| Loop Id: 9 | Module: kmeans-acfl-O3 | Source: main.cpp:61-67 | Coverage: 91.78% |
|---|
| Loop Id: 9 | Module: kmeans-acfl-O3 | Source: main.cpp:61-67 | Coverage: 91.78% |
|---|
0x1bbc ADD X13, X13, #1 |
0x1bc0 ADD X15, X15, #16 |
0x1bc4 CMP X13, W9,SXTW |
0x1bc8 B.GE 1b88 |
0x1bcc LDP D4, D3, [X15, #1016] [3] |
0x1bd0 FSUB D3, D1, S3 |
0x1bd4 FSUB D4, D0, S4 |
0x1bd8 FMUL D3, D3, D3 |
0x1bdc FMADD D3, D4, D4, D3 |
0x1be0 FCMP D3, D2 |
0x1be4 B.PL 1bbc |
0x1be8 FMOV D2, D3 |
0x1bec STR W13, [X14, X8,LSL #2] [2] |
0x1bf0 LDR W9, [X20] [1] |
0x1bf4 B 1bbc |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 61 - 67 |
-------------------------------------------------------------------------------- |
61: for (int j = 0; j < k; ++j) { |
62: double dist = |
63: (points[i].x - centroids[j].x) * (points[i].x - centroids[j].x) + |
64: (points[i].y - centroids[j].y) * (points[i].y - centroids[j].y); |
65: if (dist < optimal_dist) { |
66: optimal_dist = dist; |
67: assignment[i] = j; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○100.00 | __kmp_invoke_microtask | libomp.so |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.53 |
| CQA speedup if fully vectorized | 1.48 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.46 |
| Bottlenecks | |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:61-67 |
| 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 | 4.00 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 2.61 |
| CQA cycles if fully vectorized | 2.70 |
| Front-end cycles | 1.63 |
| P0 cycles | 1.25 |
| P1 cycles | 1.25 |
| P2 cycles | 0.50 |
| P3 cycles | 0.50 |
| P4 cycles | 0.50 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 1.38 |
| P9 cycles | 1.38 |
| P10 cycles | 1.38 |
| P11 cycles | 1.38 |
| P12 cycles | 0.75 |
| P13 cycles | 0.58 |
| P14 cycles | 0.67 |
| P15 cycles | 0.25 |
| P16 cycles | 0.25 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 4 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 13.00 |
| Nb uops | 13.00 |
| Nb loads | NA |
| Nb stores | 0.50 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.25 |
| Nb FLOP add-sub | 2.00 |
| Nb FLOP mul | 1.00 |
| Nb FLOP fma | 1.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 5.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 18.00 |
| Bytes stored | 2.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 10.80 |
| Vectorization ratio load | 75.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 53.13 |
| Vector-efficiency ratio load | 81.25 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 50.00 |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 50.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.50 |
| CQA speedup if fully vectorized | 1.50 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.13 |
| Bottlenecks | |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:61-67 |
| 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 | 4.00 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 2.67 |
| CQA cycles if fully vectorized | 2.67 |
| Front-end cycles | 1.88 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 0.50 |
| P3 cycles | 0.50 |
| P4 cycles | 0.50 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 1.50 |
| P9 cycles | 1.50 |
| P10 cycles | 1.50 |
| P11 cycles | 1.50 |
| P12 cycles | 1.17 |
| P13 cycles | 0.83 |
| P14 cycles | 1.00 |
| P15 cycles | 0.50 |
| P16 cycles | 0.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 4 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 15.00 |
| Nb uops | 15.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.25 |
| Nb FLOP add-sub | 2.00 |
| Nb FLOP mul | 1.00 |
| Nb FLOP fma | 1.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 6.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 20.00 |
| Bytes stored | 4.00 |
| Stride 0 | 2.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 9.09 |
| Vectorization ratio load | 50.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 62.50 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 50.00 |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 50.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.57 |
| CQA speedup if fully vectorized | 1.47 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.91 |
| Bottlenecks | |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:61-67 |
| 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 | 4.00 |
| CQA cycles if no scalar integer | 4.00 |
| CQA cycles if FP arith vectorized | 2.55 |
| CQA cycles if fully vectorized | 2.73 |
| Front-end cycles | 1.38 |
| P0 cycles | 1.00 |
| P1 cycles | 1.00 |
| P2 cycles | 0.50 |
| P3 cycles | 0.50 |
| P4 cycles | 0.50 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 1.25 |
| P9 cycles | 1.25 |
| P10 cycles | 1.25 |
| P11 cycles | 1.25 |
| P12 cycles | 0.33 |
| P13 cycles | 0.33 |
| P14 cycles | 0.33 |
| P15 cycles | 0.00 |
| P16 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 4 |
| 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 | 1.25 |
| Nb FLOP add-sub | 2.00 |
| Nb FLOP mul | 1.00 |
| Nb FLOP fma | 1.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 4.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 16.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 12.50 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 56.25 |
| Vector-efficiency ratio load | 100.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | 50.00 |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 50.00 |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source file and lines | main.cpp:61-67 |
| Module | kmeans-acfl-O3 |
| nb instructions | 13 |
| nb uops | 13 |
| loop length | 52 |
| used w registers | 1.50 |
| used x registers | 3.50 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 5 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 2.00 |
| micro-operation queue | 1.63 cycles |
| front end | 1.63 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.25 | 1.25 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.38 | 1.38 | 1.38 | 1.38 | 0.75 | 0.58 | 0.67 | 0.25 | 0.25 |
| cycles | 1.25 | 1.25 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.38 | 1.38 | 1.38 | 1.38 | 0.75 | 0.58 | 0.67 | 0.25 | 0.25 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 4.00 |
| Front-end | 1.63 |
| Dispatch | 1.38 |
| Data deps. | 4.00 |
| Overall L1 | 4.00 |
| all | 26% |
| load | 75% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 10% |
| load | 75% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 58% |
| load | 81% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 50% |
| all | 50% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| all | 53% |
| load | 81% |
| store | 25% |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source file and lines | main.cpp:61-67 |
| Module | kmeans-acfl-O3 |
| nb instructions | 15 |
| nb uops | 15 |
| loop length | 60 |
| used w registers | 2 |
| used x registers | 5 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 5 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 2.00 |
| micro-operation queue | 1.88 cycles |
| front end | 1.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.50 | 1.50 | 1.50 | 1.50 | 1.17 | 0.83 | 1.00 | 0.50 | 0.50 |
| cycles | 1.50 | 1.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.50 | 1.50 | 1.50 | 1.50 | 1.17 | 0.83 | 1.00 | 0.50 | 0.50 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 4.00 |
| Front-end | 1.88 |
| Dispatch | 1.50 |
| Data deps. | 4.00 |
| Overall L1 | 4.00 |
| all | 20% |
| load | 50% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 9% |
| load | 50% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 50% |
| load | 62% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 50% |
| all | 50% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| all | 50% |
| load | 62% |
| store | 25% |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X13, X13, #1 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (50.0%) |
| ADD X15, X15, #16 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP X13, W9,SXTW | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| B.GE 1b88 <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0xac> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D4, D3, [X15, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| FSUB D3, D1, S3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (50.0%) |
| FSUB D4, D0, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (50.0%) |
| FMUL D3, D3, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (50.0%) |
| FMADD D3, D4, D4, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (50.0%) |
| FCMP D3, D2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (50.0%) |
| B.PL 1bbc <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0xe0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D2, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (50.0%) |
| STR W13, [X14, X8,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (25.0%) |
| LDR W9, [X20] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | scal (25.0%) |
| B 1bbc <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0xe0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source file and lines | main.cpp:61-67 |
| Module | kmeans-acfl-O3 |
| nb instructions | 11 |
| nb uops | 11 |
| loop length | 44 |
| used w registers | 1 |
| used x registers | 2 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 5 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 2.00 |
| micro-operation queue | 1.38 cycles |
| front end | 1.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 0.33 | 0.33 | 0.33 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 0.33 | 0.33 | 0.33 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 4.00 |
| Front-end | 1.38 |
| Dispatch | 1.25 |
| Data deps. | 4.00 |
| Overall L1 | 4.00 |
| all | 33% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 12% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 66% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 50% |
| all | 50% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| all | 56% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 50% |
| add-sub | 50% |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X13, X13, #1 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (50.0%) |
| ADD X15, X15, #16 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP X13, W9,SXTW | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| B.GE 1b88 <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0xac> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D4, D3, [X15, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| FSUB D3, D1, S3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (50.0%) |
| FSUB D4, D0, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (50.0%) |
| FMUL D3, D3, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (50.0%) |
| FMADD D3, D4, D4, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (50.0%) |
| FCMP D3, D2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (50.0%) |
| B.PL 1bbc <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0xe0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Run run_1_thread | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 1 |
|---|---|
| Run run_2_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 2 |
| Run run_4_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 4 |
| Run run_8_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 8 |
| Run run_16_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 16 |
| Run run_32_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 32 |
| Run run_48_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 48 |
| Run run_64_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 64 |
| Run run_80_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 80 |
| Run run_96_threads | Number processes: 1Number nodes: 1Run Command: <executable> input/100000000.in 1000 100000000 50 25MPI Command: Dataset: Run Directory: /home/fmusial/KMEANS_BenchmarksOMP_PROC_BIND: trueOMP_NUM_THREADS: 96 |
| (run_1_thread) Efficiency | (run_1_thread) Potential Speed-Up (%) | (run_2_threads) Efficiency | (run_2_threads) Potential Speed-Up (%) | (run_4_threads) Efficiency | (run_4_threads) Potential Speed-Up (%) | (run_8_threads) Efficiency | (run_8_threads) Potential Speed-Up (%) | (run_16_threads) Efficiency | (run_16_threads) Potential Speed-Up (%) | (run_32_threads) Efficiency | (run_32_threads) Potential Speed-Up (%) | (run_48_threads) Efficiency | (run_48_threads) Potential Speed-Up (%) | (run_64_threads) Efficiency | (run_64_threads) Potential Speed-Up (%) | (run_80_threads) Efficiency | (run_80_threads) Potential Speed-Up (%) | (run_96_threads) Efficiency | (run_96_threads) Potential Speed-Up (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0.97 | 2.5 | 0.92 | 6.97 | 0.83 | 11.98 | 0.75 | 14.73 | 0.67 | 13.89 | 0.63 | 12.15 | 0.59 | 11.27 | 0.56 | 10.79 | 0.51 | 11.07 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 101.55001068115 | 91.78002166748 |
| run_2_threads | 2 | 0.97 | 1.94 | 2 | 50.604995727539 | 88.308456420898 |
| run_4_threads | 4 | 0.92 | 3.66 | 4 | 25.579996109009 | 82.270233154297 |
| run_8_threads | 8 | 0.83 | 6.67 | 8 | 13.259998321533 | 72.315658569336 |
| run_16_threads | 16 | 0.75 | 11.97 | 16 | 6.5199999809265 | 58.47093963623 |
| run_32_threads | 32 | 0.67 | 21.48 | 32 | 3.3749997615814 | 42.254295349121 |
| run_48_threads | 48 | 0.63 | 30.45 | 48 | 2.2999999523163 | 33.236248016357 |
| run_64_threads | 64 | 0.59 | 37.95 | 64 | 1.7950000762939 | 27.687551498413 |
| run_80_threads | 80 | 0.56 | 44.53 | 80 | 1.5049996376038 | 24.339414596558 |
| run_96_threads | 96 | 0.51 | 48.66 | 96 | 1.3349997997284 | 22.452100753784 |
