| Loop Id: 389 | Module: exec | Source: ideal_gas_kernel.f90:49-55 | Coverage: 5.72% |
|---|
| Loop Id: 389 | Module: exec | Source: ideal_gas_kernel.f90:49-55 | Coverage: 5.72% |
|---|
0x4459a0 VMOVUPD (%RDX,%R13,8),%ZMM6 [1] |
0x4459a7 VDIVPD %ZMM6,%ZMM1,%ZMM7 |
0x4459ad VMULPD %ZMM2,%ZMM6,%ZMM8 |
0x4459b3 VMULPD (%RAX,%R13,8),%ZMM8,%ZMM8 [2] |
0x4459ba VMULPD %ZMM7,%ZMM7,%ZMM7 |
0x4459c0 VMULPD %ZMM3,%ZMM6,%ZMM6 |
0x4459c6 VMULPD %ZMM8,%ZMM6,%ZMM6 |
0x4459cc VMULPD %ZMM6,%ZMM7,%ZMM6 |
0x4459d2 VSQRTPD %ZMM6,%ZMM6 |
0x4459d8 VMOVUPD %ZMM8,(%R14,%R13,8) [3] |
0x4459df VMOVUPD %ZMM6,(%RSI,%R13,8) [4] |
0x4459e6 ADD $0x8,%R13 |
0x4459ea CMP %R15,%R13 |
0x4459ed JB 4459a0 |
/home/eoseret/qaas_runs_CPU_9468/171-152-3172/intel/CloverLeafFC/build/CloverLeafFC/CloverLeaf_ref/kernels/ideal_gas_kernel.f90: 49 - 55 |
-------------------------------------------------------------------------------- |
49: DO j=x_min,x_max |
50: v=1.0_8/density(j,k) |
51: pressure(j,k)=(1.4_8-1.0_8)*density(j,k)*energy(j,k) |
52: pressurebyenergy=(1.4_8-1.0_8)*density(j,k) |
53: pressurebyvolume=-density(j,k)*pressure(j,k) |
54: sound_speed_squared=v*v*(pressure(j,k)*pressurebyenergy-pressurebyvolume) |
55: soundspeed(j,k)=SQRT(sound_speed_squared) |
| 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 | 5.67 |
| Bottlenecks | P0, |
| Function | ideal_gas_kernel_.DIR.OMP.PARALLEL.2 |
| Source | ideal_gas_kernel.f90:49-55 |
| 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 | 34.00 |
| CQA cycles if no scalar integer | 34.00 |
| CQA cycles if FP arith vectorized | 34.00 |
| CQA cycles if fully vectorized | 34.00 |
| Front-end cycles | 3.00 |
| DIV/SQRT cycles | 6.00 |
| P0 cycles | 3.00 |
| P1 cycles | 0.67 |
| P2 cycles | 0.67 |
| P3 cycles | 1.00 |
| P4 cycles | 6.00 |
| P5 cycles | 1.00 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.67 |
| P11 cycles | 34.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 34.34 - 34.51 |
| Stall cycles (UFS) | 30.64 - 30.80 |
| Nb insns | 14.00 |
| Nb uops | 17.00 |
| Nb loads | 2.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.88 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 48.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 8.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 8.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 7.53 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 128.00 |
| Stride 0 | 0.00 |
| Stride 1 | 4.00 |
| 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 | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | 100.00 |
| 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 | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | 100.00 |
| 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 | 5.67 |
| Bottlenecks | P0, |
| Function | ideal_gas_kernel_.DIR.OMP.PARALLEL.2 |
| Source | ideal_gas_kernel.f90:49-55 |
| 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 | 34.00 |
| CQA cycles if no scalar integer | 34.00 |
| CQA cycles if FP arith vectorized | 34.00 |
| CQA cycles if fully vectorized | 34.00 |
| Front-end cycles | 3.00 |
| DIV/SQRT cycles | 6.00 |
| P0 cycles | 3.00 |
| P1 cycles | 0.67 |
| P2 cycles | 0.67 |
| P3 cycles | 1.00 |
| P4 cycles | 6.00 |
| P5 cycles | 1.00 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.67 |
| P11 cycles | 34.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 34.34 - 34.51 |
| Stall cycles (UFS) | 30.64 - 30.80 |
| Nb insns | 14.00 |
| Nb uops | 17.00 |
| Nb loads | 2.00 |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.88 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 48.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 8.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 8.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 7.53 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 128.00 |
| Stride 0 | 0.00 |
| Stride 1 | 4.00 |
| 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 | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | 100.00 |
| 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 | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | 100.00 |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | ideal_gas_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | ideal_gas_kernel.f90:49-55 |
| Module | exec |
| nb instructions | 14 |
| nb uops | 17 |
| loop length | 79 |
| used x86 registers | 6 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 6 |
| nb stack references | 0 |
| micro-operation queue | 3.00 cycles |
| front end | 3.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 6.00 | 0.00 | 0.67 | 0.67 | 1.00 | 6.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.67 |
| cycles | 6.00 | 3.00 | 0.67 | 0.67 | 1.00 | 6.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.67 |
| Cycles executing div or sqrt instructions | 34.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 34.34-34.51 |
| Stall cycles | 30.64-30.80 |
| RS full (events) | 33.74-33.92 |
| Front-end | 3.00 |
| Dispatch | 6.00 |
| DIV/SQRT | 34.00 |
| Data deps. | 1.00 |
| Overall L1 | 34.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 100% |
| 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,%R13,8),%ZMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VDIVPD %ZMM6,%ZMM1,%ZMM7 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMULPD %ZMM2,%ZMM6,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD (%RAX,%R13,8),%ZMM8,%ZMM8 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMULPD %ZMM7,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM3,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM8,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM6,%ZMM7,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VSQRTPD %ZMM6,%ZMM6 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 23-32 | 18 |
| VMOVUPD %ZMM8,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM6,(%RSI,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| ADD $0x8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R15,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 4459a0 <ideal_gas_kernel_module_mp_ideal_gas_kernel_.DIR.OMP.PARALLEL.2+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | ideal_gas_kernel_.DIR.OMP.PARALLEL.2 |
| Source file and lines | ideal_gas_kernel.f90:49-55 |
| Module | exec |
| nb instructions | 14 |
| nb uops | 17 |
| loop length | 79 |
| used x86 registers | 6 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 6 |
| nb stack references | 0 |
| micro-operation queue | 3.00 cycles |
| front end | 3.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 6.00 | 0.00 | 0.67 | 0.67 | 1.00 | 6.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.67 |
| cycles | 6.00 | 3.00 | 0.67 | 0.67 | 1.00 | 6.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 0.67 |
| Cycles executing div or sqrt instructions | 34.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 34.34-34.51 |
| Stall cycles | 30.64-30.80 |
| RS full (events) | 33.74-33.92 |
| Front-end | 3.00 |
| Dispatch | 6.00 |
| DIV/SQRT | 34.00 |
| Data deps. | 1.00 |
| Overall L1 | 34.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 100% |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | 100% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 100% |
| 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,%R13,8),%ZMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
| VDIVPD %ZMM6,%ZMM1,%ZMM7 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 22-24 | 16 |
| VMULPD %ZMM2,%ZMM6,%ZMM8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD (%RAX,%R13,8),%ZMM8,%ZMM8 | 1 | 0.50 | 0 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMULPD %ZMM7,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM3,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM8,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VMULPD %ZMM6,%ZMM7,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VSQRTPD %ZMM6,%ZMM6 | 3 | 2.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 23-32 | 18 |
| VMOVUPD %ZMM8,(%R14,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| VMOVUPD %ZMM6,(%RSI,%R13,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 1 |
| ADD $0x8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %R15,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 4459a0 <ideal_gas_kernel_module_mp_ideal_gas_kernel_.DIR.OMP.PARALLEL.2+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
