| Loop Id: 272 | Module: exec | Source: flux_calc_kernel.f90:56-60 | Coverage: 4.38% |
|---|
| Loop Id: 272 | Module: exec | Source: flux_calc_kernel.f90:56-60 | Coverage: 4.38% |
|---|
0x437e60 VMULPD (%R8,%R13,8),%YMM13,%YMM14 [6] |
0x437e66 VMOVUPD (%R11,%R13,8),%YMM15 [10] |
0x437e6c VADDPD (%RDX,%R13,8),%YMM15,%YMM15 [9] |
0x437e72 VADDPD (%RCX,%R13,8),%YMM15,%YMM15 [8] |
0x437e78 VADDPD (%R12,%R13,8),%YMM15,%YMM15 [3] |
0x437e7e VMULPD %YMM15,%YMM14,%YMM14 |
0x437e83 VMOVUPD %YMM14,(%R14,%R13,8) [1] |
0x437e89 VMULPD (%RSI,%R13,8),%YMM13,%YMM14 [4] |
0x437e8f VMOVUPD (%RAX,%R13,8),%YMM15 [5] |
0x437e95 VADDPD -0x8(%RAX,%R13,8),%YMM15,%YMM15 [5] |
0x437e9c VADDPD -0x8(%RDI,%R13,8),%YMM15,%YMM15 [7] |
0x437ea3 VADDPD (%RDI,%R13,8),%YMM15,%YMM15 [7] |
0x437ea9 VMULPD %YMM15,%YMM14,%YMM14 |
0x437eae VMOVUPD %YMM14,(%R15,%R13,8) [2] |
0x437eb4 ADD $0x4,%R13 |
0x437eb8 CMP %R10,%R13 |
0x437ebb JB 437e60 |
/home/eoseret/qaas_runs_CPU_9468/171-152-3172/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/flux_calc_kernel.f90: 56 - 60 |
-------------------------------------------------------------------------------- |
56: DO j=x_min,x_max+1 |
57: vol_flux_x(j,k)=0.25_8*dt*xarea(j,k) & |
58: *(xvel0(j,k)+xvel0(j,k+1)+xvel1(j,k)+xvel1(j,k+1)) |
59: vol_flux_y(j,k)=0.25_8*dt*yarea(j,k) & |
60: *(yvel0(j,k)+yvel0(j+1,k)+yvel1(j,k)+yvel1(j+1,k)) |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.50 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.25 |
| Bottlenecks | P1, |
| Function | flux_calc_kernel_.DIR.OMP.PARALLEL.2 |
| Source | flux_calc_kernel.f90:56-60 |
| 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 | 5.00 |
| CQA cycles if no scalar integer | 5.00 |
| CQA cycles if FP arith vectorized | 3.33 |
| CQA cycles if fully vectorized | 2.50 |
| Front-end cycles | 4.00 |
| DIV/SQRT cycles | 3.50 |
| P0 cycles | 5.00 |
| P1 cycles | 3.33 |
| P2 cycles | 3.33 |
| P3 cycles | 1.00 |
| P4 cycles | 3.00 |
| 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) | 4.26 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 17.00 |
| Nb uops | 16.00 |
| Nb loads | 10.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 8.00 |
| Nb FLOP add-sub | 24.00 |
| Nb FLOP mul | 16.00 |
| 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 | 76.80 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 320.00 |
| Bytes stored | 64.00 |
| Stride 0 | 0.00 |
| Stride 1 | 8.00 |
| Stride n | 2.00 |
| 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 | 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 | 50.00 |
| 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 | 1.50 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.25 |
| Bottlenecks | P1, |
| Function | flux_calc_kernel_.DIR.OMP.PARALLEL.2 |
| Source | flux_calc_kernel.f90:56-60 |
| 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 | 5.00 |
| CQA cycles if no scalar integer | 5.00 |
| CQA cycles if FP arith vectorized | 3.33 |
| CQA cycles if fully vectorized | 2.50 |
| Front-end cycles | 4.00 |
| DIV/SQRT cycles | 3.50 |
| P0 cycles | 5.00 |
| P1 cycles | 3.33 |
| P2 cycles | 3.33 |
| P3 cycles | 1.00 |
| P4 cycles | 3.00 |
| 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) | 4.26 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 17.00 |
| Nb uops | 16.00 |
| Nb loads | 10.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 8.00 |
| Nb FLOP add-sub | 24.00 |
| Nb FLOP mul | 16.00 |
| 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 | 76.80 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 320.00 |
| Bytes stored | 64.00 |
| Stride 0 | 0.00 |
| Stride 1 | 8.00 |
| Stride n | 2.00 |
| 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 | 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 | 50.00 |
| 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 | flux_calc_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | flux_calc_kernel.f90:56-60 |
| Module | exec |
| nb instructions | 17 |
| nb uops | 16 |
| loop length | 93 |
| used x86 registers | 12 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 3 |
| used zmm registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.50 |
| micro-operation queue | 4.00 cycles |
| front end | 4.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.50 | 3.50 | 3.33 | 3.33 | 1.00 | 3.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| cycles | 3.50 | 5.00 | 3.33 | 3.33 | 1.00 | 3.00 | 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 | 4.26 |
| Stall cycles | 0.00 |
| Front-end | 4.00 |
| Dispatch | 5.00 |
| Data deps. | 1.00 |
| Overall L1 | 5.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| 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 | 50% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMULPD (%R8,%R13,8),%YMM13,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD (%R11,%R13,8),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RDX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%RCX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%R12,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMULPD %YMM15,%YMM14,%YMM14 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %YMM14,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMULPD (%RSI,%R13,8),%YMM13,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD (%RAX,%R13,8),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD -0x8(%RAX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD -0x8(%RDI,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%RDI,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMULPD %YMM15,%YMM14,%YMM14 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %YMM14,(%R15,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R10,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 437e60 <flux_calc_kernel_module_mp_flux_calc_kernel_.DIR.OMP.PARALLEL.2+0x630> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | flux_calc_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | flux_calc_kernel.f90:56-60 |
| Module | exec |
| nb instructions | 17 |
| nb uops | 16 |
| loop length | 93 |
| used x86 registers | 12 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 3 |
| used zmm registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.50 |
| micro-operation queue | 4.00 cycles |
| front end | 4.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.50 | 3.50 | 3.33 | 3.33 | 1.00 | 3.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 3.33 |
| cycles | 3.50 | 5.00 | 3.33 | 3.33 | 1.00 | 3.00 | 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 | 4.26 |
| Stall cycles | 0.00 |
| Front-end | 4.00 |
| Dispatch | 5.00 |
| Data deps. | 1.00 |
| Overall L1 | 5.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| 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 | 50% |
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMULPD (%R8,%R13,8),%YMM13,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD (%R11,%R13,8),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD (%RDX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%RCX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%R12,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMULPD %YMM15,%YMM14,%YMM14 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %YMM14,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMULPD (%RSI,%R13,8),%YMM13,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD (%RAX,%R13,8),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VADDPD -0x8(%RAX,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD -0x8(%RDI,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VADDPD (%RDI,%R13,8),%YMM15,%YMM15 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
| VMULPD %YMM15,%YMM14,%YMM14 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMOVUPD %YMM14,(%R15,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R10,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 437e60 <flux_calc_kernel_module_mp_flux_calc_kernel_.DIR.OMP.PARALLEL.2+0x630> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
