search for: memchecks

I'm building a simple R extension around a CUDA-enabled dynamic library, and I want to run the whole package with cuda-memcheck for debugging purposes. I can run it just fine with Valgrind: $ R --no-save -d valgrind < test.R However, if I try the same thing with cuda-memcheck, $ R --no-save -d cuda-memcheck < test.R I get: *** Further command line arguments ('--no-save ')

...t; > > There is a work taking place by multiple people in this area and more > is expected to happen and I’d like to make sure we’re working toward > a common end goal. > > > > > > I tried to collect the use-cases for run-time memory checks and the > specific memchecks required for each: > > > > > > 1. Loop Vectorizer: each memory access is checked against all other > memory accesses in the loop (except read vs read) > > > 2. Loop Distribution: only memory accesses in different partitions > are checked against each other. T...

...ity/profitability analysis part is split from the transform part. 3. Versioning within the actual transform pass. Loop vectorization and loop distribution is the example here. LV is probably the stronger example to illustrate why it sometimes makes sense to do this within a pass: besides failed memchecks, LV also falls back on the original loop if the induction variable may overflow, so the versioning is further amended by the pass. Given this I think the way forward is to create a utility class for loop versioning that we could use from all of these places. The class will get the initial set of...

...binary instrumentation. This gives us much better register allocation (function-wide instead of local), possible compiler optimizations (static analysis can prove that some accesses always read initialized memory), and a fast start-up. Our preliminary measurements show 3x-4x slowdown; compare it to Memchecks's 20x and DrMemory's 10x. (See http://groups.csail.mit.edu/commit/papers/2011/bruening-cgo11-drmemory.pdf for those numbers). But this brings the major issue as well: msan needs to see all program events, including system calls and reads/writes in system libraries, so we either need to comp...

> On October 21, 2016 at 6:27 AM Tamsy <dovecot-list at mohtex.net> wrote: > > > Timo Sirainen wrote on 20.10.2016 04:01: > > http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz > > http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz.sig > > > > There are quite a lot of changes since v2.2.25. Please try out this RC so we can get a good

Timo Sirainen wrote on 20.10.2016 04:01: > http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz > http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz.sig > > There are quite a lot of changes since v2.2.25. Please try out this RC so we can get a good and stable v2.2.26 out. > > * master: Removed hardcoded 511 backlog limit for listen(). The kernel > should

...t; > > There is a work taking place by multiple people in this area and more > is expected to happen and I’d like to make sure we’re working toward > a common end goal. > > > > > > I tried to collect the use-cases for run-time memory checks and the > specific memchecks required for each: > > > > > > 1. Loop Vectorizer: each memory access is checked against all other > memory accesses in the loop (except read vs read) > > > 2. Loop Distribution: only memory accesses in different partitions > are checked against each other. T...

...ves us much better register allocation (function-wide instead of > local), > possible compiler optimizations (static analysis can prove that some > accesses always read initialized memory), > and a fast start-up. > Our preliminary measurements show 3x-4x slowdown; compare it to > Memchecks's 20x and DrMemory's 10x. > (See > http://groups.csail.mit.edu/commit/papers/2011/bruening-cgo11-drmemory.pdf for > those numbers). > But this brings the major issue as well: msan needs to see all program > events, including system calls and reads/writes in system libraries,...

It seems that at some point in the not-so-distant-past that the loop vectorizer gained the ability to vectorize loops without explicit `llvm.loop` & `llvm.mem.parallel_loop_access` metadata. While that's awesome, there seems to be a regression in that `llvm.mem.parallel_loop_access` metadata doesn't make it into the alias analysis, and therefore a `vector.memcheck` basic block is

By default valgrind suppresses many leaks. I'm not even sure exactly how it decides which ones to suppress, but certainly global variables pointing to malloc’d data are suppressed, which is not useful behaviour. Tell valgrind to show all leaks. It won't give an error on them. However to do this we also need a much more comprehensive list of suppressions so that we don't constantly

Adam, Please find the attached test case (run with ToT opt -O3). As you can see, `y_body` successfully is vectorized, though %33 and %46 are deemed MayAlias despite their exclusive use in loads ands stores marked with `llvm.mem.parallel_loop_access`. Many Thanks, Josh On Thu, Mar 19, 2015 at 12:55 PM, Adam Nemet <anemet at apple.com> wrote: > > > On Mar 19, 2015, at 9:43 AM,

On Mon, Jun 18, 2012 at 5:07 PM, Joerg Sonnenberger <joerg at britannica.bec.de > wrote: > On Mon, Jun 18, 2012 at 02:39:34PM +0400, Kostya Serebryany wrote: > > Another difference from Memcheck is that we propose to use 8 shadow bits > > per byte of application memory and use a > > direct shadow mapping (for 64-bit linux that is just clearing 46-th bit > of >

On 10/20/2016 10:34 PM, Aki Tuomi wrote: >> On October 21, 2016 at 6:27 AM Tamsy <dovecot-list at mohtex.net> wrote: >> >> >> Timo Sirainen wrote on 20.10.2016 04:01: >>> http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz >>> http://dovecot.org/releases/2.2/rc/dovecot-2.2.26.rc1.tar.gz.sig >>> >>> There are quite a lot of

...ks specific to loop vectorizer, with this check we can’t use LAA for LICM loop versioning. > If we like to make this reusable probably we need to remove this or make it conditional. > > Probably, agents to LAA can implements such check instead LAA. > > Not really. Don’t you need memchecks for loop-invariant addresses as well? > We do need memcheck for loop-invariant addresses, but with current implementation if there is any invariant store, LAA simply returns by setting CanVecMem to false. > > I think we should just teach the analysis to also emit run-time checks for loop...

...nvariantStore’ (or a name with invariant store) makes more sense over ‘hasAccessToLoopInvariantAddress’. Right but it’s the address that’s invariant not the store so hasLoopInvariantStore is a misleading name. How about hasStoreToLoopInvariantAddress? > > You will also need to generate the memchecks for such accesses in > > canCheckPtrAtRT and addRuntimeCheck. Without those memchecks passing, > > the result of the dependence analysis is incorrect. > I did not understood this point correctly, I feel the current functionality take cares of it > And we do not need any new handl...

On Mon, Jun 18, 2012 at 5:43 PM, Joerg Sonnenberger <joerg at britannica.bec.de > wrote: > On Mon, Jun 18, 2012 at 05:19:11PM +0400, Kostya Serebryany wrote: > > On Mon, Jun 18, 2012 at 5:07 PM, Joerg Sonnenberger < > joerg at britannica.bec.de > > > wrote: > > > > > On Mon, Jun 18, 2012 at 02:39:34PM +0400, Kostya Serebryany wrote: > > > >

On Mon, Jun 18, 2012 at 02:39:34PM +0400, Kostya Serebryany wrote: > Another difference from Memcheck is that we propose to use 8 shadow bits > per byte of application memory and use a > direct shadow mapping (for 64-bit linux that is just clearing 46-th bit of > the application memory address). > This greatly simplifies the instrumentation code and avoids races on shadow >

On Mon, Jun 18, 2012 at 05:19:11PM +0400, Kostya Serebryany wrote: > On Mon, Jun 18, 2012 at 5:07 PM, Joerg Sonnenberger <joerg at britannica.bec.de > > wrote: > > > On Mon, Jun 18, 2012 at 02:39:34PM +0400, Kostya Serebryany wrote: > > > Another difference from Memcheck is that we propose to use 8 shadow bits > > > per byte of application memory and use a

Hi, We are having an issue with the loop vectorizer and noalias pointers, as it is generating `vector.memcheck` while we can guarantee that the pointers will not overlap. It seems that in `LoopVectorize.cpp` the function `emitMemRuntimeChecks` is called but there are no checks to disable this behavior (like "strong noalias") We are actually using a technique similar to the

On Mon, Jun 18, 2012 at 6:30 PM, Joerg Sonnenberger <joerg at britannica.bec.de > wrote: > On Mon, Jun 18, 2012 at 05:52:49PM +0400, Kostya Serebryany wrote: > > On Mon, Jun 18, 2012 at 5:43 PM, Joerg Sonnenberger < > joerg at britannica.bec.de > > > wrote: > > > > > On Mon, Jun 18, 2012 at 05:19:11PM +0400, Kostya Serebryany wrote: > > > >