| Loop Id: 173 | Module: exec | Source: advec_mom_kernel.f90:138-144 | Coverage: 2.99% |
|---|
| Loop Id: 173 | Module: exec | Source: advec_mom_kernel.f90:138-144 | Coverage: 2.99% |
|---|
0x4356b0 VMOVUPD -0x8(%RCX,%R11,8),%ZMM13 [5] |
0x4356bb VMOVUPD (%RCX,%R11,8),%ZMM14 [5] |
0x4356c2 VMULPD (%R10,%R11,8),%ZMM14,%ZMM14 [4] |
0x4356c9 VMOVUPD -0x8(%RBX,%R11,8),%ZMM15 [7] |
0x4356d4 VMOVUPD (%RBX,%R11,8),%ZMM16 [7] |
0x4356db VFMADD132PD (%R13,%R11,8),%ZMM14,%ZMM16 [1] |
0x4356e3 VFMADD231PD -0x8(%R10,%R11,8),%ZMM13,%ZMM16 [4] |
0x4356ee VFMADD231PD -0x8(%R13,%R11,8),%ZMM15,%ZMM16 [1] |
0x4356f9 VMULPD %ZMM2,%ZMM16,%ZMM13 |
0x4356ff VMOVUPD %ZMM13,(%RAX,%R11,8) [2] |
0x435706 VSUBPD -0x8(%RDI,%R11,8),%ZMM13,%ZMM13 [6] |
0x435711 VADDPD (%RDI,%R11,8),%ZMM13,%ZMM13 [6] |
0x435718 VMOVUPD %ZMM13,(%R14,%R11,8) [3] |
0x43571f ADD $0x8,%R11 |
0x435723 CMP %R8,%R11 |
0x435726 JB 4356b0 |
/scratch_na/users/xoserete/qaas_runs/171-415-7919/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/advec_mom_kernel.f90: 138 - 144 |
-------------------------------------------------------------------------------- |
138: DO j=x_min-1,x_max+2 |
139: ! Staggered cell mass post advection |
140: node_mass_post(j,k)=0.25_8*(density1(j ,k-1)*post_vol(j ,k-1) & |
141: +density1(j ,k )*post_vol(j ,k ) & |
142: +density1(j-1,k-1)*post_vol(j-1,k-1) & |
143: +density1(j-1,k )*post_vol(j-1,k )) |
144: node_mass_pre(j,k)=node_mass_post(j,k)-node_flux(j-1,k)+node_flux(j,k) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| 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 | 1.05 |
| Bottlenecks | micro-operation queue, P0, P1, P5, |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source | advec_mom_kernel.f90:138-144 |
| 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 | 3.50 |
| CQA cycles if no scalar integer | 3.50 |
| CQA cycles if FP arith vectorized | 3.50 |
| CQA cycles if fully vectorized | 3.50 |
| Front-end cycles | 3.50 |
| DIV/SQRT cycles | 3.50 |
| P0 cycles | 3.50 |
| P1 cycles | 3.33 |
| P2 cycles | 3.33 |
| P3 cycles | 1.00 |
| P4 cycles | 3.50 |
| P5 cycles | 1.00 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 3.33 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 3.94 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 16.00 |
| Nb uops | 15.00 |
| Nb loads | 10.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 22.86 |
| Nb FLOP add-sub | 16.00 |
| Nb FLOP mul | 16.00 |
| Nb FLOP fma | 24.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 219.43 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 640.00 |
| Bytes stored | 128.00 |
| Stride 0 | 0.00 |
| Stride 1 | 2.00 |
| Stride n | 5.00 |
| 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 | NA |
| 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 | NA |
| 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 | 1.05 |
| Bottlenecks | micro-operation queue, P0, P1, P5, |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source | advec_mom_kernel.f90:138-144 |
| 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 | 3.50 |
| CQA cycles if no scalar integer | 3.50 |
| CQA cycles if FP arith vectorized | 3.50 |
| CQA cycles if fully vectorized | 3.50 |
| Front-end cycles | 3.50 |
| DIV/SQRT cycles | 3.50 |
| P0 cycles | 3.50 |
| P1 cycles | 3.33 |
| P2 cycles | 3.33 |
| P3 cycles | 1.00 |
| P4 cycles | 3.50 |
| P5 cycles | 1.00 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 3.33 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 3.94 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 16.00 |
| Nb uops | 15.00 |
| Nb loads | 10.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 22.86 |
| Nb FLOP add-sub | 16.00 |
| Nb FLOP mul | 16.00 |
| Nb FLOP fma | 24.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 219.43 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 640.00 |
| Bytes stored | 128.00 |
| Stride 0 | 0.00 |
| Stride 1 | 2.00 |
| Stride n | 5.00 |
| 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 | NA |
| 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 | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | advec_mom_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | advec_mom_kernel.f90:138-144 |
| Module | exec |
| nb instructions | 16 |
| nb uops | 15 |
| loop length | 120 |
| used x86 registers | 9 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 5 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.00 |
| micro-operation queue | 3.50 cycles |
| front end | 3.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.50 | 0.00 | 3.33 | 3.33 | 1.00 | 3.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| cycles | 3.50 | 3.50 | 3.33 | 3.33 | 1.00 | 3.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 3.94 |
| Stall cycles | 0.00 |
| Front-end | 3.50 |
| Dispatch | 3.50 |
| Data deps. | 1.00 |
| Overall L1 | 3.50 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| 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 -0x8(%RCX,%R11,8),%ZMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%RCX,%R11,8),%ZMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMULPD (%R10,%R11,8),%ZMM14,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD -0x8(%RBX,%R11,8),%ZMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%RBX,%R11,8),%ZMM16 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VFMADD132PD (%R13,%R11,8),%ZMM14,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VFMADD231PD -0x8(%R10,%R11,8),%ZMM13,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VFMADD231PD -0x8(%R13,%R11,8),%ZMM15,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMULPD %ZMM2,%ZMM16,%ZMM13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %ZMM13,(%RAX,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VSUBPD -0x8(%RDI,%R11,8),%ZMM13,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD (%RDI,%R11,8),%ZMM13,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VMOVUPD %ZMM13,(%R14,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| ADD $0x8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R8,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 4356b0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x39d0> | 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.f90:138-144 |
| Module | exec |
| nb instructions | 16 |
| nb uops | 15 |
| loop length | 120 |
| used x86 registers | 9 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 5 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.00 |
| micro-operation queue | 3.50 cycles |
| front end | 3.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.50 | 0.00 | 3.33 | 3.33 | 1.00 | 3.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| cycles | 3.50 | 3.50 | 3.33 | 3.33 | 1.00 | 3.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 3.94 |
| Stall cycles | 0.00 |
| Front-end | 3.50 |
| Dispatch | 3.50 |
| Data deps. | 1.00 |
| Overall L1 | 3.50 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | 100% |
| fma | 100% |
| 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 -0x8(%RCX,%R11,8),%ZMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%RCX,%R11,8),%ZMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMULPD (%R10,%R11,8),%ZMM14,%ZMM14 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD -0x8(%RBX,%R11,8),%ZMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VMOVUPD (%RBX,%R11,8),%ZMM16 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VFMADD132PD (%R13,%R11,8),%ZMM14,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VFMADD231PD -0x8(%R10,%R11,8),%ZMM13,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VFMADD231PD -0x8(%R13,%R11,8),%ZMM15,%ZMM16 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMULPD %ZMM2,%ZMM16,%ZMM13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %ZMM13,(%RAX,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VSUBPD -0x8(%RDI,%R11,8),%ZMM13,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VADDPD (%RDI,%R11,8),%ZMM13,%ZMM13 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.65 |
| VMOVUPD %ZMM13,(%R14,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| ADD $0x8,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R8,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 4356b0 <advec_mom_kernel_mod_mp_advec_mom_kernel_.DIR.OMP.PARALLEL.2+0x39d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
