#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send #2251

JacobDomagala · 2024-02-26T21:58:14Z

BuildStats issue - DARMA-tasking/build-stats#31

github-actions · 2024-02-26T22:02:29Z

Pipelines results

PR tests (gcc-12, ubuntu, mpich)

Build for 2fde58d (2024-04-19 13:48:17 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (gcc-12, ubuntu, mpich, verbose)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-9, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-13, alpine, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (gcc-8, ubuntu, mpich, address sanitizer)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-13, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-12, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-11, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (gcc-10, ubuntu, openmpi, no LB)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (gcc-9, ubuntu, mpich, zoltan, json schema test)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (gcc-11, ubuntu, mpich, trace runtime, coverage)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (intel icpx, ubuntu, mpich, verbose)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-14, ubuntu, mpich, verbose)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (clang-10, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

Compilation - successful

Testing - passed

Build log

PR tests (intel icpc, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get full report use -qopt-report=4 -qopt-report-phase ipo
remark #11074: Inlining inhibited by limit max-size 
remark #11074: Inlining inhibited by limit max-total-size 
remark #11076: To get %0D%0A%0D%0A%0D%0A ==> And there is more. Read log. <==

Build log

PR tests (nvidia cuda 11.2, gcc-9, ubuntu, mpich)

Build for 33955ec (2024-05-29 08:18:42 UTC)

/vt/src/vt/pipe/pipe_manager.impl.h(135): warning: missing return statement at end of non-void function "vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&vt::vrt::collection::lb::GreedyLB::collectHandler, Target=vt::objgroup::proxy::ProxyElm<vt::vrt::collection::lb::GreedyLB>]"
          detected during:
            instantiation of "auto vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&vt::vrt::collection::lb::GreedyLB::collectHandler, Target=vt::objgroup::proxy::ProxyElm<vt::vrt::collection::lb::GreedyLB>]" 
/vt/src/vt/objgroup/proxy/proxy_objgroup.impl.h(204): here
            instantiation of "vt::objgroup::proxy::Proxy<ObjT>::PendingSendType vt::objgroup::proxy::Proxy<ObjT>::reduce<f,Op,Target,Args...>(Target, Args &&...) const [with ObjT=vt::vrt::collection::lb::GreedyLB, f=&vt::vrt::collection::lb::GreedyLB::collectHandler, Op=vt::collective::PlusOp, Target=vt::objgroup::proxy::ProxyElm<vt::vrt::collection::lb::GreedyLB>, Args=<vt::vrt::collection::lb::GreedyPayload>]" 
/vt/src/vt/vrt/collection/balance/greedylb/greedylb.cc(222): here

/vt/src/vt/pipe/pipe_manager.impl.h(135): warning: missing return statement at end of non-void function "vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&MyObj::handler, Target=vt::objgroup::proxy::ProxyElm<MyObj>]"
          detected during instantiation of "auto vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&MyObj::handler, Target=vt::objgroup::proxy::ProxyElm<MyObj>]" 
/vt/examples/callback/callback.cc(147): here

/vt/src/vt/pipe/pipe_manager.impl.h(135): warning: missing return statement at end of non-void function "vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&colHan, Target=vt::vrt::collection::VrtElmProxy<MyCol, vt::Index1D>]"
          detected during instantiation of "auto vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&colHan, Target=vt::vrt::collection::VrtElmProxy<MyCol, vt::Index1D>]" 
/vt/examples/callback/callback.cc(153): here

/vt/src/vt/pipe/pipe_manager.impl.h(135): warning: missing return statement at end of non-void function "vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&MyObj::handler, Target=vt::objgroup::proxy::ProxyElm<MyObj>]"
          detected during instantiation of "auto vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&MyObj::handler, Target=vt::objgroup::proxy::ProxyElm<MyObj>]" 
/vt/examples/callback/callback.cc(147): here

/vt/src/vt/pipe/pipe_manager.impl.h(135): warning: missing return statement at end of non-void function "vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&colHan, Target=vt::vrt::collection::VrtElmProxy<MyCol, vt::Index1D>]"
          detected during instantiation of "auto vt::pipe::PipeManager::makeSend<f,Target>(Target) [with f=&colHan, Target=vt::vrt::collection::VrtElmProxy<MyCol, vt::Index1D>]" 
/vt/examples/callback/callback.cc(153%0D%0A%0D%0A%0D%0A ==> And there is more. Read log. <==

Build log

PR tests (nvidia cuda 12.2.0, gcc-9, ubuntu, mpich, verbose)

Build for 33955ec (2024-05-29 08:18:42 UTC)

/vt/lib/CLI/CLI/CLI11.hpp(1029): warning #2361-D: invalid narrowing conversion from "double" to "unsigned long"
          TT { std::declval<CC>() }
               ^
          detected during:
            instantiation of "vt::CLI::detail::is_direct_constructible<T, C>::test [with T=std::vector<std::string, std::allocator<std::string>>, C=double]" based on template arguments <std::vector<std::string, std::allocator<std::string>>, double> at line 1041
            instantiation of class "vt::CLI::detail::is_direct_constructible<T, C> [with T=std::vector<std::string, std::allocator<std::string>>, C=double]" at line 5005
            instantiation of "void vt::CLI::Option::results(T &) const [with T=std::vector<std::string, std::allocator<std::string>>]" at line 5034
            instantiation of "T vt::CLI::Option::as<T>() const [with T=std::vector<std::string, std::allocator<std::string>>]" at line 7315

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

/vt/lib/CLI/CLI/CLI11.hpp(1029): warning #2361-D: invalid narrowing conversion from "int" to "unsigned long"
          TT { std::declval<CC>() }
               ^
          detected during:
            instantiation of "vt::CLI::detail::is_direct_constructible<T, C>::test [with T=std::vector<std::string, std::allocator<std::string>>, C=int]" based on template arguments <std::vector<std::string, std::allocator<std::string>>, int> at line 1041
            instantiation of class "vt::CLI::detail::is_direct_constructible<T, C> [with T=std::vector<std::string, std::allocator<std::string>>, C=int]" at line 5005
            instantiation of "void vt::CLI::Option::results(T &) const [with T=std::vector<std::string, std::allocator<std::string>>]" at line 5034
            instantiation of "T vt::CLI::Option::as<T>() const [with T=std::vector<std::string, std::allocator<std::string>>]" at line 7315

/vt/tests/perf/send_cost.cc(169): warning #177-D: variable "prevNode" was declared but never referenced
    auto const prevNode = (thisNode - 1 + num_nodes_) % num_nodes_;
               ^

Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"

Testing - passed

Build log

JacobDomagala · 2024-04-25T13:06:10Z

With the most recent commit:

Raw MPI

Objgroup send with payload wrapped in `shared_ptr`

Objgroup send with payload as `const&`

JacobDomagala · 2024-05-07T11:26:52Z

tests/perf/send_cost.cc

+
+    StartTimer(fmt::format("Payload size {}", size));
+
+    std::vector<int32_t> recvData(size, data);


This is "inside" timer block to match the allocation on vt's receiving side. I think this is fair.

JacobDomagala · 2024-05-07T11:29:22Z

Raw MPI

ObjGroup send

Collection send

JacobDomagala · 2024-05-07T11:31:27Z

~~Next step would be to update `BuildStats' to plot the results~~ Created DARMA-tasking/build-stats#31

…d::shared_ptr

lifflander · 2024-05-29T18:06:56Z

@JacobDomagala This look good to me!

JacobDomagala self-assigned this Feb 26, 2024

JacobDomagala linked an issue Feb 26, 2024 that may be closed by this pull request

Write benchmark to compare raw MPI send to objgroup send and collection send #2249

Closed

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch 3 times, most recently from 68c939b to 8e435ff Compare February 28, 2024 23:00

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch 3 times, most recently from 2fde58d to 869b5b7 Compare April 23, 2024 16:17

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch from a32f160 to 720784e Compare April 25, 2024 13:06

JacobDomagala marked this pull request as ready for review May 7, 2024 11:25

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch from 720784e to 309c87a Compare May 7, 2024 11:25

JacobDomagala commented May 7, 2024

View reviewed changes

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch from 309c87a to d88ae28 Compare May 7, 2024 11:30

JacobDomagala requested review from lifflander, cz4rs, nmm0, thearusable and nlslatt May 7, 2024 17:04

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch 3 times, most recently from d68673a to 43cf917 Compare May 16, 2024 10:11

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch from 43cf917 to 5511597 Compare May 28, 2024 16:41

JacobDomagala added 4 commits May 29, 2024 10:18

#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send

fb29855

#2249: Add test for collection's send

b98b40d

#2249: Fix runtime failures

4e524f1

#2249: Update Objgroup send perf test

d191408

JacobDomagala added 5 commits May 29, 2024 10:18

#2249: Update Collection send perf test

e6d30fc

#2249: Update ObjGroup send test with message that uses payload as st…

a06166e

…d::shared_ptr

#2249: Use payload as pointer to data to avoid extra allocation cost

e82ca2e

#2249: Fix code quality issue

4563c33

#2249: Disable global timer for send_cost tests and adjust payload sizes

33955ec

JacobDomagala force-pushed the 2249-write-benchmark-to-compare-raw-mpi-send-to-objgroup-send-and-collection-send branch from 5511597 to 33955ec Compare May 29, 2024 08:18

lifflander approved these changes May 29, 2024

View reviewed changes

lifflander merged commit 6617858 into develop May 29, 2024
26 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send #2251

#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send #2251

JacobDomagala commented Feb 26, 2024 •

edited

Loading

github-actions bot commented Feb 26, 2024 •

edited

Loading

JacobDomagala commented Apr 25, 2024

JacobDomagala May 7, 2024

JacobDomagala commented May 7, 2024

JacobDomagala commented May 7, 2024 •

edited

Loading

lifflander commented May 29, 2024


		StartTimer(fmt::format("Payload size {}", size));

		std::vector<int32_t> recvData(size, data);

#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send #2251

#2249: Add perf test for raw MPI Send/Recv and ObjGroup's Send #2251

Conversation

JacobDomagala commented Feb 26, 2024 • edited Loading

github-actions bot commented Feb 26, 2024 • edited Loading

Pipelines results

JacobDomagala commented Apr 25, 2024

Raw MPI

Objgroup send with payload wrapped in shared_ptr

Objgroup send with payload as const&

JacobDomagala May 7, 2024

Choose a reason for hiding this comment

JacobDomagala commented May 7, 2024

Raw MPI

ObjGroup send

Collection send

JacobDomagala commented May 7, 2024 • edited Loading

lifflander commented May 29, 2024

JacobDomagala commented Feb 26, 2024 •

edited

Loading

github-actions bot commented Feb 26, 2024 •

edited

Loading

Objgroup send with payload wrapped in `shared_ptr`

Objgroup send with payload as `const&`

JacobDomagala commented May 7, 2024 •

edited

Loading