Loop Id: 15415 | Module: libgromacs_mpi.so.9.0.0 | Source: update.cpp:498-501 [...] | Coverage: 0.03% |
---|
Loop Id: 15415 | Module: libgromacs_mpi.so.9.0.0 | Source: update.cpp:498-501 [...] | Coverage: 0.03% |
---|
0xb36b20 VMOVAPS (%R10,%RAX,4),%ZMM1 [4] |
0xb36b27 VMOVAPS -0x7b56b1(%RIP),%ZMM2 [6] |
0xb36b31 VPERMPS %ZMM1,%ZMM2,%ZMM2 |
0xb36b37 VMOVAPS -0x7b5681(%RIP),%ZMM3 [6] |
0xb36b41 VPERMPS %ZMM1,%ZMM3,%ZMM3 |
0xb36b47 VMOVAPS -0x7b5651(%RIP),%ZMM4 [6] |
0xb36b51 VPERMPS %ZMM1,%ZMM4,%ZMM1 |
0xb36b57 MOV 0x30(%RSP),%RDI [7] |
0xb36b5c VMULPS -0x80(%RDI,%RDX,1),%ZMM2,%ZMM2 [5] |
0xb36b64 MOV 0x28(%RSP),%RSI [7] |
0xb36b69 VFMADD213PS -0x80(%RSI,%RDX,1),%ZMM0,%ZMM2 [3] |
0xb36b71 VMULPS -0x40(%RDI,%RDX,1),%ZMM3,%ZMM3 [5] |
0xb36b79 VFMADD213PS -0x40(%RSI,%RDX,1),%ZMM0,%ZMM3 [3] |
0xb36b81 VMULPS (%RDI,%RDX,1),%ZMM1,%ZMM1 [5] |
0xb36b88 VFMADD213PS (%RSI,%RDX,1),%ZMM0,%ZMM1 [3] |
0xb36b8f VMOVAPS %ZMM2,-0x80(%RSI,%RDX,1) [3] |
0xb36b97 VMOVAPS %ZMM3,-0x40(%RSI,%RDX,1) [3] |
0xb36b9f VMOVAPS %ZMM1,(%RSI,%RDX,1) [3] |
0xb36ba6 MOV 0x18(%RSP),%R8 [7] |
0xb36bab VFMADD213PS -0x80(%R8,%RDX,1),%ZMM0,%ZMM2 [1] |
0xb36bb3 VFMADD213PS -0x40(%R8,%RDX,1),%ZMM0,%ZMM3 [1] |
0xb36bbb VFMADD213PS (%R8,%RDX,1),%ZMM0,%ZMM1 [1] |
0xb36bc2 MOV 0x20(%RSP),%R9 [7] |
0xb36bc7 VMOVAPS %ZMM2,-0x80(%R9,%RDX,1) [2] |
0xb36bcf VMOVAPS %ZMM3,-0x40(%R9,%RDX,1) [2] |
0xb36bd7 VMOVAPS %ZMM1,(%R9,%RDX,1) [2] |
0xb36bde ADD $0x10,%RAX |
0xb36be2 ADD $0xc0,%R9 |
0xb36be9 MOV %R9,0x20(%RSP) [7] |
0xb36bee ADD $0xc0,%R8 |
0xb36bf5 MOV %R8,0x18(%RSP) [7] |
0xb36bfa ADD $0xc0,%RDI |
0xb36c01 MOV %RDI,0x30(%RSP) [7] |
0xb36c06 ADD $0xc0,%RSI |
0xb36c0d MOV %RSI,0x28(%RSP) [7] |
0xb36c12 CMP %RCX,%RAX |
0xb36c15 JL b36b20 |
/home/eoseret/gromacs-2024.2/src/gromacs/mdlib/update.cpp: 498 - 501 |
-------------------------------------------------------------------------------- |
498: for (int a = start; a < nrend; a += UpdateSimdTraits::width) |
499: { |
500: UpdateSimdReal invMass0, invMass1, invMass2; |
501: expandScalarsToTriplets(load<UpdateSimdReal>(invMass.data() + a), &invMass0, &invMass1, &invMass2); |
/home/eoseret/gromacs-2024.2/src/gromacs/simd/include/gromacs/simd/impl_x86_avx_512/impl_x86_avx_512_util_float.h: 316 - 320 |
-------------------------------------------------------------------------------- |
316: triplets0->simdInternal_ = _mm512_permutexvar_ps( |
317: _mm512_set_epi32(5, 4, 4, 4, 3, 3, 3, 2, 2, 2, 1, 1, 1, 0, 0, 0), scalar.simdInternal_); |
318: triplets1->simdInternal_ = _mm512_permutexvar_ps( |
319: _mm512_set_epi32(10, 10, 9, 9, 9, 8, 8, 8, 7, 7, 7, 6, 6, 6, 5, 5), scalar.simdInternal_); |
320: triplets2->simdInternal_ = _mm512_permutexvar_ps( |
/home/eoseret/gromacs-2024.2/src/gromacs/simd/include/gromacs/simd/impl_x86_avx_512/impl_x86_avx_512_simd_float.h: 109 - 202 |
-------------------------------------------------------------------------------- |
109: _mm512_store_ps(m, a.simdInternal_); |
[...] |
197: return { _mm512_mul_ps(a.simdInternal_, b.simdInternal_) }; |
198: } |
199: |
200: static inline SimdFloat gmx_simdcall fma(SimdFloat a, SimdFloat b, SimdFloat c) |
201: { |
202: return { _mm512_fmadd_ps(a.simdInternal_, b.simdInternal_, c.simdInternal_) }; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►80.57+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 | |
►9.97+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
►9.46+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►82.79+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 | |
►11.62+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
►5.59+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►77.68+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 | |
►18.46+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
►3.86+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►96.64+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 | |
►3.36+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►83.33+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 | |
►10.34+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
►4.60+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
►1.72+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | gmx::Update::Impl::update_coor[...] | update.cpp:1888 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Update::update_coords(t_i[...] | update.cpp:239 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1642 | libgromacs_mpi.so.9.0.0 |
○ | gmx::Mdrunner::mdrunner() | runner.cpp:2311 | libgromacs_mpi.so.9.0.0 |
○ | gmx::gmx_mdrun(int, gmx_hw_inf[...] | mdrun.cpp:280 | gmx_mpi |
○ | gmx::gmx_mdrun(int, char**) | mdrun.cpp:82 | gmx_mpi |
○ | gmx::CommandLineModuleManager:[...] | cmdlinemodulemanager.cpp:569 | libgromacs_mpi.so.9.0.0 |
○ | main | gmx.cpp:58 | gmx_mpi |
○ | __libc_start_call_main | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.11 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.10 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | P5, P6, P7, |
Function | .omp_outlined..70 |
Source | update.cpp:498-501,impl_x86_avx_512_util_float.h:316-320,impl_x86_avx_512_simd_float.h:109-109,impl_x86_avx_512_simd_float.h:197-202 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 13.33 |
CQA cycles if no scalar integer | 12.00 |
CQA cycles if FP arith vectorized | 13.33 |
CQA cycles if fully vectorized | 12.17 |
Front-end cycles | 7.00 |
P0 cycles | 1.50 |
P1 cycles | 1.50 |
P2 cycles | 1.25 |
P3 cycles | 1.25 |
P4 cycles | 0.50 |
P5 cycles | 13.33 |
P6 cycles | 13.33 |
P7 cycles | 13.33 |
P8 cycles | 12.00 |
P9 cycles | 9.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
P12 cycles | 6.00 |
P13 cycles | 6.00 |
DIV/SQRT cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 37.00 |
Nb uops | 42.00 |
Nb loads | 17.00 |
Nb stores | 10.00 |
Nb stack references | 4.00 |
FLOP/cycle | 18.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 48.00 |
Nb FLOP fma | 96.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 96.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 864.00 |
Bytes stored | 416.00 |
Stride 0 | 2.00 |
Stride 1 | 5.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 84.62 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 60.00 |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 86.54 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | 65.00 |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 100.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.11 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.10 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | P5, P6, P7, |
Function | .omp_outlined..70 |
Source | update.cpp:498-501,impl_x86_avx_512_util_float.h:316-320,impl_x86_avx_512_simd_float.h:109-109,impl_x86_avx_512_simd_float.h:197-202 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 13.33 |
CQA cycles if no scalar integer | 12.00 |
CQA cycles if FP arith vectorized | 13.33 |
CQA cycles if fully vectorized | 12.17 |
Front-end cycles | 7.00 |
P0 cycles | 1.50 |
P1 cycles | 1.50 |
P2 cycles | 1.25 |
P3 cycles | 1.25 |
P4 cycles | 0.50 |
P5 cycles | 13.33 |
P6 cycles | 13.33 |
P7 cycles | 13.33 |
P8 cycles | 12.00 |
P9 cycles | 9.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
P12 cycles | 6.00 |
P13 cycles | 6.00 |
DIV/SQRT cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 37.00 |
Nb uops | 42.00 |
Nb loads | 17.00 |
Nb stores | 10.00 |
Nb stack references | 4.00 |
FLOP/cycle | 18.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 48.00 |
Nb FLOP fma | 96.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 96.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 864.00 |
Bytes stored | 416.00 |
Stride 0 | 2.00 |
Stride 1 | 5.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 84.62 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 60.00 |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 86.54 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | 65.00 |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 100.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 100.00 |
Path / |
Function | .omp_outlined..70 |
Source file and lines | update.cpp:498-501 |
Module | libgromacs_mpi.so.9.0.0 |
nb instructions | 37 |
nb uops | 42 |
loop length | 251 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 5 |
nb stack references | 4 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 1.25 | 1.25 | 0.50 | 9.00 | 9.00 | 9.00 | 6.00 | 6.00 | 3.00 | 0.00 | 6.00 | 6.00 |
cycles | 1.50 | 1.50 | 1.25 | 1.25 | 0.50 | 13.33 | 13.33 | 13.33 | 12.00 | 9.00 | 3.00 | 0.00 | 6.00 | 6.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
Front-end | 7.00 |
Dispatch | 13.33 |
Data deps. | 1.00 |
Overall L1 | 13.33 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 84% |
load | 100% |
store | 60% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 86% |
load | 100% |
store | 65% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVAPS (%R10,%RAX,4),%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VMOVAPS -0x7b56b1(%RIP),%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM2,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
VMOVAPS -0x7b5681(%RIP),%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
VMOVAPS -0x7b5651(%RIP),%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM4,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
MOV 0x30(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMULPS -0x80(%RDI,%RDX,1),%ZMM2,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
MOV 0x28(%RSP),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VFMADD213PS -0x80(%RSI,%RDX,1),%ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMULPS -0x40(%RDI,%RDX,1),%ZMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VFMADD213PS -0x40(%RSI,%RDX,1),%ZMM0,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMULPS (%RDI,%RDX,1),%ZMM1,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VFMADD213PS (%RSI,%RDX,1),%ZMM0,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMOVAPS %ZMM2,-0x80(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM3,-0x40(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM1,(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
MOV 0x18(%RSP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VFMADD213PS -0x80(%R8,%RDX,1),%ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VFMADD213PS -0x40(%R8,%RDX,1),%ZMM0,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VFMADD213PS (%R8,%RDX,1),%ZMM0,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
MOV 0x20(%RSP),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVAPS %ZMM2,-0x80(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM3,-0x40(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM1,(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD $0xc0,%R9 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %R9,0x20(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%R8 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %R8,0x18(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RDI,0x30(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RSI,0x28(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JL b36b20 <.omp_outlined..70+0x3260> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
Function | .omp_outlined..70 |
Source file and lines | update.cpp:498-501 |
Module | libgromacs_mpi.so.9.0.0 |
nb instructions | 37 |
nb uops | 42 |
loop length | 251 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 5 |
nb stack references | 4 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.50 | 1.25 | 1.25 | 0.50 | 9.00 | 9.00 | 9.00 | 6.00 | 6.00 | 3.00 | 0.00 | 6.00 | 6.00 |
cycles | 1.50 | 1.50 | 1.25 | 1.25 | 0.50 | 13.33 | 13.33 | 13.33 | 12.00 | 9.00 | 3.00 | 0.00 | 6.00 | 6.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
Front-end | 7.00 |
Dispatch | 13.33 |
Data deps. | 1.00 |
Overall L1 | 13.33 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 84% |
load | 100% |
store | 60% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 86% |
load | 100% |
store | 65% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVAPS (%R10,%RAX,4),%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VMOVAPS -0x7b56b1(%RIP),%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM2,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
VMOVAPS -0x7b5681(%RIP),%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
VMOVAPS -0x7b5651(%RIP),%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VPERMPS %ZMM1,%ZMM4,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 5 | 1 | vect (100.0%) |
MOV 0x30(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMULPS -0x80(%RDI,%RDX,1),%ZMM2,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
MOV 0x28(%RSP),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VFMADD213PS -0x80(%RSI,%RDX,1),%ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMULPS -0x40(%RDI,%RDX,1),%ZMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VFMADD213PS -0x40(%RSI,%RDX,1),%ZMM0,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMULPS (%RDI,%RDX,1),%ZMM1,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
VFMADD213PS (%RSI,%RDX,1),%ZMM0,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VMOVAPS %ZMM2,-0x80(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM3,-0x40(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM1,(%RSI,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
MOV 0x18(%RSP),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VFMADD213PS -0x80(%R8,%RDX,1),%ZMM0,%ZMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VFMADD213PS -0x40(%R8,%RDX,1),%ZMM0,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
VFMADD213PS (%R8,%RDX,1),%ZMM0,%ZMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 1 | vect (100.0%) |
MOV 0x20(%RSP),%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
VMOVAPS %ZMM2,-0x80(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM3,-0x40(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
VMOVAPS %ZMM1,(%R9,%RDX,1) | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 1 | 1 | 5 | 2 | vect (100.0%) |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
ADD $0xc0,%R9 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %R9,0x20(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%R8 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %R8,0x18(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%RDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RDI,0x30(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
ADD $0xc0,%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
MOV %RSI,0x28(%RSP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JL b36b20 <.omp_outlined..70+0x3260> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
Run 1x1 | Number processes: 1Number processes per node: 1OMP_NUM_THREADS: 1 |
---|---|
Run 2x1 | Number processes: 2Number processes per node: 2OMP_NUM_THREADS: 1 |
Run 4x1 | Number processes: 4Number processes per node: 4OMP_NUM_THREADS: 1 |
Run 8x1 | Number processes: 8Number processes per node: 8OMP_NUM_THREADS: 1 |
Run 16x1 | Number processes: 16Number processes per node: 16OMP_NUM_THREADS: 1 |
Run 32x1 | Number processes: 32Number processes per node: 32OMP_NUM_THREADS: 1 |
Run 64x1 | Number processes: 64Number processes per node: 64OMP_NUM_THREADS: 1 |
Run 128x1 | Number processes: 128Number processes per node: 128OMP_NUM_THREADS: 1 |
Run 192x1 | Number processes: 192Number nodes: 1Number processes per node: 192Run Command: <executable> mdrun -s ion_channel.tpr -nsteps 10000 -pin on -deffnm aoccMPI Command: mpirun -genv I_MPI_FABRICS=shm -n <number_processes>Dataset: Run Directory: .OMP_NUM_THREADS: 1 |
(1x1) Efficiency | (1x1) Potential Speed-Up (%) | (2x1) Efficiency | (2x1) Potential Speed-Up (%) | (4x1) Efficiency | (4x1) Potential Speed-Up (%) | (8x1) Efficiency | (8x1) Potential Speed-Up (%) | (16x1) Efficiency | (16x1) Potential Speed-Up (%) | (32x1) Efficiency | (32x1) Potential Speed-Up (%) | (64x1) Efficiency | (64x1) Potential Speed-Up (%) | (128x1) Efficiency | (128x1) Potential Speed-Up (%) | (192x1) Efficiency | (192x1) Potential Speed-Up (%) |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 0 | 0.68 | 0.08 | 0.36 | 0.26 | 0.3 | 0.28 | 0.44 | 0.15 | 1.28 | 0 | 1.99 | 0 | 1.69 | 0 | 1.87 | 0 |
Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
---|---|---|---|---|---|---|
1x1 | 1 | 1 | 1 | 1 | 1.4899996519089 | 0.17874176800251 |
2x1 | 2 | 0.68 | 1.36 | 2 | 1.1299999952316 | 0.24157938361168 |
4x1 | 4 | 0.36 | 1.45 | 4 | 1.1399999856949 | 0.41118076443672 |
8x1 | 8 | 0.3 | 2.42 | 8 | 0.74499994516373 | 0.39722812175751 |
16x1 | 16 | 0.44 | 6.98 | 16 | 0.27999994158745 | 0.25808727741241 |
32x1 | 20 | 1.28 | 40.88 | 32 | 0.08500000089407 | 0.070920720696449 |
64x1 | 38 | 1.99 | 127.56 | 64 | 0.050000004470348 | 0.029388876631856 |
128x1 | 73 | 1.69 | 216.11 | 128 | 0.034999992698431 | 0.040567979216576 |
192x1 | 86 | 1.87 | 358.48 | 192 | 0.024999996647239 | 0.030857361853123 |