| Loop Id: 209 | Module: exec | Source: advec_cell.cpp:211-216 | Coverage: 3.59% |
|---|
| Loop Id: 209 | Module: exec | Source: advec_cell.cpp:211-216 | Coverage: 3.59% |
|---|
0x42e5b8 VMOVUPD (%R12,%RAX,1),%ZMM10 [4] |
0x42e5bf VMOVUPD (%R10,%RAX,1),%ZMM14 [1] |
0x42e5c6 VMULPD (%RCX,%RAX,1),%ZMM10,%ZMM11 [3] |
0x42e5cd VSUBPD (%R9,%RAX,1),%ZMM14,%ZMM15 [8] |
0x42e5d4 VADDPD (%R8,%RAX,1),%ZMM10,%ZMM0 [7] |
0x42e5db VSUBPD (%RBX,%RAX,1),%ZMM11,%ZMM12 [6] |
0x42e5e2 VFMADD132PD (%RDX,%RAX,1),%ZMM15,%ZMM11 [5] |
0x42e5e9 VSUBPD (%RDI,%RAX,1),%ZMM0,%ZMM1 [10] |
0x42e5f0 VADDPD (%R11,%RAX,1),%ZMM12,%ZMM13 [2] |
0x42e5f7 VDIVPD %ZMM13,%ZMM11,%ZMM4 |
0x42e5fd VDIVPD %ZMM1,%ZMM13,%ZMM2 |
0x42e603 VMOVUPD %ZMM2,(%RCX,%RAX,1) [3] |
0x42e60a VMOVUPD %ZMM4,(%RDX,%RAX,1) [5] |
0x42e611 VMOVUPD 0x40(%R12,%RAX,1),%ZMM5 [4] |
0x42e619 VMOVUPD 0x40(%R10,%RAX,1),%ZMM8 [1] |
0x42e621 VMULPD 0x40(%RCX,%RAX,1),%ZMM5,%ZMM6 [3] |
0x42e629 VSUBPD 0x40(%R9,%RAX,1),%ZMM8,%ZMM9 [8] |
0x42e631 VADDPD 0x40(%R8,%RAX,1),%ZMM5,%ZMM10 [7] |
0x42e639 VSUBPD 0x40(%RBX,%RAX,1),%ZMM6,%ZMM3 [6] |
0x42e641 VFMADD132PD 0x40(%RDX,%RAX,1),%ZMM9,%ZMM6 [5] |
0x42e649 VSUBPD 0x40(%RDI,%RAX,1),%ZMM10,%ZMM11 [10] |
0x42e651 VADDPD 0x40(%R11,%RAX,1),%ZMM3,%ZMM7 [2] |
0x42e659 VDIVPD %ZMM11,%ZMM7,%ZMM12 |
0x42e65f VDIVPD %ZMM7,%ZMM6,%ZMM13 |
0x42e665 VMOVUPD %ZMM12,0x40(%RCX,%RAX,1) [3] |
0x42e66d VMOVUPD %ZMM13,0x40(%RDX,%RAX,1) [5] |
0x42e675 SUB $-0x80,%RAX |
0x42e679 CMP %RAX,0xf8(%RSP) [9] |
0x42e681 JNE 42e5b8 |
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 211 - 216 |
-------------------------------------------------------------------------------- |
211: double pre_mass_s = density1(i, j) * pre_vol(i, j); |
212: double post_mass_s = pre_mass_s + mass_flux_y(i, j) - mass_flux_y(i + 0, j + 1); |
213: double post_ener_s = (energy1(i, j) * pre_mass_s + ener_flux(i, j) - ener_flux(i + 0, j + 1)) / post_mass_s; |
214: double advec_vol_s = pre_vol(i, j) + vol_flux_y(i, j) - vol_flux_y(i + 0, j + 1); |
215: density1(i, j) = post_mass_s / advec_vol_s; |
216: energy1(i, j) = post_ener_s; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○97.58 | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○2.42 | GOMP_parallel | libgomp.h:982 | libgomp.so.1.0.0 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 4.92 |
| Bottlenecks | P0, |
| Function | advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D |
| Source | advec_cell.cpp:211-216 |
| 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 | 64.00 |
| CQA cycles if no scalar integer | 64.00 |
| CQA cycles if FP arith vectorized | 64.00 |
| CQA cycles if fully vectorized | 64.00 |
| Front-end cycles | 8.33 |
| P0 cycles | 13.00 |
| P1 cycles | 7.00 |
| P2 cycles | 6.33 |
| P3 cycles | 6.33 |
| P4 cycles | 2.00 |
| P5 cycles | 13.00 |
| P6 cycles | 1.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 2.00 |
| P10 cycles | 0.00 |
| P11 cycles | 6.33 |
| DIV/SQRT cycles | 64.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 29.00 |
| Nb uops | 36.00 |
| Nb loads | 19.00 |
| Nb stores | 4.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 2.50 |
| Nb FLOP add-sub | 80.00 |
| Nb FLOP mul | 16.00 |
| Nb FLOP fma | 16.00 |
| Nb FLOP div | 32.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 22.13 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 1160.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| 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 | 100.00 |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | 100.00 |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 100.00 |
| Vector-efficiency ratio load | 100.00 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 100.00 |
| Vector-efficiency ratio fma | 100.00 |
| Vector-efficiency ratio div_sqrt | 100.00 |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 4.92 |
| Bottlenecks | P0, |
| Function | advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D |
| Source | advec_cell.cpp:211-216 |
| 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 | 64.00 |
| CQA cycles if no scalar integer | 64.00 |
| CQA cycles if FP arith vectorized | 64.00 |
| CQA cycles if fully vectorized | 64.00 |
| Front-end cycles | 8.33 |
| P0 cycles | 13.00 |
| P1 cycles | 7.00 |
| P2 cycles | 6.33 |
| P3 cycles | 6.33 |
| P4 cycles | 2.00 |
| P5 cycles | 13.00 |
| P6 cycles | 1.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 2.00 |
| P10 cycles | 0.00 |
| P11 cycles | 6.33 |
| DIV/SQRT cycles | 64.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 29.00 |
| Nb uops | 36.00 |
| Nb loads | 19.00 |
| Nb stores | 4.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 2.50 |
| Nb FLOP add-sub | 80.00 |
| Nb FLOP mul | 16.00 |
| Nb FLOP fma | 16.00 |
| Nb FLOP div | 32.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 22.13 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 1160.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| 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 | 100.00 |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | 100.00 |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 100.00 |
| Vector-efficiency ratio load | 100.00 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 100.00 |
| Vector-efficiency ratio fma | 100.00 |
| Vector-efficiency ratio div_sqrt | 100.00 |
| Vector-efficiency ratio other | NA |
| Path / |
| nb instructions | 29 |
| nb uops | 36 |
| loop length | 207 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 16 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 5.00 |
| micro-operation queue | 8.33 cycles |
| front end | 8.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 13.00 | 0.00 | 6.33 | 6.33 | 2.00 | 13.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| cycles | 13.00 | 7.00 | 6.33 | 6.33 | 2.00 | 13.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| Cycles executing div or sqrt instructions | 64.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 8.33 |
| Dispatch | 13.00 |
| DIV/SQRT | 64.00 |
| Data deps. | 1.00 |
| Overall L1 | 64.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R12,%RAX,1),%ZMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMOVUPD (%R10,%RAX,1),%ZMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMULPD (%RCX,%RAX,1),%ZMM10,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD (%R9,%RAX,1),%ZMM14,%ZMM15 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD (%R8,%RAX,1),%ZMM10,%ZMM0 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VSUBPD (%RBX,%RAX,1),%ZMM11,%ZMM12 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VFMADD132PD (%RDX,%RAX,1),%ZMM15,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD (%RDI,%RAX,1),%ZMM0,%ZMM1 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD (%R11,%RAX,1),%ZMM12,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VDIVPD %ZMM13,%ZMM11,%ZMM4 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VDIVPD %ZMM1,%ZMM13,%ZMM2 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VMOVUPD %ZMM2,(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD %ZMM4,(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD 0x40(%R12,%RAX,1),%ZMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMOVUPD 0x40(%R10,%RAX,1),%ZMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMULPD 0x40(%RCX,%RAX,1),%ZMM5,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD 0x40(%R9,%RAX,1),%ZMM8,%ZMM9 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD 0x40(%R8,%RAX,1),%ZMM5,%ZMM10 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VSUBPD 0x40(%RBX,%RAX,1),%ZMM6,%ZMM3 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VFMADD132PD 0x40(%RDX,%RAX,1),%ZMM9,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD 0x40(%RDI,%RAX,1),%ZMM10,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD 0x40(%R11,%RAX,1),%ZMM3,%ZMM7 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VDIVPD %ZMM11,%ZMM7,%ZMM12 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VDIVPD %ZMM7,%ZMM6,%ZMM13 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VMOVUPD %ZMM12,0x40(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD %ZMM13,0x40(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %RAX,0xf8(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | N/A |
| JNE 42e5b8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_._omp_fn.7+0x318> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| nb instructions | 29 |
| nb uops | 36 |
| loop length | 207 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 16 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 5.00 |
| micro-operation queue | 8.33 cycles |
| front end | 8.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 13.00 | 0.00 | 6.33 | 6.33 | 2.00 | 13.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| cycles | 13.00 | 7.00 | 6.33 | 6.33 | 2.00 | 13.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| Cycles executing div or sqrt instructions | 64.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 8.33 |
| Dispatch | 13.00 |
| DIV/SQRT | 64.00 |
| Data deps. | 1.00 |
| Overall L1 | 64.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R12,%RAX,1),%ZMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMOVUPD (%R10,%RAX,1),%ZMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMULPD (%RCX,%RAX,1),%ZMM10,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD (%R9,%RAX,1),%ZMM14,%ZMM15 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD (%R8,%RAX,1),%ZMM10,%ZMM0 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VSUBPD (%RBX,%RAX,1),%ZMM11,%ZMM12 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VFMADD132PD (%RDX,%RAX,1),%ZMM15,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD (%RDI,%RAX,1),%ZMM0,%ZMM1 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD (%R11,%RAX,1),%ZMM12,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VDIVPD %ZMM13,%ZMM11,%ZMM4 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VDIVPD %ZMM1,%ZMM13,%ZMM2 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VMOVUPD %ZMM2,(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD %ZMM4,(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD 0x40(%R12,%RAX,1),%ZMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMOVUPD 0x40(%R10,%RAX,1),%ZMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 | vect (100.0%) |
| VMULPD 0x40(%RCX,%RAX,1),%ZMM5,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD 0x40(%R9,%RAX,1),%ZMM8,%ZMM9 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD 0x40(%R8,%RAX,1),%ZMM5,%ZMM10 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VSUBPD 0x40(%RBX,%RAX,1),%ZMM6,%ZMM3 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VFMADD132PD 0x40(%RDX,%RAX,1),%ZMM9,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | vect (100.0%) |
| VSUBPD 0x40(%RDI,%RAX,1),%ZMM10,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VADDPD 0x40(%R11,%RAX,1),%ZMM3,%ZMM7 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 | vect (100.0%) |
| VDIVPD %ZMM11,%ZMM7,%ZMM12 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VDIVPD %ZMM7,%ZMM6,%ZMM13 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 | vect (100.0%) |
| VMOVUPD %ZMM12,0x40(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| VMOVUPD %ZMM13,0x40(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 | vect (100.0%) |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %RAX,0xf8(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | N/A |
| JNE 42e5b8 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_._omp_fn.7+0x318> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |