| Loop Id: 10 | Module: kmeans-gcc-Ofast | Source: main.cpp:81-84 | Coverage: 5.76% |
|---|
| Loop Id: 10 | Module: kmeans-gcc-Ofast | Source: main.cpp:81-84 | Coverage: 5.76% |
|---|
0x401ee4 LDR W0, [X27, X1,LSL #2] [4] |
0x401ee8 ADD X1, X1, #1 |
0x401eec LDP D28, D30, [X4], #16 [5] |
0x401ef0 LDR D29, [X22, X0,SXTW #3] [2] |
0x401ef4 SBFM X2, X0, #62, #31 |
0x401ef8 LDR D31, [X26, X0,SXTW #3] [3] |
0x401efc LDR W7, [X8, X2] [1] |
0x401f00 FADD D28, D29, D28 |
0x401f04 FADD D30, D31, D30 |
0x401f08 ADD W7, W7, #1 |
0x401f0c STR W7, [X8, X2] [1] |
0x401f10 STR D28, [X22, X0,SXTW #3] [2] |
0x401f14 STR D30, [X26, X0,SXTW #3] [3] |
0x401f18 CMP W25, W1 |
0x401f1c B.GT 401ee4 |
/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:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-Ofast |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | main | main.cpp:19 | kmeans-gcc-Ofast |
| ○ | __libc_start_main | libc-2.31.so | |
| ○ | _start | new_allocator.h:104 | kmeans-gcc-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 | 1.70 |
| CQA speedup if FP arith vectorized | 1.13 |
| CQA speedup if fully vectorized | 4.39 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.06 |
| Bottlenecks | P10, |
| 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 | 1.67 |
| CQA cycles if FP arith vectorized | 2.50 |
| CQA cycles if fully vectorized | 0.65 |
| Front-end cycles | 1.88 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 1.25 |
| P3 cycles | 1.25 |
| P4 cycles | 1.25 |
| P5 cycles | 1.25 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 1.00 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 0.50 |
| P14 cycles | 0.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 15.00 |
| Nb uops | 15.00 |
| 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 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 10.00 |
| Vectorization ratio load | 25.00 |
| 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 | 23.75 |
| Vector-efficiency ratio load | 28.13 |
| Vector-efficiency ratio store | 20.83 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 20.83 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.70 |
| CQA speedup if FP arith vectorized | 1.13 |
| CQA speedup if fully vectorized | 4.39 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.06 |
| Bottlenecks | P10, |
| 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 | 1.67 |
| CQA cycles if FP arith vectorized | 2.50 |
| CQA cycles if fully vectorized | 0.65 |
| Front-end cycles | 1.88 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 1.25 |
| P3 cycles | 1.25 |
| P4 cycles | 1.25 |
| P5 cycles | 1.25 |
| P6 cycles | 1.00 |
| P7 cycles | 1.00 |
| P8 cycles | 1.00 |
| P9 cycles | 1.00 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 0.50 |
| P14 cycles | 0.50 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 15.00 |
| Nb uops | 15.00 |
| 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 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 10.00 |
| Vectorization ratio load | 25.00 |
| 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 | 23.75 |
| Vector-efficiency ratio load | 28.13 |
| Vector-efficiency ratio store | 20.83 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 20.83 |
| 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-gcc-Ofast |
| nb instructions | 15 |
| nb uops | 15 |
| loop length | 60 |
| used w registers | 4 |
| used x registers | 8 |
| 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 | 1.88 cycles |
| front end | 1.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| cycles | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 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 | 1.88 |
| Dispatch | 2.83 |
| Data deps. | 1.00 |
| Overall L1 | 2.83 |
| all | 12% |
| load | 25% |
| 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 | 10% |
| load | 25% |
| 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 | 23% |
| load | 28% |
| store | 20% |
| 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 | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 23% |
| load | 28% |
| store | 20% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 20% |
| 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 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR W0, [X27, X1,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| ADD X1, X1, #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 |
| LDP D28, D30, [X4], #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (50.0%) |
| LDR D29, [X22, X0,SXTW #3] | 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%) |
| SBFM X2, X0, #62, #31 | 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 |
| LDR D31, [X26, X0,SXTW #3] | 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%) |
| LDR W7, [X8, X2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | scal (12.5%) |
| FADD D28, D29, D28 | 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%) |
| FADD D30, D31, D30 | 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%) |
| ADD W7, W7, #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%) |
| STR W7, [X8, X2] | 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%) |
| STR D28, [X22, X0,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| STR D30, [X26, X0,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| CMP W25, W1 | 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 401ee4 <_Z7k_meansiP7point_tS0_PiS0_ii+0x138> | 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) |
| Source file and lines | main.cpp:81-84 |
| Module | kmeans-gcc-Ofast |
| nb instructions | 15 |
| nb uops | 15 |
| loop length | 60 |
| used w registers | 4 |
| used x registers | 8 |
| 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 | 1.88 cycles |
| front end | 1.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 1.00 | 1.00 | 1.00 | 1.00 | 2.83 | 2.50 | 2.67 | 0.50 | 0.50 |
| cycles | 0.50 | 0.50 | 1.25 | 1.25 | 1.25 | 1.25 | 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 | 1.88 |
| Dispatch | 2.83 |
| Data deps. | 1.00 |
| Overall L1 | 2.83 |
| all | 12% |
| load | 25% |
| 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 | 10% |
| load | 25% |
| 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 | 23% |
| load | 28% |
| store | 20% |
| 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 | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 23% |
| load | 28% |
| store | 20% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 20% |
| 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 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR W0, [X27, X1,LSL #2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | N/A |
| ADD X1, X1, #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 |
| LDP D28, D30, [X4], #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (50.0%) |
| LDR D29, [X22, X0,SXTW #3] | 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%) |
| SBFM X2, X0, #62, #31 | 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 |
| LDR D31, [X26, X0,SXTW #3] | 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%) |
| LDR W7, [X8, X2] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 0.33 | scal (12.5%) |
| FADD D28, D29, D28 | 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%) |
| FADD D30, D31, D30 | 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%) |
| ADD W7, W7, #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%) |
| STR W7, [X8, X2] | 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%) |
| STR D28, [X22, X0,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| STR D30, [X26, X0,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| CMP W25, W1 | 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 401ee4 <_Z7k_meansiP7point_tS0_PiS0_ii+0x138> | 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 | 0.95 | 0.3 | 0.86 | 0.79 | 0.71 | 1.62 | 0.55 | 2.49 | 0.38 | 3.21 | 0.31 | 3.32 | 0.26 | 3.29 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 9.3249950408936 | 5.7632880210876 |
| run_2_threads | 1 | 0.95 | 1.89 | 2 | 9.3249998092651 | 5.666006565094 |
| run_4_threads | 1 | 0.86 | 3.43 | 4 | 9.3229932785034 | 5.5153603553772 |
| run_8_threads | 1 | 0.71 | 5.68 | 8 | 9.3279981613159 | 5.5828881263733 |
| run_16_threads | 1 | 0.55 | 8.72 | 16 | 9.3309926986694 | 5.4666028022766 |
| run_32_threads | 1 | 0.38 | 12.23 | 32 | 9.3459949493408 | 5.1994442939758 |
| run_48_threads | 1 | 0.31 | 14.78 | 48 | 9.3529930114746 | 4.7925524711609 |
| run_64_threads | 1 | 0.26 | 16.81 | 64 | 9.3549995422363 | 4.4609441757202 |
