Language safety in a multithread environment

Article: Fall Processor Forum 2006: IBM's POWER6
By: Gabriele Svelto (gabriele.svelto.delete@this.gmail.com), November 8, 2006 2:29 am
Room: Moderated Discussions
Wilco (Wilco.Dijkstra@ntlworld.com) on 11/7/06 wrote:
---------------------------
>There is also external fragmentation. Suppose you allocate 10000 4-byte blocks.
>Free them, and allocate 5000 8-byte blocks. Do you reuse the pages that were used
>for the 4-byte blocks? My guess is not. It takes only one allocated block in a page
>to keep it from being used for any other size. Ie. worst case fragmentation is in the order of 1000 times overhead...

Well, there is nothing preventing me from reusing an empty page specialized for 4-bytes blocks for 8-bytes one, in fact I do it though not too much aggressively as specializing a page has a cost which can be avoided through caching. In your example 10000 4-byte blocks will end in 3 pages as the 5000 8-bytes one so I don't really see a problem there. While the worst case of having just one used block per page is nasty in practice it almost never happens, you'd need to allocate a lot of blocks of the same size and then free most of them statistically leaving only a few per page, highly unlikely, allocation patterns are not that random as they might look like. BTW every type of allocator - except for relocating collectors - will suffer from unbounded fragmentation in pathological cases, luckily those never happen in practice.

>You always have some form of fragmentation of course, the goal is to minimise it
>as much as possible. Some freelist implementations suffer from the same issue -
>merging freed blocks with adjacent free blocks is essential in a traditional heap implementation.

That's exactly what happens for blocks larger than 256-bytes and it is essential, but for small blocks it is usually a waste of cycles unless you have some form of defer mechanism so that you don't spend a lot of time merging and splitting again the same blocks..

>GCC uses a conservative garbage collector. I think it actually has 2 of them -
>as if just one is not complex enough :-). To be less conservative they allocate
>structures of the same type together so that GC can find the pointers. However the
>allocation policy means that different sized structures are allocated all over the
>place causing a slowdown due to extra cache and TLB misses. I believe the future
>goal is to use a region based allocator and get rid of GC (it makes no sense in a compiler).
>
>There is little documentation about it, most info is in the discussion lists, but Google found this: http://gcc.gnu.org/onlinedocs/gcc/Garbage-Collection.html

The link that you found points to the use of Boehm GC but its for the runtime, specifically it should be used for Objective-C and Java (when using gcj), not GCC itself. I remember that GCC used to make a lot of region based allocations through a library which previously relied on alloca() and I remember that there were a lot of changes around it.

>What I was referring to was using free(p, size) rather than free(p) which would
>allow to avoid the per-block overhead in existing heap implementations.

Well, you don't really need the per-block overhead if you store the size elsewhere, in my case the size is held by the page the block is allocated in, the page address can be obtained by a look-up in a radix-tree which I use for mapping all the memory so the segregated objects are effectively allocated side-by-side without allocator meta-data between them.

> An even
>better interface uses type and alignment indeed. In my region based allocator you
>write Type *p = ALLOC(region, Type) and it allocates a correctly aligned block using
>pointer increment (its all inlined of course, so we're talking a few cycles per allocation).

Yeah, regions are nice and fast though they are not a silver-bullet, they may be very nasty to use in a multi-threaded workload for example. I'd guess that every thread should handle and free his own regions and never pass objects to other ones otherwise it would be tricky to know when the region can be released.

>Segregation is a very bad idea, the key is to allocate objects which are used together
>next to each other, not separate them. Often that means you can free them all in
>one go as well, making deallocation a nop.

I think it's really a trade-off, most applications do allocate only a small set of sizes of small objects and do a few larger allocations. The smaller allocations are likely to come from the same places and are also likely to be used in the same places, data-structures being the first and most prominent components to show this behaviour. Strings as you mentioned before are different on the other hand and as most higher-level language do are treated separately as they should.

Anyway there are tradeoffs between linked-list allocators and segregation. Linked-lists do not guarantee that subsequent allocations will go to subsequent places, in fact one of the problems with linked-list allocation is that they show very poor spatial locality and may cause lots of cache/TLB misses. What segregation gives you on the other hand are objects which do not have allocator meta-data in-between thus not polluting the caches with non-useful data, better TLB profile and possibly better cache profile as for a class of sizes way-contention may be aggresively reduced through colouring. On top of that in a multi-threaded environment you ensure optimal allocation in respect to NUMA (you don't have objects crossing page boundaries unless they're large). You can also fight in a simple way false aliasing by letting different threads allocate objects from different set of pages with no further checking. Now segregation has significant downsides in a situation I'm very practical with: small heaps. If you've got a few hundred KiBs or even a few MiBs specializing a page is a suicide.

Region-based allocation on the other hand will always be faster and if used together with per-object or per-size regions will have the same positive effects on cache and internal fragmentation and gives you the additional benefit of zero-overhead free. However it doesn't work everywhere and the programs using it must be designed for it. For many workloads it's very easy but it gets tricky for multi-threaded ones (unless threads are not allowed to pass allocated objects between themselves) and it is not a replacement for malloc().

Gabriele
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
POWER6 article onlineDavid Kanter2006/10/16 10:31 PM
  POWER6 article onlineNiels Jørgen Kruse2006/10/16 11:59 PM
    POWER6 article onlineDavid Kanter2006/10/17 12:03 AM
      Interesting cachesPaul Aaron Clayton2006/10/17 06:35 AM
  POWER6 article onlinerwessel2006/10/17 12:17 AM
    POWER6 article onlineGabriele Svelto2006/10/17 12:49 AM
      POWER6 article onlinerwessel2006/10/17 12:55 AM
      POWER6 article onlineDavid Kanter2006/10/17 01:01 AM
        POWER6 article onlineGabriele Svelto2006/10/17 01:06 AM
  BCD arithmetic remarkRob Thorpe2006/10/17 06:57 AM
    BCD arithmetic remarkDavid Kanter2006/10/17 08:04 AM
      BCD arithmetic remarkRob Thorpe2006/10/17 08:33 AM
        Java perfSerge Monkewitz2006/10/17 12:25 PM
          Java perfRob Thorpe2006/10/18 04:27 AM
            Java perfsp2006/10/18 04:50 AM
              Java perfRob Thorpe2006/10/18 08:36 AM
                Data parallelism in .NET using GPUsStephen Goss2006/10/18 11:48 PM
                  Data parallelism in .NET using GPUssp2006/10/19 01:08 AM
                    Data parallelism in .NET using GPUsStephen Goss2006/10/21 02:22 AM
                      Data parallelism in .NET using GPUsfastpathguru2006/11/01 02:30 PM
                        Data parallelism in .NET using GPUsIan Ameline2006/11/01 05:31 PM
                Java perfGabriele Svelto2006/10/19 12:23 AM
                  Java perfRob Thorpe2006/10/19 02:58 AM
              Numerical Java perfWes Felter2006/10/18 10:25 AM
                Numerical Java perfsp2006/10/18 10:46 AM
                  Numerical Java perfRob Thorpe2006/10/18 11:23 AM
                    Numerical Java perfTzvetan Mikov2006/10/18 11:44 AM
                      Numerical Java perfRob Thorpe2006/10/19 04:30 AM
                        Numerical Java perfsp2006/10/19 05:22 AM
                          Numerical Java perfGabriele Svelto2006/10/19 05:33 AM
                          Numerical Java perfRob Thorpe2006/10/19 07:08 AM
                            Numerical Java perfJuho Snellman2006/10/20 08:38 AM
                              Numerical Java perfRob Thorpe2006/10/23 04:54 AM
                                SBCL garbage collectorJuho Snellman2006/10/25 03:29 AM
                          Numerical Java perfTzvetan Mikov2006/10/19 09:04 AM
                        Language safety in a multithread environmentTzvetan Mikov2006/10/19 09:34 AM
                          Language safety in a multithread environmentRicardo B2006/10/19 11:43 AM
                            Language safety in a multithread environmentTzvetan Mikov2006/10/19 12:11 PM
                              Language safety in a multithread environmentRicardo B2006/10/19 02:23 PM
                                Language safety in a multithread environmentTzvetan Mikov2006/10/19 04:08 PM
                                  Language safety in a multithread environmentRicardo B2006/10/20 05:04 AM
                                    Language safety in a multithread environmentTzvetan Mikov2006/10/20 01:53 PM
                                      Language safety in a multithread environmentRicardo B2006/10/20 02:06 PM
                                      PSRicardo B2006/10/20 02:12 PM
                                        PSTzvetan Mikov2006/10/20 03:30 PM
                          Language safety in a multithread environmentGabriele Svelto2006/10/20 01:26 AM
                            Language safety in a multithread environmentTzvetan Mikov2006/10/20 01:34 PM
                              Language safety in a multithread environmentS. Rao2006/10/20 08:39 PM
                                Language safety in a multithread environmentTzvetan Mikov2006/10/21 09:39 AM
                                  Language safety in a multithread environmentS. Rao2006/10/21 03:54 PM
                                    Language safety in a multithread environmentRicardo B2006/10/21 04:45 PM
                                    Language safety in a multithread environmentTzvetan Mikov2006/10/22 09:42 AM
                                      Language safety in a multithread environmentRob Thorpe2006/10/23 09:35 AM
                                        Language safety in a multithread environmentLinus Torvalds2006/10/23 04:06 PM
                                          Language safety in a multithread environmentTzvetan Mikov2006/10/23 11:55 PM
                                            Language safety in a multithread environmentLinus Torvalds2006/10/24 07:35 AM
                                              Language safety in a multithread environmentTzvetan Mikov2006/10/24 11:26 AM
                                                ClarificationTzvetan Mikov2006/10/24 12:15 PM
                                                Language safety in a multithread environmentLinus Torvalds2006/10/25 07:37 AM
                                                  Language safety in a multithread environmentRob Thorpe2006/10/25 07:52 AM
                                                  Language safety in a multithread environmentTzvetan Mikov2006/10/25 09:01 AM
                                                    Language safety in a multithread environmentLinus Torvalds2006/10/25 05:24 PM
                                                      Language safety in a multithread environmentS. Rao2006/10/25 06:08 PM
                                                        Other approachesRob Thorpe2006/10/26 10:09 AM
                                                          Hang on I forgot the other approachesRob Thorpe2006/10/26 10:27 AM
                                                            Hang on I forgot the other approachesS. Rao2006/10/26 02:16 PM
                                                      Language safety in a multithread environmentGabriele Svelto2006/10/26 03:56 AM
                                                        Language safety in a multithread environmentLinus Torvalds2006/10/26 07:52 AM
                                                          Language safety in a multithread environmentGabriele Svelto2006/10/26 08:11 AM
                                                            "Safety" and different types of safetyRob Thorpe2006/10/26 08:58 AM
                                                              "Safety" and different types of safetyLinus Torvalds2006/10/26 09:26 AM
                                                                "Safety" and different types of safetyRob Thorpe2006/10/26 09:50 AM
                                                                  "Safety" and different types of safetyTzvetan Mikov2006/10/26 10:56 AM
                                                                    Exactly!Gabriele Svelto2006/10/27 12:29 AM
                                                                  message passing languagesFoo_2006/10/28 01:19 AM
                                                        Language safety in a multithread environmentRob Thorpe2006/10/26 10:45 AM
                                                          RecapTzvetan Mikov2006/10/26 11:19 AM
                                                            Information and ickiness on JavaRob Thorpe2006/10/27 04:38 AM
                                                              Excellent threadJasonB2006/10/27 02:57 PM
                                                                Excellent threadsp2006/10/28 12:38 AM
                                                              Information and ickiness on JavaTzvetan Mikov2006/10/27 05:12 PM
                                                      Language safety in a multithread environmentTzvetan Mikov2006/10/26 08:17 AM
                                                        Language safety in a multithread environmentLinus Torvalds2006/10/26 08:57 AM
                                                          Language safety in a multithread environmentRob Thorpe2006/10/26 09:38 AM
                                                            Language safety in a multithread environmentS. Rao2006/10/26 02:51 PM
                                                              Language safety in a multithread environmentRob Thorpe2006/10/27 01:26 AM
                                                                Language safety in a multithread environmentLinus Torvalds2006/10/27 08:40 AM
                                                                  Language safety in a multithread environmentRob Thorpe2006/10/27 09:06 AM
                                                                    Language safety in a multithread environmentLinus Torvalds2006/10/27 10:53 AM
                                                                      Language safety in a multithread environmentrwessel2006/10/27 03:21 PM
                                                                        Explicit vs implicit barriersTzvetan Mikov2006/10/27 05:39 PM
                                                                          Explicit vs implicit barriersLinus Torvalds2006/10/27 06:28 PM
                                                                            Explicit vs implicit barriersTzvetan Mikov2006/10/28 06:02 PM
                                                                              Explicit vs implicit barriersLinus Torvalds2006/10/28 07:55 PM
                                                                                Explicit vs implicit barriersRob Thorpe2006/10/31 12:37 PM
                                                                            Explicit vs implicit barriersRob Thorpe2006/10/31 12:15 PM
                                                                          Explicit vs implicit barriersrwessel2006/10/27 06:39 PM
                                                                      Why OoO stores are evil but OoO loads are o.k.?Michael S2006/10/28 02:10 PM
                                                                        Why OoO stores are evil but OoO loads are o.k.?Linus Torvalds2006/10/28 04:29 PM
                                                                          Why OoO stores are evil but OoO loads are o.k.?Ricardo B2006/10/30 06:36 AM
                                                                            Why OoO stores are evil but OoO loads are o.k.?Linus Torvalds2006/10/30 09:57 AM
                                                                              Why OoO stores are evil but OoO loads are o.k.?Tzvetan Mikov2006/10/30 11:55 AM
                                                                                Why OoO stores are evil but OoO loads are o.k.?Michael S2006/10/30 12:14 PM
                                                                                  Why OoO stores are evil but OoO loads are o.k.?Tzvetan Mikov2006/10/30 12:20 PM
                                                                                    Why OoO stores are evil but OoO loads are o.k.?Michael S2006/10/30 01:11 PM
                                                                                      A reference would be nice :-) (NT)Tzvetan Mikov2006/10/30 01:32 PM
                                                                                        A reference Michael S2006/10/30 03:37 PM
                                                                                          A reference Tzvetan Mikov2006/11/03 08:57 PM
                                                                                            check your e-mbox (NT)Michael S2006/11/04 12:47 PM
                                                                                      Why OoO stores are evil but OoO loads are o.k.?David Kanter2006/10/30 01:40 PM
                                                                                        Why OoO stores are evil but OoO loads are o.k.?Michael S2006/10/30 02:28 PM
                                                                                          Why OoO stores are evil but OoO loads are o.k.?David Kanter2006/10/30 02:43 PM
                                                                                            Why OoO stores are evil but OoO loads are o.k.?Michael S2006/10/30 04:36 PM
                                                                                              Why OoO stores are evil but OoO loads are o.k.?David Kanter2006/10/30 10:14 PM
                                                                                Why OoO stores are evil but OoO loads are o.k.?Linus Torvalds2006/10/30 12:53 PM
                                                                      Language safety in a multithread environmentRob Thorpe2006/10/31 11:25 AM
                                                                        Language safety in a multithread environmentLinus Torvalds2006/10/31 12:59 PM
                                                                          Language safety in a multithread environmentRob Thorpe2006/10/31 01:38 PM
                                                                            Language safety in a multithread environmentLinus Torvalds2006/10/31 02:02 PM
                                                                              Language safety in a multithread environmentLinus Torvalds2006/10/31 03:54 PM
                                                                                Will reply tommorrow, very busy today (NT)Rob Thorpe2006/11/01 11:14 AM
                                                                              Language safety in a multithread environmentRob Thorpe2006/11/02 01:30 PM
                                                                                Language safety in a multithread environmentrwessel2006/11/02 02:06 PM
                                                                                  Language safety in a multithread environmentGabriele Svelto2006/11/03 02:39 AM
                                                                                    Language safety in a multithread environmentLinus Torvalds2006/11/03 09:40 AM
                                                                                      Language safety in a multithread environmentGabriele Svelto2006/11/03 10:12 AM
                                                                                        Language safety in a multithread environmentLinus Torvalds2006/11/03 01:20 PM
                                                                                          Language safety in a multithread environmentGabriele Svelto2006/11/06 03:42 AM
                                                                                      Language safety in a multithread environmentEric Bron2006/11/04 04:47 AM
                                                                                        Language safety in a multithread environmentGabriele Svelto2006/11/06 04:13 AM
                                                                                      Language safety in a multithread environmentWilco2006/11/04 12:29 PM
                                                                                        Language safety in a multithread environmentRicardo B2006/11/04 02:54 PM
                                                                                        Language safety in a multithread environmentGabriele Svelto2006/11/06 03:54 AM
                                                                                          Language safety in a multithread environmentWilco2006/11/06 12:26 PM
                                                                                            Language safety in a multithread environmentGabriele Svelto2006/11/07 01:54 AM
                                                                                              Language safety in a multithread environmentWilco2006/11/07 04:34 PM
                                                                                                Language safety in a multithread environmentGabriele Svelto2006/11/08 02:29 AM
                                                                                      Language safety in a multithread environmentrwessel2006/11/04 10:13 PM
                                                                                        Language safety in a multithread environmentrwessel2006/11/04 10:23 PM
                                                                                      Language safety in a multithread environmentMichael S2006/11/05 04:05 AM
                                                                                        Language safety in a multithread environmentLinus Torvalds2006/11/05 10:14 AM
                                                                                          unaligned SSE testsEric Bron2006/11/05 02:26 PM
                                                                                            unaligned SSE testsMichael S2006/11/05 03:47 PM
                                                                                              unaligned SSE testsEric Bron2006/11/05 04:23 PM
                                                                                                unaligned SSE testsMichael S2006/11/05 05:03 PM
                                                                                                  unaligned SSE testsEric Bron2006/11/05 05:28 PM
                                                                                                    Now results make sense. How about Psc? (NT)Michael S2006/11/05 05:37 PM
                                                                                                      tomorrow, it's 01:43 PM where I'm (NT)Eric Bron2006/11/05 05:44 PM
                                                                                                        I mean 01:43 AM (NT)Eric Bron2006/11/05 05:45 PM
                                                                                                      PSC scoresEric Bron2006/11/06 02:25 AM
                                                                                                        PSC scoresMichael S2006/11/06 04:28 AM
                                                                                                          PSC scoresIan Ameline2006/11/06 09:00 AM
                                                                                                            meaningful performance gainMichael S2006/11/06 09:33 AM
                                                                                                              meaningful performance gainLinus Torvalds2006/11/06 11:15 AM
                                                                                                                Dynamically resolved alignmentDavid Kanter2006/11/06 12:49 PM
                                                                                                                  Dynamically resolved alignmentRicardo B2006/11/06 01:46 PM
                                                                                                                  Dynamically resolved alignmentLinus Torvalds2006/11/06 01:48 PM
                                                                                                                meaningful performance gainEric Bron2006/11/07 02:23 AM
                                                                                                        RE: "I suppose we will have to continue to align" ...Not really :)redpriest2006/11/06 05:11 PM
                                                                                                          Your point?Michael S2006/11/06 05:47 PM
                                                                                                            Actually Michael, it's quite a bit more than that.redpriest2006/11/06 06:30 PM
                                                                                                              Actually Michael, it's quite a bit more than that.anonymous2006/11/06 08:36 PM
                                                                                                                Actually Michael, it's quite a bit more than that.Linus Torvalds2006/11/06 09:01 PM
                                                                                                                  Actually Michael, it's quite a bit more than that.Rob Thorpe2006/11/07 03:31 AM
                                                                                                                  Actually Michael, it's quite a bit more than that.anonymous2006/11/07 07:27 AM
                                                                                                              link vs linqMichael S2006/11/07 02:04 AM
                                                                                                                link vs linqanonymous2006/11/07 07:13 AM
                                                                                                                  Thank you (NT)Michael S2006/11/07 08:04 AM
                                                                                                          Barcelona dreamsEric Bron2006/11/07 01:08 AM
                                                                                          Language safety in a multithread environmentWilco2006/11/05 03:14 PM
                                                                                            Language safety in a multithread environmentRicardo B2006/11/05 03:56 PM
                                                                                              Language safety in a multithread environmentWilco2006/11/05 06:52 PM
                                                                                                Language safety in a multithread environmentRicardo B2006/11/05 09:09 PM
                                                                                                  Language safety in a multithread environmentWilco2006/11/06 02:25 PM
                                                                                                    Language safety in a multithread environmentRicardo B2006/11/06 03:48 PM
                                                                                                      Language safety in a multithread environmentWilco2006/11/06 04:44 PM
                                                                                                        Language safety in a multithread environmentRicardo B2006/11/06 04:53 PM
                                                                                                        A common problemRob Thorpe2006/11/07 09:45 AM
                                                                                                          A common problemWilco2006/11/09 04:46 PM
                                                                                                            A common problemRob Thorpe2006/11/10 08:29 AM
                                                                                                              A common problemrwessel2006/11/13 04:47 PM
                                                                                                                A common problemWilco2006/11/13 05:51 PM
                                                                                                                  A common problemRob Thorpe2006/11/14 03:38 AM
                                                                                                                    A common problemLinus Torvalds2006/11/14 09:37 AM
                                                                                                                      A common problemRob Thorpe2006/11/14 11:18 AM
                                                                                                                        A common problemagony2006/11/14 02:57 PM
                                                                                                                          A common problemrwessel2006/11/14 04:13 PM
                                                                                                                            A common problemAndi Kleen2006/11/15 04:24 AM
                                                                                                                              A common problemrwessel2006/11/15 04:42 PM
                                                                                                                        A common problemDoug Siebert2006/11/14 09:50 PM
                                                                                                                          x86 versus other platformsDavid Kanter2006/11/15 12:58 AM
                                                                                                                            x86 versus other platformsj2006/11/15 01:57 AM
                                                                                                                          A common problemRob Thorpe2006/11/15 11:56 AM
                                                                                                                            A common problemWilco2006/11/15 01:54 PM
                                                                                                                              A common problemCarlie Coats2006/11/16 06:44 AM
                                                                                                                              A common problemLinus Torvalds2006/11/16 10:03 AM
                                                                                                                      A common problemCarlie Coats2006/11/16 06:38 AM
                                                                                                                        A common problemRob Thorpe2006/11/16 07:29 AM
                                                                                                                    A common problemWilco2006/11/15 02:13 PM
                                                                                                                      A common problemRob Thorpe2006/11/16 09:20 AM
                                                                                                                        A common problemrwessel2006/11/16 04:27 PM
                                                                                                                        A common problemWilco2006/11/17 02:20 PM
                                                                                                                          A common problemRob Thorpe2006/11/20 04:14 AM
                                                                                          You are aiming too lowMichael S2006/11/05 04:19 PM
                                                                                            And you're aiming quite highRob Thorpe2006/11/06 08:00 AM
                                                                                    Language safety in a multithread environmentWilco2006/11/04 11:20 AM
                                                                                      Language safety in a multithread environmentGabriele Svelto2006/11/06 04:10 AM
                                                                                        Language safety in a multithread environmentWilco2006/11/06 10:59 AM
                                                                                          Language safety in a multithread environmentGabriele Svelto2006/11/08 02:47 AM
                                                                                            Language safety in a multithread environmentWilco2006/11/13 05:13 PM
                                                                                              Language safety in a multithread environmentGabriele Svelto2006/11/14 02:15 AM
                                                                                                Language safety in a multithread environmentWilco2006/11/17 02:51 PM
                                                                                    Language safety in a multithread environmentrwessel2006/11/04 10:11 PM
                                                                                  Language safety in a multithread environmentRob Thorpe2006/11/03 09:58 AM
                                                                  Language safety in a multithread environmentbandwidth2006/10/27 06:47 PM
                                                                    Language safety in a multithread environmentLinus Torvalds2006/10/27 07:52 PM
                                                                      Language safety in a multithread environmentLinus Torvalds2006/10/27 08:10 PM
                                                                        Language safety in a multithread environmentbandwidth2006/10/28 03:17 AM
                                                                      Language safety in a multithread environmentbandwidth2006/10/28 03:09 AM
                                                                        Language safety in a multithread environmentLinus Torvalds2006/10/28 09:23 AM
                                                                      Language safety in a multithread environmentGabriele Svelto2006/10/30 03:26 AM
                                                                        Language safety in a multithread environmentRicardo B2006/10/30 06:52 AM
                                                                        Language safety in a multithread environmentJasonB2006/10/30 07:12 AM
                                                                          Language safety in a multithread environmentGabriele Svelto2006/10/30 07:28 AM
                                                                            Language safety in a multithread environmentJasonB2006/10/30 08:32 AM
                                                                              Language safety in a multithread environmentGabriele Svelto2006/10/30 08:48 AM
                                                                                Language safety in a multithread environmentJasonB2006/10/30 09:21 AM
                                                                          Language safety in a multithread environmentRicardo B2006/10/30 07:31 AM
                                                                            Language safety in a multithread environmentGabriele Svelto2006/10/30 07:43 AM
                                                                              Language safety in a multithread environmentRicardo B2006/10/30 07:54 AM
                                                                                Language safety in a multithread environmentGabriele Svelto2006/10/30 08:02 AM
                                                                                  Language safety in a multithread environmentRicardo B2006/10/30 08:12 AM
                                                                                    Language safety in a multithread environmentGabriele Svelto2006/10/30 08:29 AM
                                                                                      Language safety in a multithread environmentRicardo B2006/10/30 08:40 AM
                                                                                Language safety in a multithread environmentdraugaz2006/10/30 12:31 PM
                                                                              Language safety in a multithread environmentLinus Torvalds2006/10/30 10:09 AM
                                                                                Language safety in a multithread environmentGabriele Svelto2006/10/31 02:01 AM
                                                                                  Language safety in a multithread environmentLinus Torvalds2006/10/31 08:59 AM
                                                                    Language safety in a multithread environmentpgerassi2006/10/27 08:00 PM
                                                                      Language safety in a multithread environmentbandwidth2006/10/28 03:25 AM
                                                                        Language safety in a multithread environmentpgerassi2006/10/31 01:32 AM
                                                                      Language safety in a multithread environmentRob Thorpe2006/10/31 06:52 AM
                                                        pythonFoo_2006/10/28 01:51 AM
                                                          pythonTzvetan Mikov2006/10/28 04:55 PM
                                                            pythonFoo_2006/10/29 03:51 AM
                                                          pythonRob Thorpe2006/10/31 05:01 AM
                                        Language safety in a multithread environmentTzvetan Mikov2006/10/24 10:53 AM
                                          Language safety in a multithread environmentRob Thorpe2006/10/25 01:00 AM
                                          Language safety in a multithread environment (Lock-free structures)Ray2006/10/28 11:25 AM
                                            Language safety in a multithread environment (Lock-free structures)Linus Torvalds2006/10/28 11:58 AM
                                              Language safety in a multithread environment (Lock-free structures)Ray2006/10/28 04:47 PM
                                                Language safety in a multithread environment (Lock-free structures)Linus Torvalds2006/10/28 08:02 PM
                                        Language safety in a multithread environmentJuho Snellman2006/10/25 03:59 AM
                                          Language safety in a multithread environmentRob Thorpe2006/10/25 04:38 AM
                                            Language safety in a multithread environmentJuho Snellman2006/10/25 06:38 AM
                                              Language safety in a multithread environmentRob Thorpe2006/10/25 07:06 AM
                                                More on this topicRob Thorpe2006/10/25 08:41 AM
                                                  More on this topicTzvetan Mikov2006/10/25 10:17 AM
                                                    More on this topicRob Thorpe2006/10/26 02:02 AM
                                                Language safety in a multithread environmentJuho Snellman2006/10/25 10:33 AM
                                                  Language safety in a multithread environmentRob Thorpe2006/10/26 01:48 AM
                                      Language safety in a multithread environmentS. Rao2006/10/23 03:40 PM
                                        Language safety in a multithread environmentTzvetan Mikov2006/10/23 11:38 PM
                                        Language safety in a multithread environmentGabriele Svelto2006/10/24 01:02 AM
                                          Language safety in a multithread environmentS. Rao2006/10/24 12:40 PM
                                        Comparison to stack allocationRob Thorpe2006/10/24 03:09 AM
                                          Comparison to stack allocationS. Rao2006/10/24 12:32 PM
                                            Exactly, see my other post (NT)Rob Thorpe2006/10/25 12:53 AM
                          Language safety in a multithread environmentDavid Wragg2006/10/20 02:46 AM
                            Language safety in a multithread environmentTzvetan Mikov2006/10/21 09:24 AM
                          Ugh, evil problemRob Thorpe2006/10/20 03:56 AM
                            Ugh, evil problemGabriele Svelto2006/10/20 04:38 AM
                              Ugh, evil problemRob Thorpe2006/10/20 05:47 AM
                                Ugh, evil problemGabriele Svelto2006/10/20 05:54 AM
                                Ugh, evil problemRicardo B2006/10/20 06:43 AM
                            Ugh, evil problemJasonB2006/10/20 06:17 AM
                              Ugh, evil problemS. Rao2006/10/20 08:09 PM
                                Ugh, evil problemJasonB2006/10/21 07:58 AM
                                SecondedRob Thorpe2006/10/23 01:53 AM
                          Copying GC Rob Thorpe2006/10/23 02:51 AM
                            Copying GC Tzvetan Mikov2006/10/23 11:13 PM
                              Copying GC Rob Thorpe2006/10/24 01:22 AM
              Python + native extensionsFoo_2006/10/18 02:29 PM
                Python + native extensionssp2006/10/19 01:05 AM
  z9 - Power5 connection?foobar2006/10/17 01:15 PM
    z9 - Power5 connection?David Kanter2006/10/17 02:03 PM
      z9 - Power5 connection?foobar2006/10/17 02:33 PM
        z9 - Power5 connection?rwessel2006/10/17 07:39 PM
          z9 - Power5 connection?foobar2006/10/17 08:38 PM
            Sounds like I should edit the article...David Kanter2006/10/17 10:48 PM
            z9 - Power5 connection?Jesper Frimann2006/10/17 11:59 PM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell avocado?