A non straw man view of hardware transactional memory

By: anon2 (anon.delete@this.anon.com), March 31, 2021 11:03 pm
Room: Moderated Discussions
Ganon (anon.delete@this.gmail.com) on March 31, 2021 7:52 pm wrote:
> First, TSX is being used by SAP HANA; and here is a more recent
> (2017) paper from SAP folk directly mentioning it:
>
> SAP HANA – The Evolution of an In-Memory DBMS from Pure OLAP Processing Towards Mixed Workloads
>
> "
> As a last optimization HANA uses Intel TSX operations to increase scalability. These
> operations are especially important in the B-tree used for the lookup of value IDs in the delta
> fragment because the delta fragment is accessed both for read operations and also updated concurrently
> by any update operation. In [KDR+14] it is shown that using TSX results in far better scalability
> with the number of concurrent threads. This is especially important on systems with a growing number
> of available cores as we see them already today in deployments of SAP HANA.
> "
>
> The claim that this improvement only shows up in toy benchmarks is false.

This is not saying what you think it says, and Linus is not saying what you think he says either.

Firstly, this HANA paper uses KDR+14 Improving in-memory database index performance with Intel® Transactional Synchronization Extensions as justification for the use of TSX.

That's not to say HANA sees no benefit from TSX in real usage, but there is no evidence of it shown here, so this does not disprove the claim.

Secondly, I don't think Linus would say TSX is worse than everything including clunky 1990s locking. Rather that it has never proven to be competitive against modern parallel techniques.

And that's exactly what KDR+14 benchmarks, is a large data structure in isolation (which itself is very unrealistic of real world), with some well chosen mix of updates and lookups, benchmarking TSX against a naive single exclusive or reader/writer lock.

But that's not what TSX is up against. This has the same smell as those early stupid GPGPU benchmarks that tried to claim 10x, 100x, 1000x performance improvement over CPU despite not even a single component of the GPU having better than 10x advantage over the CPU (FLOPS, memory bandwidth, etc), and many things being worse (BW and latency to system memory, instruction latencies, branches, performance per thread etc). Most of their speedups came because they completely rewrote the algorithms for vectorization and parallelism for the GPU and did not re-test the modern baseline on the CPU.

The modern baseline for a central highly contended b-tree is using RCU (or similar) for persistence guarantees and fine grained (per node) sequence counters for validity/atomicity of lookup vs updates, and fine grained locking pushed down to the lowest common nodes to protect updates from one another (or possibly for simplicity a global lock for rebalancing and leaf-node locks for non-rebalancing updates, but b-trees are quite amenable to have fine graned rebalance operations because splits and joins frequency drops by an order of magnitude or two as you move up levels, if parameters are chosen correctly.

So now what the naive TSX implementation is up against is something with zero atomic operations on the lookup-side, compared with what is quite a heavy transaction begin/end in Intel implementations. So TSX is slower right out of the gate, which is a big problem (in theory you would think an implementation might be able to make it almost zero cost, although complexity and cost is obviously then hidden in the microarchitecture).

And what's more the modern implementation doesn't all come crashing down in a heap as soon as one processor aborts because it collided with an update or took a slightly different apth that used a few more cache lines, or took an interrupt. When you have to take the fallback and the fallback path taking the lock causes all other threads to abort their transactions and get stuck in the fallback path and everything falls off the cliff. So then you need to fix your fallback path, at which point you find it works better than TSX anyway.

Nothing against the early discoverers and proponents of transactional memory, it is a awesome idea and lock elision is very very clever and cool. And for the software environment they were working with in the 90s it may have actually been a good solution.

Modern parallel software techniques have killed it though.

>
>
> In fact in
> https://static.sched.com/hosted_files/bkk19/3c/BKK19-202_New-Technologies-in-Arm-Architecture.pdf
> ARM mentions
>
> "Improved competitiveness with other architectures that support HTM."
>
> as a reason for introducing TME; how can anyone interpret this to mean anything less
> than this being a blocker for large clients using Intel RTM/HLE from adopting ARM?

This means it does not have the checkbox and others do.

And it's not to say nothing can possibly ever use it, HANA for example probably has pretty crufty fragile implementations of things and if they can avoid redesigning their core data structures for a while longer (or they put all their effort into unfortunately redesigning it for TM rather than a more general scalable technique and don't want to change it again) then good. But that's a very small niche and shrinking.

>
>
> Second, regarding the straw man characterization that transactional memory was supposed
> to solve all concurrent programming challenges;

I didn't see anybody arguing against such a strawman.

> don't think anybody sane actually believed
> that.

I certainly have heard avcoates who thought it would solve practically all data structure parallel access/update problems.

> Hardware transaction memory is merely meant to simplify things under a limited set
> of conditions (compared to doing lock-free, hierarchical/striped locking, etc etc):
>
> - You are transacting over no more than a small number of (say - You specifically designed the data structure and access patterns
> with transactional memory and this cache line limit in mind
> - You are targeting a controlled and known in advance system
> environment (no need for non-transactional code paths)
>
> There is enough value provided through code simplifications even in this
> restricted environment to keep hardware transactional memory around.

There is not a very significant body of evidence to support that.

I would say though that I have less confidence in Intel's implementations of such things particularly looking at what Apple have done with M1 atomic operations, so it's entirely possible a really good design team could come up with an implementation that's significantly better and opens up a more significant niche of legacy code that could benefit from it.
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
Armv9 officially announcedJon Masters2021/03/30 11:41 AM
  Armv9 officially announcedGabriele Svelto2021/03/30 01:27 PM
    HTM and TLEFoo_2021/03/30 01:31 PM
      HTM and TLEdmcq2021/03/30 03:03 PM
      Intel RTM and HLE is a successGanon2021/03/30 05:22 PM
        Intel RTM and HLE is a success (is it?)Foo_2021/03/31 01:16 AM
          Intel RTM and HLE was an abject failureanonymou52021/03/31 03:04 AM
          Intel RTM and HLE is a success (is it?)Andrey2021/03/31 05:27 AM
            Intel RTM and HLE is a success (is it?)Foo_2021/03/31 05:58 AM
              Intel RTM and HLE is a success (is it?)Andrey2021/03/31 07:45 AM
                Intel RTM and HLE is a success (is it?)Foo_2021/03/31 09:32 AM
                  Intel RTM and HLE is a success (is it?)Andrey2021/03/31 09:57 AM
                    Intel RTM and HLE is a success (is it?)anonymou52021/03/31 10:39 AM
                      ^ feel free to delete this one -- broken HTML there (NT)anonymou52021/03/31 10:40 AM
                      Intel RTM and HLE is a success (is it?)Andrey2021/03/31 10:47 AM
                    Intel RTM and HLE is a success (is it?)anonymou52021/03/31 10:40 AM
                Intel RTM and HLE is a success (is it?)Ganon2021/03/31 09:58 AM
                  Intel RTM and HLE is a success (is it?)anonymou52021/03/31 10:42 AM
                  Intel RTM and HLE is a success (is it?)Linus Torvalds2021/03/31 11:54 AM
                    Intel RTM and HLE is a success (is it?)Linus Torvalds2021/03/31 12:00 PM
                      Any idea about IBM?Mark Roulo2021/03/31 12:15 PM
                        Any idea about IBM?Linus Torvalds2021/03/31 12:37 PM
                          Any idea about IBM?dmcq2021/03/31 03:04 PM
                            Any idea about IBM?Linus Torvalds2021/03/31 04:44 PM
                              A non straw man view of hardware transactional memoryGanon2021/03/31 07:52 PM
                                A non straw man view of hardware transactional memoryanon22021/03/31 11:03 PM
                                  A non straw man view of hardware transactional memoryCarson2021/04/02 01:11 AM
                                    A non straw man view of hardware transactional memoryanon22021/04/02 05:28 AM
                              IBM zArch TM - guaranteed progressDavid Kanter2021/03/31 08:37 PM
                              Any idea about IBM?Andrey2021/03/31 11:31 PM
                                Any idea about IBM?Linus Torvalds2021/04/01 10:54 AM
                                  Any idea about IBM?Andrey2021/04/02 12:50 PM
                        Any idea about IBM?someone2021/04/01 12:02 AM
                      Intel RTM and HLE is a success (is it?)anon22021/03/31 03:46 PM
                        Intel RTM and HLE is a success (is it?)Linus Torvalds2021/03/31 05:08 PM
                          Leaving it to software is tricky!David Kanter2021/03/31 08:41 PM
                            And a hardware predicttor needs access to fallback timingCarson2021/04/01 11:13 PM
                              Hardware fallback pathAnon2021/04/02 10:51 AM
                              And a hardware predicttor needs access to fallback timingLinus Torvalds2021/04/03 10:41 AM
                                And a hardware predicttor needs access to fallback timingLinus Torvalds2021/04/03 11:11 AM
                                  And a hardware predicttor needs access to fallback timingsr2021/04/03 11:30 AM
                                    And a hardware predicttor needs access to fallback timingLinus Torvalds2021/04/03 12:14 PM
                                      And a hardware predicttor needs access to fallback timingsr2021/04/03 12:39 PM
                                        And a hardware predicttor needs access to fallback timingAnon2021/04/03 02:08 PM
                                          And a hardware predicttor needs access to fallback timingsr2021/04/03 02:33 PM
                                            And a hardware predicttor needs access to fallback timingdmcq2021/04/04 05:35 AM
                                        And a hardware predicttor needs access to fallback timingLinus Torvalds2021/04/03 02:22 PM
                                          Transactional memory isn't exclusive to lockingsr2021/04/04 12:17 AM
                                            Transactional memory isn't exclusive to lockingAspect of Anonimity2021/04/04 03:49 AM
                                            Transactional memory isn't exclusive to lockingAndrey2021/04/04 04:58 AM
                                              Transactional memory isn't exclusive to lockingsr2021/04/04 10:10 AM
                                                Transactional memory isn't exclusive to lockingAndrey2021/04/04 10:33 AM
                                                  Transactional memory isn't exclusive to lockingsr2021/04/05 02:41 AM
                                      And a hardware predicttor needs access to fallback timingGeertB2021/04/04 07:08 PM
                            Leaving it to software is tricky!Andrey2021/04/02 03:00 PM
                          Intel RTM and HLE is a success (is it?)@never_released2021/04/01 08:21 AM
                            Intel RTM and HLE is a success (is it?)@never_released2021/04/01 08:30 AM
                            Intel RTM and HLE is a success (is it?)Linus Torvalds2021/04/01 10:00 AM
                              Intel RTM and HLE is a success (is it?)dmcq2021/04/01 10:35 AM
                                Intel RTM and HLE is a success (is it?)Linus Torvalds2021/04/01 10:59 AM
                                  Is HTM actually in ARMv9?dncq2021/04/01 11:26 AM
                                    Is HTM actually in ARMv9?Linus Torvalds2021/04/01 12:13 PM
                              Intel RTM and HLE is a success (is it?)Jörn Engel2021/04/01 09:15 PM
                          Intel RTM and HLE is a success (is it?)---2021/04/02 10:00 AM
                      Intel RTM and HLE is a success (is it?)Jon Masters2021/04/01 10:56 AM
                        RockMichael S2021/04/01 12:29 PM
            Intel RTM and HLE is a success (is it?)Linus Torvalds2021/03/31 11:50 AM
              Intel RTM and HLE is a success (is it?)anon22021/03/31 03:57 PM
                Intel RTM and HLE is a success (is it?)anon32021/03/31 04:09 PM
          Intel RTM and HLE is a success (is it?)someone2021/03/31 11:56 PM
            Intel RTM and HLE is a success (is it?)someone2021/04/01 12:21 AM
              Intel RTM and HLE is a success (is it?)none2021/04/01 04:31 AM
                Intel RTM and HLE is a success (is it?)anonymou52021/04/01 09:24 AM
                  Intel RTM and HLE is a success (is it?)anony2021/04/01 10:26 AM
                  Intel RTM and HLE is a success (is it?)none2021/04/01 11:20 AM
                Intel RTM and HLE is a success (is it?)Brendan2021/04/01 05:23 PM
                  Intel RTM and HLE is a success (is it?)Adrian2021/04/02 01:03 AM
      Transactional memory similarity to garbage collectionPaul A. Clayton2021/04/05 01:53 PM
        Maybe notMark Roulo2021/04/05 03:07 PM
        Transactional memory similarity to garbage collectionAnon2021/04/05 03:14 PM
        No conflict between theory and practiceAspect of Anonimity2021/04/05 07:57 PM
          No conflict between theory and practiceNoSpammer2021/04/05 09:38 PM
            No conflict between theory and practicedmcq2021/04/06 07:05 AM
              No conflict between theory and practicesr2021/04/06 09:22 AM
                No conflict between theory and practiceBen LaHaise2021/04/06 03:43 PM
                  No conflict between theory and practicesr2021/04/07 09:42 AM
                    No conflict between theory and practiceAnon2021/04/07 10:06 AM
                    No conflict between theory and practiceLinus Torvalds2021/04/07 10:35 AM
                      No conflict between theory and practicesr2021/04/07 12:34 PM
                        If HTM were well implemented, nobody would complain (NT)Anon2021/04/07 12:54 PM
                          If HTM were well implemented, nobody would complaindmcq2021/04/07 03:36 PM
                            If HTM were well implemented, nobody would complainAnon2021/04/07 04:04 PM
                          If HTM were well implemented, nobody would complain---2021/04/08 09:37 AM
                        No conflict between theory and practiceLinus Torvalds2021/04/07 01:20 PM
                          No conflict between theory and practiceAndrey2021/04/07 02:32 PM
                            No conflict between theory and practicedmcq2021/04/07 03:32 PM
                              No conflict between theory and practiceanonymou52021/04/07 04:26 PM
                              No conflict between theory and practiceAndrey2021/04/07 05:54 PM
                                No conflict between theory and practiceLinus Torvalds2021/04/08 08:41 AM
                                  No conflict between theory and practiceAndrey2021/04/08 09:12 AM
                                  No conflict between theory and practiceRobert Williams2021/04/08 09:15 AM
                                    No conflict between theory and practiceLinus Torvalds2021/04/08 09:56 AM
                                      No conflict between theory and practiceRobert Williams2021/04/08 07:50 PM
                                        No conflict between theory and practiceLinus Torvalds2021/04/09 09:25 AM
                                          TSX for all?Robert Williams2021/04/09 12:46 PM
                                            It helps adoption when developers can run the code an their machines.Mark Roulo2021/04/09 12:54 PM
                                              It helps adoption when developers can run the code an their machines.me2021/04/09 02:21 PM
                                                It helps adoption when developers can run the code an their machines.Andrey2021/04/10 07:08 AM
                                                  It helps adoption when developers can run the code an their machines.me2021/04/10 12:43 PM
                                                    It helps adoption when developers can run the code an their machines.Robert Williams2021/04/10 07:05 PM
                                                      It helps adoption when developers can run the code an their machines.Andrey2021/04/11 01:42 AM
                                                        It helps adoption when developers can run the code an their machines.Michael S2021/04/11 04:23 AM
                                              It helps adoption when developers can run the code an their machines.Robert Williams2021/04/10 08:24 AM
                                                It helps adoption when developers can run the code an their machines.Andrey2021/04/10 10:36 AM
                                                  It helps adoption when developers can run the code an their machines.Michael S2021/04/10 10:58 AM
                                                    It helps adoption when developers can run the code an their machines.Robert Williams2021/04/10 11:42 AM
                                                    It helps adoption when developers can run the code an their machines.Brendan2021/04/10 11:27 PM
                                                      It helps adoption when developers can run the code an their machines.Michael S2021/04/11 03:34 AM
                                                        It helps adoption when developers can run the code an their machines.Brendan2021/04/11 04:18 PM
                                            TSX for all?wumpus2021/04/09 01:10 PM
                                            TSX for all?Linus Torvalds2021/04/09 03:03 PM
                                              [CLICK BAIT?] Torvalds to recommend arm64!anonymous22021/04/09 03:17 PM
                                              TSX for all?Linus Torvalds2021/04/09 03:22 PM
                                                amen! (NT)anonymou52021/04/09 05:42 PM
                                            TSX for all?Emil Briggs2021/04/10 05:52 AM
                                              TSX for all?Michael S2021/04/10 11:13 AM
                                                TSX for all?Brendan2021/04/10 11:05 PM
                                          No conflict between theory and practiceanonymouse2021/04/09 03:02 PM
                            No conflict between theory and practiceLinus Torvalds2021/04/07 05:12 PM
                              No conflict between theory and practiceAndrey2021/04/07 05:33 PM
                                No conflict between theory and practiceanon22021/04/07 08:12 PM
                                  No conflict between theory and practiceAndrey2021/04/08 12:29 AM
                                    No conflict between theory and practiceAnon2021/04/08 12:50 AM
                                    No conflict between theory and practiceanon22021/04/08 12:52 AM
                                      No conflict between theory and practiceAndrey2021/04/08 02:41 AM
                                        No conflict between theory and practiceAdrian2021/04/08 03:09 AM
                                          No conflict between theory and practiceAndrey2021/04/08 03:50 AM
                                            No conflict between theory and practiceAdrian2021/04/08 05:07 AM
                                            No conflict between theory and practiceanon22021/04/08 05:18 AM
                                              No conflict between theory and practiceAndrey2021/04/08 08:18 AM
                                                No conflict between theory and practiceanon22021/04/08 09:11 AM
                                                  No conflict between theory and practiceAndrey2021/04/08 09:48 AM
                                                    No conflict between theory and practiceanon22021/04/08 04:10 PM
                                            No conflict between theory and practice---2021/04/08 08:30 PM
                                              No conflict between theory and practicedmcq2021/04/09 02:25 AM
                                                No conflict between theory and practiceLinus Torvalds2021/04/09 09:44 AM
                                        No conflict between theory and practiceanon22021/04/08 04:09 AM
                                          No conflict between theory and practicesr2021/04/10 01:22 AM
                                            No conflict between theory and practiceAnon2021/04/10 04:00 AM
                                              No conflict between theory and practiceEtienne Lorrain2021/04/12 12:56 AM
                                                No conflict between theory and practiceAnon2021/04/12 01:54 AM
                                                  No conflict between theory and practicedmcq2021/04/12 01:44 PM
                              No conflict between theory and practiceGabriele Svelto2021/04/08 01:03 AM
                                No conflict between theory and practicedmcq2021/04/12 01:53 PM
                                  No conflict between theory and practicedmcq2021/04/14 04:50 AM
                      transactional memory = memory lock/unlocksr2021/04/10 12:56 AM
                        transactional memory = memory lock/unlockAnon2021/04/10 04:05 AM
                    No conflict between theory and practiceanon22021/04/07 05:19 PM
                No conflict between theory and practicedmcq2021/04/07 01:16 PM
            No conflict between theory and practiceAnon2021/04/06 10:46 AM
            No conflict between theory and practiceAspect of Anonimity2021/04/06 02:16 PM
              No conflict between theory and practiceNoSpammer2021/04/10 12:02 AM
                No conflict between theory and practicesr2021/04/10 01:47 AM
                No conflict between theory and practiceAspect of Anonimity2021/04/10 11:30 PM
                  No conflict between theory and practiceAndrey2021/04/11 05:05 AM
                    HmAspect of Anonimity2021/04/12 07:29 PM
                      Special internal SRAM to store Mutex?Etienne Lorrain2021/04/13 01:01 AM
                        Special internal SRAM to store Mutex?Anon2021/04/13 01:26 AM
                        Special internal SRAM to store Mutex?Linus Torvalds2021/04/13 09:53 AM
                        Special internal SRAM to store Mutex?Dan Fay2021/04/13 12:03 PM
                          Special internal SRAM to store Mutex?Ben LaHaise2021/04/13 03:32 PM
                          Special internal SRAM to store Mutex?Gabriele Svelto2021/04/13 11:43 PM
                        Special internal SRAM to store Mutex?Carson2021/04/13 10:19 PM
          No conflict between theory and practicesr2021/04/06 07:12 AM
            No conflict between theory and practiceAnon2021/04/06 10:43 AM
            No conflict between theory and practiceAspect of Anonimity2021/04/06 03:20 PM
              No conflict between theory and practicesr2021/04/07 10:09 AM
                No conflict between theory and practiceanon22021/04/07 08:53 PM
  Armv9 officially announceddmcq2021/03/30 03:28 PM
    Totally backwads logic on compatibilityHeikki Kultala2021/03/30 03:44 PM
      Totally backwads logic on compatibilityDoug S2021/03/31 12:09 PM
        Totally backwads logic on compatibilitydmcq2021/03/31 03:15 PM
  Armv9 officially announcedv92021/04/12 03:57 PM
    Armv9 officially announcedj2021/04/13 05:07 AM
      Armv9 officially announcedDoug S2021/04/13 10:21 AM
        Armv9 officially announcedanonymou52021/04/13 11:06 AM
          Armv9 officially announcedDoug S2021/04/13 01:01 PM
        Armv9 officially announceddmcq2021/04/13 03:20 PM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell avocado?