| Loop Id: 66 | Module: exec | Source: initAtoms.c:221-228 | Coverage: 0.02% |
|---|
| Loop Id: 66 | Module: exec | Source: initAtoms.c:221-228 | Coverage: 0.02% |
|---|
0x40ac50 VPBROADCASTQ %RDX,%ZMM18 |
0x40ac56 VPADDQ %ZMM18,%ZMM17,%ZMM18 |
0x40ac5c VPSLLQ $0x3,%ZMM18,%ZMM19 |
0x40ac63 VPSLLQ $0x4,%ZMM18,%ZMM18 |
0x40ac6a VPADDQ %ZMM19,%ZMM18,%ZMM18 |
0x40ac70 KXNORW %K0,%K0,%K1 |
0x40ac74 VPXORD %XMM19,%XMM19,%XMM19 |
0x40ac7a VGATHERQPD (%R11,%ZMM18,1),%ZMM19{%K1} [1] |
0x40ac81 KXNORW %K0,%K0,%K1 |
0x40ac85 VXORPD %XMM20,%XMM20,%XMM20 |
0x40ac8b VGATHERQPD 0x8(%R11,%ZMM18,1),%ZMM20{%K1} [1] |
0x40ac93 KXNORW %K0,%K0,%K1 |
0x40ac97 VXORPD %XMM21,%XMM21,%XMM21 |
0x40ac9d VGATHERQPD 0x10(%R11,%ZMM18,1),%ZMM21{%K1} [1] |
0x40aca5 VPMOVSXDQ (%R15,%RDX,4),%ZMM18 [2] |
0x40acac VPSLLQ $0x4,%ZMM18,%ZMM18 |
0x40acb3 KXNORW %K0,%K0,%K1 |
0x40acb7 VXORPD %XMM22,%XMM22,%XMM22 |
0x40acbd VGATHERQPD 0x8(%R8,%ZMM18,1),%ZMM22{%K1} [3] |
0x40acc5 VADDPD %ZMM16,%ZMM19,%ZMM16 |
0x40accb VADDPD %ZMM15,%ZMM20,%ZMM15 |
0x40acd1 VADDPD %ZMM14,%ZMM21,%ZMM14 |
0x40acd7 VADDPD %ZMM13,%ZMM22,%ZMM13 |
0x40acdd ADD $0x8,%RDX |
0x40ace1 CMP %EBX,%EDX |
0x40ace3 JLE 40ac50 |
/home/eoseret/qaas_runs_CPU_9468/171-148-3214/intel/CoMD/build/CoMD/CoMD/src-openmp/initAtoms.c: 221 - 228 |
-------------------------------------------------------------------------------- |
221: for (int iOff=MAXATOMS*iBox, ii=0; ii<s->boxes->nAtoms[iBox]; ++ii, ++iOff) |
222: { |
223: v0 += s->atoms->p[iOff][0]; |
224: v1 += s->atoms->p[iOff][1]; |
225: v2 += s->atoms->p[iOff][2]; |
226: |
227: int iSpecies = s->atoms->iSpecies[iOff]; |
228: v3 += s->species[iSpecies].mass; |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.17 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.04 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.23 |
| Bottlenecks | P0, P5, |
| Function | computeVcm.extracted |
| Source | initAtoms.c:221-228 |
| 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 | 13.50 |
| CQA cycles if no scalar integer | 11.50 |
| CQA cycles if FP arith vectorized | 13.50 |
| CQA cycles if fully vectorized | 13.00 |
| Front-end cycles | 7.00 |
| DIV/SQRT cycles | 13.50 |
| P0 cycles | 2.00 |
| P1 cycles | 11.00 |
| P2 cycles | 11.00 |
| P3 cycles | 0.00 |
| P4 cycles | 13.50 |
| P5 cycles | 1.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 11.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 3 |
| FE+BE cycles (UFS) | 13.72 - 88.60 |
| Stall cycles (UFS) | 7.62 - 82.15 |
| Nb insns | 26.00 |
| Nb uops | 42.00 |
| Nb loads | 5.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.37 |
| Nb FLOP add-sub | 32.00 |
| 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 | 21.33 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 2.00 |
| Vectorization ratio all | 94.74 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 91.67 |
| Vector-efficiency ratio all | 76.97 |
| Vector-efficiency ratio load | 90.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 100.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 67.71 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.17 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.04 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.23 |
| Bottlenecks | P0, P5, |
| Function | computeVcm.extracted |
| Source | initAtoms.c:221-228 |
| 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 | 13.50 |
| CQA cycles if no scalar integer | 11.50 |
| CQA cycles if FP arith vectorized | 13.50 |
| CQA cycles if fully vectorized | 13.00 |
| Front-end cycles | 7.00 |
| DIV/SQRT cycles | 13.50 |
| P0 cycles | 2.00 |
| P1 cycles | 11.00 |
| P2 cycles | 11.00 |
| P3 cycles | 0.00 |
| P4 cycles | 13.50 |
| P5 cycles | 1.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 11.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 3 |
| FE+BE cycles (UFS) | 13.72 - 88.60 |
| Stall cycles (UFS) | 7.62 - 82.15 |
| Nb insns | 26.00 |
| Nb uops | 42.00 |
| Nb loads | 5.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.37 |
| Nb FLOP add-sub | 32.00 |
| 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 | 21.33 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 2.00 |
| Vectorization ratio all | 94.74 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 91.67 |
| Vector-efficiency ratio all | 76.97 |
| Vector-efficiency ratio load | 90.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 100.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 67.71 |
| Path / |
| Function | computeVcm.extracted |
| Source file and lines | initAtoms.c:221-228 |
| Module | exec |
| nb instructions | 26 |
| nb uops | 42 |
| loop length | 153 |
| used x86 registers | 5 |
| used mmx registers | 0 |
| used xmm registers | 4 |
| used ymm registers | 0 |
| used zmm registers | 10 |
| nb stack references | 0 |
| micro-operation queue | 7.00 cycles |
| front end | 7.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 13.50 | 1.00 | 11.00 | 11.00 | 0.00 | 13.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 11.00 |
| cycles | 13.50 | 2.00 | 11.00 | 11.00 | 0.00 | 13.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 11.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 3.00 |
| FE+BE cycles | 13.72-88.60 |
| Stall cycles | 7.62-82.15 |
| RS full (events) | 12.88-0.91 |
| Front-end | 7.00 |
| Dispatch | 13.50 |
| Data deps. | 3.00 |
| Overall L1 | 13.50 |
| all | 87% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 80% |
| all | 100% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 94% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 91% |
| all | 73% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 67% |
| all | 79% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 67% |
| all | 76% |
| load | 90% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 67% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VPBROADCASTQ %RDX,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPADDQ %ZMM18,%ZMM17,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPSLLQ $0x3,%ZMM18,%ZMM19 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| VPSLLQ $0x4,%ZMM18,%ZMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| VPADDQ %ZMM19,%ZMM18,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VPXORD %XMM19,%XMM19,%XMM19 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
| VGATHERQPD (%R11,%ZMM18,1),%ZMM19{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM20,%XMM20,%XMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x8(%R11,%ZMM18,1),%ZMM20{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM21,%XMM21,%XMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x10(%R11,%ZMM18,1),%ZMM21{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VPMOVSXDQ (%R15,%RDX,4),%ZMM18 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
| VPSLLQ $0x4,%ZMM18,%ZMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM22,%XMM22,%XMM22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x8(%R8,%ZMM18,1),%ZMM22{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VADDPD %ZMM16,%ZMM19,%ZMM16 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM15,%ZMM20,%ZMM15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM14,%ZMM21,%ZMM14 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM13,%ZMM22,%ZMM13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ADD $0x8,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %EBX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JLE 40ac50 <computeVcm.extracted+0x230> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | computeVcm.extracted |
| Source file and lines | initAtoms.c:221-228 |
| Module | exec |
| nb instructions | 26 |
| nb uops | 42 |
| loop length | 153 |
| used x86 registers | 5 |
| used mmx registers | 0 |
| used xmm registers | 4 |
| used ymm registers | 0 |
| used zmm registers | 10 |
| nb stack references | 0 |
| micro-operation queue | 7.00 cycles |
| front end | 7.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 13.50 | 1.00 | 11.00 | 11.00 | 0.00 | 13.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 11.00 |
| cycles | 13.50 | 2.00 | 11.00 | 11.00 | 0.00 | 13.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 11.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 3.00 |
| FE+BE cycles | 13.72-88.60 |
| Stall cycles | 7.62-82.15 |
| RS full (events) | 12.88-0.91 |
| Front-end | 7.00 |
| Dispatch | 13.50 |
| Data deps. | 3.00 |
| Overall L1 | 13.50 |
| all | 87% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 80% |
| all | 100% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 94% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 91% |
| all | 73% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 67% |
| all | 79% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 67% |
| all | 76% |
| load | 90% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 67% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VPBROADCASTQ %RDX,%ZMM18 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| VPADDQ %ZMM18,%ZMM17,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| VPSLLQ $0x3,%ZMM18,%ZMM19 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| VPSLLQ $0x4,%ZMM18,%ZMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| VPADDQ %ZMM19,%ZMM18,%ZMM18 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VPXORD %XMM19,%XMM19,%XMM19 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.33 |
| VGATHERQPD (%R11,%ZMM18,1),%ZMM19{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM20,%XMM20,%XMM20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x8(%R11,%ZMM18,1),%ZMM20{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM21,%XMM21,%XMM21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x10(%R11,%ZMM18,1),%ZMM21{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VPMOVSXDQ (%R15,%RDX,4),%ZMM18 | 2 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
| VPSLLQ $0x4,%ZMM18,%ZMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 1 |
| KXNORW %K0,%K0,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| VXORPD %XMM22,%XMM22,%XMM22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| VGATHERQPD 0x8(%R8,%ZMM18,1),%ZMM22{%K1} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 0-29 | 2.67 |
| VADDPD %ZMM16,%ZMM19,%ZMM16 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM15,%ZMM20,%ZMM15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM14,%ZMM21,%ZMM14 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %ZMM13,%ZMM22,%ZMM13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ADD $0x8,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %EBX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JLE 40ac50 <computeVcm.extracted+0x230> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
