| Loop Id: 94 | Module: exec | Source: advec_cell_kernel.f90:100-101 | Coverage: 1.01% |
|---|
| Loop Id: 94 | Module: exec | Source: advec_cell_kernel.f90:100-101 | Coverage: 1.01% |
|---|
0x41e3ce VMOVUPD (%RDX,%RAX,1),%YMM13 [1] |
0x41e3d3 VADDPD (%RBX,%RAX,1),%YMM13,%YMM1 [3] |
0x41e3d8 VSUBPD (%R15,%RAX,1),%YMM1,%YMM5 [2] |
0x41e3de VMOVUPD %YMM5,(%R14,%RAX,1) [6] |
0x41e3e4 VMOVUPD (%RDX,%RAX,1),%YMM4 [1] |
0x41e3e9 VMOVUPD %YMM4,(%R12,%RAX,1) [5] |
0x41e3ef VMOVUPD 0x20(%RDX,%RAX,1),%YMM8 [1] |
0x41e3f5 VADDPD 0x20(%RAX,%RBX,1),%YMM8,%YMM6 [4] |
0x41e3fb VSUBPD 0x20(%R15,%RAX,1),%YMM6,%YMM7 [2] |
0x41e402 VMOVUPD %YMM7,0x20(%R14,%RAX,1) [6] |
0x41e409 VMOVUPD 0x20(%RDX,%RAX,1),%YMM9 [1] |
0x41e40f VMOVUPD %YMM9,0x20(%R12,%RAX,1) [5] |
0x41e416 VMOVUPD 0x40(%RDX,%RAX,1),%YMM3 [1] |
0x41e41c VADDPD 0x40(%RAX,%RBX,1),%YMM3,%YMM11 [4] |
0x41e422 VSUBPD 0x40(%R15,%RAX,1),%YMM11,%YMM10 [2] |
0x41e429 VMOVUPD %YMM10,0x40(%R14,%RAX,1) [6] |
0x41e430 VMOVUPD 0x40(%RDX,%RAX,1),%YMM15 [1] |
0x41e436 VMOVUPD %YMM15,0x40(%R12,%RAX,1) [5] |
0x41e43d VMOVUPD 0x60(%RDX,%RAX,1),%YMM12 [1] |
0x41e443 VADDPD 0x60(%RAX,%RBX,1),%YMM12,%YMM14 [4] |
0x41e449 VSUBPD 0x60(%R15,%RAX,1),%YMM14,%YMM0 [2] |
0x41e450 VMOVUPD %YMM0,0x60(%R14,%RAX,1) [6] |
0x41e457 VMOVUPD 0x60(%RDX,%RAX,1),%YMM2 [1] |
0x41e45d VMOVUPD %YMM2,0x60(%R12,%RAX,1) [5] |
0x41e464 SUB $-0x80,%RAX |
0x41e468 CMP %RAX,0x120(%RSP) [7] |
0x41e470 JNE 41e3ce |
/scratch_na/users/xoserete/qaas_runs/171-214-9740/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_cell_kernel.f90: 100 - 101 |
-------------------------------------------------------------------------------- |
100: pre_vol(j,k)=volume(j,k)+vol_flux_x(j+1,k)-vol_flux_x(j,k) |
101: post_vol(j,k)=volume(j,k) |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.03 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.42 |
| Bottlenecks | micro-operation queue, |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:100-101 |
| 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 | 5.67 |
| CQA cycles if no scalar integer | 5.67 |
| CQA cycles if FP arith vectorized | 5.50 |
| CQA cycles if fully vectorized | 2.83 |
| Front-end cycles | 5.67 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 4.00 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 4.00 |
| P4 cycles | 4.00 |
| P5 cycles | 0.50 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 0.00 |
| P10 cycles | 5.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.85 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 17.00 |
| Nb stores | 8.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 5.65 |
| 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 | 136.94 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 520.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| Stride 1 | 3.00 |
| Stride n | 3.00 |
| 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 | NA |
| Vectorization ratio add_sub | 100.00 |
| 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 | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| 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 | 1.03 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.42 |
| Bottlenecks | micro-operation queue, |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:100-101 |
| 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 | 5.67 |
| CQA cycles if no scalar integer | 5.67 |
| CQA cycles if FP arith vectorized | 5.50 |
| CQA cycles if fully vectorized | 2.83 |
| Front-end cycles | 5.67 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 4.00 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 4.00 |
| P4 cycles | 4.00 |
| P5 cycles | 0.50 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 0.00 |
| P10 cycles | 5.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.85 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 17.00 |
| Nb stores | 8.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 5.65 |
| 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 | 136.94 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 520.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| Stride 1 | 3.00 |
| Stride n | 3.00 |
| 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 | NA |
| Vectorization ratio add_sub | 100.00 |
| 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 | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:100-101 |
| Module | exec |
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 168 |
| used x86 registers | 7 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 16 |
| used zmm registers | 0 |
| nb stack references | 1 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 4.00 | 5.67 | 5.67 | 4.00 | 4.00 | 0.50 | 4.00 | 4.00 | 4.00 | 0.00 | 5.67 |
| cycles | 0.50 | 4.00 | 5.67 | 5.67 | 4.00 | 4.00 | 0.50 | 4.00 | 4.00 | 4.00 | 0.00 | 5.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.85 |
| Stall cycles | 0.00 |
| Front-end | 5.67 |
| Dispatch | 5.67 |
| Data deps. | 1.00 |
| Overall L1 | 5.67 |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%RDX,%RAX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RBX,%RAX,1),%YMM13,%YMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R15,%RAX,1),%YMM1,%YMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM5,(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD (%RDX,%RAX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM4,(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RAX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x20(%RAX,%RBX,1),%YMM8,%YMM6 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x20(%R15,%RAX,1),%YMM6,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,0x20(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RAX,1),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM9,0x20(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RAX,1),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x40(%RAX,%RBX,1),%YMM3,%YMM11 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x40(%R15,%RAX,1),%YMM11,%YMM10 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM10,0x40(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RAX,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM15,0x40(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RAX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x60(%RAX,%RBX,1),%YMM12,%YMM14 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x60(%R15,%RAX,1),%YMM14,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM0,0x60(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RAX,1),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM2,0x60(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RAX,0x120(%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 |
| JNE 41e3ce <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x13be> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:100-101 |
| Module | exec |
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 168 |
| used x86 registers | 7 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 16 |
| used zmm registers | 0 |
| nb stack references | 1 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 4.00 | 5.67 | 5.67 | 4.00 | 4.00 | 0.50 | 4.00 | 4.00 | 4.00 | 0.00 | 5.67 |
| cycles | 0.50 | 4.00 | 5.67 | 5.67 | 4.00 | 4.00 | 0.50 | 4.00 | 4.00 | 4.00 | 0.00 | 5.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.85 |
| Stall cycles | 0.00 |
| Front-end | 5.67 |
| Dispatch | 5.67 |
| Data deps. | 1.00 |
| Overall L1 | 5.67 |
| all | 100% |
| load | 100% |
| store | 100% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%RDX,%RAX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RBX,%RAX,1),%YMM13,%YMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R15,%RAX,1),%YMM1,%YMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM5,(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD (%RDX,%RAX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM4,(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RAX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x20(%RAX,%RBX,1),%YMM8,%YMM6 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x20(%R15,%RAX,1),%YMM6,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,0x20(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RAX,1),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM9,0x20(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RAX,1),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x40(%RAX,%RBX,1),%YMM3,%YMM11 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x40(%R15,%RAX,1),%YMM11,%YMM10 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM10,0x40(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RAX,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM15,0x40(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RAX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD 0x60(%RAX,%RBX,1),%YMM12,%YMM14 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x60(%R15,%RAX,1),%YMM14,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM0,0x60(%R14,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RAX,1),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD %YMM2,0x60(%R12,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| SUB $-0x80,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RAX,0x120(%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 |
| JNE 41e3ce <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x13be> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
