64ac40ab64
ck_epoch: there is no need to update record epoch for synchronize.
...
This is in preparation for upcoming work for allowing record sharing.
The write-side operations rely only on global state. Future work, we can play
tricks by caching latest call epoch while still building on the core EBR
concept.
8 years ago
77fc933229
regressions/epoch/torture: include synchronize latency.
8 years ago
f8d5022030
configure: do not rely on pathsearch if full executable path provided.
...
This issue was pointed out by Mark Callaghan. Fixes #90 .
8 years ago
24d26965d1
regressions/ck_epoch_section_2: Force exit after timer.
8 years ago
343246d377
build: release 0.6.0.
8 years ago
d24fc277ad
epoch: fix idle detection bug in synchronize.
...
An idle grace period requires all threads to be idle. This optimization
introduced a regression with idle detection if subset of threads are
both active and idle. Unfortunately, none of our test machines detected
the problem.
This issue was reported by Julie Zhao <julie.zhao@sparkpos....>
8 years ago
255a47553a
Merge pull request #88 from akopytov/benchmarks
...
Add benchmarks for ck_pr_add_64(), ck_pr_faa_64() and ck_pr_neg_64().
8 years ago
696ae6e995
Add benchmarks for ck_pr_add_64(), ck_pr_faa_64() and ck_pr_neg_64().
8 years ago
d8d5b01a1a
Merge pull request #87 from akopytov/aarch64_timer
...
Add AArch64 timer support to rdtsc().
8 years ago
ab8f2b0344
Add AArch64 timer support to rdtsc().
...
Add support for RDTSC-like timer on AArch64. This is only used by the
internal regression/benchmark test suite.
8 years ago
4a028fb517
Merge pull request #86 from akopytov/lse
...
AArch64 LSE support.
8 years ago
5f1be5dc83
AArch64 LSE support.
...
Add a new configure option, --enable-lse, which is only effective for
the AArch64 architecture. When used, most ck_pr_* atomics will use Large
System Extensions instructions as per the ARMv8.1 specification, rather
then LL/SC instruction pairs.
8 years ago
dae84bac06
ck_pr/aarch64: style.
8 years ago
4425c94ef7
ck_pr/aarch64: Don't forget the "cc" and "memory" clobbers.
8 years ago
02af290b85
ck_pr: Add an option to disable any double function
8 years ago
566bb28dba
Merge pull request #84 from hbowden/master
...
Add cygwin support.
8 years ago
92dfe0726c
Add cygwin support.
8 years ago
2868848a2f
ck_pr/ppc: Get the right prototype for ck_pr_cas_ptr_value().
8 years ago
5ae12a19d0
gcc/ck_pr: Try to make sure the compiler isn't unhappy about constness.
8 years ago
1c9257af77
ck_pr: missed a few occurrences of stdbool.h that should be ck_stdbool.h.
8 years ago
2159452170
ck_pr/aarch64: Use the right asm constraints.
...
We don't have to claim we will read the value from variables when we do not,
this was only done to work around a bug on some versions of gcc for arm
a while ago, hopefully this won't be needed here.
This should fix the (harmless) warnings described in issue #83 .
8 years ago
7c456ca778
ck_pr/aarch64: That should be CK_PR_AARCH64_H, not CK_PR_ARM_H
8 years ago
92aabcade0
ck_pr: First cut at an aarch64 native implementation.
...
This seems to survive a "make check" on a 48 cores arm64 board.
8 years ago
1b461ca57a
regressions/ck_spinlock: Add ck_hclh to the check target.
8 years ago
2552550256
regressions/ck_hp: Make sure stores are visible before attempting CAS.
8 years ago
5530535f2a
doc: enfores => enforces
8 years ago
9c072391cf
ck_pr/arm : We never defined CK_PR_CAS_S, so there's no need to undef it.
8 years ago
e9e45034f3
Merge pull request #82 from iamthebot/master
...
use __restrict__ under GCC to support both C++ and C
8 years ago
d113d23def
build: Bump version for release.
8 years ago
bc594bf809
use __restrict__ under GCC to support both C++ and C
8 years ago
f449e90b3f
build: Fix clang detection to require major >= 3.
8 years ago
24133c8d31
Merge pull request #77 from guotie/patch-1
...
Update ck_ring.h
8 years ago
4f01918cbb
Update ck_ring.h
...
fix bug
8 years ago
0771af0163
doc: ck_epoch_poll now only takes one argument.
9 years ago
8ce1f45ee7
Merge pull request #73 from LebedevRI/ht
...
ck_ht: Call user-specified hash function, regression test included.
9 years ago
3bb8e04def
ck_ht_hash(): actually use user-provided hash function
...
Fixes failing test that i have added in previous commit.
9 years ago
b6d82a481a
Ht: regressions: validate serial: check that our hash function was actually called.
...
Of course, assumes that there won't be an overflow caueing
it to be exactly 0 in the end...
The test fails.
9 years ago
e60c05bb65
ck_epoch: Epoch goal must be ordered with respect prior operations.
9 years ago
03bd7a4158
regressions/ck_epoch: Change formatting.
9 years ago
7f625a6fe1
ck_rhs: Make sure we zero all of the descs, not just the first one.
9 years ago
04f9c9d697
Merge pull request #69 from LebedevRI/master
...
ck_queue: update doc: no tail queue, add STAILQ description
9 years ago
1a10ab230e
ck_queue: update doc: no tail queue, add STAILQ description
...
Singly-linked tail queue description is taken from sys/queue.h
9 years ago
42dd531427
doc: Change html target to just use text output.
9 years ago
2700010b84
[git] Additional .gitignore entries.
9 years ago
f97d3da5c3
regressions/ck_sequence: Use flag rather than counter value for first set.
...
Prevents resetting exit barrier on overflow. Otherwise, hangs occur
on higher-performing systems.
9 years ago
c06fd5739f
ck_epoch: Switch to full barrier semantics.
...
May as well capture synchronize -> non-temporal use-case.
9 years ago
ece3a24a4f
regressions/ck_epoch: Switch to heap allocated records for torture test.
9 years ago
5b64342668
regressions/ck_epoch: Remove counter dependencies from torture parity test.
9 years ago
f22f921576
regressions/ck_epoch_section_2: Switch to heap allocated records.
9 years ago
5999d8a243
regressions/ck_epoch: Shorten stack walk length for ck_epoch_synchronize.
...
This test was taking excessively long (read: hours) on some targets.
9 years ago
Samy Al Bahra
Olivier Houchard
Alexey Kopytov
Harry
Olivier Houchard
Samy Al Bahra
alfredo
铁哥
Roman Lebedev