aboutsummaryrefslogtreecommitdiff
path: root/target-i386/translate.c
diff options
context:
space:
mode:
authorEmilio G. Cota <cota@braap.org>2016-06-27 15:02:06 -0400
committerRichard Henderson <rth@twiddle.net>2016-10-26 08:29:01 -0700
commit37b995f6e7a1cb6fa378c5cd4217b9dd9e1fc98b (patch)
treec9d3061fdcd06dbf63f4220e1eaec8b4ba583b91 /target-i386/translate.c
parentea97ebe89f7a879ea9aba90140e40c29b5cbd653 (diff)
downloadqemu-arm-37b995f6e7a1cb6fa378c5cd4217b9dd9e1fc98b.tar.gz
target-i386: remove helper_lock()
It's been superseded by the atomic helpers. The use of the atomic helpers provides a significant performance and scalability improvement. Below is the result of running the atomic_add-test microbenchmark with: $ x86_64-linux-user/qemu-x86_64 tests/atomic_add-bench -o 5000000 -r $r -n $n , where $n is the number of threads and $r is the allowed range for the additions. The scenarios measured are: - atomic: implements x86' ADDL with the atomic_add helper (i.e. this patchset) - cmpxchg: implement x86' ADDL with a TCG loop using the cmpxchg helper - master: before this patchset Results sorted in ascending range, i.e. descending degree of contention. Y axis is Throughput in Mops/s. Tests are run on an AMD machine with 64 Opteron 6376 cores. atomic_add-bench: 5000000 ops/thread, [0,1] range 25 ++---------+----------+---------+----------+----------+----------+---++ + atomic +-E--+ + + + + + | |cmpxchg +-H--+ | 20 +Emaster +-N--+ ++ || | |++ | || | 15 +++ ++ |N| | |+| | 10 ++| ++ |+|+ | | | -+E+------ +++ ---+E+------+E+------+E+-----+E+------+E| |+E+E+- +++ +E+------+E+-- | 5 ++|+ ++ |+N+H+--- +++ | ++++N+--+H++----+++ + +++ --++H+------+H+------+H++----+H+---+--- | 0 ++---------+-----H----+---H-----+----------+----------+----------+---H+ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 5000000 ops/thread, [0,2] range 25 ++---------+----------+---------+----------+----------+----------+---++ ++atomic +-E--+ + + + + + | |cmpxchg +-H--+ | 20 ++master +-N--+ ++ |E| | |++ | ||E | 15 ++| ++ |N|| | |+|| ---+E+------+E+-----+E+------+E| 10 ++| | ---+E+------+E+-----+E+--- +++ +++ ||H+E+--+E+-- | |+++++ | | || | 5 ++|+H+-- +++ ++ |+N+ - ---+H+------+H+------ | + +N+--+H++----+H+---+--+H+----++H+--- + + +H+---+--+H| 0 ++---------+----------+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 5000000 ops/thread, [0,8] range 40 ++---------+----------+---------+----------+----------+----------+---++ ++atomic +-E--+ + + + + + | 35 +cmpxchg +-H--+ ++ | master +-N--+ ---+E+------+E+------+E+-----+E+------+E| 30 ++| ---+E+-- +++ ++ | | -+E+--- | 25 ++E ---- +++ ++ |+++++ -+E+ | 20 +E+ E-- +++ ++ |H|+++ | |+| +H+------- | 15 ++H+ ---+++ +H+------ ++ |N++H+-- +++--- +H+------++| 10 ++ +++ - +++ ---+H+ +++ +H+ | | +H+-----+H+------+H+-- | 5 ++| +++ ++ ++N+N+--+N++ + + + + + | 0 ++---------+----------+---------+----------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 5000000 ops/thread, [0,128] range 160 ++---------+---------+----------+---------+----------+----------+---++ + atomic +-E--+ + + + + + | 140 +cmpxchg +-H--+ +++ +++ ++ | master +-N--+ E--------E------+E+------++| 120 ++ --| | +++ E+ | -- +++ +++ ++| 100 ++ - ++ | +++- +++ ++| 80 ++ -+E+ -+H+------+H+------H--------++ | ---- ---- +++ H| | ---+E+-----+E+- ---+H+ ++| 60 ++ +E+--- +++ ---+H+--- ++ | --+++ ---+H+-- | 40 ++ +E+-+H+--- ++ | +H+ | 20 +EE+ ++ +N+ + + + + + + | 0 ++N-N---N--+---------+----------+---------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads atomic_add-bench: 5000000 ops/thread, [0,1024] range 350 ++---------+---------+----------+---------+----------+----------+---++ + atomic +-E--+ + + + + + | 300 +cmpxchg +-H--+ +++ | master +-N--+ +++ || | +++ | ----E| 250 ++ | ----E---- ++ | ----E--- | ---+H| 200 ++ -+E+--- +++ ---+H+--- ++ | ---- -+H+-- | | +E+ +++ ---- +++ | 150 ++ ---+++ ---+H+- ++ | --- -+H+-- | 100 ++ ---+E+ ---- +++ ++ | +++ ---+E+-----+H+- | | -+E+------+H+-- | 50 ++ +E+ ++ +EE+ + + + + + + | 0 ++N-N---N--+---------+----------+---------+----------+----------+---++ 0 10 20 30 40 50 60 Number of threads hi-res: http://imgur.com/a/fMRmq For master I stopped measuring master after 8 threads, because there is little point in measuring the well-known performance collapse of a contended lock. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Emilio G. Cota <cota@braap.org> Message-Id: <1467054136-10430-21-git-send-email-cota@braap.org> Signed-off-by: Richard Henderson <rth@twiddle.net>
Diffstat (limited to 'target-i386/translate.c')
-rw-r--r--target-i386/translate.c15
1 files changed, 0 insertions, 15 deletions
diff --git a/target-i386/translate.c b/target-i386/translate.c
index cfa3956543..927b366534 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -4536,10 +4536,6 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
s->aflag = aflag;
s->dflag = dflag;
- /* lock generation */
- if (prefixes & PREFIX_LOCK)
- gen_helper_lock();
-
/* now check op code */
reswitch:
switch(b) {
@@ -8211,20 +8207,11 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
default:
goto unknown_op;
}
- /* lock generation */
- if (s->prefix & PREFIX_LOCK)
- gen_helper_unlock();
return s->pc;
illegal_op:
- if (s->prefix & PREFIX_LOCK)
- gen_helper_unlock();
- /* XXX: ensure that no lock was generated */
gen_illegal_opcode(s);
return s->pc;
unknown_op:
- if (s->prefix & PREFIX_LOCK)
- gen_helper_unlock();
- /* XXX: ensure that no lock was generated */
gen_unknown_opcode(env, s);
return s->pc;
}
@@ -8316,8 +8303,6 @@ void tcg_x86_init(void)
offsetof(CPUX86State, bnd_regs[i].ub),
bnd_regu_names[i]);
}
-
- helper_lock_init();
}
/* generate intermediate code for basic block 'tb'. */