| Loop Id: 924 | Module: exec | Source: MultiBsplineRef.hpp:276-286 | Coverage: 0.19% |
|---|
| Loop Id: 924 | Module: exec | Source: MultiBsplineRef.hpp:276-286 | Coverage: 0.19% |
|---|
0x441290 VMULPD (%RBX,%RDI,8),%YMM8,%YMM9 [9] |
0x441295 VMOVUPD %YMM9,(%RBX,%RDI,8) [9] |
0x44129a VMULPD (%R8,%RDI,8),%YMM7,%YMM9 [1] |
0x4412a0 VMOVUPD %YMM9,(%R8,%RDI,8) [1] |
0x4412a6 VMULPD (%R10,%RDI,8),%YMM6,%YMM9 [3] |
0x4412ac VMOVUPD %YMM9,(%R10,%RDI,8) [3] |
0x4412b2 VMULPD (%R13,%RDI,8),%YMM5,%YMM9 [5] |
0x4412b9 VMOVUPD %YMM9,(%R13,%RDI,8) [5] |
0x4412c0 VMULPD (%RDX,%RDI,8),%YMM4,%YMM9 [6] |
0x4412c5 VMOVUPD %YMM9,(%RDX,%RDI,8) [6] |
0x4412ca VMULPD (%RCX,%RDI,8),%YMM3,%YMM9 [8] |
0x4412cf VMOVUPD %YMM9,(%RCX,%RDI,8) [8] |
0x4412d4 VMULPD (%RSI,%RDI,8),%YMM2,%YMM9 [2] |
0x4412d9 VMOVUPD %YMM9,(%RSI,%RDI,8) [2] |
0x4412de VMULPD (%R11,%RDI,8),%YMM1,%YMM9 [4] |
0x4412e4 VMOVUPD %YMM9,(%R11,%RDI,8) [4] |
0x4412ea VMULPD (%RAX,%RDI,8),%YMM0,%YMM9 [7] |
0x4412ef VMOVUPD %YMM9,(%RAX,%RDI,8) [7] |
0x4412f4 ADD $0x4,%RDI |
0x4412f8 CMP %R9,%RDI |
0x4412fb JL 441290 |
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 276 - 286 |
-------------------------------------------------------------------------------- |
276: for (int n = 0; n < num_splines; n++) |
277: { |
278: gx[n] *= dxInv; |
279: gy[n] *= dyInv; |
280: gz[n] *= dzInv; |
281: hxx[n] *= dxx; |
282: hyy[n] *= dyy; |
283: hzz[n] *= dzz; |
284: hxy[n] *= dxy; |
285: hxz[n] *= dxz; |
286: hyz[n] *= dyz; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►83.98+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:100 | exec |
| ○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:196 | exec |
| ○ | main.extracted.107 | refwrap.h:338 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so | |
| ►8.53+ | qmcplusplus::SPOSet::evaluate_[...] | OhmmsVector.h:144 | exec |
| ○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:263 | exec |
| ○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:238 | exec |
| ○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:171 | exec |
| ○ | main.extracted.112 | miniqmc.cpp:397 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so | |
| ►7.48+ | qmcplusplus::SPOSet::evaluate_[...] | OhmmsVector.h:144 | exec |
| ○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:263 | exec |
| ○ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:238 | exec |
| ○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:170 | exec |
| ○ | main.extracted.112 | miniqmc.cpp:397 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.07 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.07 |
| Bottlenecks | micro-operation queue, |
| Function | miniqmcreference::einspline_spo_ref |
| Source | MultiBsplineRef.hpp:276-286 |
| 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 | 4.83 |
| CQA cycles if no scalar integer | 4.83 |
| CQA cycles if FP arith vectorized | 4.50 |
| CQA cycles if fully vectorized | 2.42 |
| Front-end cycles | 4.83 |
| P0 cycles | 4.50 |
| P1 cycles | 4.50 |
| P2 cycles | 3.00 |
| P3 cycles | 3.00 |
| P4 cycles | 4.50 |
| P5 cycles | 0.00 |
| P6 cycles | 1.00 |
| P7 cycles | 4.50 |
| P8 cycles | 4.50 |
| P9 cycles | 4.50 |
| P10 cycles | 0.00 |
| P11 cycles | 3.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 21.00 |
| Nb uops | 20.00 |
| Nb loads | 9.00 |
| Nb stores | 9.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.45 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 36.00 |
| 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 | 119.17 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 288.00 |
| Stride 0 | 0.00 |
| Stride 1 | 9.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | 50.00 |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.07 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.07 |
| Bottlenecks | micro-operation queue, |
| Function | miniqmcreference::einspline_spo_ref |
| Source | MultiBsplineRef.hpp:276-286 |
| 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 | 4.83 |
| CQA cycles if no scalar integer | 4.83 |
| CQA cycles if FP arith vectorized | 4.50 |
| CQA cycles if fully vectorized | 2.42 |
| Front-end cycles | 4.83 |
| P0 cycles | 4.50 |
| P1 cycles | 4.50 |
| P2 cycles | 3.00 |
| P3 cycles | 3.00 |
| P4 cycles | 4.50 |
| P5 cycles | 0.00 |
| P6 cycles | 1.00 |
| P7 cycles | 4.50 |
| P8 cycles | 4.50 |
| P9 cycles | 4.50 |
| P10 cycles | 0.00 |
| P11 cycles | 3.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 21.00 |
| Nb uops | 20.00 |
| Nb loads | 9.00 |
| Nb stores | 9.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.45 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 36.00 |
| 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 | 119.17 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 288.00 |
| Stride 0 | 0.00 |
| Stride 1 | 9.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | 50.00 |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | miniqmcreference::einspline_spo_ref |
| Source file and lines | MultiBsplineRef.hpp:276-286 |
| Module | exec |
 |
 |
| nb instructions | 21 |
| nb uops | 20 |
| loop length | 109 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 4.83 cycles |
| front end | 4.83 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.50 | 4.50 | 3.00 | 3.00 | 4.50 | 0.00 | 1.00 | 4.50 | 4.50 | 4.50 | 0.00 | 3.00 |
| cycles | 4.50 | 4.50 | 3.00 | 3.00 | 4.50 | 0.00 | 1.00 | 4.50 | 4.50 | 4.50 | 0.00 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 4.83 |
| Dispatch | 4.50 |
| Data deps. | 1.00 |
| Overall L1 | 4.83 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | 50% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMULPD (%RBX,%RDI,8),%YMM8,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RBX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R8,%RDI,8),%YMM7,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R8,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R10,%RDI,8),%YMM6,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R10,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R13,%RDI,8),%YMM5,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R13,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RDX,%RDI,8),%YMM4,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RDX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RCX,%RDI,8),%YMM3,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RCX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RSI,%RDI,8),%YMM2,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R11,%RDI,8),%YMM1,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R11,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RAX,%RDI,8),%YMM0,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| ADD $0x4,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %R9,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JL 441290 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0xfd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| Function | miniqmcreference::einspline_spo_ref |
| Source file and lines | MultiBsplineRef.hpp:276-286 |
| Module | exec |
|
|
| nb instructions | 21 |
| nb uops | 20 |
| loop length | 109 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 4.83 cycles |
| front end | 4.83 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.50 | 4.50 | 3.00 | 3.00 | 4.50 | 0.00 | 1.00 | 4.50 | 4.50 | 4.50 | 0.00 | 3.00 |
| cycles | 4.50 | 4.50 | 3.00 | 3.00 | 4.50 | 0.00 | 1.00 | 4.50 | 4.50 | 4.50 | 0.00 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 4.83 |
| Dispatch | 4.50 |
| Data deps. | 1.00 |
| Overall L1 | 4.83 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | 50% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMULPD (%RBX,%RDI,8),%YMM8,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RBX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R8,%RDI,8),%YMM7,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R8,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R10,%RDI,8),%YMM6,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R10,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R13,%RDI,8),%YMM5,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R13,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RDX,%RDI,8),%YMM4,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RDX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RCX,%RDI,8),%YMM3,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RCX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RSI,%RDI,8),%YMM2,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RSI,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%R11,%RDI,8),%YMM1,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%R11,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| VMULPD (%RAX,%RDI,8),%YMM0,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (50.0%) |
| VMOVUPD %YMM9,(%RAX,%RDI,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 | vect (50.0%) |
| ADD $0x4,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %R9,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JL 441290 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEERNS6_INS2_10TinyVectorIdLj3EEESaISB_EEES9_+0xfd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |