mirror of
https://github.com/yuzu-emu/unicorn.git
synced 2025-10-29 00:28:12 +00:00
cb92eea81a
Emulating LL/SC with cmpxchg is not correct, since it can suffer from the ABA problem. Portable parallel code, however, is written assuming only cmpxchg--and not LL/SC--is available. This means that in practice emulating LL/SC with cmpxchg is a viable alternative. The appended emulates LL/SC pairs in aarch64 with cmpxchg helpers. This works in both user and system mode. In usermode, it avoids pausing all other CPUs to perform the LL/SC pair. The subsequent performance and scalability improvement is significant, as the plots below show. They plot the throughput of atomic_add-bench compiled for ARM and executed on a 64-core x86 machine. Hi-res plots: http://imgur.com/a/JVc8Y atomic_add-bench: 1000000 ops/thread, [0,1] range 18 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 16 ++master +-H--+ ++ || | 14 ++ ++ | | | 12 ++| ++ | | | 10 ++++ ++ 8 ++E ++ |+++ | 6 ++ | ++ | | | 4 ++ | ++ | | | 2 +H++E+--- ++ + | +E++----+E+---+--+E+----++E+------+E+------+E++----+E+---+--+E| 0 ++H-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,2] range 18 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 16 ++master +-H--+ ++ | | | 14 ++E ++ | | | 12 ++| ++ |+++ | 10 ++ | ++ 8 ++ | ++ | | | 6 ++ | ++ | | | 4 ++ | ++ | +E+--- | 2 +H+ +E+-----+++ +++ +++ ---+E+-----+E+------+++ +++ + +E+---+--+E+----++E+------+E+--- ++++ +++ + +E| 0 ++H-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,128] range 70 ++---------+----------+---------+----------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 60 ++master +-H--+ +++ ---+E+-----+E+------+E+ | +E+------E-------+E+--- | | --- +++ | 50 ++ +++--- ++ | -+E+ | 40 ++ +++---- ++ | E- | | --| | 30 ++ -- +++ ++ | +E+ | 20 ++E+ ++ |E+ | | | 10 ++ ++ + + + + + + + | 0 +HH-H----H-+-----H----+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 1000000 ops/thread, [0,1024] range 160 ++---------+---------+----------+---------+----------+----------+---++ +cmpxchg +-E--+ + + + + + | 140 ++master +-H--+ +++ +++ | -+E+-----+E+-------E| 120 ++ +++ ---- +++ | +++ ----E-- | 100 ++ --E--- +++ ++ | +++ ---- +++ | 80 ++ --E-- ++ | ---- +++ | | -+E+ | 60 ++ ---- +++ ++ | +E+- | 40 ++ -- ++ | +E+ | 20 +EE+ ++ +++ + + + + + + | 0 +HH-H---H--+-----H---+----------+---------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads Backports commit 1dd089d0eec060dcd8478735114d98421d414805 from qemu |
||
|---|---|---|
| .. | ||
| crypto | ||
| default-configs | ||
| docs | ||
| fpu | ||
| hw | ||
| include | ||
| qapi | ||
| qobject | ||
| qom | ||
| scripts | ||
| target-arm | ||
| target-i386 | ||
| target-m68k | ||
| target-mips | ||
| target-sparc | ||
| tcg | ||
| util | ||
| aarch64.h | ||
| aarch64eb.h | ||
| accel.c | ||
| arm.h | ||
| armeb.h | ||
| atomic_template.h | ||
| CODING_STYLE | ||
| configure | ||
| COPYING | ||
| COPYING.LIB | ||
| cpu-exec-common.c | ||
| cpu-exec.c | ||
| cpus.c | ||
| cputlb.c | ||
| exec.c | ||
| gen_all_header.sh | ||
| glib_compat.c | ||
| HACKING | ||
| header_gen.py | ||
| ioport.c | ||
| LICENSE | ||
| m68k.h | ||
| Makefile | ||
| Makefile.objs | ||
| Makefile.target | ||
| memory.c | ||
| memory_mapping.c | ||
| mips.h | ||
| mips64.h | ||
| mips64el.h | ||
| mipsel.h | ||
| powerpc.h | ||
| qapi-schema.json | ||
| qemu-timer.c | ||
| rules.mak | ||
| softmmu_template.h | ||
| sparc.h | ||
| sparc64.h | ||
| tcg-runtime.c | ||
| translate-all.c | ||
| translate-all.h | ||
| translate-common.c | ||
| unicorn_common.h | ||
| VERSION | ||
| vl.c | ||
| vl.h | ||
| x86_64.h | ||