| Loop Id: 122 | Module: exec | Source: advec_cell_kernel.f90:177-183 | Coverage: 0.02% |
|---|
| Loop Id: 122 | Module: exec | Source: advec_cell_kernel.f90:177-183 | Coverage: 0.02% |
|---|
0x41fdd0 ADD W5, W5, #1 |
0x41fdd4 CMP W7, W13 |
0x41fdd8 B.GE 41fe30 |
0x41fddc SUB X10, X8, #8 |
0x41fde0 MOVZ X0, #0 |
0x41fde4 ORR P3.B, P1/Z, P1.B, P1.B |
(123) 0x41fde8 LD1D {Z6.D}, P3/Z, [X4, X0,LSL #3] |
(123) 0x41fdec LD1D {Z7.D}, P3/Z, [X3, X0,LSL #3] |
(123) 0x41fdf0 LD1D {Z16.D}, P3/Z, [X8, X0,LSL #3] |
(123) 0x41fdf4 LD1D {Z18.D}, P3/Z, [X10, X0,LSL #3] |
(123) 0x41fdf8 LD1D {Z20.D}, P3/Z, [X9, X0,LSL #3] |
(123) 0x41fdfc FSUB Z17.D, Z6.D, Z7.D |
(123) 0x41fe00 FADD Z19.D, Z17.D, Z16.D |
(123) 0x41fe04 FSUB Z21.D, Z19.D, Z18.D |
(123) 0x41fe08 FADD Z22.D, Z21.D, Z20.D |
(123) 0x41fe0c ST1D {Z22.D}, P3, [X1, X0,LSL #3] |
(123) 0x41fe10 LD1D {Z23.D}, P3/Z, [X4, X0,LSL #3] |
(123) 0x41fe14 LD1D {Z24.D}, P3/Z, [X3, X0,LSL #3] |
(123) 0x41fe18 FSUB Z25.D, Z23.D, Z24.D |
(123) 0x41fe1c FSUB Z26.D, Z22.D, Z25.D |
(123) 0x41fe20 ST1D {Z26.D}, P3, [X2, X0,LSL #3] |
(123) 0x41fe24 ADD X0, X0, X12 |
(123) 0x41fe28 WHILELO P3.D, X0, X28 |
(123) 0x41fe2c B.NE 41fde8 |
0x41fe30 ADD X9, X9, X15 |
0x41fe34 ADD X4, X4, X27 |
0x41fe38 ADD X3, X3, X27 |
0x41fe3c ADD X8, X8, X16 |
0x41fe40 ADD X1, X1, X18 |
0x41fe44 ADD X2, X2, X17 |
0x41fe48 CMP W14, W5 |
0x41fe4c B.GT 41fdd0 |
/home/hbollore/qaas/qaas-runs/169-814-4157/intel/CloverLeaf/build/CloverLeaf/CloverLeaf_ref/kernels/advec_cell_kernel.f90: 177 - 183 |
-------------------------------------------------------------------------------- |
177: IF(sweep_number.EQ.1)THEN |
178: !$OMP DO |
179: DO k=y_min-2,y_max+2 |
180: !$OMP SIMD |
181: DO j=x_min-2,x_max+2 |
182: pre_vol(j,k)=volume(j,k)+(vol_flux_y(j ,k+1)-vol_flux_y(j,k)+vol_flux_x(j+1,k )-vol_flux_x(j,k)) |
183: post_vol(j,k)=pre_vol(j,k)-(vol_flux_y(j ,k+1)-vol_flux_y(j,k)) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_cell_kernel | advec_cell_kernel.f90:270 | exec |
| ○ | advec_cell_driver | advec_cell_driver.f90:84 | exec |
| ○ | advection | advection.f90:57 | exec |
| ○ | hydro | hydro.f90:64 | exec |
| ○ | main | clover_leaf.f90:41 | exec |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | clover_leaf.f90:41 | exec |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.62 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 4.94 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.68 |
| Bottlenecks | |
| Function | advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:177-177,advec_cell_kernel.f90:180-180,advec_cell_kernel.f90:183-183 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 2.63 |
| CQA cycles if no scalar integer | 1.63 |
| CQA cycles if FP arith vectorized | 2.63 |
| CQA cycles if fully vectorized | 0.53 |
| Front-end cycles | 1.56 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 2.63 |
| P2 cycles | 2.63 |
| P3 cycles | 2.63 |
| P4 cycles | 2.63 |
| P5 cycles | 0.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 12.50 |
| Nb uops | 12.50 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 5.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 16.67 |
| Vector-efficiency ratio all | 22.86 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 14.58 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 5.05 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.71 |
| Bottlenecks | P2, P3, P4, P5, |
| Function | advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:177-177,advec_cell_kernel.f90:180-180,advec_cell_kernel.f90:183-183 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 3.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 3.00 |
| CQA cycles if fully vectorized | 0.59 |
| Front-end cycles | 1.75 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 3.00 |
| P2 cycles | 3.00 |
| P3 cycles | 3.00 |
| P4 cycles | 3.00 |
| P5 cycles | 0.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 14.00 |
| Nb uops | 14.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 10.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 33.33 |
| Vector-efficiency ratio all | 22.50 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 16.67 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 4.80 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.64 |
| Bottlenecks | P2, P3, P4, P5, |
| Function | advec_cell_kernel._omp_fn.0 |
| Source | advec_cell_kernel.f90:177-177,advec_cell_kernel.f90:180-180,advec_cell_kernel.f90:183-183 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 2.25 |
| CQA cycles if no scalar integer | 2.25 |
| CQA cycles if FP arith vectorized | 2.25 |
| CQA cycles if fully vectorized | 0.47 |
| Front-end cycles | 1.38 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 2.25 |
| P2 cycles | 2.25 |
| P3 cycles | 2.25 |
| P4 cycles | 2.25 |
| P5 cycles | 0.00 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 11.00 |
| Nb uops | 11.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 23.21 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| Path / |
| Function | advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:177-183 |
| Module | exec |
| nb instructions | 12.50 |
| loop length | 50 |
| nb stack references | 0 |
| front end | 1.56 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 2.63 | 2.63 | 2.63 | 2.63 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 2.63 | 2.63 | 2.63 | 2.63 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.56 |
| Data deps. | 1.00 |
| Overall L1 | 2.63 |
| all | 5% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 16% |
| Function | advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:177-183 |
| Module | exec |
| nb instructions | 14 |
| loop length | 56 |
| nb stack references | 0 |
| front end | 1.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 3.00 | 3.00 | 3.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 3.00 | 3.00 | 3.00 | 3.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.75 |
| Data deps. | 1.00 |
| Overall L1 | 3.00 |
| all | 10% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 33% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD W5, W5, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP W7, W13 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.GE 41fe30 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0xd50> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| SUB X10, X8, #8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| MOVZ X0, #0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ORR P3.B, P1/Z, P1.B, P1.B | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
| ADD X9, X9, X15 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X4, X4, X27 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X3, X3, X27 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X8, X8, X16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X1, X1, X18 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X2, X2, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP W14, W5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.GT 41fdd0 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0xcf0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| Function | advec_cell_kernel._omp_fn.0 |
| Source file and lines | advec_cell_kernel.f90:177-183 |
| Module | exec |
| nb instructions | 11 |
| loop length | 44 |
| nb stack references | 0 |
| front end | 1.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 2.25 | 2.25 | 2.25 | 2.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 2.25 | 2.25 | 2.25 | 2.25 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.38 |
| Data deps. | 1.00 |
| Overall L1 | 2.25 |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD W5, W5, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP W7, W13 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.GE 41fe30 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0xd50> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| ADD X9, X9, X15 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X4, X4, X27 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X3, X3, X27 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X8, X8, X16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X1, X1, X18 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| ADD X2, X2, X17 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| CMP W14, W5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| B.GT 41fdd0 <__advec_cell_kernel_module_MOD_advec_cell_kernel._omp_fn.0+0xcf0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |