| Loop Id: 336 | Module: exec | Source: ideal_gas.cpp:40-45 | Coverage: 4.31% |
|---|
| Loop Id: 336 | Module: exec | Source: ideal_gas.cpp:40-45 | Coverage: 4.31% |
|---|
0x427820 LD1D {Z2.D}, P1/Z, [X22, X0,LSL #3] [2] |
0x427824 LD1D {Z1.D}, P1/Z, [X5, X0,LSL #3] [1] |
0x427828 MOVPRFX Z0, Z5 |
0x42782c FDIV Z0.D, P0/M, Z0.D, Z2.D |
0x427830 FMUL Z6.D, Z1.D, Z2.D |
0x427834 FMUL Z7.D, Z0.D, Z0.D |
0x427838 FMUL Z16.D, Z6.D, Z4.D |
0x42783c ST1D {Z16.D}, P1, [X3, X0,LSL #3] [3] |
0x427840 LD1D {Z17.D}, P1/Z, [X22, X0,LSL #3] [2] |
0x427844 FMUL Z18.D, Z17.D, Z3.D |
0x427848 FMUL Z19.D, Z18.D, Z7.D |
0x42784c FMUL Z20.D, Z19.D, Z16.D |
0x427850 FSQRT Z20.D, P0/M, Z20.D |
0x427854 ST1D {Z20.D}, P1, [X24, X0,LSL #3] [4] |
0x427858 ADD X0, X0, X8 |
0x42785c WHILELO P1.D, X0, X1 |
0x427860 B.NE 427820 |
/home/hbollore/qaas-runs/170-290-5445/intel/CloverLeafCXX/build/CloverLeafCXX/src/omp/ideal_gas.cpp: 40 - 45 |
-------------------------------------------------------------------------------- |
40: double v = 1.0 / density(i, j); |
41: pressure(i, j) = (1.4 - 1.0) * density(i, j) * energy(i, j); |
42: double pressurebyenergy = (1.4 - 1.0) * density(i, j); |
43: double pressurebyvolume = -density(i, j) * pressure(i, j); |
44: double sound_speed_squared = v * v * (pressure(i, j) * pressurebyenergy - pressurebyvolume); |
45: soundspeed(i, j) = std::sqrt(sound_speed_squared); |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.42+ | __kmp_GOMP_microtask_wrapper(i[...] | libomp.so | |
| ○ | __kmp_invoke_microtask | libomp.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 | 1.50 |
| Bottlenecks | P6, P7, |
| Function | ideal_gas_kernel(int, int, int, int, clover::Buffer2D |
| Source | ideal_gas.cpp:40-45 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 4.50 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 4.50 |
| CQA cycles if fully vectorized | 4.50 |
| Front-end cycles | 2.13 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.25 |
| P3 cycles | 1.00 |
| P4 cycles | 0.25 |
| P5 cycles | 4.50 |
| P6 cycles | 4.50 |
| P7 cycles | 3.00 |
| P8 cycles | 3.00 |
| P9 cycles | 2.50 |
| P10 cycles | 2.50 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 2.00 - 1.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 17.00 |
| Nb uops | 17.00 |
| Nb loads | NA |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.11 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 24.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 4.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 4.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 35.56 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 96.00 |
| Bytes stored | 64.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 92.86 |
| 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 | 0.00 |
| 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 | 100.00 |
| 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 | 1.50 |
| Bottlenecks | P6, P7, |
| Function | ideal_gas_kernel(int, int, int, int, clover::Buffer2D |
| Source | ideal_gas.cpp:40-45 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 4.50 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 4.50 |
| CQA cycles if fully vectorized | 4.50 |
| Front-end cycles | 2.13 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.25 |
| P3 cycles | 1.00 |
| P4 cycles | 0.25 |
| P5 cycles | 4.50 |
| P6 cycles | 4.50 |
| P7 cycles | 3.00 |
| P8 cycles | 3.00 |
| P9 cycles | 2.50 |
| P10 cycles | 2.50 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 2.00 - 1.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 17.00 |
| Nb uops | 17.00 |
| Nb loads | NA |
| Nb stores | 2.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.11 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 24.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 4.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 4.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 35.56 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 96.00 |
| Bytes stored | 64.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 92.86 |
| 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 | 0.00 |
| 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 | 100.00 |
| Path / |
| Function | ideal_gas_kernel(int, int, int, int, clover::Buffer2D |
| Source file and lines | ideal_gas.cpp:40-45 |
| Module | exec |
| nb instructions | 17 |
| loop length | 68 |
| nb stack references | 0 |
| front end | 2.13 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.50 | 0.25 | 1.00 | 0.25 | 4.50 | 4.50 | 1.00 | 1.00 | 2.50 | 2.50 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.50 | 0.25 | 1.00 | 0.25 | 4.50 | 4.50 | 3.00 | 3.00 | 2.50 | 2.50 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | 2.00-1.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 2.13 |
| Data deps. | 1.00 |
| Overall L1 | 4.50 |
| all | 83% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 92% |
| 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 | 0% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LD1D {Z2.D}, P1/Z, [X22, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| LD1D {Z1.D}, P1/Z, [X5, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| MOVPRFX Z0, Z5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
| FDIV Z0.D, P0/M, Z0.D, Z2.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1-0.50 |
| FMUL Z6.D, Z1.D, Z2.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z7.D, Z0.D, Z0.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z16.D, Z6.D, Z4.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ST1D {Z16.D}, P1, [X3, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| LD1D {Z17.D}, P1/Z, [X22, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| FMUL Z18.D, Z17.D, Z3.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z19.D, Z18.D, Z7.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z20.D, Z19.D, Z16.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FSQRT Z20.D, P0/M, Z20.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 7-16 | 1-0.50 |
| ST1D {Z20.D}, P1, [X24, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| ADD X0, X0, X8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| WHILELO P1.D, X0, X1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 2 |
| B.NE 427820 <_Z16ideal_gas_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_._omp_fn.0+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| Function | ideal_gas_kernel(int, int, int, int, clover::Buffer2D |
| Source file and lines | ideal_gas.cpp:40-45 |
| Module | exec |
| nb instructions | 17 |
| loop length | 68 |
| nb stack references | 0 |
| front end | 2.13 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.50 | 0.25 | 1.00 | 0.25 | 4.50 | 4.50 | 1.00 | 1.00 | 2.50 | 2.50 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.50 | 0.25 | 1.00 | 0.25 | 4.50 | 4.50 | 3.00 | 3.00 | 2.50 | 2.50 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | 2.00-1.00 |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 2.13 |
| Data deps. | 1.00 |
| Overall L1 | 4.50 |
| all | 83% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 92% |
| 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 | 0% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LD1D {Z2.D}, P1/Z, [X22, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| LD1D {Z1.D}, P1/Z, [X5, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| MOVPRFX Z0, Z5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
| FDIV Z0.D, P0/M, Z0.D, Z2.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1-0.50 |
| FMUL Z6.D, Z1.D, Z2.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z7.D, Z0.D, Z0.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z16.D, Z6.D, Z4.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ST1D {Z16.D}, P1, [X3, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| LD1D {Z17.D}, P1/Z, [X22, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 6 | 0.50 |
| FMUL Z18.D, Z17.D, Z3.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z19.D, Z18.D, Z7.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FMUL Z20.D, Z19.D, Z16.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| FSQRT Z20.D, P0/M, Z20.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 7-16 | 1-0.50 |
| ST1D {Z20.D}, P1, [X24, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| ADD X0, X0, X8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
| WHILELO P1.D, X0, X1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 2 |
| B.NE 427820 <_Z16ideal_gas_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_._omp_fn.0+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |