Loop Id: 16802 | Module: libgromacs_mpi.so.9.0.0 | Source: bonded.cpp:2072-2087 | Coverage: 0.06% |
---|
Loop Id: 16802 | Module: libgromacs_mpi.so.9.0.0 | Source: bonded.cpp:2072-2087 | Coverage: 0.06% |
---|
0xbc7dd0 LEA (%RSI,%RSI,2),%RSI |
0xbc7dd4 SAL $0x4,%RSI |
0xbc7dd8 VMOVSS (%R15,%RSI,1),%XMM1 [2] |
0xbc7dde VMOVSS 0x4(%R15,%RSI,1),%XMM0 [2] |
0xbc7de5 VCVTSI2SSL 0x8(%R15,%RSI,1),%XMM9,%XMM2 [2] |
0xbc7dec LEA 0x5(%RDX),%ESI |
0xbc7def CMP %R13D,%ESI |
0xbc7df2 CMOVL %ESI,%EDX |
0xbc7df5 VMOVSS %XMM0,0xd40(%RSP,%RCX,1) [3] |
0xbc7dfe VMOVSS %XMM1,0xd80(%RSP,%RCX,1) [3] |
0xbc7e07 VMOVSS %XMM2,0xdc0(%RSP,%RCX,1) [3] |
0xbc7e10 ADD $0x4,%RCX |
0xbc7e14 ADD $0x5,%RAX |
0xbc7e18 CMP $0x40,%RCX |
0xbc7e1c JE bc7610 |
0xbc7e22 MOVSXD %EDX,%RDI |
0xbc7e25 MOVSXD (%R12,%RDI,4),%RSI [1] |
0xbc7e29 MOV 0x4(%R12,%RDI,4),%R8D [1] |
0xbc7e2e MOV %R8D,0xe00(%RSP,%RCX,1) [3] |
0xbc7e36 MOV 0x8(%R12,%RDI,4),%R8D [1] |
0xbc7e3b MOV %R8D,0x100(%RSP,%RCX,1) [3] |
0xbc7e43 MOV 0xc(%R12,%RDI,4),%R8D [1] |
0xbc7e48 MOV %R8D,0xc0(%RSP,%RCX,1) [3] |
0xbc7e50 MOV 0x10(%R12,%RDI,4),%EDI [1] |
0xbc7e55 MOV %EDI,0x80(%RSP,%RCX,1) [3] |
0xbc7e5c VXORPS %XMM0,%XMM0,%XMM0 |
0xbc7e60 CMP %RBX,%RAX |
0xbc7e63 JL bc7dd0 |
0xbc7e69 VXORPS %XMM1,%XMM1,%XMM1 |
0xbc7e6d VXORPS %XMM2,%XMM2,%XMM2 |
0xbc7e71 JMP bc7df5 |
/home/eoseret/gromacs-2024.2/src/gromacs/listed_forces/bonded.cpp: 2072 - 2087 |
-------------------------------------------------------------------------------- |
2072: for (s = 0; s < GMX_SIMD_REAL_WIDTH; s++) |
2073: { |
2074: type = forceatoms[iu]; |
2075: ai[s] = forceatoms[iu + 1]; |
2076: aj[s] = forceatoms[iu + 2]; |
2077: ak[s] = forceatoms[iu + 3]; |
2078: al[s] = forceatoms[iu + 4]; |
2079: |
2080: /* At the end fill the arrays with the last atoms and 0 params */ |
2081: if (i + s * nfa1 < nbonds) |
2082: { |
2083: cp[s] = forceparams[type].pdihs.cpA; |
2084: phi0[s] = forceparams[type].pdihs.phiA; |
2085: mult[s] = forceparams[type].pdihs.mult; |
2086: |
2087: if (iu + nfa1 < nbonds) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►66.80+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | |
►21.62+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
►11.58+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►79.75+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | |
►18.18+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
►2.07+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►77.33+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | |
►22.67+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►96.85+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | |
►3.15+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►79.02+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | |
►12.05+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
►8.48+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 |
---|---|---|---|
►100.00+ | calculateSimpleBond(int, int, [...] | bonded.cpp:4143 | libgromacs_mpi.so.9.0.0 |
○ | (anonymous namespace)::calc_on[...] | listed_forces.cpp:356 | libgromacs_mpi.so.9.0.0 |
○ | .omp_outlined.#0xbe5d40 | listed_forces.cpp:428 | libgromacs_mpi.so.9.0.0 |
○ | __kmp_invoke_microtask | libomp.so | |
○ | __kmp_fork_call | libomp.so | |
○ | __kmpc_fork_call | libomp.so | |
○ | ListedForces::calculate(gmx_wa[...] | listed_forces.cpp:387 | libgromacs_mpi.so.9.0.0 |
○ | do_force(_IO_FILE*, t_commrec [...] | sim_util.cpp:2047 | libgromacs_mpi.so.9.0.0 |
○ | gmx::LegacySimulator::do_md() | md.cpp:1248 | 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 | 2.08 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.82 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.08 |
Bottlenecks | |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source | bonded.cpp:2072-2087 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.50 |
CQA cycles if no scalar integer | 2.17 |
CQA cycles if FP arith vectorized | 4.50 |
CQA cycles if fully vectorized | 0.46 |
Front-end cycles | 4.17 |
P0 cycles | 2.38 |
P1 cycles | 2.38 |
P2 cycles | 2.25 |
P3 cycles | 2.25 |
P4 cycles | 1.25 |
P5 cycles | 4.50 |
P6 cycles | 4.50 |
P7 cycles | 4.50 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.25 |
P11 cycles | 0.25 |
P12 cycles | 1.50 |
P13 cycles | 1.50 |
DIV/SQRT cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 25.50 |
Nb uops | 25.00 |
Nb loads | 6.50 |
Nb stores | 7.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 26.00 |
Bytes stored | 28.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.50 |
Stride indirect | 1.00 |
Vectorization ratio all | 13.13 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 9.32 |
Vector-efficiency ratio load | 7.03 |
Vector-efficiency ratio store | 6.25 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.19 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 10.11 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.04 |
Bottlenecks | P5, P6, P7, |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source | bonded.cpp:2072-2087 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 4.00 |
CQA cycles if fully vectorized | 0.40 |
Front-end cycles | 3.83 |
P0 cycles | 2.00 |
P1 cycles | 2.00 |
P2 cycles | 1.75 |
P3 cycles | 1.75 |
P4 cycles | 1.50 |
P5 cycles | 4.00 |
P6 cycles | 4.00 |
P7 cycles | 4.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 1.50 |
P13 cycles | 1.50 |
DIV/SQRT cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 23.00 |
Nb uops | 23.00 |
Nb loads | 5.00 |
Nb stores | 7.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 20.00 |
Bytes stored | 28.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 20.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 75.00 |
Vector-efficiency ratio all | 10.83 |
Vector-efficiency ratio load | 7.81 |
Vector-efficiency ratio store | 6.25 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 21.88 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.14 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | P5, P6, P7, |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source | bonded.cpp:2072-2087 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.00 |
CQA cycles if no scalar integer | 2.33 |
CQA cycles if FP arith vectorized | 5.00 |
CQA cycles if fully vectorized | 0.52 |
Front-end cycles | 4.50 |
P0 cycles | 2.75 |
P1 cycles | 2.75 |
P2 cycles | 2.75 |
P3 cycles | 2.75 |
P4 cycles | 1.00 |
P5 cycles | 5.00 |
P6 cycles | 5.00 |
P7 cycles | 5.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.50 |
P11 cycles | 0.50 |
P12 cycles | 1.50 |
P13 cycles | 1.50 |
DIV/SQRT cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 28.00 |
Nb uops | 27.00 |
Nb loads | 8.00 |
Nb stores | 7.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
Bytes stored | 28.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 1.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 6.25 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 25.00 |
Vector-efficiency ratio all | 7.81 |
Vector-efficiency ratio load | 6.25 |
Vector-efficiency ratio store | 6.25 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source file and lines | bonded.cpp:2072-2087 |
Module | libgromacs_mpi.so.9.0.0 |
nb instructions | 25.50 |
nb uops | 25 |
loop length | 139.50 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3.50 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.17 cycles |
front end | 4.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.38 | 2.38 | 2.25 | 2.25 | 1.25 | 4.50 | 4.50 | 4.50 | 0.00 | 0.00 | 0.25 | 0.25 | 1.50 | 1.50 |
cycles | 2.38 | 2.38 | 2.25 | 2.25 | 1.25 | 4.50 | 4.50 | 4.50 | 0.00 | 0.00 | 0.25 | 0.25 | 1.50 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 4.17 |
Dispatch | 4.50 |
Data deps. | 2.00 |
Overall L1 | 4.50 |
all | 0% |
load | 0% |
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 | 0% |
all | 33% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 13% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 7% |
load | 7% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 10% |
all | 12% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 9% |
load | 7% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source file and lines | bonded.cpp:2072-2087 |
Module | libgromacs_mpi.so.9.0.0 |
nb instructions | 23 |
nb uops | 23 |
loop length | 126 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.83 cycles |
front end | 3.83 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 1.75 | 1.75 | 1.50 | 4.00 | 4.00 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.50 | 1.50 |
cycles | 2.00 | 2.00 | 1.75 | 1.75 | 1.50 | 4.00 | 4.00 | 4.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.50 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 3.83 |
Dispatch | 4.00 |
Data deps. | 2.00 |
Overall L1 | 4.00 |
all | 0% |
load | 0% |
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 | 0% |
all | 50% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 20% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 7% |
load | 7% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 15% |
load | NA (no load vectorizable/vectorized instructions) |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 10% |
load | 7% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 21% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSS %XMM0,0xd40(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
VMOVSS %XMM1,0xd80(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
VMOVSS %XMM2,0xdc0(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
ADD $0x4,%RCX | 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 $0x5,%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 |
CMP $0x40,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE bc7610 <_ZN12_GLOBAL__N_15pdihsIL18BondedKernelFlavor0EEENSt9enable_ifIXeqT_LS1_0EEfE4typeEiPKiPK9t_iparamsPA3_KfPA4_fPA3_fPK5t_pbcfPfN3gmx8ArrayRefISA_EEP8t_fcdataP12t_disresdataP12t_oriresdataPi+0x350> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOVSXD %EDX,%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 |
MOVSXD (%R12,%RDI,4),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
MOV 0x4(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0xe00(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0x8(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0x100(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0xc(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0xc0(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0x10(%R12,%RDI,4),%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV %EDI,0x80(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
VXORPS %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
CMP %RBX,%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 bc7dd0 <_ZN12_GLOBAL__N_15pdihsIL18BondedKernelFlavor0EEENSt9enable_ifIXeqT_LS1_0EEfE4typeEiPKiPK9t_iparamsPA3_KfPA4_fPA3_fPK5t_pbcfPfN3gmx8ArrayRefISA_EEP8t_fcdataP12t_disresdataP12t_oriresdataPi+0xb10> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
VXORPS %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
VXORPS %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
JMP bc7df5 <_ZN12_GLOBAL__N_15pdihsIL18BondedKernelFlavor0EEENSt9enable_ifIXeqT_LS1_0EEfE4typeEiPKiPK9t_iparamsPA3_KfPA4_fPA3_fPK5t_pbcfPfN3gmx8ArrayRefISA_EEP8t_fcdataP12t_disresdataP12t_oriresdataPi+0xb35> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
Function | std::enable_if<((BondedKernelFlavor)0)==((BondedKernelFlavor)0), float>::type (anonymous namespace)::pdihs<(BondedKernelFlavor)0>(int, int const*, t_iparams const*, float const (*) [3], float (*) [4], float (*) [3], t_pbc const*, float, float*, gmx::ArrayRef |
Source file and lines | bonded.cpp:2072-2087 |
Module | libgromacs_mpi.so.9.0.0 |
nb instructions | 28 |
nb uops | 27 |
loop length | 153 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 2.75 | 2.75 | 1.00 | 5.00 | 5.00 | 5.00 | 0.00 | 0.00 | 0.50 | 0.50 | 1.50 | 1.50 |
cycles | 2.75 | 2.75 | 2.75 | 2.75 | 1.00 | 5.00 | 5.00 | 5.00 | 0.00 | 0.00 | 0.50 | 0.50 | 1.50 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 4.50 |
Dispatch | 5.00 |
Data deps. | 2.00 |
Overall L1 | 5.00 |
all | 0% |
load | 0% |
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 | 0% |
all | 16% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 6% |
load | 0% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 6% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 9% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 7% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA (%RSI,%RSI,2),%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 |
SAL $0x4,%RSI | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
VMOVSS (%R15,%RSI,1),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (6.3%) |
VMOVSS 0x4(%R15,%RSI,1),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | scal (6.3%) |
VCVTSI2SSL 0x8(%R15,%RSI,1),%XMM9,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | scal (6.3%) |
LEA 0x5(%RDX),%ESI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %R13D,%ESI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (6.3%) |
CMOVL %ESI,%EDX | 1 | 0.50 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
VMOVSS %XMM0,0xd40(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
VMOVSS %XMM1,0xd80(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
VMOVSS %XMM2,0xdc0(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 | scal (6.3%) |
ADD $0x4,%RCX | 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 $0x5,%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 |
CMP $0x40,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JE bc7610 <_ZN12_GLOBAL__N_15pdihsIL18BondedKernelFlavor0EEENSt9enable_ifIXeqT_LS1_0EEfE4typeEiPKiPK9t_iparamsPA3_KfPA4_fPA3_fPK5t_pbcfPfN3gmx8ArrayRefISA_EEP8t_fcdataP12t_disresdataP12t_oriresdataPi+0x350> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOVSXD %EDX,%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 |
MOVSXD (%R12,%RDI,4),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
MOV 0x4(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0xe00(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0x8(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0x100(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0xc(%R12,%RDI,4),%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (6.3%) |
MOV %R8D,0xc0(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
MOV 0x10(%R12,%RDI,4),%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV %EDI,0x80(%RSP,%RCX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (6.3%) |
VXORPS %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
CMP %RBX,%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 bc7dd0 <_ZN12_GLOBAL__N_15pdihsIL18BondedKernelFlavor0EEENSt9enable_ifIXeqT_LS1_0EEfE4typeEiPKiPK9t_iparamsPA3_KfPA4_fPA3_fPK5t_pbcfPfN3gmx8ArrayRefISA_EEP8t_fcdataP12t_disresdataP12t_oriresdataPi+0xb10> | 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 | 0.92 | 0.01 | 0.86 | 0.02 | 0.83 | 0.02 | 0.88 | 0.01 | 0.87 | 0.01 | 0.96 | 0 | 0.94 | 0 | 0.7 | 0.02 |
Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
---|---|---|---|---|---|---|
1x1 | 1 | 1 | 1 | 1 | 1.0700000524521 | 0.12835821509361 |
2x1 | 2 | 0.92 | 1.84 | 2 | 0.7150000333786 | 0.12851026654243 |
4x1 | 4 | 0.86 | 3.44 | 4 | 0.43499994277954 | 0.12500751018524 |
8x1 | 8 | 0.83 | 6.61 | 8 | 0.27999994158745 | 0.10466206073761 |
16x1 | 16 | 0.88 | 14.09 | 16 | 0.2049999833107 | 0.091847889125347 |
32x1 | 18 | 0.87 | 27.69 | 32 | 0.16499997675419 | 0.075182303786278 |
64x1 | 34 | 0.96 | 61.48 | 64 | 0.069999985396862 | 0.043787430971861 |
128x1 | 55 | 0.94 | 120.55 | 128 | 0.064999990165234 | 0.052225634455681 |
192x1 | 85 | 0.7 | 135.13 | 192 | 0.065000012516975 | 0.058784272521734 |