| Loop Id: 195 | Module: exec | Source: advec_mom_kernel.f90:95-97 | Coverage: 3.03% |
|---|
| Loop Id: 195 | Module: exec | Source: advec_mom_kernel.f90:95-97 | Coverage: 3.03% |
|---|
0x42e520 VMOVUPD (%RDX,%R10,8),%YMM7 [3] |
0x42e526 VADDPD (%RSI,%R10,8),%YMM7,%YMM7 [1] |
0x42e52c VSUBPD -0x8(%RDX,%R10,8),%YMM7,%YMM7 [3] |
0x42e533 VMOVUPD %YMM7,(%R12,%R10,8) [2] |
0x42e539 VADDPD (%RAX,%R10,8),%YMM7,%YMM7 [6] |
0x42e53f VSUBPD (%R15,%R10,8),%YMM7,%YMM7 [5] |
0x42e545 VMOVUPD %YMM7,(%RDI,%R10,8) [4] |
0x42e54b ADD $0x4,%R10 |
0x42e54f CMP %R9,%R10 |
0x42e552 JB 42e520 |
/home/eoseret/qaas_runs_CPU_9468/171-152-3172/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 95 - 97 |
-------------------------------------------------------------------------------- |
95: DO j=x_min-2,x_max+2 |
96: post_vol(j,k)= volume(j,k)+vol_flux_x(j+1,k )-vol_flux_x(j,k) |
97: pre_vol(j,k)=post_vol(j,k)+vol_flux_y(j ,k+1)-vol_flux_y(j,k) |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.30 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.08 |
| Bottlenecks | micro-operation queue, |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source | advec_mom_kernel.f90:95-97 |
| 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 | 2.17 |
| CQA cycles if no scalar integer | 2.17 |
| CQA cycles if FP arith vectorized | 1.67 |
| CQA cycles if fully vectorized | 1.08 |
| Front-end cycles | 2.17 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 2.00 |
| P1 cycles | 1.67 |
| P2 cycles | 1.67 |
| P3 cycles | 1.00 |
| P4 cycles | 2.00 |
| P5 cycles | 0.50 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 1.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 2.43 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 10.00 |
| Nb uops | 9.00 |
| Nb loads | 5.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.38 |
| Nb FLOP add-sub | 16.00 |
| 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 | 103.38 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 160.00 |
| Bytes stored | 64.00 |
| Stride 0 | 0.00 |
| Stride 1 | 5.00 |
| Stride n | 1.00 |
| 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 | 1.30 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.08 |
| Bottlenecks | micro-operation queue, |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source | advec_mom_kernel.f90:95-97 |
| 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 | 2.17 |
| CQA cycles if no scalar integer | 2.17 |
| CQA cycles if FP arith vectorized | 1.67 |
| CQA cycles if fully vectorized | 1.08 |
| Front-end cycles | 2.17 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 2.00 |
| P1 cycles | 1.67 |
| P2 cycles | 1.67 |
| P3 cycles | 1.00 |
| P4 cycles | 2.00 |
| P5 cycles | 0.50 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 1.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 2.43 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 10.00 |
| Nb uops | 9.00 |
| Nb loads | 5.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.38 |
| Nb FLOP add-sub | 16.00 |
| 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 | 103.38 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 160.00 |
| Bytes stored | 64.00 |
| Stride 0 | 0.00 |
| Stride 1 | 5.00 |
| Stride n | 1.00 |
| 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_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | advec_mom_kernel.f90:95-97 |
| Module | exec |
| nb instructions | 10 |
| nb uops | 9 |
| loop length | 52 |
| used x86 registers | 8 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 1 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 2.17 cycles |
| front end | 2.17 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 2.00 | 1.67 | 1.67 | 1.00 | 2.00 | 0.50 | 1.00 | 1.00 | 1.00 | 0.00 | 1.67 |
| cycles | 0.50 | 2.00 | 1.67 | 1.67 | 1.00 | 2.00 | 0.50 | 1.00 | 1.00 | 1.00 | 0.00 | 1.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 2.43 |
| Stall cycles | 0.00 |
| Front-end | 2.17 |
| Dispatch | 2.00 |
| Data deps. | 1.00 |
| Overall L1 | 2.17 |
| 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,%R10,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RSI,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD -0x8(%RDX,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,(%R12,%R10,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VADDPD (%RAX,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R15,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,(%RDI,%R10,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 42e520 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x1940> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | advec_mom_kernel.f90:95-97 |
| Module | exec |
| nb instructions | 10 |
| nb uops | 9 |
| loop length | 52 |
| used x86 registers | 8 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 1 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 2.17 cycles |
| front end | 2.17 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 2.00 | 1.67 | 1.67 | 1.00 | 2.00 | 0.50 | 1.00 | 1.00 | 1.00 | 0.00 | 1.67 |
| cycles | 0.50 | 2.00 | 1.67 | 1.67 | 1.00 | 2.00 | 0.50 | 1.00 | 1.00 | 1.00 | 0.00 | 1.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 2.43 |
| Stall cycles | 0.00 |
| Front-end | 2.17 |
| Dispatch | 2.00 |
| Data deps. | 1.00 |
| Overall L1 | 2.17 |
| 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,%R10,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RSI,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD -0x8(%RDX,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,(%R12,%R10,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VADDPD (%RAX,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VSUBPD (%R15,%R10,8),%YMM7,%YMM7 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMOVUPD %YMM7,(%RDI,%R10,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R9,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 42e520 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x1940> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
