| Loop Id: 674 | Module: libqmcwfs.so | Source: TwoBodyJastrowRef.h:107-132 [...] | Coverage: 0.02% |
|---|
| Loop Id: 674 | Module: libqmcwfs.so | Source: TwoBodyJastrowRef.h:107-132 [...] | Coverage: 0.02% |
|---|
0x3c780 VXORPD %XMM1,%XMM1,%XMM1 |
0x3c784 VMOVSD -0x40(%RBP),%XMM0 |
0x3c789 VSUBSD %XMM1,%XMM0,%XMM0 |
0x3c78d CALL 4efe0 <@plt_start@+0x640> |
0x3c792 MOV -0x38(%RBP),%RCX |
0x3c796 MOV -0x48(%RBP),%RBX |
0x3c79a MOV (%RCX),%RAX |
0x3c79d VMOVSD %XMM0,(%RAX,%RBX,8) |
0x3c7a2 INC %RBX |
0x3c7a5 MOV 0x8(%RCX),%RCX |
0x3c7a9 SUB %RAX,%RCX |
0x3c7ac SAR $0x3,%RCX |
0x3c7b0 CMP %RBX,%RCX |
0x3c7b3 MOV -0x30(%RBP),%RCX |
0x3c7b7 JBE 3c896 |
0x3c7bd CMPB $0,0x298(%RCX) |
0x3c7c4 JE 3c8a5 |
0x3c7ca MOVSXD 0x2a0(%RCX),%R12 |
0x3c7d1 MOV 0xd8(%R15),%RAX |
0x3c7d8 MOV 0x248(%R15),%ESI |
0x3c7df MOV 0x290(%RCX),%R14 |
0x3c7e6 MOV %RCX,%RDI |
0x3c7e9 VMOVSD (%RAX,%R12,8),%XMM0 |
0x3c7ef VMOVSD %XMM0,-0x40(%RBP) |
0x3c7f4 CALL 4ed60 <@plt_start@+0x3c0> |
0x3c7f9 MOV 0xa0(%R15),%RCX |
0x3c800 MOV %RBX,-0x48(%RBP) |
0x3c804 TEST %RCX,%RCX |
0x3c807 JE 3c780 |
0x3c80d MOV 0x48(%RAX),%RAX |
0x3c811 LEA (%RBX,%RBX,4),%RDX |
0x3c815 VXORPS %XMM1,%XMM1,%XMM1 |
0x3c819 MOV 0x18(%RAX,%RDX,8),%RAX |
0x3c81e MOV %RAX,-0x50(%RBP) |
0x3c822 MOV 0x18(%R14),%RAX |
0x3c826 IMUL (%RAX,%R12,4),%ECX |
0x3c82b XOR %EAX,%EAX |
0x3c82d MOVSXD %ECX,%RBX |
0x3c830 SAL $0x3,%RBX |
0x3c834 NOPW %CS:(%RAX,%RAX,1) |
(675) 0x3c840 MOV 0x200(%R15),%RCX |
(675) 0x3c847 MOV 0x268(%R14),%R8 |
(675) 0x3c84e MOV 0x1d0(%R15),%R9 |
(675) 0x3c855 VMOVSD %XMM1,-0x58(%RBP) |
(675) 0x3c85a LEA 0x1(%RAX),%R13 |
(675) 0x3c85e MOV %R12D,%ESI |
(675) 0x3c861 ADD %RBX,%RCX |
(675) 0x3c864 MOV (%RCX,%RAX,8),%RDI |
(675) 0x3c868 MOV 0x18(%R8),%RCX |
(675) 0x3c86c MOV -0x50(%RBP),%R8 |
(675) 0x3c870 MOV (%RCX,%RAX,4),%EDX |
(675) 0x3c873 MOV 0x4(%RCX,%RAX,4),%ECX |
(675) 0x3c877 CALL 30ac0 <_ZNK11qmcplusplus14BsplineFunctorIdE9evaluateVEiiiPKdPd> |
(675) 0x3c87c VMOVSD -0x58(%RBP),%XMM1 |
(675) 0x3c881 MOV %R13,%RAX |
(675) 0x3c884 VADDSD %XMM1,%XMM0,%XMM1 |
(675) 0x3c888 CMP %R13,0xa0(%R15) |
(675) 0x3c88f JA 3c840 |
0x3c891 JMP 3c784 |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/optional: 433 - 950 |
-------------------------------------------------------------------------------- |
433: { return static_cast<const _Dp*>(this)->_M_payload._M_engaged; } |
[...] |
950: if (this->_M_is_engaged()) |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 313 - 316 |
-------------------------------------------------------------------------------- |
313: inline int first(int igroup) const { return (*group_offsets_)[igroup]; } |
314: |
315: ///return the last index of a group i |
316: inline int last(int igroup) const { return (*group_offsets_)[igroup + 1]; } |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 229 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
[...] |
229: return X[i]; |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/shared_ptr_base.h: 1296 - 1296 |
-------------------------------------------------------------------------------- |
1296: { return _M_ptr; } |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 919 - 1169 |
-------------------------------------------------------------------------------- |
919: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
[...] |
1046: return *(this->_M_impl._M_start + __n); |
[...] |
1169: { return _M_data_ptr(this->_M_impl._M_start); } |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h: 338 - 338 |
-------------------------------------------------------------------------------- |
338: { return *_M_data; } |
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 132 |
-------------------------------------------------------------------------------- |
107: for (int k = 0; k < ratios.size(); ++k) |
108: ratios[k] = std::exp(Uat[VP.refPtcl] - computeU(VP.getRefPS(), VP.refPtcl, VP.getDistTableAB(myTableID).getDistRow(k).data())); |
[...] |
126: const int igt = P.GroupID[iat] * NumGroups; |
127: for (int jg = 0; jg < NumGroups; ++jg) |
128: { |
129: const FuncType& f2(*F[igt + jg]); |
130: int iStart = P.first(jg); |
131: int iEnd = P.last(jg); |
132: curUat += f2.evaluateV(iat, iStart, iEnd, dist, DistCompressed.data()); |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.28 |
| CQA speedup if FP arith vectorized | 1.90 |
| CQA speedup if fully vectorized | 5.38 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.15 |
| Bottlenecks | |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source | optional:433-433,optional:950-950,OhmmsVector.h:229-229,stl_vector.h:919-919,stl_vector.h:1046-1046,refwrap.h:338-338,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.83 |
| CQA cycles if no scalar integer | 3.00 |
| CQA cycles if FP arith vectorized | 3.60 |
| CQA cycles if fully vectorized | 1.27 |
| Front-end cycles | 5.92 |
| DIV/SQRT cycles | 3.00 |
| P0 cycles | 2.75 |
| P1 cycles | 2.75 |
| P2 cycles | 2.75 |
| P3 cycles | 2.75 |
| P4 cycles | 6.83 |
| P5 cycles | 6.83 |
| P6 cycles | 6.83 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.50 |
| P10 cycles | 0.50 |
| P11 cycles | 1.00 |
| P12 cycles | 1.00 |
| P13 cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 34.50 |
| Nb uops | 35.50 |
| Nb loads | 15.00 |
| Nb stores | 3.50 |
| Nb stack references | 4.50 |
| FLOP/cycle | 0.15 |
| Nb FLOP add-sub | 1.00 |
| 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 | 19.13 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 103.00 |
| Bytes stored | 28.00 |
| Stride 0 | 2.50 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 5.50 |
| Stride indirect | 0.50 |
| Vectorization ratio all | 8.33 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 25.00 |
| Vector-efficiency ratio all | 12.11 |
| Vector-efficiency ratio load | 8.63 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.89 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.56 |
| CQA speedup if FP arith vectorized | 2.02 |
| CQA speedup if fully vectorized | 5.33 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.12 |
| Bottlenecks | P5, P6, P7, |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source | optional:433-433,optional:950-950,OhmmsVector.h:229-229,stl_vector.h:919-919,stl_vector.h:1046-1046,refwrap.h:338-338,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 7.67 |
| CQA cycles if no scalar integer | 3.00 |
| CQA cycles if FP arith vectorized | 3.79 |
| CQA cycles if fully vectorized | 1.44 |
| Front-end cycles | 6.83 |
| DIV/SQRT cycles | 3.50 |
| P0 cycles | 3.50 |
| P1 cycles | 3.50 |
| P2 cycles | 3.50 |
| P3 cycles | 3.00 |
| P4 cycles | 7.67 |
| P5 cycles | 7.67 |
| P6 cycles | 7.67 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.50 |
| P10 cycles | 0.50 |
| P11 cycles | 1.00 |
| P12 cycles | 1.00 |
| P13 cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 40.00 |
| Nb uops | 41.00 |
| Nb loads | 17.00 |
| Nb stores | 4.00 |
| Nb stack references | 5.00 |
| FLOP/cycle | 0.13 |
| Nb FLOP add-sub | 1.00 |
| 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 | 19.43 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 117.00 |
| Bytes stored | 32.00 |
| Stride 0 | 3.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 8.00 |
| Stride indirect | 1.00 |
| Vectorization ratio all | 8.33 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 25.00 |
| Vector-efficiency ratio all | 12.11 |
| Vector-efficiency ratio load | 8.20 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.89 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.00 |
| CQA speedup if FP arith vectorized | 1.76 |
| CQA speedup if fully vectorized | 5.43 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.20 |
| Bottlenecks | P5, P6, P7, |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source | optional:433-433,optional:950-950,OhmmsVector.h:229-229,stl_vector.h:919-919,stl_vector.h:1046-1046,refwrap.h:338-338,TwoBodyJastrowRef.h:107-108,TwoBodyJastrowRef.h:126-127 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.00 |
| CQA cycles if no scalar integer | 3.00 |
| CQA cycles if FP arith vectorized | 3.42 |
| CQA cycles if fully vectorized | 1.10 |
| Front-end cycles | 5.00 |
| DIV/SQRT cycles | 2.50 |
| P0 cycles | 2.00 |
| P1 cycles | 2.00 |
| P2 cycles | 2.00 |
| P3 cycles | 2.50 |
| P4 cycles | 6.00 |
| P5 cycles | 6.00 |
| P6 cycles | 6.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.50 |
| P10 cycles | 0.50 |
| P11 cycles | 1.00 |
| P12 cycles | 1.00 |
| P13 cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 29.00 |
| Nb uops | 30.00 |
| Nb loads | 13.00 |
| Nb stores | 3.00 |
| Nb stack references | 4.00 |
| FLOP/cycle | 0.17 |
| Nb FLOP add-sub | 1.00 |
| 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 | 18.83 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 89.00 |
| Bytes stored | 24.00 |
| Stride 0 | 2.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 3.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 8.33 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 25.00 |
| Vector-efficiency ratio all | 12.11 |
| Vector-efficiency ratio load | 9.06 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.89 |
| Path / |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source file and lines | TwoBodyJastrowRef.h:107-132 |
| Module | libqmcwfs.so |
 |
| nb instructions | 34.50 |
| nb uops | 35.50 |
| loop length | 167 |
| used x86 registers | 9.50 |
| used mmx registers | 0 |
| used xmm registers | 2 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 4.50 |
| micro-operation queue | 5.92 cycles |
| front end | 5.92 cycles |
| ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.00 | 2.75 | 2.75 | 2.75 | 2.75 | 6.83 | 6.83 | 6.83 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| cycles | 3.00 | 2.75 | 2.75 | 2.75 | 2.75 | 6.83 | 6.83 | 6.83 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 5.92 |
| Dispatch | 6.83 |
| Data deps. | 0.00 |
| Overall L1 | 6.83 |
| 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 | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 8% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 9% |
| load | 5% |
| 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 | 8% |
| all | 14% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 12% |
| load | 8% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source file and lines | TwoBodyJastrowRef.h:107-132 |
| Module | libqmcwfs.so |
|
| nb instructions | 40 |
| nb uops | 41 |
| loop length | 193 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 2 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 5 |
| micro-operation queue | 6.83 cycles |
| front end | 6.83 cycles |
| ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.50 | 3.50 | 3.50 | 3.50 | 3.00 | 7.67 | 7.67 | 7.67 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| cycles | 3.50 | 3.50 | 3.50 | 3.50 | 3.00 | 7.67 | 7.67 | 7.67 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 6.83 |
| Dispatch | 7.67 |
| Data deps. | 0.00 |
| Overall L1 | 7.67 |
| 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 | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 8% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 9% |
| load | 3% |
| 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 | 8% |
| all | 14% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 12% |
| load | 8% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSD -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VSUBSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
| CALL 4efe0 <@plt_start@+0x640> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV -0x48(%RBP),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV (%RCX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| VMOVSD %XMM0,(%RAX,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
| INC %RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MOV 0x8(%RCX),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| SUB %RAX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SAR $0x3,%RCX | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| CMP %RBX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| JBE 3c896 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x146> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
| CMPB $0,0x298(%RCX) | 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 |
| JE 3c8a5 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x155> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
| MOVSXD 0x2a0(%RCX),%R12 | 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 |
| MOV 0xd8(%R15),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV 0x248(%R15),%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV 0x290(%RCX),%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VMOVSD (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VMOVSD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
| CALL 4ed60 <@plt_start@+0x3c0> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV 0xa0(%R15),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV %RBX,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| TEST %RCX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| JE 3c780 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x30> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
| MOV 0x48(%RAX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| LEA (%RBX,%RBX,4),%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| VXORPS %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| MOV 0x18(%RAX,%RDX,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV %RAX,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| MOV 0x18(%R14),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| IMUL (%RAX,%R12,4),%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOVSXD %ECX,%RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SAL $0x3,%RBX | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 |
| JMP 3c784 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x34> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE |
| Source file and lines | TwoBodyJastrowRef.h:107-132 |
| Module | libqmcwfs.so |
|
| nb instructions | 29 |
| nb uops | 30 |
| loop length | 141 |
| used x86 registers | 9 |
| used mmx registers | 0 |
| used xmm registers | 2 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 4 |
| micro-operation queue | 5.00 cycles |
| front end | 5.00 cycles |
| ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 2.50 | 2.00 | 2.00 | 2.00 | 2.50 | 6.00 | 6.00 | 6.00 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| cycles | 2.50 | 2.00 | 2.00 | 2.00 | 2.50 | 6.00 | 6.00 | 6.00 | 0.00 | 0.00 | 0.50 | 0.50 | 1.00 | 1.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 5.00 |
| Dispatch | 6.00 |
| Data deps. | 0.00 |
| Overall L1 | 6.00 |
| 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 | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 8% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 9% |
| load | 6% |
| 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 | 8% |
| all | 14% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 12% |
| load | 9% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VMOVSD -0x40(%RBP),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VSUBSD %XMM1,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
| CALL 4efe0 <@plt_start@+0x640> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV -0x48(%RBP),%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV (%RCX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| VMOVSD %XMM0,(%RAX,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
| INC %RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MOV 0x8(%RCX),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| SUB %RAX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| SAR $0x3,%RCX | 1 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| CMP %RBX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| JBE 3c896 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x146> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
| CMPB $0,0x298(%RCX) | 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 |
| JE 3c8a5 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x155> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
| MOVSXD 0x2a0(%RCX),%R12 | 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 |
| MOV 0xd8(%R15),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV 0x248(%R15),%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV 0x290(%RCX),%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VMOVSD (%RAX,%R12,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VMOVSD %XMM0,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 1 | 1 |
| CALL 4ed60 <@plt_start@+0x3c0> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV 0xa0(%R15),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
| MOV %RBX,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| TEST %RCX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| JE 3c780 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x30> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |