Aborted
Any clue in how to proceed?
Thank you!
Best Regards,
Pau
[Public]
Hi Pau,
From: Pau Galindo Figuerola via gem5-users gem5-users@gem5.org
Sent: Friday, March 22, 2024 10:47 AM
To: The gem5 Users mailing list gem5-users@gem5.org
Cc: Pau Galindo Figuerola pau.galindo.figuerola@estudiantat.upc.edu
Subject: [gem5-users] GPU FS Multiple CPU
Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.
Hi all,
I'm trying to run GPU FS with 4 CPU. That's because I want to replicate a real APU device that has 4 x86 CPUs with 2 threads each.
When running it in FS along with a Vega10 GPU I'm facing the following error:
M5 Terminal Output:
[ 0.332000] smpboot: CPU0: AMD Fake gem5 x86_64 CPU (family: 0xf, model: 0x25, stepping: 0x1)
[ 0.336000] Performance Events: Broken PMU hardware detected, using software events only.
[ 0.340000] Failed to access perfctr msr (MSR c0010007 is 0)
[ 0.344000] rcu: Hierarchical SRCU implementation.
[ 0.348000] NMI watchdog: Perf NMI watchdog permanently disabled
[ 0.352000] smp: Bringing up secondary CPUs ...
[ 0.356000] x86: Booting SMP configuration:
Simulation Output:
src/cpu/kvm/base.cc:1109: panic: KVM: Failed to enter virtualized mode (hw reason: 0x80000021)
Memory Usage: 28921692 KBytes
Program aborted at tick 1951958177000
--- BEGIN LIBC BACKTRACE ---
gem5/build/VEGA_X86/gem5.opt(_ZN4gem515print_backtraceEv+0x30)[0x60b9fa48cea0]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem512abortHandlerEi+0x4c)[0x60b9fa4b2d3c]
/lib/x86_64-linux-gnu/libc.so.6(+0x42520)[0x7bfede642520]
/lib/x86_64-linux-gnu/libc.so.6(pthread_kill+0x12c)[0x7bfede6969fc]
/lib/x86_64-linux-gnu/libc.so.6(raise+0x16)[0x7bfede642476]
/lib/x86_64-linux-gnu/libc.so.6(abort+0xd3)[0x7bfede6287f3]
gem5/build/VEGA_X86/gem5.opt(+0xd67ec5)[0x60b9f9363ec5]
gem5/build/VEGA_X86/gem5.opt(+0xf31d05)[0x60b9f952dd05]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem510BaseKvmCPU4tickEv+0x99)[0x60b9f952f609]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem510EventQueue10serviceOneEv+0xc2)[0x60b9fa4a3042]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem59doSimLoopEPNS_10EventQueueE+0x68)[0x60b9fa4cc458]
gem5/build/VEGA_X86/gem5.opt(_ZNSt6thread11_State_implINS_8_InvokerISt5tupleIJZN4gem516SimulatorThreads17runUntilLocalExitEvEUlPNS3_10EventQueueEE_S6_EEEEE6_M_runEv+0x9f)[0x60b9fa4cd6df]
/lib/x86_64-linux-gnu/libstdc++.so.6(+0xdc253)[0x7bfedeadc253]
/lib/x86_64-linux-gnu/libc.so.6(+0x94ac3)[0x7bfede694ac3]
/lib/x86_64-linux-gnu/libc.so.6(+0x126850)[0x7bfede726850]
--- END LIBC BACKTRACE ---
For more info on how to address this issue, please visit https://www.gem5.org/documentation/general_docs/common-errors/
Aborted
Any clue in how to proceed?
Thank you!
Best Regards,
Pau
[Public]
Hi Pau,
Does the host system have 4 CPUs available for KVM to use? I have seen similar errors occasionally with even 2 CPUs and simply rerunning the simulation seemed to fix it. Unfortunately, I am not a KVM expert so I am not entirely sure how to make it more robust.
-Matt
From: Pau Galindo Figuerola via gem5-users gem5-users@gem5.org
Sent: Friday, March 22, 2024 10:47 AM
To: The gem5 Users mailing list gem5-users@gem5.org
Cc: Pau Galindo Figuerola pau.galindo.figuerola@estudiantat.upc.edu
Subject: [gem5-users] GPU FS Multiple CPU
Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.
Hi all,
I'm trying to run GPU FS with 4 CPU. That's because I want to replicate a real APU device that has 4 x86 CPUs with 2 threads each.
When running it in FS along with a Vega10 GPU I'm facing the following error:
M5 Terminal Output:
[ 0.332000] smpboot: CPU0: AMD Fake gem5 x86_64 CPU (family: 0xf, model: 0x25, stepping: 0x1)
[ 0.336000] Performance Events: Broken PMU hardware detected, using software events only.
[ 0.340000] Failed to access perfctr msr (MSR c0010007 is 0)
[ 0.344000] rcu: Hierarchical SRCU implementation.
[ 0.348000] NMI watchdog: Perf NMI watchdog permanently disabled
[ 0.352000] smp: Bringing up secondary CPUs ...
[ 0.356000] x86: Booting SMP configuration:
Simulation Output:
src/cpu/kvm/base.cc:1109: panic: KVM: Failed to enter virtualized mode (hw reason: 0x80000021)
Memory Usage: 28921692 KBytes
Program aborted at tick 1951958177000
--- BEGIN LIBC BACKTRACE ---
gem5/build/VEGA_X86/gem5.opt(_ZN4gem515print_backtraceEv+0x30)[0x60b9fa48cea0]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem512abortHandlerEi+0x4c)[0x60b9fa4b2d3c]
/lib/x86_64-linux-gnu/libc.so.6(+0x42520)[0x7bfede642520]
/lib/x86_64-linux-gnu/libc.so.6(pthread_kill+0x12c)[0x7bfede6969fc]
/lib/x86_64-linux-gnu/libc.so.6(raise+0x16)[0x7bfede642476]
/lib/x86_64-linux-gnu/libc.so.6(abort+0xd3)[0x7bfede6287f3]
gem5/build/VEGA_X86/gem5.opt(+0xd67ec5)[0x60b9f9363ec5]
gem5/build/VEGA_X86/gem5.opt(+0xf31d05)[0x60b9f952dd05]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem510BaseKvmCPU4tickEv+0x99)[0x60b9f952f609]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem510EventQueue10serviceOneEv+0xc2)[0x60b9fa4a3042]
gem5/build/VEGA_X86/gem5.opt(_ZN4gem59doSimLoopEPNS_10EventQueueE+0x68)[0x60b9fa4cc458]
gem5/build/VEGA_X86/gem5.opt(_ZNSt6thread11_State_implINS_8_InvokerISt5tupleIJZN4gem516SimulatorThreads17runUntilLocalExitEvEUlPNS3_10EventQueueEE_S6_EEEEE6_M_runEv+0x9f)[0x60b9fa4cd6df]
/lib/x86_64-linux-gnu/libstdc++.so.6(+0xdc253)[0x7bfedeadc253]
/lib/x86_64-linux-gnu/libc.so.6(+0x94ac3)[0x7bfede694ac3]
/lib/x86_64-linux-gnu/libc.so.6(+0x126850)[0x7bfede726850]
--- END LIBC BACKTRACE ---
For more info on how to address this issue, please visit https://www.gem5.org/documentation/general_docs/common-errors/
Aborted
Any clue in how to proceed?
Thank you!
Best Regards,
Pau