| Loop Id: 7 | Module: kmeans-acfl-Ofast | Source: main.cpp:81-84 | Coverage: 8.64% |
|---|
| Loop Id: 7 | Module: kmeans-acfl-Ofast | Source: main.cpp:81-84 | Coverage: 8.64% |
|---|
0x192c LDRSW X11, [X9], #4 [1] |
0x1930 SUBS X8, X8, #1 |
0x1934 LDP D1, D2, [X10, #1016] [2] |
0x1938 ADD X10, X10, #16 |
0x193c LDR D0, [X25, X11,LSL #3] [4] |
0x1940 LDR D3, [X26, X11,LSL #3] [5] |
0x1944 LDR W12, [X24, X11,LSL #2] [3] |
0x1948 FADD D0, D0, D1 |
0x194c FADD D1, D3, D2 |
0x1950 ADD W12, W12, #1 |
0x1954 STR W12, [X24, X11,LSL #2] [3] |
0x1958 STR D0, [X25, X11,LSL #3] [4] |
0x195c STR D1, [X26, X11,LSL #3] [5] |
0x1960 B.NE 192c |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 81 - 84 |
-------------------------------------------------------------------------------- |
81: for (int i = 0; i < n; ++i) { |
82: count[assignment[i]]++; |
83: sum_x[assignment[i]] += points[i].x; |
84: sum_y[assignment[i]] += points[i].y; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:20 | kmeans-acfl-Ofast |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-acfl-Ofast |
| 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 | 1.42 |
| CQA speedup if FP arith vectorized | 1.31 |
| CQA speedup if fully vectorized | 1.58 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.06 |
| Bottlenecks | P12, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) |
| Source | main.cpp:81-84 |
| 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 | 2.83 |
| CQA cycles if no scalar integer | 2.00 |
| CQA cycles if FP arith vectorized | 2.17 |
| CQA cycles if fully vectorized | 1.79 |
| Front-end cycles | 1.75 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.67 |
| P5 cycles | 0.67 |
| P6 cycles | 0.58 |
| P7 cycles | 0.58 |
| P8 cycles | 1.00 |
| P9 cycles | 1.00 |
| P10 cycles | 1.00 |
| P11 cycles | 1.00 |
| P12 cycles | 2.83 |
| P13 cycles | 2.50 |
| P14 cycles | 2.67 |
| P15 cycles | 0.50 |
| P16 cycles | 0.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 14.00 |
| Nb uops | 14.00 |
| Nb loads | NA |
| Nb stores | 3.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.71 |
| Nb FLOP add-sub | 2.00 |
| 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 | 21.18 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 40.00 |
| Bytes stored | 20.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 11.11 |
| Vectorization ratio load | 33.33 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 52.78 |
| Vector-efficiency ratio load | 66.67 |
| Vector-efficiency ratio store | 41.67 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.42 |
| CQA speedup if FP arith vectorized | 1.31 |
| CQA speedup if fully vectorized | 1.58 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.06 |
| Bottlenecks | P12, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) |
| Source | main.cpp:81-84 |
| 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 | 2.83 |
| CQA cycles if no scalar integer | 2.00 |
| CQA cycles if FP arith vectorized | 2.17 |
| CQA cycles if fully vectorized | 1.79 |
| Front-end cycles | 1.75 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.67 |
| P5 cycles | 0.67 |
| P6 cycles | 0.58 |
| P7 cycles | 0.58 |
| P8 cycles | 1.00 |
| P9 cycles | 1.00 |
| P10 cycles | 1.00 |
| P11 cycles | 1.00 |
| P12 cycles | 2.83 |
| P13 cycles | 2.50 |
| P14 cycles | 2.67 |
| P15 cycles | 0.50 |
| P16 cycles | 0.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 14.00 |
| Nb uops | 14.00 |
| Nb loads | NA |
| Nb stores | 3.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.71 |
| Nb FLOP add-sub | 2.00 |
| 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 | 21.18 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 40.00 |
| Bytes stored | 20.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 11.11 |
| Vectorization ratio load | 33.33 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 52.78 |
| Vector-efficiency ratio load | 66.67 |
| Vector-efficiency ratio store | 41.67 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) |
| Source file and lines | main.cpp:81-84 |
| Module | kmeans-acfl-Ofast |
| nb instructions | 14 |
| nb uops | 14 |
| loop length | 56 |
| used w registers | 1 |
| used x registers | 7 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 4 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.75 cycles |
| front end | 1.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.75 |
| Dispatch | 2.83 |
| Data deps. | 1.00 |
| Overall L1 | 2.83 |
| all | 14% |
| load | 33% |
| 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 | 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 | NA (no other vectorizable/vectorized instructions) |
| all | 11% |
| load | 33% |
| store | 0% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 53% |
| load | 66% |
| store | 41% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 52% |
| load | 66% |
| store | 41% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDRSW X11, [X9], #4 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| SUBS X8, X8, #1 | 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 (50.0%) |
| LDP D1, D2, [X10, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| ADD X10, X10, #16 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| LDR D0, [X25, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (50.0%) |
| LDR D3, [X26, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (50.0%) |
| LDR W12, [X24, X11,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| FADD D0, D0, D1 | 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%) |
| FADD D1, D3, D2 | 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 W12, W12, #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 |
| STR W12, [X24, X11,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (25.0%) |
| STR D0, [X25, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| STR D1, [X26, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| B.NE 192c <_Z7k_meansiP7point_tS0_PiS0_ii+0x12c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) |
| Source file and lines | main.cpp:81-84 |
| Module | kmeans-acfl-Ofast |
| nb instructions | 14 |
| nb uops | 14 |
| loop length | 56 |
| used w registers | 1 |
| used x registers | 7 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 0 |
| used d registers | 4 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.75 cycles |
| front end | 1.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.75 |
| Dispatch | 2.83 |
| Data deps. | 1.00 |
| Overall L1 | 2.83 |
| all | 14% |
| load | 33% |
| 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 | 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 | NA (no other vectorizable/vectorized instructions) |
| all | 11% |
| load | 33% |
| store | 0% |
| 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 | NA (no other vectorizable/vectorized instructions) |
| all | 53% |
| load | 66% |
| store | 41% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| 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 | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 52% |
| load | 66% |
| store | 41% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDRSW X11, [X9], #4 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| SUBS X8, X8, #1 | 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 (50.0%) |
| LDP D1, D2, [X10, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| ADD X10, X10, #16 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| LDR D0, [X25, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (50.0%) |
| LDR D3, [X26, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (50.0%) |
| LDR W12, [X24, X11,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| FADD D0, D0, D1 | 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%) |
| FADD D1, D3, D2 | 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 W12, W12, #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 |
| STR W12, [X24, X11,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0.50 | 0.50 | 1 | 0.50 | scal (25.0%) |
| STR D0, [X25, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| STR D1, [X26, X11,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (50.0%) |
| B.NE 192c <_Z7k_meansiP7point_tS0_PiS0_ii+0x12c> | 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 | 0.96 | 0.36 | 0.89 | 0.85 | 0.82 | 1.18 | 0.74 | 1.26 | 0.68 | 1.07 | 0.65 | 0.89 | 0.64 | 0.73 | 0.62 | 0.66 | 0.62 | 0.56 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 7.8949975967407 | 8.6402177810669 |
| run_2_threads | 1 | 0.96 | 1.92 | 2 | 7.8799986839294 | 8.4201517105103 |
| run_4_threads | 1 | 0.89 | 3.56 | 4 | 7.8649988174438 | 7.6671857833862 |
| run_8_threads | 1 | 0.82 | 6.54 | 8 | 7.7599992752075 | 6.4701704978943 |
| run_16_threads | 1 | 0.74 | 11.92 | 16 | 7.6299996376038 | 4.9410696029663 |
| run_32_threads | 1 | 0.68 | 21.76 | 32 | 7.7249984741211 | 3.3541750907898 |
| run_48_threads | 1 | 0.65 | 31.41 | 48 | 7.7699995040894 | 2.5647795200348 |
| run_64_threads | 1 | 0.64 | 41.2 | 64 | 7.7199974060059 | 2.0505468845367 |
| run_80_threads | 1 | 0.62 | 49.58 | 80 | 7.8350009918213 | 1.7253150939941 |
| run_96_threads | 1 | 0.62 | 59.56 | 96 | 7.7699995040894 | 1.4769477844238 |
