| Loop Id: 108 | Module: exec | Source: advec_cell_kernel.f90:256-261 | Coverage: 3.67% |
|---|
| Loop Id: 108 | Module: exec | Source: advec_cell_kernel.f90:256-261 | Coverage: 3.67% |
|---|
0x42e180 VMOVUPD (%R14,%RAX,1),%ZMM12 [3] |
0x42e187 VMOVUPD (%R11,%RAX,1),%ZMM13 [2] |
0x42e18e MOV 0x100(%RSP),%RSI [9] |
0x42e196 VMULPD (%RCX,%RAX,1),%ZMM12,%ZMM14 [1] |
0x42e19d VSUBPD (%R10,%RAX,1),%ZMM13,%ZMM1 [4] |
0x42e1a4 VADDPD (%R9,%RAX,1),%ZMM12,%ZMM6 [10] |
0x42e1ab VSUBPD (%R8,%RAX,1),%ZMM6,%ZMM5 [6] |
0x42e1b2 VSUBPD (%R12,%RAX,1),%ZMM14,%ZMM0 [5] |
0x42e1b9 VFMADD132PD (%RDX,%RAX,1),%ZMM1,%ZMM14 [7] |
0x42e1c0 VADDPD (%RBX,%RAX,1),%ZMM0,%ZMM2 [8] |
0x42e1c7 VDIVPD %ZMM2,%ZMM14,%ZMM8 |
0x42e1cd VDIVPD %ZMM5,%ZMM2,%ZMM4 |
0x42e1d3 VMOVUPD %ZMM4,(%RCX,%RAX,1) [1] |
0x42e1da VMOVUPD %ZMM8,(%RDX,%RAX,1) [7] |
0x42e1e1 VMOVUPD 0x40(%R14,%RAX,1),%ZMM9 [3] |
0x42e1e9 VMOVUPD 0x40(%R11,%RAX,1),%ZMM3 [2] |
0x42e1f1 VMULPD 0x40(%RCX,%RAX,1),%ZMM9,%ZMM11 [1] |
0x42e1f9 VSUBPD 0x40(%R10,%RAX,1),%ZMM3,%ZMM15 [4] |
0x42e201 VADDPD 0x40(%R9,%RAX,1),%ZMM9,%ZMM12 [10] |
0x42e209 VSUBPD 0x40(%R8,%RAX,1),%ZMM12,%ZMM14 [6] |
0x42e211 VSUBPD 0x40(%R12,%RAX,1),%ZMM11,%ZMM7 [5] |
0x42e219 VFMADD132PD 0x40(%RDX,%RAX,1),%ZMM15,%ZMM11 [7] |
0x42e221 VADDPD 0x40(%RBX,%RAX,1),%ZMM7,%ZMM10 [8] |
0x42e229 VDIVPD %ZMM14,%ZMM10,%ZMM0 |
0x42e22f VDIVPD %ZMM10,%ZMM11,%ZMM2 |
0x42e235 VMOVUPD %ZMM0,0x40(%RCX,%RAX,1) [1] |
0x42e23d VMOVUPD %ZMM2,0x40(%RDX,%RAX,1) [7] |
0x42e245 SUB $-0x80,%RAX |
0x42e249 CMP %RSI,%RAX |
0x42e24c JNE 42e180 |
/home/eoseret/qaas_runs_CPU_9468/171-152-3172/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_cell_kernel.f90: 256 - 261 |
-------------------------------------------------------------------------------- |
256: pre_mass_s=density1(j,k)*pre_vol(j,k) |
257: post_mass_s=pre_mass_s+mass_flux_y(j,k)-mass_flux_y(j,k+1) |
258: post_ener_s=(energy1(j,k)*pre_mass_s+ener_flux(j,k)-ener_flux(j,k+1))/post_mass_s |
259: advec_vol_s=pre_vol(j,k)+vol_flux_y(j,k)-vol_flux_y(j,k+1) |
260: density1(j,k)=post_mass_s/advec_vol_s |
261: energy1(j,k)=post_ener_s |
| 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._omp_fn.0 |
| Source | advec_cell_kernel.f90:256-261 |
| 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 | 8.50 |
| DIV/SQRT cycles | 13.00 |
| P0 cycles | 7.00 |
| P1 cycles | 6.33 |
| P2 cycles | 6.33 |
| P3 cycles | 2.00 |
| P4 cycles | 13.00 |
| P5 cycles | 1.00 |
| P6 cycles | 2.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 0.00 |
| P10 cycles | 6.33 |
| P11 cycles | 64.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 64.30 - 64.32 |
| Stall cycles (UFS) | 54.95 - 54.97 |
| Nb insns | 30.00 |
| Nb uops | 37.00 |
| 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._omp_fn.0 |
| Source | advec_cell_kernel.f90:256-261 |
| 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 | 8.50 |
| DIV/SQRT cycles | 13.00 |
| P0 cycles | 7.00 |
| P1 cycles | 6.33 |
| P2 cycles | 6.33 |
| P3 cycles | 2.00 |
| P4 cycles | 13.00 |
| P5 cycles | 1.00 |
| P6 cycles | 2.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 0.00 |
| P10 cycles | 6.33 |
| P11 cycles | 64.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 64.30 - 64.32 |
| Stall cycles (UFS) | 54.95 - 54.97 |
| Nb insns | 30.00 |
| Nb uops | 37.00 |
| 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 / |
| Function | advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:256-261 |
| Module | exec |
| nb instructions | 30 |
| nb uops | 37 |
| loop length | 210 |
| used x86 registers | 12 |
| 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 | 8.50 cycles |
| front end | 8.50 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 |
| FE+BE cycles | 64.30-64.32 |
| Stall cycles | 54.95-54.97 |
| ROB full (events) | 57.33-57.35 |
| RS full (events) | 0.19 |
| Front-end | 8.50 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R14,%RAX,1),%ZMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%R11,%RAX,1),%ZMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| MOV 0x100(%RSP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMULPD (%RCX,%RAX,1),%ZMM12,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD (%R10,%RAX,1),%ZMM13,%ZMM1 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD (%R9,%RAX,1),%ZMM12,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD (%R8,%RAX,1),%ZMM6,%ZMM5 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD (%R12,%RAX,1),%ZMM14,%ZMM0 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VFMADD132PD (%RDX,%RAX,1),%ZMM1,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD (%RBX,%RAX,1),%ZMM0,%ZMM2 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VDIVPD %ZMM2,%ZMM14,%ZMM8 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VDIVPD %ZMM5,%ZMM2,%ZMM4 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMOVUPD %ZMM4,(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM8,(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD 0x40(%R14,%RAX,1),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD 0x40(%R11,%RAX,1),%ZMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMULPD 0x40(%RCX,%RAX,1),%ZMM9,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD 0x40(%R10,%RAX,1),%ZMM3,%ZMM15 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD 0x40(%R9,%RAX,1),%ZMM9,%ZMM12 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD 0x40(%R8,%RAX,1),%ZMM12,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD 0x40(%R12,%RAX,1),%ZMM11,%ZMM7 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VFMADD132PD 0x40(%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 |
| VADDPD 0x40(%RBX,%RAX,1),%ZMM7,%ZMM10 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VDIVPD %ZMM14,%ZMM10,%ZMM0 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VDIVPD %ZMM10,%ZMM11,%ZMM2 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMOVUPD %ZMM0,0x40(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM2,0x40(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RSI,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 42e180 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x28e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:256-261 |
| Module | exec |
| nb instructions | 30 |
| nb uops | 37 |
| loop length | 210 |
| used x86 registers | 12 |
| 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 | 8.50 cycles |
| front end | 8.50 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 |
| FE+BE cycles | 64.30-64.32 |
| Stall cycles | 54.95-54.97 |
| ROB full (events) | 57.33-57.35 |
| RS full (events) | 0.19 |
| Front-end | 8.50 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R14,%RAX,1),%ZMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%R11,%RAX,1),%ZMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| MOV 0x100(%RSP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| VMULPD (%RCX,%RAX,1),%ZMM12,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD (%R10,%RAX,1),%ZMM13,%ZMM1 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD (%R9,%RAX,1),%ZMM12,%ZMM6 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD (%R8,%RAX,1),%ZMM6,%ZMM5 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD (%R12,%RAX,1),%ZMM14,%ZMM0 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VFMADD132PD (%RDX,%RAX,1),%ZMM1,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD (%RBX,%RAX,1),%ZMM0,%ZMM2 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VDIVPD %ZMM2,%ZMM14,%ZMM8 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VDIVPD %ZMM5,%ZMM2,%ZMM4 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMOVUPD %ZMM4,(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM8,(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD 0x40(%R14,%RAX,1),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD 0x40(%R11,%RAX,1),%ZMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMULPD 0x40(%RCX,%RAX,1),%ZMM9,%ZMM11 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD 0x40(%R10,%RAX,1),%ZMM3,%ZMM15 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD 0x40(%R9,%RAX,1),%ZMM9,%ZMM12 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD 0x40(%R8,%RAX,1),%ZMM12,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VSUBPD 0x40(%R12,%RAX,1),%ZMM11,%ZMM7 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VFMADD132PD 0x40(%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 |
| VADDPD 0x40(%RBX,%RAX,1),%ZMM7,%ZMM10 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VDIVPD %ZMM14,%ZMM10,%ZMM0 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VDIVPD %ZMM10,%ZMM11,%ZMM2 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMOVUPD %ZMM0,0x40(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM2,0x40(%RDX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RSI,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JNE 42e180 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x28e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
