| Loop Id: 4 | Module: kmeans-gcc-O3-vectorize | Source: main.cpp:60-65 | Coverage: 88.51% |
|---|
| Loop Id: 4 | Module: kmeans-gcc-O3-vectorize | Source: main.cpp:60-65 | Coverage: 88.51% |
|---|
0x401c6c LDP D28, D27, [X4] [2] |
0x401c70 FMOV D29, D26 |
0x401c74 ORR X0, XZR, X7 |
0x401c78 MOVZ W1, #0 |
0x401c7c HINT #0 |
0x401c80 LDP D31, D30, [X0] [1] |
0x401c84 FSUB D30, D27, S30 |
0x401c88 FSUB D31, D28, S31 |
0x401c8c FMUL D30, D30, D30 |
0x401c90 FMADD D31, D31, D31, D30 |
0x401c94 FCMPE D29, D31 |
0x401c98 B.GT 401ccc |
0x401c9c ADD W1, W1, #1 |
0x401ca0 ADD X0, X0, #16 |
0x401ca4 CMP W2, W1 |
0x401ca8 B.NE 401c80 |
0x401cac ADD X3, X3, #1 |
0x401cb0 ADD X4, X4, #16 |
0x401cb4 CMP W6, W3 |
0x401cb8 B.GT 401c6c |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 60 - 65 |
-------------------------------------------------------------------------------- |
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) { |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►50.00+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►50.00+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►75.00+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►25.00+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►87.49+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►12.51+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►93.74+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►6.26+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►96.86+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►3.14+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►97.92+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►2.08+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.41+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | pthread_condattr_setpshared | libc.so.6 | |
| ○ | __clone | libc.so.6 | |
| ►1.59+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-vectorize |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-vectorize |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| 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 | 3.56 |
| CQA speedup if FP arith vectorized | 2.29 |
| CQA speedup if fully vectorized | 5.16 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.19 |
| Bottlenecks | micro-operation queue, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source | main.cpp:60-65 |
| 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 | 2.38 |
| CQA cycles if no scalar integer | 0.67 |
| CQA cycles if FP arith vectorized | 1.04 |
| CQA cycles if fully vectorized | 0.46 |
| Front-end cycles | 2.38 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 2.00 |
| P3 cycles | 2.00 |
| P4 cycles | 2.00 |
| P5 cycles | 2.00 |
| P6 cycles | 1.50 |
| P7 cycles | 1.50 |
| P8 cycles | 1.50 |
| P9 cycles | 1.50 |
| 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 | NA |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 20.00 |
| Nb uops | 19.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.11 |
| 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 | 13.47 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 32.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 18.18 |
| 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 | 26.14 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 20.83 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 18.75 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.56 |
| CQA speedup if FP arith vectorized | 2.29 |
| CQA speedup if fully vectorized | 5.16 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.19 |
| Bottlenecks | micro-operation queue, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source | main.cpp:60-65 |
| 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 | 2.38 |
| CQA cycles if no scalar integer | 0.67 |
| CQA cycles if FP arith vectorized | 1.04 |
| CQA cycles if fully vectorized | 0.46 |
| Front-end cycles | 2.38 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 2.00 |
| P3 cycles | 2.00 |
| P4 cycles | 2.00 |
| P5 cycles | 2.00 |
| P6 cycles | 1.50 |
| P7 cycles | 1.50 |
| P8 cycles | 1.50 |
| P9 cycles | 1.50 |
| 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 | NA |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 20.00 |
| Nb uops | 19.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.11 |
| 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 | 13.47 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 32.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 18.18 |
| 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 | 26.14 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 20.83 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 18.75 |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source file and lines | main.cpp:60-65 |
| Module | kmeans-gcc-O3-vectorize |
| nb instructions | 20 |
| nb uops | 19 |
| loop length | 80 |
| used w registers | 4 |
| used x registers | 5 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 6 |
| 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 | 2.38 cycles |
| front end | 2.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 2.00 | 2.00 | 2.00 | 2.00 | 1.50 | 1.50 | 1.50 | 1.50 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 2.00 | 2.00 | 2.00 | 2.00 | 1.50 | 1.50 | 1.50 | 1.50 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Front-end | 2.38 |
| Dispatch | 2.00 |
| Overall L1 | 2.38 |
| all | 40% |
| 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 | 18% |
| 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 | 27% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 26% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 20% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDP D28, D27, [X4] | 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%) |
| FMOV D29, D26 | 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%) |
| ORR X0, XZR, X7 | 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 |
| MOVZ W1, #0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| HINT #0 | N/A | ||||||||||||||||||
| LDP D31, D30, [X0] | 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%) |
| FSUB D30, D27, S30 | 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%) |
| FSUB D31, D28, S31 | 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%) |
| FMUL D30, D30, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMADD D31, D31, D31, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (25.0%) |
| FCMPE D29, D31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401ccc <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD W1, W1, #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 (12.5%) |
| ADD X0, X0, #16 | 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 W2, W1 | 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.NE 401c80 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x80> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD X3, X3, #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 |
| ADD X4, X4, #16 | 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 W6, W3 | 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.GT 401c6c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x6c> | 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_fn.0] |
| Source file and lines | main.cpp:60-65 |
| Module | kmeans-gcc-O3-vectorize |
| nb instructions | 20 |
| nb uops | 19 |
| loop length | 80 |
| used w registers | 4 |
| used x registers | 5 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 6 |
| 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 | 2.38 cycles |
| front end | 2.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 2.00 | 2.00 | 2.00 | 2.00 | 1.50 | 1.50 | 1.50 | 1.50 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 2.00 | 2.00 | 2.00 | 2.00 | 1.50 | 1.50 | 1.50 | 1.50 | 0.67 | 0.67 | 0.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Front-end | 2.38 |
| Dispatch | 2.00 |
| Overall L1 | 2.38 |
| all | 40% |
| 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 | 18% |
| 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 | 27% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 26% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 20% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDP D28, D27, [X4] | 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%) |
| FMOV D29, D26 | 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%) |
| ORR X0, XZR, X7 | 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 |
| MOVZ W1, #0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| HINT #0 | N/A | ||||||||||||||||||
| LDP D31, D30, [X0] | 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%) |
| FSUB D30, D27, S30 | 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%) |
| FSUB D31, D28, S31 | 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%) |
| FMUL D30, D30, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMADD D31, D31, D31, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (25.0%) |
| FCMPE D29, D31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401ccc <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xcc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD W1, W1, #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 (12.5%) |
| ADD X0, X0, #16 | 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 W2, W1 | 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.NE 401c80 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x80> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD X3, X3, #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 |
| ADD X4, X4, #16 | 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 W6, W3 | 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.GT 401c6c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x6c> | 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: 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_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 | 0.92 | 7.27 | 0.79 | 18.68 | 0.61 | 34.07 | 0.43 | 50.72 | 0.26 | 64.94 | 0.19 | 71.39 | 0.15 | 74.79 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 90.816993713379 | 88.506103515625 |
| run_2_threads | 2 | 0.92 | 1.84 | 2 | 45.432987213135 | 88.509010314941 |
| run_4_threads | 4 | 0.79 | 3.16 | 4 | 22.771997451782 | 88.50569152832 |
| run_8_threads | 8 | 0.61 | 4.92 | 8 | 11.394988059998 | 88.40909576416 |
| run_16_threads | 16 | 0.43 | 6.81 | 16 | 5.7049946784973 | 88.268295288086 |
| run_32_threads | 32 | 0.26 | 8.45 | 32 | 2.8709998130798 | 88.225112915039 |
| run_48_threads | 48 | 0.19 | 9.18 | 48 | 1.9229996204376 | 88.261489868164 |
| run_64_threads | 64 | 0.15 | 9.58 | 64 | 1.4529993534088 | 87.953941345215 |
