| Loop Id: 7 | Module: kmeans-acfl-Ofast | Source: main.cpp:59-67 | Coverage: 1.19% |
|---|
| Loop Id: 7 | Module: kmeans-acfl-Ofast | Source: main.cpp:59-67 | Coverage: 1.19% |
|---|
0x1a58 ADD X8, X8, #1 |
0x1a5c CMP W12, W8 |
0x1a60 B.EQ 1ab4 |
0x1a64 CMP W9, #1 |
0x1a68 B.LT 1a58 |
0x1a6c FMOV D1, X15 |
0x1a70 LDR Q0, [X10, X8,LSL #4] |
0x1a74 LDR X14, [X19] |
0x1a78 ORR X13, XZR, XZR |
0x1a7c B 1a8c |
(8) 0x1a80 ADD X13, X13, #1 |
(8) 0x1a84 CMP X13, W9,SXTW |
(8) 0x1a88 B.GE 1a58 |
(8) 0x1a8c LDR Q2, [X11, X13,LSL #4] |
(8) 0x1a90 FSUB V2.2D, V0.2D, V2.2D |
(8) 0x1a94 FMUL V2.2D, V2.2D, V2.2D |
(8) 0x1a98 FADDP D2, V2.2D |
(8) 0x1a9c FCMP D2, D1 |
(8) 0x1aa0 B.GE 1a80 |
(8) 0x1aa4 FMOV D1, D2 |
(8) 0x1aa8 STR W13, [X14, X8,LSL #2] |
(8) 0x1aac LDR W9, [X20] |
(8) 0x1ab0 B 1a80 |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 59 - 67 |
-------------------------------------------------------------------------------- |
59: for (int i = 0; i < n; ++i) { |
60: double optimal_dist = DBL_MAX; |
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 |
|---|---|---|---|
| ○93.63 | __kmp_invoke_microtask | libomp.so | |
| ►6.37+ | __kmp_invoke_microtask | libomp.so | |
| ○ | _dl_rtld_di_serinfo | ld-2.31.so | |
| ○ | _dl_rtld_di_serinfo | ld-2.31.so | |
| ○ | _dl_rtld_di_serinfo | ld-2.31.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 | 1.33 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 6.15 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.23 |
| Bottlenecks | |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:59-61 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.33 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.33 |
| CQA cycles if fully vectorized | 0.22 |
| Front-end cycles | 1.04 |
| P0 cycles | 1.33 |
| P1 cycles | 1.33 |
| P2 cycles | 0.92 |
| P3 cycles | 0.92 |
| P4 cycles | 0.92 |
| P5 cycles | 0.92 |
| P6 cycles | 0.17 |
| P7 cycles | 0.17 |
| P8 cycles | 0.17 |
| P9 cycles | 0.17 |
| P10 cycles | 0.44 |
| P11 cycles | 0.44 |
| P12 cycles | 0.44 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 8.33 |
| Nb uops | 8.33 |
| 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 | 10.67 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 16.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 13.33 |
| Vectorization ratio load | 50.00 |
| 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 | 24.58 |
| Vector-efficiency ratio load | 37.50 |
| 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 | 18.06 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 6.67 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.33 |
| Bottlenecks | P0, P1, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:59-61 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.00 |
| CQA cycles if fully vectorized | 0.15 |
| Front-end cycles | 0.63 |
| P0 cycles | 1.00 |
| P1 cycles | 1.00 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.75 |
| P5 cycles | 0.75 |
| 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 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 5.00 |
| Nb uops | 5.00 |
| 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 | 18.75 |
| 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 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.50 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 6.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.20 |
| Bottlenecks | P0, P1, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source | main.cpp:59-61 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.50 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.50 |
| CQA cycles if fully vectorized | 0.25 |
| Front-end cycles | 1.25 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 1.00 |
| P3 cycles | 1.00 |
| P4 cycles | 1.00 |
| P5 cycles | 1.00 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.25 |
| P9 cycles | 0.25 |
| P10 cycles | 0.67 |
| P11 cycles | 0.67 |
| P12 cycles | 0.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 10.00 |
| Nb uops | 10.00 |
| 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 | 16.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 24.00 |
| Bytes stored | 0.00 |
| Stride 0 | 1.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 20.00 |
| Vectorization ratio load | 50.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 27.50 |
| Vector-efficiency ratio load | 37.50 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 20.83 |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source file and lines | main.cpp:59-67 |
| Module | kmeans-acfl-Ofast |
| nb instructions | 8.33 |
| nb uops | 8.33 |
| loop length | 33.33 |
| used w registers | 3 |
| used x registers | 5 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 0.67 |
| used q registers | 0.67 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.04 cycles |
| front end | 1.04 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.33 | 1.33 | 0.92 | 0.92 | 0.92 | 0.92 | 0.17 | 0.17 | 0.17 | 0.17 | 0.44 | 0.44 | 0.44 | 0.00 | 0.00 |
| cycles | 1.33 | 1.33 | 0.92 | 0.92 | 0.92 | 0.92 | 0.17 | 0.17 | 0.17 | 0.17 | 0.44 | 0.44 | 0.44 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.04 |
| Dispatch | 1.33 |
| Data deps. | 1.00 |
| Overall L1 | 1.33 |
| all | 16% |
| load | 50% |
| 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 | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 13% |
| load | 50% |
| 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% |
| all | 25% |
| load | 37% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 16% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 24% |
| load | 37% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .omp_outlined] |
| Source file and lines | main.cpp:59-67 |
| Module | kmeans-acfl-Ofast |
| nb instructions | 5 |
| nb uops | 5 |
| loop length | 20 |
| used w registers | 3 |
| used x registers | 1 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 0 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 0.63 cycles |
| front end | 0.63 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 0.75 | 0.75 | 0.75 | 0.75 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| cycles | 1.00 | 1.00 | 0.75 | 0.75 | 0.75 | 0.75 | 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 | 0.63 |
| Dispatch | 1.00 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| 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% |
| all | 18% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X8, X8, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| CMP W12, W8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
| B.EQ 1ab4 <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0x108> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| CMP W9, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.LT 1a58 <_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 | 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:59-67 |
| Module | kmeans-acfl-Ofast |
| nb instructions | 10 |
| nb uops | 10 |
| loop length | 40 |
| used w registers | 3 |
| used x registers | 7 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 1 |
| used q registers | 1 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.25 cycles |
| front end | 1.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.25 |
| Dispatch | 1.50 |
| Data deps. | 1.00 |
| Overall L1 | 1.50 |
| all | 25% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 20% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 28% |
| load | 37% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 18% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 27% |
| load | 37% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 20% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X8, X8, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| CMP W12, W8 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
| B.EQ 1ab4 <_Z7k_meansiP7point_tS0_PiS0_ii.omp_outlined+0x108> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| CMP W9, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.LT 1a58 <_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 | 1 | 0.50 | N/A |
| FMOV D1, X15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| LDR Q0, [X10, X8,LSL #4] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (50.0%) |
| LDR X14, [X19] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | scal (25.0%) |
| ORR X13, XZR, XZR | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| B 1a8c <_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 | 1 | 0.50 | N/A |
| Run run_1_thread | Number processes: 1Number nodes: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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: 1Number processes per node: 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_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 (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0.91 | 0.1 | 0.88 | 0.13 | 0.78 | 0.21 | 0.64 | 0.28 | 0.54 | 0.25 | 0.45 | 0.26 | 0.4 | 0.25 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 1.2249989509583 | 1.1863832473755 |
| run_2_threads | 2 | 0.91 | 1.83 | 2 | 0.65099972486496 | 1.1831297874451 |
| run_4_threads | 4 | 0.88 | 3.51 | 4 | 0.34999975562096 | 1.0539207458496 |
| run_8_threads | 8 | 0.78 | 6.21 | 8 | 0.16199992597103 | 0.92311418056488 |
| run_16_threads | 16 | 0.64 | 10.21 | 16 | 0.088999927043915 | 0.77311760187149 |
| run_32_threads | 32 | 0.54 | 17.35 | 32 | 0.060999944806099 | 0.54989278316498 |
| run_48_threads | 48 | 0.45 | 21.57 | 48 | 0.03999999165535 | 0.47461527585983 |
| run_64_threads | 64 | 0.4 | 25.63 | 64 | 0.035999987274408 | 0.41261896491051 |
