| Loop Id: 88 | Module: exec | Source: advec_cell_kernel.f90:165-170 | Coverage: 2.62% |
|---|
| Loop Id: 88 | Module: exec | Source: advec_cell_kernel.f90:165-170 | Coverage: 2.62% |
|---|
0x41eca3 VMOVUPD (%R15,%RAX,1),%YMM12 [5] |
0x41eca9 VMOVUPD (%RBX,%RAX,1),%YMM13 [3] |
0x41ecae VMULPD (%RSI,%RAX,1),%YMM12,%YMM14 [7] |
0x41ecb3 VSUBPD (%R8,%RAX,1),%YMM13,%YMM1 [4] |
0x41ecb9 VADDPD (%R11,%RAX,1),%YMM12,%YMM5 [1] |
0x41ecbf VSUBPD (%RDI,%RAX,1),%YMM5,%YMM4 [10] |
0x41ecc4 VSUBPD (%R10,%RAX,1),%YMM14,%YMM0 [6] |
0x41ecca VFMADD132PD (%RCX,%RAX,1),%YMM1,%YMM14 [2] |
0x41ecd0 VADDPD (%R13,%RAX,1),%YMM0,%YMM2 [8] |
0x41ecd7 VDIVPD %YMM2,%YMM14,%YMM7 |
0x41ecdb VDIVPD %YMM4,%YMM2,%YMM8 |
0x41ecdf VMOVUPD %YMM8,(%RSI,%RAX,1) [7] |
0x41ece4 VMOVUPD %YMM7,(%RCX,%RAX,1) [2] |
0x41ece9 VMOVUPD 0x20(%R15,%RAX,1),%YMM6 [5] |
0x41ecf0 VMOVUPD 0x20(%RBX,%RAX,1),%YMM10 [3] |
0x41ecf6 VMULPD 0x20(%RSI,%RAX,1),%YMM6,%YMM9 [7] |
0x41ecfc VSUBPD 0x20(%R8,%RAX,1),%YMM10,%YMM15 [4] |
0x41ed03 VADDPD 0x20(%R11,%RAX,1),%YMM6,%YMM12 [1] |
0x41ed0a VSUBPD 0x20(%RDI,%RAX,1),%YMM12,%YMM14 [10] |
0x41ed10 VSUBPD 0x20(%R10,%RAX,1),%YMM9,%YMM3 [6] |
0x41ed17 VFMADD132PD 0x20(%RCX,%RAX,1),%YMM15,%YMM9 [2] |
0x41ed1e VADDPD 0x20(%R13,%RAX,1),%YMM3,%YMM11 [8] |
0x41ed25 VDIVPD %YMM14,%YMM11,%YMM0 |
0x41ed2a VDIVPD %YMM11,%YMM9,%YMM2 |
0x41ed2f VMOVUPD %YMM0,0x20(%RSI,%RAX,1) [7] |
0x41ed35 VMOVUPD %YMM2,0x20(%RCX,%RAX,1) [2] |
0x41ed3b ADD $0x40,%RAX |
0x41ed3f CMP %RAX,0xf0(%RSP) [9] |
0x41ed47 JNE 41eca3 |
/scratch_na/users/xoserete/qaas_runs/171-214-9740/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_cell_kernel.f90: 165 - 170 |
-------------------------------------------------------------------------------- |
165: pre_mass_s=density1(j,k)*pre_vol(j,k) |
166: post_mass_s=pre_mass_s+mass_flux_x(j,k)-mass_flux_x(j+1,k) |
167: post_ener_s=(energy1(j,k)*pre_mass_s+ener_flux(j,k)-ener_flux(j+1,k))/post_mass_s |
168: advec_vol_s=pre_vol(j,k)+vol_flux_x(j,k)-vol_flux_x(j+1,k) |
169: density1(j,k)=post_mass_s/advec_vol_s |
170: 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 | 4.57 |
| Bottlenecks | P0, |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:165-170 |
| 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 | 32.00 |
| CQA cycles if no scalar integer | 32.00 |
| CQA cycles if FP arith vectorized | 32.00 |
| CQA cycles if fully vectorized | 32.00 |
| Front-end cycles | 7.00 |
| DIV/SQRT cycles | 5.50 |
| P0 cycles | 7.00 |
| P1 cycles | 6.33 |
| P2 cycles | 6.33 |
| P3 cycles | 2.00 |
| P4 cycles | 6.00 |
| 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 | 32.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 32.28 - 32.30 |
| Stall cycles (UFS) | 24.58 - 24.60 |
| Nb insns | 29.00 |
| Nb uops | 28.00 |
| Nb loads | 19.00 |
| Nb stores | 4.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 2.50 |
| Nb FLOP add-sub | 40.00 |
| Nb FLOP mul | 8.00 |
| Nb FLOP fma | 8.00 |
| Nb FLOP div | 16.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 22.25 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 584.00 |
| Bytes stored | 128.00 |
| 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 | 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 | 50.00 |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | 50.00 |
| 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 | 4.57 |
| Bottlenecks | P0, |
| Function | __advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:165-170 |
| 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 | 32.00 |
| CQA cycles if no scalar integer | 32.00 |
| CQA cycles if FP arith vectorized | 32.00 |
| CQA cycles if fully vectorized | 32.00 |
| Front-end cycles | 7.00 |
| DIV/SQRT cycles | 5.50 |
| P0 cycles | 7.00 |
| P1 cycles | 6.33 |
| P2 cycles | 6.33 |
| P3 cycles | 2.00 |
| P4 cycles | 6.00 |
| 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 | 32.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 32.28 - 32.30 |
| Stall cycles (UFS) | 24.58 - 24.60 |
| Nb insns | 29.00 |
| Nb uops | 28.00 |
| Nb loads | 19.00 |
| Nb stores | 4.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 2.50 |
| Nb FLOP add-sub | 40.00 |
| Nb FLOP mul | 8.00 |
| Nb FLOP fma | 8.00 |
| Nb FLOP div | 16.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 22.25 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 584.00 |
| Bytes stored | 128.00 |
| 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 | 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 | 50.00 |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | 50.00 |
| 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.f90:165-170 |
| Module | exec |
| nb instructions | 29 |
| nb uops | 28 |
| loop length | 170 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 16 |
| used zmm registers | 0 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 5.00 |
| micro-operation queue | 7.00 cycles |
| front end | 7.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 5.50 | 6.50 | 6.33 | 6.33 | 2.00 | 6.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| cycles | 5.50 | 7.00 | 6.33 | 6.33 | 2.00 | 6.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| Cycles executing div or sqrt instructions | 32.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 32.28-32.30 |
| Stall cycles | 24.58-24.60 |
| LB full (events) | 25.56-25.58 |
| Front-end | 7.00 |
| Dispatch | 7.00 |
| DIV/SQRT | 32.00 |
| Data deps. | 1.00 |
| Overall L1 | 32.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | 50% |
| 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 (%R15,%RAX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD (%RBX,%RAX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMULPD (%RSI,%RAX,1),%YMM12,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD (%R8,%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 |
| VADDPD (%R11,%RAX,1),%YMM12,%YMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%RDI,%RAX,1),%YMM5,%YMM4 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R10,%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 |
| VFMADD132PD (%RCX,%RAX,1),%YMM1,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD (%R13,%RAX,1),%YMM0,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VDIVPD %YMM2,%YMM14,%YMM7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VDIVPD %YMM4,%YMM2,%YMM8 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VMOVUPD %YMM8,(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD %YMM7,(%RCX,%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(%R15,%RAX,1),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x20(%RBX,%RAX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMULPD 0x20(%RSI,%RAX,1),%YMM6,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD 0x20(%R8,%RAX,1),%YMM10,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD 0x20(%R11,%RAX,1),%YMM6,%YMM12 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x20(%RDI,%RAX,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 0x20(%R10,%RAX,1),%YMM9,%YMM3 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VFMADD132PD 0x20(%RCX,%RAX,1),%YMM15,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD 0x20(%R13,%RAX,1),%YMM3,%YMM11 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VDIVPD %YMM14,%YMM11,%YMM0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VDIVPD %YMM11,%YMM9,%YMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VMOVUPD %YMM0,0x20(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD %YMM2,0x20(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x40,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RAX,0xf0(%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 41eca3 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x1c93> | 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.f90:165-170 |
| Module | exec |
| nb instructions | 29 |
| nb uops | 28 |
| loop length | 170 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 16 |
| used zmm registers | 0 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 5.00 |
| micro-operation queue | 7.00 cycles |
| front end | 7.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 5.50 | 6.50 | 6.33 | 6.33 | 2.00 | 6.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| cycles | 5.50 | 7.00 | 6.33 | 6.33 | 2.00 | 6.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.33 |
| Cycles executing div or sqrt instructions | 32.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 32.28-32.30 |
| Stall cycles | 24.58-24.60 |
| LB full (events) | 25.56-25.58 |
| Front-end | 7.00 |
| Dispatch | 7.00 |
| DIV/SQRT | 32.00 |
| Data deps. | 1.00 |
| Overall L1 | 32.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | 50% |
| 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 (%R15,%RAX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD (%RBX,%RAX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMULPD (%RSI,%RAX,1),%YMM12,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD (%R8,%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 |
| VADDPD (%R11,%RAX,1),%YMM12,%YMM5 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%RDI,%RAX,1),%YMM5,%YMM4 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R10,%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 |
| VFMADD132PD (%RCX,%RAX,1),%YMM1,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD (%R13,%RAX,1),%YMM0,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VDIVPD %YMM2,%YMM14,%YMM7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VDIVPD %YMM4,%YMM2,%YMM8 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VMOVUPD %YMM8,(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD %YMM7,(%RCX,%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(%R15,%RAX,1),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x20(%RBX,%RAX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMULPD 0x20(%RSI,%RAX,1),%YMM6,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VSUBPD 0x20(%R8,%RAX,1),%YMM10,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD 0x20(%R11,%RAX,1),%YMM6,%YMM12 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD 0x20(%RDI,%RAX,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 0x20(%R10,%RAX,1),%YMM9,%YMM3 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VFMADD132PD 0x20(%RCX,%RAX,1),%YMM15,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VADDPD 0x20(%R13,%RAX,1),%YMM3,%YMM11 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VDIVPD %YMM14,%YMM11,%YMM0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VDIVPD %YMM11,%YMM9,%YMM2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-15 | 8 |
| VMOVUPD %YMM0,0x20(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD %YMM2,0x20(%RCX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x40,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RAX,0xf0(%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 41eca3 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0x1c93> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
