similar to: debug_rnglists status

Hi Victor, The work Wolfgang is doing should get us to the "minimum syntactically correct DWARF v5" stage, which we really wanted to have for LLVM 7.0. That is, once we have .debug_rnglists and .debug_loclists done, you can ask for DWARF 5 and get something that conforms to the spec. However, it won't conform if you ask for type units (I'm working on that) or split DWARF. If

tl;dr: in DWARFv5, using DW_AT_ranges even when the range is contiguous reduces linked, uncompressed debug_addr size for optimized builds by 93% and reduces total .o file size (with compression and split) by 15%. It does grow .dwo file size a bit - DWARFv5, no compression, not split shows the net effect if all bytes are equal: -O3 clang binary grows by 0.4%, -O0 clang binary shrinks by 0.1% Should

David, could you please clarify on which code did you gain 10% improvement? I have run numerous tests with and w/o this option and it looks like it has no effect on performance (I am talking of the old 2016 sample to be concrete). Maybe we could investigate it together? Just tell me where to start? On 02/07/2018 02:11 AM, Xinliang David Li wrote: > Victor, thanks for the experiment. > >

Hello everyone, LLVM buildmasters (both main and staging) will be restarted in 2 hours (~3:00 AM PDT). -- Best Regards, Victor Leschuk | Software Engineer |Access Softek

Hello all, clang-related PGO documentation recommends using PGO with -O2 (for example: https://clang.llvm.org/docs/UsersManual.html#profile-guided-optimization). The question is: is there any reason why exactly -O2 is used in examples? Are there any factors which can cause problems when using PGO with -O3? Thanks in advance for your advice! -- Best Regards, Victor Leschuk | Software Engineer

Victor, please file a bug tracking the issue. We can put relevant information there including test cases used in the experiment etc. thanks, David On Wed, Feb 7, 2018 at 2:15 PM, Victor Leschuk <vleschuk at accesssoftek.com> wrote: > David, could you please clarify on which code did you gain 10% > improvement? I have run numerous tests with and w/o this option and it > looks

Hello David, thanks for detailed response! Do you have any tests that you use to measure the PGO effectiveness? I have tested clang version 6.0 with the same sample that Jie Chen used in 2016 and actually both frontend-based PGO and IR-based make code run slower, see the average time: clang++ -O3: 3.15 sec  clang++ -O3 and -fprofile-instr-use: 3.160 sec clang++ -O3 and -fprofile-use: 3.180 sec

Maybe we should update the documentation to state this directly? Currently its a little bit confusing. On 01/29/2018 05:51 AM, Xinliang David Li wrote: > It means using PGO with -O2 and above (including -O3). > > David > > On Sun, Jan 28, 2018 at 6:48 PM, Victor Leschuk via llvm-dev > <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> wrote: > >

Hello David! I have recently started acquaintance with PGO in LLVM/clang and found your e-mail thread: http://lists.llvm.org/pipermail/llvm-dev/2016-May/099395.html . Here you posted a nice list of optimizations that use profiling and of those which could be using but don't. However that thread is about 2 years old. Could you please kindly let me know if there were any significant changes in

Victor, thanks for the experiment. My suspicion is it is due to the remaining issues with block layout -- especially with loop rotation (with PGO). Another problem is that tail dup is not happening after loop rotation which can limit the effectiveness of loop rotation. I tried the internal option -mllvm -force-precise-rotation-cost and there is about 10% speedup with -fprofile-use. This option

It means using PGO with -O2 and above (including -O3). David On Sun, Jan 28, 2018 at 6:48 PM, Victor Leschuk via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Hello all, > > clang-related PGO documentation recommends using PGO with -O2 (for > example: > https://clang.llvm.org/docs/UsersManual.html#profile-guided-optimization). > The question is: is there any reason why

On Sun, Feb 4, 2018 at 9:59 PM, Victor Leschuk <vleschuk at accesssoftek.com> wrote: > Hello David! > > I have recently started acquaintance with PGO in LLVM/clang and found > your e-mail thread: > http://lists.llvm.org/pipermail/llvm-dev/2016-May/099395.html . Here you > posted a nice list of optimizations that use profiling and of those > which could be using but

On some previous occasion that introduced additional indirection (don't remember the details) my debugger people groused about the additional performance cost of chasing down data in a different object-file section. So we (Sony) might be happier with low_pc as expressions, than with a ranges-always solution. But hard to say without data, and getting both modes in at least as a temporary

24.09.2019 8:26, Rui Ueyama пишет: > Hi Alexey, > > Thank you for sharing this proposal. Reducing the size of debug info > is generally a good thing, and I believe you'd see more debug info > size reduction in Rust programs than in C++ programs, because I heard > that the Rust compiler driver passes a lot of object files to the > linker, expecting that the linker would

Hello Adrian, sorry for the delay with the response. Somehow I missed your message.. On 09/13/2016 12:43 AM, Adrian Prantl wrote: >> On Sep 10, 2016, at 12:50 PM, Victor Leschuk via llvm-dev <llvm-dev at lists.llvm.org> wrote: >> >> Hello all, >> >> I am currently implementing support for DWARFv5 DW_AT_alignment attr and I got a question about align field in

Hello David and all involved =) On 02/05/2018 09:38 AM, Xinliang David Li wrote: > ThinLTO also works well with PGO. Could you please let me know if there are any problems which prevent using PGO with FullLTO? Thanks in advance! -- Best Regards, Victor Leschuk | Software Engineer | Access Softek

On Wed, Jun 3, 2020 at 6:34 AM Robinson, Paul <paul.robinson at sony.com> wrote: > > DWARF was designed in an era when COMDAT and ICF were not a thing, or at least not common, certainly not when talking about function code. The overhead of a unit occurred only once per translation unit, so that expense was reasonably amortized. > > > > Splitting functions into their own

Hello all, I am currently implementing support for DWARFv5 DW_AT_alignment attr and I got a question about align field in debug info section of IR/Bitcode. Currently it is being dumped almost in any case, however according to code we use align from DI* objects only when dealing with class/structure bitfields: DwarfUnit::constructMemberDIE. Dumping align information everywhere only for 1 case

On Thu, Jun 4, 2020 at 8:27 AM Robinson, Paul <paul.robinson at sony.com> wrote: > > > > > -----Original Message----- > > From: David Blaikie <dblaikie at gmail.com> > > Sent: Wednesday, June 3, 2020 5:31 PM > > To: Robinson, Paul <paul.robinson at sony.com> > > Cc: jh7370.2008 at my.bristol.ac.uk; llvm-dev at lists.llvm.org > >

I don't totally follow the proposed encoding change & would appreciate a small example. Is the idea to replace e.g. an 'AT_low_pc (<direct address>) + relocation for <direct address>' with an 'AT_low_pc (<indirection into a pool of addresses> + offset)', s.t. the cost of a relocation for the address is paid down the more it's used? How do you figure