ck_pr_load_32_2 (and thus ck_pr_load_ptr_2) were previously implemented in
terms of lock cmpxchg8b, which is considerably slower than just using movq.
Relevant tests making use of load_ptr_2 still pass, so I'm confident this
change is correct.
C casts to unsigned int by default, so we were experiencing some negative
undefined behavior in the 1 << 31 case. x86 now works; bts and btc are
both passing.
It turns out that the "p" constraint doesn't work on clang, so we have to get
rid of that. This means that we may need to require GCC 4.3+ if it turns out
that GCC 4.1 / 4.2 still run out of registers compiling this version.
Fix a typo that was causing several validation tests to hang.
(Doing cmpxchg8b (%eax) isn't going to work very well.) I am
wondering if something is wrong with the general implementation
of ck_pr_bts_64 and ck_pr_btc_64 because it's pretty clear that
with the stack tests passing, ck_pr_cas_32_2_value works fine.
This is the software combining tree barrier from the MCS paper. Currently,
it uses a binary tree; it may be changed later to use an n-ary tree.
Validation (combining_validation.c in regressions/ck_barrier/validate)
has also been added.
Making things work properly with PIC on 32-bit x86 architectures is tricky
because of our lack of %ebx. Additionally, GCC versions < 4.3 have some
problems determining what registers may be reused, causing some of the inline
assembly constraints to be a little counterintuitive. (Thanks to Ian Lance
Taylor for the suggestion to get around the reuse issues.)
This change makes us use sane assembler in cases where we're running
non-PIC and use the heavyweight versions only for PIC. There may still be
some issues in this code; for example, it's apparent that 64-bit btc and
bts intrinsic atomics are broken in the version of GCC I'm using, so those
will have to be implemented.
Additionally, the ck_stack tests currently don't work with fPIC (not sure
if that's the fault of the tests or the port). Everything does pass now in
non-PIC, excluding btc/bts tests (in my current environment).
Make the assumption that all of our 32-bit x86 architecture targets
have SSE and SSE2. This allows us to use MOVQ, which is nicer than
using cmpxchg8b for loads / stores.
Fix up some of the CAS stuff for -fPIC. This isn't entirely done,
and at least ck_fifo_mpmc hangs with this code. Not entirely sure
why.
CK_CC_PACKED will drop structures to one-byte alignment in certain
cases. Obviously, this will mean bad performance on most architectures.
Thanks to Matt Johnson from https://rigel.crhc.illinois.edu/ for
reporting this problem.
Instead of executing a join on the threads, aggregate existing state
of their counters. This can mean one missed increment per thread,
which is not a big deal.
Samy Al Bahra
David Joseph
Samy Al Bahra
Devon H. O'Dell