3rd-party/linux-kernel-module-cheat
1
0
Fork 0
mirror of https://github.com/cirosantilli/linux-kernel-module-cheat.git synced 2026-01-23 02:05:57 +01:00
Code Issues Releases Wiki Activity

gem5: take one quick failed shot at se.py --smt

Browse Source
This commit is contained in:
Ciro Santilli 六四事件 法轮功
2020-04-25 01:00:00 +00:00
parent d0aac8d6f9
commit 7f332f2412
1 changed files with 25 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
README.adoc
View File

@@ -4150,7 +4150,7 @@ and then <<dry-run,hack the produced command>> by replacing:
with: with:
.... ....
--cmd '/home/ciro/bak/git/linux-kernel-module-cheat/out/userland/default/aarch64/posix/getpid.out;/home/ciro/bak/git/linux-kernel-module-cheat/out/userland/default/aarch64/posix/getpid.out' \ --cmd '/path/to/linux-kernel-module-cheat/out/userland/default/aarch64/posix/getpid.out;/path/to/linux-kernel-module-cheat/out/userland/default/aarch64/posix/getpid.out' \
--param 'system.cpu[:].workload[:].release = "5.4.3"' \ --param 'system.cpu[:].workload[:].release = "5.4.3"' \
.... ....
@@ -4190,6 +4190,29 @@ which starts with:
and therefore shows one instruction running on each CPU for each process at the same time. and therefore shows one instruction running on each CPU for each process at the same time.
===== gem5 syscall emulation --smt
gem5 b1623cb2087873f64197e503ab8894b5e4d4c7b4 syscall emulation has an `--smt` option presumably for <<hardware-threads>> but it has been neglected forever it seems: https://github.com/cirosantilli/linux-kernel-module-cheat/issues/104
If we start from the manually hacked working command from <<gem5-syscall-emulation-multiple-executables>> and try to add:
....
--cpu 1 --cpu-type Derivo3CPU --caches
....
We choose <<gem5-deriveo3cpu,`DerivO3CPU`>> because of the se.py assert:
....
example/se.py:115: assert(options.cpu_type == "DerivO3CPU")
....
But then that fails with:
....
gem5.opt: /path/to/linux-kernel-module-cheat/out/gem5/master3/build/ARM/cpu/o3/cpu.cc:205: FullO3CPU<Impl>::FullO3CPU(DerivO3CPUParams*) [with Impl = O3CPUImpl]: Assertion `params->numPhysVecPredRegs >= numThreads * TheISA::NumVecPredRegs' failed.
Program aborted at tick 0
....
=== QEMU user mode quirks === QEMU user mode quirks
==== QEMU user mode does not show stdout immediately ==== QEMU user mode does not show stdout immediately
@@ -22499,7 +22522,7 @@ Intel name: "Hyperthreading"
* https://stackoverflow.com/questions/5593328/software-threads-vs-hardware-threads/61415402#61415402 * https://stackoverflow.com/questions/5593328/software-threads-vs-hardware-threads/61415402#61415402
* https://superuser.com/questions/122536/what-is-hyper-threading-and-how-does-it-work * https://superuser.com/questions/122536/what-is-hyper-threading-and-how-does-it-work
gem5 appears to possibly have attempted to implement hardware threads in <<gem5-syscall-emulation-mode>>: https://github.com/cirosantilli/linux-kernel-module-cheat/issues/104 when using <<gem5-syscall-emulation-multiple-executables>>. gem5 appears to possibly have attempted to implement hardware threads in <<gem5-syscall-emulation-mode>> as mentioned at <<gem5-syscall-emulation-smt>>.
On fs.py it is not exposed in any in-tree config however, and as pointed by the above issue O3 FS has an assert that prevents it in https://github.com/gem5/gem5/blob/377898c4034c72b84b2662ed252fa25079a4ea62/src/cpu/o3/cpu.cc#L313[src/cpu/o3/cpu.cc]: On fs.py it is not exposed in any in-tree config however, and as pointed by the above issue O3 FS has an assert that prevents it in https://github.com/gem5/gem5/blob/377898c4034c72b84b2662ed252fa25079a4ea62/src/cpu/o3/cpu.cc#L313[src/cpu/o3/cpu.cc]: