| Loop Id: 4 | Module: kmeans-gcc-O3-funroll | Source: main.cpp:60-67 | Coverage: 85.44% |
|---|
| Loop Id: 4 | Module: kmeans-gcc-O3-funroll | Source: main.cpp:60-67 | Coverage: 85.44% |
|---|
(5) 0x401d2c ANDS W10, W5, #64 |
(5) 0x401d30 LDP D27, D28, [X18] |
(5) 0x401d34 FMOV D30, D26 |
(5) 0x401d38 ORR X16, XZR, X8 |
(5) 0x401d3c MOVZ W15, #0 |
(5) 0x401d40 B.EQ 401dc8 |
(5) 0x401d44 CMP W10, #1 |
(5) 0x401d48 B.EQ 401d9c |
(5) 0x401d4c CMP W10, #2 |
(5) 0x401d50 B.EQ 401d78 |
(5) 0x401d54 LDP D31, D29, [X8] |
(5) 0x401d58 FSUB D0, D28, S29 |
(5) 0x401d5c FSUB D1, D27, S31 |
(5) 0x401d60 FMUL D2, D0, D0 |
(5) 0x401d64 FMADD D3, D1, D1, D2 |
(5) 0x401d68 FCMPE D26, D3 |
(5) 0x401d6c B.GT 401ec4 |
(5) 0x401d70 MOVZ W15, #1 |
(5) 0x401d74 ADD X16, X8, #16 |
(5) 0x401d78 LDP D4, D5, [X16] |
(5) 0x401d7c FSUB D6, D28, S5 |
(5) 0x401d80 FSUB D7, D27, S4 |
(5) 0x401d84 FMUL D16, D6, D6 |
(5) 0x401d88 FMADD D17, D7, D7, D16 |
(5) 0x401d8c FCMPE D30, D17 |
(5) 0x401d90 B.GT 401eb8 |
(5) 0x401d94 ADD W15, W15, #1 |
(5) 0x401d98 ADD X16, X16, #16 |
(5) 0x401d9c LDP D18, D19, [X16] |
(5) 0x401da0 FSUB D20, D28, S19 |
(5) 0x401da4 FSUB D21, D27, S18 |
(5) 0x401da8 FMUL D22, D20, D20 |
(5) 0x401dac FMADD D23, D21, D21, D22 |
(5) 0x401db0 FCMPE D30, D23 |
(5) 0x401db4 B.GT 401eac |
(5) 0x401db8 ADD W15, W15, #1 |
(5) 0x401dbc ADD X16, X16, #16 |
(5) 0x401dc0 CMP W5, W15 |
(5) 0x401dc4 B.EQ 401e5c |
0x401dc8 LDP D24, D25, [X16] |
0x401dcc FSUB D29, D28, S25 |
0x401dd0 FSUB D31, D27, S24 |
0x401dd4 FMUL D0, D29, D29 |
0x401dd8 FMADD D1, D31, D31, D0 |
0x401ddc FCMPE D30, D1 |
0x401de0 B.GT 401ea0 |
0x401de4 LDR D4, [X16, #24] |
0x401de8 ADD X11, X16, #16 |
0x401dec ADD W12, W15, #1 |
0x401df0 LDR D2, [X16, #16] |
0x401df4 FSUB D5, D28, S4 |
0x401df8 FSUB D3, D27, S2 |
0x401dfc FMUL D6, D5, D5 |
0x401e00 FMADD D7, D3, D3, D6 |
0x401e04 FCMPE D30, D7 |
0x401e08 B.GT 401e94 |
0x401e0c LDP D16, D17, [X11, #16] |
0x401e10 ADD W13, W12, #1 |
0x401e14 FSUB D18, D28, S17 |
0x401e18 FSUB D19, D27, S16 |
0x401e1c FMUL D20, D18, D18 |
0x401e20 FMADD D21, D19, D19, D20 |
0x401e24 FCMPE D30, D21 |
0x401e28 B.GT 401e88 |
0x401e2c LDP D22, D23, [X11, #32] |
0x401e30 ADD W14, W12, #2 |
0x401e34 FSUB D24, D28, S23 |
0x401e38 FSUB D25, D27, S22 |
0x401e3c FMUL D29, D24, D24 |
0x401e40 FMADD D31, D25, D25, D29 |
0x401e44 FCMPE D30, D31 |
0x401e48 B.GT 401e7c |
0x401e4c ADD W15, W12, #3 |
0x401e50 ADD X16, X11, #48 |
0x401e54 CMP W5, W15 |
0x401e58 B.NE 401dc8 |
(5) 0x401e5c ADD X3, X3, #1 |
(5) 0x401e60 ADD X18, X18, #16 |
(5) 0x401e64 CMP W17, W3 |
(5) 0x401e68 B.GT 401d2c |
0x401e88 FMOV D30, D21 |
0x401e8c STR W13, [X6, X3,LSL #2] |
0x401e90 B 401e2c |
0x401e94 FMOV D30, D7 |
0x401e98 STR W12, [X6, X3,LSL #2] |
0x401e9c B 401e0c |
0x401ea0 FMOV D30, D1 |
0x401ea4 STR W15, [X6, X3,LSL #2] |
0x401ea8 B 401de4 |
(5) 0x401eac FMOV D30, D23 |
(5) 0x401eb0 STR W15, [X6, X3,LSL #2] |
(5) 0x401eb4 B 401db8 |
(5) 0x401eb8 FMOV D30, D17 |
(5) 0x401ebc STR W15, [X6, X3,LSL #2] |
(5) 0x401ec0 B 401d94 |
(5) 0x401ec4 FMOV D30, D3 |
(5) 0x401ec8 STR WZR, [X6, X3,LSL #2] |
(5) 0x401ecc B 401d70 |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 60 - 67 |
-------------------------------------------------------------------------------- |
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 |
|---|---|---|---|
| ►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-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►50.11+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►49.89+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►75.03+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►24.97+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►87.49+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►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-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►93.71+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►6.29+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►96.86+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►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-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►97.89+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►2.11+ | GOMP_parallel | libgomp.h:980 | libgomp.so.1.0.0 |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:73 | kmeans-gcc-O3-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.41+ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○ | start_thread | libpthread-2.31.so | |
| ○ | __clone | libc-2.31.so | |
| ►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-funroll |
| ○ | main | main.cpp:19 | kmeans-gcc-O3-funroll |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-O3-funroll |
| 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 | 3.45 |
| CQA speedup if FP arith vectorized | 1.44 |
| CQA speedup if fully vectorized | 4.28 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.44 |
| Bottlenecks | micro-operation queue, P6, P7, P8, P9, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source | main.cpp:61-67 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.75 |
| CQA cycles if no scalar integer | 1.67 |
| CQA cycles if FP arith vectorized | 4.00 |
| CQA cycles if fully vectorized | 1.34 |
| Front-end cycles | 5.75 |
| P0 cycles | 4.00 |
| P1 cycles | 4.00 |
| P2 cycles | 1.75 |
| P3 cycles | 1.75 |
| P4 cycles | 1.75 |
| P5 cycles | 1.75 |
| P6 cycles | 5.75 |
| P7 cycles | 5.75 |
| P8 cycles | 5.75 |
| P9 cycles | 5.75 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 1.50 |
| P14 cycles | 1.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 46.00 |
| Nb uops | 46.00 |
| Nb loads | NA |
| Nb stores | 3.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 3.48 |
| Nb FLOP add-sub | 8.00 |
| Nb FLOP mul | 4.00 |
| Nb FLOP fma | 4.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 13.22 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 64.00 |
| Bytes stored | 12.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 8.82 |
| Vectorization ratio load | 60.00 |
| 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 | 25.00 |
| Vector-efficiency ratio load | 40.00 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 21.59 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 25.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.45 |
| CQA speedup if FP arith vectorized | 1.44 |
| CQA speedup if fully vectorized | 4.28 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.44 |
| Bottlenecks | micro-operation queue, P6, P7, P8, P9, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source | main.cpp:61-67 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.75 |
| CQA cycles if no scalar integer | 1.67 |
| CQA cycles if FP arith vectorized | 4.00 |
| CQA cycles if fully vectorized | 1.34 |
| Front-end cycles | 5.75 |
| P0 cycles | 4.00 |
| P1 cycles | 4.00 |
| P2 cycles | 1.75 |
| P3 cycles | 1.75 |
| P4 cycles | 1.75 |
| P5 cycles | 1.75 |
| P6 cycles | 5.75 |
| P7 cycles | 5.75 |
| P8 cycles | 5.75 |
| P9 cycles | 5.75 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 1.50 |
| P14 cycles | 1.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 46.00 |
| Nb uops | 46.00 |
| Nb loads | NA |
| Nb stores | 3.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 3.48 |
| Nb FLOP add-sub | 8.00 |
| Nb FLOP mul | 4.00 |
| Nb FLOP fma | 4.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 13.22 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 64.00 |
| Bytes stored | 12.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 8.82 |
| Vectorization ratio load | 60.00 |
| 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 | 25.00 |
| Vector-efficiency ratio load | 40.00 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 21.59 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 25.00 |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone ._omp_fn.0] |
| Source file and lines | main.cpp:60-67 |
| Module | kmeans-gcc-O3-funroll |
| nb instructions | 46 |
| nb uops | 46 |
| loop length | 184 |
| used w registers | 5 |
| used x registers | 4 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 8 |
| used d registers | 23 |
| 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 | 5.75 cycles |
| front end | 5.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 1.75 | 1.75 | 1.75 | 1.75 | 5.75 | 5.75 | 5.75 | 5.75 | 2.83 | 2.50 | 2.67 | 1.50 | 1.50 |
| cycles | 4.00 | 4.00 | 1.75 | 1.75 | 1.75 | 1.75 | 5.75 | 5.75 | 5.75 | 5.75 | 2.83 | 2.50 | 2.67 | 1.50 | 1.50 |
| Cycles executing div or sqrt instructions | NA |
| Front-end | 5.75 |
| Dispatch | 5.75 |
| Overall L1 | 5.75 |
| all | 27% |
| load | 60% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 8% |
| load | 60% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 25% |
| load | 40% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 25% |
| load | 40% |
| store | 12% |
| mul | 25% |
| add-sub | 21% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDP D24, D25, [X16] | 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 D29, D28, S25 | 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, D27, S24 | 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 D0, D29, D29 | 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 D1, D31, D31, D0 | 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 D30, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401ea0 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1e0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDR D4, [X16, #24] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| ADD X11, X16, #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 |
| ADD W12, W15, #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%) |
| LDR D2, [X16, #16] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D5, D28, S4 | 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 D3, D27, S2 | 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 D6, D5, D5 | 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 D7, D3, D3, D6 | 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 D30, D7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e94 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1d4> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D16, D17, [X11, #16] | 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%) |
| ADD W13, W12, #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%) |
| FSUB D18, D28, S17 | 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 D19, D27, S16 | 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 D20, D18, D18 | 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 D21, D19, D19, D20 | 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 D30, D21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e88 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1c8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D22, D23, [X11, #32] | 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%) |
| ADD W14, W12, #2 | 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%) |
| FSUB D24, D28, S23 | 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 D25, D27, S22 | 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 D29, D24, D24 | 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, D25, D25, D29 | 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 D30, D31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e7c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1bc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD W15, W12, #3 | 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 X16, X11, #48 | 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 W5, W15 | 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.NE 401dc8 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x108> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D21 | 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%) |
| STR W13, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401e2c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D7 | 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%) |
| STR W12, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401e0c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x14c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D1 | 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%) |
| STR W15, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401de4 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x124> | 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:60-67 |
| Module | kmeans-gcc-O3-funroll |
| nb instructions | 46 |
| nb uops | 46 |
| loop length | 184 |
| used w registers | 5 |
| used x registers | 4 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 8 |
| used d registers | 23 |
| 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 | 5.75 cycles |
| front end | 5.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 1.75 | 1.75 | 1.75 | 1.75 | 5.75 | 5.75 | 5.75 | 5.75 | 2.83 | 2.50 | 2.67 | 1.50 | 1.50 |
| cycles | 4.00 | 4.00 | 1.75 | 1.75 | 1.75 | 1.75 | 5.75 | 5.75 | 5.75 | 5.75 | 2.83 | 2.50 | 2.67 | 1.50 | 1.50 |
| Cycles executing div or sqrt instructions | NA |
| Front-end | 5.75 |
| Dispatch | 5.75 |
| Overall L1 | 5.75 |
| all | 27% |
| load | 60% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 8% |
| load | 60% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 25% |
| load | 40% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 25% |
| load | 40% |
| store | 12% |
| mul | 25% |
| add-sub | 21% |
| fma | 25% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDP D24, D25, [X16] | 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 D29, D28, S25 | 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, D27, S24 | 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 D0, D29, D29 | 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 D1, D31, D31, D0 | 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 D30, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401ea0 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1e0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDR D4, [X16, #24] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| ADD X11, X16, #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 |
| ADD W12, W15, #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%) |
| LDR D2, [X16, #16] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D5, D28, S4 | 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 D3, D27, S2 | 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 D6, D5, D5 | 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 D7, D3, D3, D6 | 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 D30, D7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e94 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1d4> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D16, D17, [X11, #16] | 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%) |
| ADD W13, W12, #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%) |
| FSUB D18, D28, S17 | 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 D19, D27, S16 | 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 D20, D18, D18 | 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 D21, D19, D19, D20 | 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 D30, D21 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e88 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1c8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDP D22, D23, [X11, #32] | 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%) |
| ADD W14, W12, #2 | 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%) |
| FSUB D24, D28, S23 | 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 D25, D27, S22 | 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 D29, D24, D24 | 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, D25, D25, D29 | 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 D30, D31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GT 401e7c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x1bc> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD W15, W12, #3 | 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 X16, X11, #48 | 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 W5, W15 | 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.NE 401dc8 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x108> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D21 | 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%) |
| STR W13, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401e2c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D7 | 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%) |
| STR W12, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401e0c <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x14c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMOV D30, D1 | 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%) |
| STR W15, [X6, X3,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (12.5%) |
| B 401de4 <_Z7k_meansiP7point_tS0_PiS0_ii._omp_fn.0+0x124> | 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 | 0.92 | 7.07 | 0.79 | 18.06 | 0.62 | 32.72 | 0.43 | 49.05 | 0.26 | 63.3 | 0.19 | 70.21 | 0.15 | 74.26 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 92.67692565918 | 85.436279296875 |
| run_2_threads | 2 | 0.92 | 1.83 | 2 | 46.74995803833 | 85.416244506836 |
| run_4_threads | 4 | 0.79 | 3.16 | 4 | 23.434997558594 | 85.600074768066 |
| run_8_threads | 8 | 0.62 | 4.94 | 8 | 11.844995498657 | 85.571273803711 |
| run_16_threads | 16 | 0.43 | 6.85 | 16 | 6.0809988975525 | 85.791465759277 |
| run_32_threads | 32 | 0.26 | 8.46 | 32 | 3.2369990348816 | 86.054695129395 |
| run_48_threads | 48 | 0.19 | 9.07 | 48 | 2.3529989719391 | 86.564071655273 |
| run_64_threads | 64 | 0.15 | 9.37 | 64 | 1.9459984302521 | 86.998237609863 |
