| Loop Id: 17 | Module: kmeans-icpx-O3-aggressive | Source: main.cpp:71-82 | Coverage: 1.02% |
|---|
| Loop Id: 17 | Module: kmeans-icpx-O3-aggressive | Source: main.cpp:71-82 | Coverage: 1.02% |
|---|
0x403960 CMP %RDI,%R8 |
0x403963 LEA 0x1(%R8),%R8 |
0x403967 JE 4038e4 |
0x40396d LEA (%RAX,%R8,8),%R9 |
0x403971 MOV %R9,%R10 |
0x403974 SAL $0x4,%R10 |
0x403978 VMOVUPD (%R15,%R10,1),%XMM1 |
0x40397e VMOVUPD 0x10(%R15,%R10,1),%XMM2 |
0x403985 VMOVUPD 0x20(%R15,%R10,1),%XMM3 |
0x40398c VMOVUPD 0x30(%R15,%R10,1),%XMM4 |
0x403993 VMOVUPD 0x40(%R15,%R10,1),%XMM5 |
0x40399a VMOVUPD 0x50(%R15,%R10,1),%XMM6 |
0x4039a1 VMOVUPD 0x60(%R15,%R10,1),%XMM7 |
0x4039a8 VMOVUPD 0x70(%R15,%R10,1),%XMM8 |
0x4039af MOV %R13,%R10 |
0x4039b2 XOR %R11D,%R11D |
0x4039b5 VMOVAPD %XMM0,%XMM9 |
0x4039b9 VMOVAPD %XMM0,%XMM10 |
0x4039bd VMOVAPD %XMM0,%XMM11 |
0x4039c1 VMOVAPD %XMM0,%XMM12 |
0x4039c5 VMOVAPD %XMM0,%XMM13 |
0x4039c9 VMOVAPD %XMM0,%XMM14 |
0x4039cd VMOVAPD %XMM0,%XMM15 |
0x4039d1 VMOVAPD %XMM0,%XMM16 |
0x4039d7 JMP 4039f0 |
(18) 0x4039e0 INC %R11 |
(18) 0x4039e3 ADD $0x10,%R10 |
(18) 0x4039e7 CMP %R11,%RDX |
(18) 0x4039ea JE 403960 |
(18) 0x4039f0 VMOVUPD (%R10),%XMM17 |
(18) 0x4039f6 VSUBPD %XMM17,%XMM1,%XMM18 |
(18) 0x4039fc VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403a02 VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403a09 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403a0f VUCOMISD %XMM16,%XMM18 |
(18) 0x403a15 JAE 403a21 |
(18) 0x403a17 MOV %R11D,(%R14,%R9,4) |
(18) 0x403a1b VMOVAPD %XMM18,%XMM16 |
(18) 0x403a21 VSUBPD %XMM17,%XMM2,%XMM18 |
(18) 0x403a27 VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403a2d VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403a34 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403a3a VUCOMISD %XMM15,%XMM18 |
(18) 0x403a40 JAE 403a4d |
(18) 0x403a42 MOV %R11D,0x4(%R14,%R9,4) |
(18) 0x403a47 VMOVAPD %XMM18,%XMM15 |
(18) 0x403a4d VSUBPD %XMM17,%XMM3,%XMM18 |
(18) 0x403a53 VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403a59 VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403a60 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403a66 VUCOMISD %XMM14,%XMM18 |
(18) 0x403a6c JAE 403a79 |
(18) 0x403a6e MOV %R11D,0x8(%R14,%R9,4) |
(18) 0x403a73 VMOVAPD %XMM18,%XMM14 |
(18) 0x403a79 VSUBPD %XMM17,%XMM4,%XMM18 |
(18) 0x403a7f VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403a85 VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403a8c VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403a92 VUCOMISD %XMM13,%XMM18 |
(18) 0x403a98 JAE 403aa5 |
(18) 0x403a9a MOV %R11D,0xc(%R14,%R9,4) |
(18) 0x403a9f VMOVAPD %XMM18,%XMM13 |
(18) 0x403aa5 VSUBPD %XMM17,%XMM5,%XMM18 |
(18) 0x403aab VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403ab1 VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403ab8 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403abe VUCOMISD %XMM12,%XMM18 |
(18) 0x403ac4 JAE 403ad1 |
(18) 0x403ac6 MOV %R11D,0x10(%R14,%R9,4) |
(18) 0x403acb VMOVAPD %XMM18,%XMM12 |
(18) 0x403ad1 VSUBPD %XMM17,%XMM6,%XMM18 |
(18) 0x403ad7 VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403add VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403ae4 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403aea VUCOMISD %XMM11,%XMM18 |
(18) 0x403af0 JAE 403afd |
(18) 0x403af2 MOV %R11D,0x14(%R14,%R9,4) |
(18) 0x403af7 VMOVAPD %XMM18,%XMM11 |
(18) 0x403afd VSUBPD %XMM17,%XMM7,%XMM18 |
(18) 0x403b03 VMULPD %XMM18,%XMM18,%XMM18 |
(18) 0x403b09 VSHUFPD $0x1,%XMM18,%XMM18,%XMM19 |
(18) 0x403b10 VADDSD %XMM18,%XMM19,%XMM18 |
(18) 0x403b16 VUCOMISD %XMM10,%XMM18 |
(18) 0x403b1c JAE 403b29 |
(18) 0x403b1e MOV %R11D,0x18(%R14,%R9,4) |
(18) 0x403b23 VMOVAPD %XMM18,%XMM10 |
(18) 0x403b29 VSUBPD %XMM17,%XMM8,%XMM17 |
(18) 0x403b2f VMULPD %XMM17,%XMM17,%XMM17 |
(18) 0x403b35 VSHUFPD $0x1,%XMM17,%XMM17,%XMM18 |
(18) 0x403b3c VADDSD %XMM17,%XMM18,%XMM17 |
(18) 0x403b42 VUCOMISD %XMM9,%XMM17 |
(18) 0x403b48 JAE 4039e0 |
(18) 0x403b4e MOV %R11D,0x1c(%R14,%R9,4) |
(18) 0x403b53 VMOVAPD %XMM17,%XMM9 |
(18) 0x403b59 JMP 4039e0 |
/home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 71 - 82 |
-------------------------------------------------------------------------------- |
71: for (int i = 0; i < n; ++i) { |
72: double optimal_dist = DBL_MAX; |
73: for (int j = 0; j < k; ++j) { |
74: double dist = |
75: (points[i].x - centroids[j].x) * (points[i].x - centroids[j].x) + |
76: (points[i].y - centroids[j].y) * (points[i].y - centroids[j].y); |
77: if (dist < optimal_dist) { |
78: optimal_dist = dist; |
79: assignment[i] = j; |
80: } |
81: } |
82: } |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_serial_fork_call(ident*,[...] | libiomp5.so | |
| ○ | __kmp_fork_call | libiomp5.so | |
| ○ | __kmpc_fork_call | libiomp5.so | |
| ○ | k_means(int, point_t*, point_t[...] | main.cpp:70 | kmeans-icpx-O3-aggressive |
| ○ | main | main.cpp:27 | kmeans-icpx-O3-aggressive |
| ○ | __libc_init_first | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | kmeans-icpx-O3-aggressive |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| 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 | 1.32 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 6.25 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.56 |
| Bottlenecks | micro-operation queue, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .extracted] |
| Source | main.cpp:71-71,main.cpp:75-75,main.cpp:79-79,main.cpp:82-82 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.25 |
| CQA cycles if no scalar integer | 4.75 |
| CQA cycles if FP arith vectorized | 6.25 |
| CQA cycles if fully vectorized | 1.00 |
| Front-end cycles | 6.25 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 4.00 |
| P3 cycles | 4.00 |
| P4 cycles | 0.00 |
| P5 cycles | 1.50 |
| P6 cycles | 1.50 |
| P7 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 6.38 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 25.00 |
| Nb uops | 25.00 |
| Nb loads | 8.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 20.48 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 94.12 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 88.89 |
| Vector-efficiency ratio all | 23.90 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 22.92 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.32 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 6.25 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.56 |
| Bottlenecks | micro-operation queue, |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .extracted] |
| Source | main.cpp:71-71,main.cpp:75-75,main.cpp:79-79,main.cpp:82-82 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.25 |
| CQA cycles if no scalar integer | 4.75 |
| CQA cycles if FP arith vectorized | 6.25 |
| CQA cycles if fully vectorized | 1.00 |
| Front-end cycles | 6.25 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 4.00 |
| P3 cycles | 4.00 |
| P4 cycles | 0.00 |
| P5 cycles | 1.50 |
| P6 cycles | 1.50 |
| P7 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 6.38 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 25.00 |
| Nb uops | 25.00 |
| Nb loads | 8.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 20.48 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 94.12 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 88.89 |
| Vector-efficiency ratio all | 23.90 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 22.92 |
| Path / |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .extracted] |
| Source file and lines | main.cpp:71-82 |
| Module | kmeans-icpx-O3-aggressive |
| nb instructions | 25 |
| nb uops | 25 |
| loop length | 121 |
| used x86 registers | 8 |
| used mmx registers | 0 |
| used xmm registers | 17 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 6.25 cycles |
| front end | 6.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 4.00 | 4.00 | 0.00 | 1.50 | 1.50 | 0.00 |
| cycles | 1.50 | 1.50 | 4.00 | 4.00 | 0.00 | 1.50 | 1.50 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 6.38 |
| Stall cycles | 0.00 |
| Front-end | 6.25 |
| Dispatch | 4.00 |
| Overall L1 | 6.25 |
| 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) |
| other | 0% |
| all | 100% |
| load | 100% |
| 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 | 100% |
| all | 94% |
| load | 100% |
| 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 | 88% |
| all | 6% |
| 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) |
| other | 6% |
| all | 25% |
| load | 25% |
| 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 | 25% |
| all | 23% |
| load | 25% |
| 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 | 22% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CMP %RDI,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 | N/A |
| LEA 0x1(%R8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 | N/A |
| JE 4038e4 <_Z7k_meansiP7point_tS0_PiS0_ii.extracted+0x94> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 | N/A |
| LEA (%RAX,%R8,8),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 | N/A |
| MOV %R9,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
| SAL $0x4,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 | N/A |
| VMOVUPD (%R15,%R10,1),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x10(%R15,%R10,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x20(%R15,%R10,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x30(%R15,%R10,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x40(%R15,%R10,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x50(%R15,%R10,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x60(%R15,%R10,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x70(%R15,%R10,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| MOV %R13,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
| XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | scal (6.3%) |
| VMOVAPD %XMM0,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| JMP 4039f0 <_Z7k_meansiP7point_tS0_PiS0_ii.extracted+0x1a0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 | N/A |
| Function | k_means(int, point_t*, point_t*, int*, point_t*, int, int) [clone .extracted] |
| Source file and lines | main.cpp:71-82 |
| Module | kmeans-icpx-O3-aggressive |
| nb instructions | 25 |
| nb uops | 25 |
| loop length | 121 |
| used x86 registers | 8 |
| used mmx registers | 0 |
| used xmm registers | 17 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 6.25 cycles |
| front end | 6.25 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 4.00 | 4.00 | 0.00 | 1.50 | 1.50 | 0.00 |
| cycles | 1.50 | 1.50 | 4.00 | 4.00 | 0.00 | 1.50 | 1.50 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 6.38 |
| Stall cycles | 0.00 |
| Front-end | 6.25 |
| Dispatch | 4.00 |
| Overall L1 | 6.25 |
| 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) |
| other | 0% |
| all | 100% |
| load | 100% |
| 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 | 100% |
| all | 94% |
| load | 100% |
| 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 | 88% |
| all | 6% |
| 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) |
| other | 6% |
| all | 25% |
| load | 25% |
| 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 | 25% |
| all | 23% |
| load | 25% |
| 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 | 22% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CMP %RDI,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 | N/A |
| LEA 0x1(%R8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 | N/A |
| JE 4038e4 <_Z7k_meansiP7point_tS0_PiS0_ii.extracted+0x94> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 | N/A |
| LEA (%RAX,%R8,8),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 | N/A |
| MOV %R9,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
| SAL $0x4,%R10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 | N/A |
| VMOVUPD (%R15,%R10,1),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x10(%R15,%R10,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x20(%R15,%R10,1),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x30(%R15,%R10,1),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x40(%R15,%R10,1),%XMM5 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x50(%R15,%R10,1),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x60(%R15,%R10,1),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| VMOVUPD 0x70(%R15,%R10,1),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 | vect (25.0%) |
| MOV %R13,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | N/A |
| XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | scal (6.3%) |
| VMOVAPD %XMM0,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| VMOVAPD %XMM0,%XMM16 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | vect (25.0%) |
| JMP 4039f0 <_Z7k_meansiP7point_tS0_PiS0_ii.extracted+0x1a0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 | 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_10_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: 10 |
| (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_10_threads) Efficiency | (run_10_threads) Potential Speed-Up (%) |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0.92 | 0.08 | 0.92 | 0.07 | 0.85 | 0.1 | 0.76 | 0.17 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| run_1_thread | 1 | 1 | 1 | 1 | 0.98999989032745 | 1.015384554863 |
| run_2_threads | 2 | 0.92 | 1.84 | 2 | 0.52999991178513 | 1.005554318428 |
| run_4_threads | 4 | 0.92 | 3.67 | 4 | 0.29999998211861 | 0.8435098528862 |
| run_8_threads | 8 | 0.85 | 6.82 | 8 | 0.16000002622604 | 0.70778912305832 |
| run_10_threads | 10 | 0.76 | 7.65 | 10 | 0.16999998688698 | 0.7048254609108 |
