| Function: k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] | Module: kmeans-gcc-O3-vectorize | Source: main.cpp:58-67 | Coverage (incl. loops): 91.74% | (excl. loops): 0.00% |
|---|
| Function: k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] | Module: kmeans-gcc-O3-vectorize | Source: main.cpp:58-67 | Coverage (incl. loops): 91.74% | (excl. loops): 0.00% |
|---|
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 58 - 67 |
-------------------------------------------------------------------------------- |
58: #pragma omp parallel for |
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; |
0x401ba0 STP X29, X30, [SP, #976]! |
0x401ba4 ADD X29, SP, #0 |
0x401ba8 STP X19, X20, [SP, #16] |
0x401bac ORR X20, XZR, X0 |
0x401bb0 STR X21, [SP, #32] |
0x401bb4 LDR W21, [X0, #24] |
0x401bb8 BL 401780 |
0x401bbc ORR W19, WZR, W0 |
0x401bc0 BL 4016e0 |
0x401bc4 ORR W4, WZR, W0 |
0x401bc8 SDIV W6, W21, W19 |
0x401bcc MSUB W1, W6, W19, W21 |
0x401bd0 CMP W0, W1 |
0x401bd4 B.LT 401c78 |
0x401bd8 MADD W4, W6, W4, W1 |
0x401bdc ADD W6, W6, W4 |
0x401be0 CMP W4, W6 |
0x401be4 B.GE 401c5c |
0x401be8 LDR W2, [X20, #28] |
0x401bec LDP X1, X7, [X20] |
0x401bf0 LDR X5, [X20, #16] |
0x401bf4 CMP W2, #0 |
0x401bf8 B.LE 401c5c |
0x401bfc MOVN X0, #32784 |
0x401c00 SBFM X3, X4, #0, #31 |
0x401c04 ADD X4, X1, W4,SXTW #4 |
0x401c08 FMOV D26, X0 |
(4) 0x401c0c LDP D28, D27, [X4] |
(4) 0x401c10 FMOV D29, D26 |
(4) 0x401c14 ORR X0, XZR, X7 |
(4) 0x401c18 MOVZ W1, #0 |
(4) 0x401c1c HINT #0 |
(4) 0x401c20 LDP D31, D30, [X0] |
(4) 0x401c24 FSUB D30, D27, S30 |
(4) 0x401c28 FSUB D31, D28, S31 |
(4) 0x401c2c FMUL D30, D30, D30 |
(4) 0x401c30 FMADD D31, D31, D31, D30 |
(4) 0x401c34 FCMPE D29, D31 |
(4) 0x401c38 B.GT 401c6c |
(4) 0x401c3c ADD W1, W1, #1 |
(4) 0x401c40 ADD X0, X0, #16 |
(4) 0x401c44 CMP W2, W1 |
(4) 0x401c48 B.NE 401c20 |
(4) 0x401c4c ADD X3, X3, #1 |
(4) 0x401c50 ADD X4, X4, #16 |
(4) 0x401c54 CMP W6, W3 |
(4) 0x401c58 B.GT 401c0c |
(5) 0x401c5c LDR X21, [SP, #32] |
(5) 0x401c60 LDP X19, X20, [SP, #16] |
(5) 0x401c64 LDP X29, X30, [SP], #48 |
(5) 0x401c68 RET |
(3) 0x401c6c FMOV D29, D31 |
(3) 0x401c70 STR W1, [X5, X3,LSL #2] |
(3) 0x401c74 B 401c3c |
0x401c78 ADD W6, W6, #1 |
0x401c7c MOVZ W1, #0 |
0x401c80 B 401bd8 |
| 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►51.21+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| ►48.79+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►74.10+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►25.90+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►86.84+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►13.16+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►94.10+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►5.90+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►96.90+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►3.10+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►97.95+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►2.05+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.42+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.58+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.76+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.24+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-vectorize |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.97+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.03+ | 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:18 | kmeans-gcc-O3-vectorize |
| ○ | __libc_start_call_main | 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 / |
The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run run_1_thread
| Source file and lines | main.cpp:58-67 |
| Module | kmeans-gcc-O3-vectorize |
| nb instructions | 30 |
| nb uops | 30 |
| loop length | 120 |
| used w registers | 8 |
| used x registers | 12 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 1 |
| used d registers | 1 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 3.75 cycles |
| front end | 3.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.00 | 3.00 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 0.25 | 0.25 | 0.25 | 0.25 | 2.50 | 2.17 | 2.33 | 1.50 | 1.50 |
| cycles | 3.00 | 3.00 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 0.25 | 0.25 | 0.25 | 0.25 | 2.50 | 2.17 | 2.33 | 1.50 | 1.50 |
| Cycles executing div or sqrt instructions | 5.00-12.50 |
| Front-end | 3.75 |
| Dispatch | 3.17 |
| DIV/SQRT | 5.00-12.50 |
| Overall L1 | 5.00-12.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| 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 | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 47% |
| load | 50% |
| store | 83% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | 25% |
| other | 35% |
| all | 50% |
| 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 | 50% |
| all | 47% |
| load | 50% |
| store | 83% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 37% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| STP X29, X30, [SP, #976]! | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (100.0%) |
| ADD X29, SP, #0 | 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%) |
| STP X19, X20, [SP, #16] | 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 (100.0%) |
| ORR X20, XZR, X0 | 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 |
| STR X21, [SP, #32] | 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 (50.0%) |
| LDR W21, [X0, #24] | 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%) |
| BL 401780 <@plt_start@+0x270> | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR W19, WZR, W0 | 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 (25.0%) |
| BL 4016e0 <@plt_start@+0x1d0> | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR W4, WZR, W0 | 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 (25.0%) |
| SDIV W6, W21, W19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5-12 | 5-12.50 | N/A |
| MSUB W1, W6, W19, W21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| CMP W0, W1 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.LT 401c78 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xd8> | 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 |
| MADD W4, W6, W4, W1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| ADD W6, W6, W4 | 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 W4, W6 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.GE 401c5c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xbc> | 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 |
| LDR W2, [X20, #28] | 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%) |
| LDP X1, X7, [X20] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.50 | scal (100.0%) |
| LDR X5, [X20, #16] | 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 (50.0%) |
| CMP W2, #0 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.LE 401c5c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xbc> | 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 |
| MOVN X0, #32784 | 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 |
| SBFM X3, X4, #0, #31 | 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 (100.0%) |
| ADD X4, X1, W4,SXTW #4 | 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%) |
| FMOV D26, X0 | 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%) |
| ADD W6, W6, #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 | N/A |
| MOVZ W1, #0 | 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 (25.0%) |
| B 401bd8 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x38> | 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 |
The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run run_1_thread
| Source file and lines | main.cpp:58-67 |
| Module | kmeans-gcc-O3-vectorize |
| nb instructions | 30 |
| nb uops | 30 |
| loop length | 120 |
| used w registers | 8 |
| used x registers | 12 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 1 |
| used d registers | 1 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 3.75 cycles |
| front end | 3.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 3.00 | 3.00 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 0.25 | 0.25 | 0.25 | 0.25 | 2.50 | 2.17 | 2.33 | 1.50 | 1.50 |
| cycles | 3.00 | 3.00 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 3.17 | 0.25 | 0.25 | 0.25 | 0.25 | 2.50 | 2.17 | 2.33 | 1.50 | 1.50 |
| Cycles executing div or sqrt instructions | 5.00-12.50 |
| Front-end | 3.75 |
| Dispatch | 3.17 |
| DIV/SQRT | 5.00-12.50 |
| Overall L1 | 5.00-12.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| 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 | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 47% |
| load | 50% |
| store | 83% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | 25% |
| other | 35% |
| all | 50% |
| 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 | 50% |
| all | 47% |
| load | 50% |
| store | 83% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 37% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| STP X29, X30, [SP, #976]! | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (100.0%) |
| ADD X29, SP, #0 | 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%) |
| STP X19, X20, [SP, #16] | 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 (100.0%) |
| ORR X20, XZR, X0 | 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 |
| STR X21, [SP, #32] | 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 (50.0%) |
| LDR W21, [X0, #24] | 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%) |
| BL 401780 <@plt_start@+0x270> | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR W19, WZR, W0 | 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 (25.0%) |
| BL 4016e0 <@plt_start@+0x1d0> | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR W4, WZR, W0 | 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 (25.0%) |
| SDIV W6, W21, W19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5-12 | 5-12.50 | N/A |
| MSUB W1, W6, W19, W21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| CMP W0, W1 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.LT 401c78 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xd8> | 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 |
| MADD W4, W6, W4, W1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| ADD W6, W6, W4 | 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 W4, W6 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.GE 401c5c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xbc> | 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 |
| LDR W2, [X20, #28] | 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%) |
| LDP X1, X7, [X20] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.50 | scal (100.0%) |
| LDR X5, [X20, #16] | 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 (50.0%) |
| CMP W2, #0 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| B.LE 401c5c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0xbc> | 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 |
| MOVN X0, #32784 | 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 |
| SBFM X3, X4, #0, #31 | 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 (100.0%) |
| ADD X4, X1, W4,SXTW #4 | 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%) |
| FMOV D26, X0 | 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%) |
| ADD W6, W6, #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 | N/A |
| MOVZ W1, #0 | 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 (25.0%) |
| B 401bd8 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x38> | 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 | 0.88 | 10.76 | 0.78 | 20.63 | 0.62 | 35.2 | 0.45 | 51.08 | 0.28 | 66.54 | 0.2 | 73.62 | 0.16 | 77.83 | 0.13 | 80.78 | 0.11 | 82.96 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 82.034980773926 | 91.73609161377 |
| run_2_threads | 2 | 0.88 | 1.77 | 2 | 43.139995574951 | 91.934501647949 |
| run_4_threads | 4 | 0.78 | 3.1 | 4 | 21.439998626709 | 91.79418182373 |
| run_8_threads | 8 | 0.62 | 4.93 | 8 | 10.774998664856 | 91.702133178711 |
| run_16_threads | 16 | 0.45 | 7.12 | 16 | 6.210000038147 | 92.08602142334 |
| run_32_threads | 32 | 0.28 | 8.84 | 32 | 3.0049993991852 | 91.91902923584 |
| run_48_threads | 48 | 0.2 | 9.62 | 48 | 2.0299999713898 | 92.075691223145 |
| run_64_threads | 64 | 0.16 | 10.01 | 64 | 1.5949996709824 | 92.253028869629 |
| run_80_threads | 80 | 0.13 | 10.23 | 80 | 1.3799998760223 | 92.6259765625 |
| run_96_threads | 96 | 0.11 | 10.35 | 96 | 1.1849998235703 | 92.989486694336 |
| Name | Coverage (%) | Time (s) |
|---|---|---|
| ▼k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0]– | 91.74 | 82.03 |
| ▼Loop 5 - main.cpp:58-67 - kmeans-gcc-O3-vectorize– | 0.00 | 0.00 |
| ▼Loop 3 - main.cpp:60-67 - kmeans-gcc-O3-vectorize– | 2.85 | 2.55 |
| ○Loop 4 - main.cpp:60-65 - kmeans-gcc-O3-vectorize | 88.88 | 79.48 |
