Loop Id: 99 | Module: exec | Source: linkCells.c:295-378 [...] | Coverage: 0.29% |
---|
Loop Id: 99 | Module: exec | Source: linkCells.c:295-378 [...] | Coverage: 0.29% |
---|
0x20fb80 INC %R12D |
0x20fb83 MOV 0x78(%R14),%RCX [1] |
0x20fb87 CMP (%RCX,%R15,4),%R12D [2] |
0x20fb8b JGE 20fb50 |
0x20fb8d MOV 0x18(%RBX),%RAX [4] |
0x20fb91 LEA (%R12,%R13,1),%ECX |
0x20fb95 VMOVSD 0x30(%R14),%XMM1 [1] |
0x20fb9b MOVSXD %ECX,%RCX |
0x20fb9e LEA (%RCX,%RCX,2),%RCX |
0x20fba2 VMOVSD (%RAX,%RCX,8),%XMM0 [3] |
0x20fba7 VUCOMISD %XMM0,%XMM1 |
0x20fbab JBE 20fbd0 |
0x20fbad VSUBSD 0x18(%R14),%XMM0,%XMM0 [1] |
0x20fbb3 MOV (%R14),%EDI [1] |
0x20fbb6 VMULSD 0x60(%R14),%XMM0,%XMM0 [1] |
0x20fbbc LEA -0x1(%RDI),%ESI |
0x20fbbf VROUNDSD $0x9,%XMM0,%XMM0,%XMM0 |
0x20fbc5 VCVTTSD2SI %XMM0,%EDX |
0x20fbc9 CMP %EDX,%EDI |
0x20fbcb CMOVNE %EDX,%ESI |
0x20fbce JMP 20fbd3 |
0x20fbd0 MOV (%R14),%ESI [1] |
0x20fbd3 VMOVUPD 0x8(%RAX,%RCX,8),%XMM0 [3] |
0x20fbd9 VMOVQ 0x4(%R14),%XMM2 [1] |
0x20fbdf MOV %R14,%RDI |
0x20fbe2 VSUBPD 0x20(%R14),%XMM0,%XMM1 [1] |
0x20fbe8 VCMPPD $0x1,0x38(%R14),%XMM0,%K2 [1] |
0x20fbf3 VMULPD 0x68(%R14),%XMM1,%XMM1 [1] |
0x20fbf9 VPCMPEQD %XMM0,%XMM0,%XMM0 |
0x20fbfd VROUNDPD $0x9,%XMM1,%XMM1 |
0x20fc03 VCVTTPD2DQ %XMM1,%XMM1 |
0x20fc07 VPCMPEQD %XMM1,%XMM2,%K1 |
0x20fc0d VPADDD %XMM0,%XMM2,%XMM1{%K1} |
0x20fc13 VMOVDQA32 %XMM1,%XMM2{%K2} |
0x20fc19 VMOVD %XMM2,%EDX |
0x20fc1d VPEXTRD $0x1,%XMM2,%ECX |
0x20fc23 CALL 20f6b0 <getBoxFromTuple> |
0x20fc28 MOV %EAX,%ECX |
0x20fc2a CMP %RCX,%R15 |
0x20fc2d JE 20fb80 |
0x20fc33 MOV %R14,%RDI |
0x20fc36 MOV %RBX,%RSI |
0x20fc39 MOV %R12D,%EDX |
0x20fc3c MOV %R15D,%ECX |
0x20fc3f MOV %EAX,%R8D |
0x20fc42 CALL 20f960 <moveAtom> |
0x20fc47 JMP 20fb83 |
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-7424/intel/CoMD/build/CoMD/CoMD/src-openmp/linkCells.c: 295 - 378 |
-------------------------------------------------------------------------------- |
295: while (ii < boxes->nAtoms[iBox]) |
296: { |
297: int jBox = getBoxFromCoord(boxes, atoms->r[iOff+ii]); |
298: if (jBox != iBox) |
299: moveAtom(boxes, atoms, ii, iBox, jBox); |
300: else |
301: ++ii; |
[...] |
352: int ix = (int)(floor((rr[0] - localMin[0])*boxes->invBoxSize[0])); |
[...] |
359: if (rr[0] < localMax[0]) |
360: { |
361: if (ix == gridSize[0]) ix = gridSize[0] - 1; |
362: } |
363: else |
364: ix = gridSize[0]; // assign to halo cell |
365: if (rr[1] < localMax[1]) |
[...] |
371: if (rr[2] < localMax[2]) |
[...] |
378: return getBoxFromTuple(boxes, ix, iy, iz); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.55 |
CQA speedup if FP arith vectorized | 1.86 |
CQA speedup if fully vectorized | 5.53 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.57 |
Bottlenecks | |
Function | updateLinkCells |
Source | linkCells.c:295-301,linkCells.c:352-352,linkCells.c:359-365,linkCells.c:371-371,linkCells.c:378-378 |
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 | 7.08 |
CQA cycles if no scalar integer | 4.58 |
CQA cycles if FP arith vectorized | 3.81 |
CQA cycles if fully vectorized | 1.28 |
Front-end cycles | 7.08 |
DIV/SQRT cycles | 2.81 |
P0 cycles | 2.25 |
P1 cycles | 2.19 |
P2 cycles | 2.00 |
P3 cycles | 2.75 |
P4 cycles | 4.50 |
P5 cycles | 4.50 |
P6 cycles | 4.50 |
P7 cycles | 3.00 |
P8 cycles | 2.96 |
P9 cycles | 3.04 |
P10 cycles | 3.00 |
P11 cycles | 1.75 |
P12 cycles | 1.75 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 38.00 |
Nb uops | 42.50 |
Nb loads | 12.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.71 |
Nb FLOP add-sub | 2.50 |
Nb FLOP mul | 2.50 |
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 | 17.17 |
Bytes prefetched | 0.00 |
Bytes loaded | 120.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 44.51 |
Vectorization ratio load | 42.22 |
Vectorization ratio store | NA |
Vectorization ratio mul | 75.00 |
Vectorization ratio add_sub | 83.33 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 43.17 |
Vector-efficiency ratio all | 16.57 |
Vector-efficiency ratio load | 16.77 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 21.88 |
Vector-efficiency ratio add_sub | 22.92 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.70 |
CQA speedup if FP arith vectorized | 2.09 |
CQA speedup if fully vectorized | 6.18 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.70 |
Bottlenecks | micro-operation queue, |
Function | updateLinkCells |
Source | linkCells.c:295-301,linkCells.c:352-352,linkCells.c:359-365,linkCells.c:371-371,linkCells.c:378-378 |
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 | 8.50 |
CQA cycles if no scalar integer | 5.00 |
CQA cycles if FP arith vectorized | 4.06 |
CQA cycles if fully vectorized | 1.38 |
Front-end cycles | 8.50 |
DIV/SQRT cycles | 3.50 |
P0 cycles | 2.75 |
P1 cycles | 2.75 |
P2 cycles | 2.50 |
P3 cycles | 3.50 |
P4 cycles | 5.00 |
P5 cycles | 5.00 |
P6 cycles | 5.00 |
P7 cycles | 3.50 |
P8 cycles | 3.50 |
P9 cycles | 3.50 |
P10 cycles | 3.50 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 45.00 |
Nb uops | 51.00 |
Nb loads | 13.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.71 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 3.00 |
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 | 15.06 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 38.46 |
Vectorization ratio load | 40.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 35.29 |
Vector-efficiency ratio all | 15.63 |
Vector-efficiency ratio load | 16.88 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 18.75 |
Vector-efficiency ratio add_sub | 20.83 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 14.34 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.43 |
CQA speedup if FP arith vectorized | 1.88 |
CQA speedup if fully vectorized | 5.29 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.54 |
Bottlenecks | micro-operation queue, |
Function | updateLinkCells |
Source | linkCells.c:295-301,linkCells.c:352-352,linkCells.c:359-365,linkCells.c:371-371,linkCells.c:378-378 |
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 | 7.17 |
CQA cycles if no scalar integer | 5.00 |
CQA cycles if FP arith vectorized | 3.81 |
CQA cycles if fully vectorized | 1.35 |
Front-end cycles | 7.17 |
DIV/SQRT cycles | 2.75 |
P0 cycles | 2.75 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 2.50 |
P4 cycles | 4.67 |
P5 cycles | 4.67 |
P6 cycles | 4.67 |
P7 cycles | 3.50 |
P8 cycles | 3.50 |
P9 cycles | 3.50 |
P10 cycles | 3.50 |
P11 cycles | 2.00 |
P12 cycles | 2.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 39.00 |
Nb uops | 43.00 |
Nb loads | 13.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.84 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 3.00 |
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 | 17.86 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 43.48 |
Vectorization ratio load | 40.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 50.00 |
Vectorization ratio add_sub | 66.67 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 42.86 |
Vector-efficiency ratio all | 16.58 |
Vector-efficiency ratio load | 16.88 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 18.75 |
Vector-efficiency ratio add_sub | 20.83 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.63 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.68 |
CQA speedup if FP arith vectorized | 1.80 |
CQA speedup if fully vectorized | 5.79 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.62 |
Bottlenecks | micro-operation queue, |
Function | updateLinkCells |
Source | linkCells.c:295-301,linkCells.c:352-352,linkCells.c:359-365,linkCells.c:371-371,linkCells.c:378-378 |
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 | 7.00 |
CQA cycles if no scalar integer | 4.17 |
CQA cycles if FP arith vectorized | 3.88 |
CQA cycles if fully vectorized | 1.21 |
Front-end cycles | 7.00 |
DIV/SQRT cycles | 3.00 |
P0 cycles | 1.75 |
P1 cycles | 1.75 |
P2 cycles | 1.50 |
P3 cycles | 3.00 |
P4 cycles | 4.33 |
P5 cycles | 4.33 |
P6 cycles | 4.33 |
P7 cycles | 2.50 |
P8 cycles | 2.42 |
P9 cycles | 2.58 |
P10 cycles | 2.50 |
P11 cycles | 1.50 |
P12 cycles | 1.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 37.00 |
Nb uops | 42.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.57 |
Nb FLOP add-sub | 2.00 |
Nb FLOP mul | 2.00 |
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 | 16.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 112.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 43.48 |
Vectorization ratio load | 44.44 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 40.00 |
Vector-efficiency ratio all | 16.30 |
Vector-efficiency ratio load | 16.67 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 25.00 |
Vector-efficiency ratio add_sub | 25.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.42 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.36 |
CQA speedup if FP arith vectorized | 1.63 |
CQA speedup if fully vectorized | 4.77 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.42 |
Bottlenecks | micro-operation queue, |
Function | updateLinkCells |
Source | linkCells.c:295-301,linkCells.c:352-352,linkCells.c:359-365,linkCells.c:371-371,linkCells.c:378-378 |
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 | 5.67 |
CQA cycles if no scalar integer | 4.17 |
CQA cycles if FP arith vectorized | 3.47 |
CQA cycles if fully vectorized | 1.19 |
Front-end cycles | 5.67 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.75 |
P1 cycles | 1.75 |
P2 cycles | 1.50 |
P3 cycles | 2.00 |
P4 cycles | 4.00 |
P5 cycles | 4.00 |
P6 cycles | 4.00 |
P7 cycles | 2.50 |
P8 cycles | 2.42 |
P9 cycles | 2.58 |
P10 cycles | 2.50 |
P11 cycles | 1.50 |
P12 cycles | 1.50 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 31.00 |
Nb uops | 34.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.71 |
Nb FLOP add-sub | 2.00 |
Nb FLOP mul | 2.00 |
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 | 19.76 |
Bytes prefetched | 0.00 |
Bytes loaded | 112.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 52.63 |
Vectorization ratio load | 44.44 |
Vectorization ratio store | NA |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 54.55 |
Vector-efficiency ratio all | 17.76 |
Vector-efficiency ratio load | 16.67 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 25.00 |
Vector-efficiency ratio add_sub | 25.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.61 |
Path / |
Function | updateLinkCells |
Source file and lines | linkCells.c:295-378 |
Module | exec |
nb instructions | 38 |
nb uops | 42.50 |
loop length | 171 |
used x86 registers | 10.50 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 7.08 cycles |
front end | 7.08 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.81 | 2.25 | 2.19 | 2.00 | 2.75 | 4.50 | 4.50 | 4.50 | 3.00 | 2.96 | 3.04 | 3.00 | 1.75 | 1.75 |
cycles | 2.81 | 2.25 | 2.19 | 2.00 | 2.75 | 4.50 | 4.50 | 4.50 | 3.00 | 2.96 | 3.04 | 3.00 | 1.75 | 1.75 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 7.08 |
Dispatch | 4.50 |
Data deps. | 0.00 |
Overall L1 | 7.08 |
all | 34% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 56% |
load | 58% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 75% |
add-sub | 75% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 62% |
all | 44% |
load | 42% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 75% |
add-sub | 83% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 43% |
all | 13% |
load | 8% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 13% |
all | 19% |
load | 19% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 21% |
add-sub | 21% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
all | 16% |
load | 16% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 21% |
add-sub | 22% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Function | updateLinkCells |
Source file and lines | linkCells.c:295-378 |
Module | exec |
nb instructions | 45 |
nb uops | 51 |
loop length | 198 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 8.50 cycles |
front end | 8.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.50 | 2.75 | 2.75 | 2.50 | 3.50 | 5.00 | 5.00 | 5.00 | 3.50 | 3.50 | 3.50 | 3.50 | 2.00 | 2.00 |
cycles | 3.50 | 2.75 | 2.75 | 2.50 | 3.50 | 5.00 | 5.00 | 5.00 | 3.50 | 3.50 | 3.50 | 3.50 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 8.50 |
Dispatch | 5.00 |
Data deps. | 0.00 |
Overall L1 | 8.50 |
all | 30% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 27% |
all | 46% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 38% |
load | 40% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 35% |
all | 12% |
load | 9% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 18% |
load | 18% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 18% |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
all | 15% |
load | 16% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 18% |
add-sub | 20% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x78(%R14),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
CMP (%RCX,%R15,4),%R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JGE 20fb50 <updateLinkCells+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x18(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%R12,%R13,1),%ECX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD 0x30(%R14),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOVSXD %ECX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%RCX,%RCX,2),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD (%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VUCOMISD %XMM0,%XMM1 | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 6 | 1 |
JBE 20fbd0 <updateLinkCells+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
VSUBSD 0x18(%R14),%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
MOV (%R14),%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMULSD 0x60(%R14),%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
LEA -0x1(%RDI),%ESI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VROUNDSD $0x9,%XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTSD2SI %XMM0,%EDX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 8 | 1 |
CMP %EDX,%EDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMOVNE %EDX,%ESI | 1 | 0.50 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
JMP 20fbd3 <updateLinkCells+0xe3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVUPD 0x8(%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVQ 0x4(%R14),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VSUBPD 0x20(%R14),%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCMPPD $0x1,0x38(%R14),%XMM0,%K2 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD 0x68(%R14),%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VROUNDPD $0x9,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTPD2DQ %XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM1,%XMM2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPADDD %XMM0,%XMM2,%XMM1{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVDQA32 %XMM1,%XMM2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVD %XMM2,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
VPEXTRD $0x1,%XMM2,%ECX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 6 | 1 |
CALL 20f6b0 <getBoxFromTuple> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RCX,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 20fb80 <updateLinkCells+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R15D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 20f960 <moveAtom> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 20fb83 <updateLinkCells+0x93> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
Function | updateLinkCells |
Source file and lines | linkCells.c:295-378 |
Module | exec |
nb instructions | 39 |
nb uops | 43 |
loop length | 176 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 7.17 cycles |
front end | 7.17 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 2.50 | 2.50 | 2.50 | 4.67 | 4.67 | 4.67 | 3.50 | 3.50 | 3.50 | 3.50 | 2.00 | 2.00 |
cycles | 2.75 | 2.75 | 2.50 | 2.50 | 2.50 | 4.67 | 4.67 | 4.67 | 3.50 | 3.50 | 3.50 | 3.50 | 2.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 7.17 |
Dispatch | 4.67 |
Data deps. | 0.00 |
Overall L1 | 7.17 |
all | 40% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 37% |
all | 46% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
all | 43% |
load | 40% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | 66% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 42% |
all | 14% |
load | 9% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 13% |
all | 18% |
load | 18% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 18% |
add-sub | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
all | 16% |
load | 16% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 18% |
add-sub | 20% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
MOV 0x78(%R14),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
CMP (%RCX,%R15,4),%R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JGE 20fb50 <updateLinkCells+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x18(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%R12,%R13,1),%ECX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD 0x30(%R14),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOVSXD %ECX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%RCX,%RCX,2),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD (%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VUCOMISD %XMM0,%XMM1 | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 6 | 1 |
JBE 20fbd0 <updateLinkCells+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
VSUBSD 0x18(%R14),%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
MOV (%R14),%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMULSD 0x60(%R14),%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
LEA -0x1(%RDI),%ESI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VROUNDSD $0x9,%XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTSD2SI %XMM0,%EDX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 8 | 1 |
CMP %EDX,%EDI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
CMOVNE %EDX,%ESI | 1 | 0.50 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
JMP 20fbd3 <updateLinkCells+0xe3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
VMOVUPD 0x8(%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVQ 0x4(%R14),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VSUBPD 0x20(%R14),%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCMPPD $0x1,0x38(%R14),%XMM0,%K2 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD 0x68(%R14),%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VROUNDPD $0x9,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTPD2DQ %XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM1,%XMM2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPADDD %XMM0,%XMM2,%XMM1{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVDQA32 %XMM1,%XMM2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVD %XMM2,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
VPEXTRD $0x1,%XMM2,%ECX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 6 | 1 |
CALL 20f6b0 <getBoxFromTuple> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RCX,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 20fb80 <updateLinkCells+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
Function | updateLinkCells |
Source file and lines | linkCells.c:295-378 |
Module | exec |
nb instructions | 37 |
nb uops | 42 |
loop length | 166 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 3.00 | 1.75 | 1.75 | 1.50 | 3.00 | 4.33 | 4.33 | 4.33 | 2.50 | 2.42 | 2.58 | 2.50 | 1.50 | 1.50 |
cycles | 3.00 | 1.75 | 1.75 | 1.50 | 3.00 | 4.33 | 4.33 | 4.33 | 2.50 | 2.42 | 2.58 | 2.50 | 1.50 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 7.00 |
Dispatch | 4.33 |
Data deps. | 0.00 |
Overall L1 | 7.00 |
all | 28% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 27% |
all | 66% |
load | 66% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 43% |
load | 44% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 40% |
all | 13% |
load | 8% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 13% |
all | 20% |
load | 20% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 25% |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 21% |
all | 16% |
load | 16% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 25% |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x78(%R14),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
CMP (%RCX,%R15,4),%R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JGE 20fb50 <updateLinkCells+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x18(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%R12,%R13,1),%ECX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD 0x30(%R14),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOVSXD %ECX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%RCX,%RCX,2),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD (%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VUCOMISD %XMM0,%XMM1 | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 6 | 1 |
JBE 20fbd0 <updateLinkCells+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV (%R14),%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVUPD 0x8(%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVQ 0x4(%R14),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VSUBPD 0x20(%R14),%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCMPPD $0x1,0x38(%R14),%XMM0,%K2 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD 0x68(%R14),%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VROUNDPD $0x9,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTPD2DQ %XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM1,%XMM2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPADDD %XMM0,%XMM2,%XMM1{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVDQA32 %XMM1,%XMM2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVD %XMM2,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
VPEXTRD $0x1,%XMM2,%ECX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 6 | 1 |
CALL 20f6b0 <getBoxFromTuple> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RCX,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 20fb80 <updateLinkCells+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R15D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 20f960 <moveAtom> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
JMP 20fb83 <updateLinkCells+0x93> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
Function | updateLinkCells |
Source file and lines | linkCells.c:295-378 |
Module | exec |
nb instructions | 31 |
nb uops | 34 |
loop length | 144 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 1.00 |
micro-operation queue | 5.67 cycles |
front end | 5.67 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.75 | 1.75 | 1.50 | 2.00 | 4.00 | 4.00 | 4.00 | 2.50 | 2.42 | 2.58 | 2.50 | 1.50 | 1.50 |
cycles | 2.00 | 1.75 | 1.75 | 1.50 | 2.00 | 4.00 | 4.00 | 4.00 | 2.50 | 2.42 | 2.58 | 2.50 | 1.50 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 5.67 |
Dispatch | 4.00 |
Data deps. | 0.00 |
Overall L1 | 5.67 |
all | 40% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 42% |
all | 66% |
load | 66% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 75% |
all | 52% |
load | 44% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 100% |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 54% |
all | 15% |
load | 8% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 15% |
all | 20% |
load | 20% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 25% |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 21% |
all | 17% |
load | 16% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 25% |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
MOV 0x78(%R14),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
CMP (%RCX,%R15,4),%R12D | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
JGE 20fb50 <updateLinkCells+0x60> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV 0x18(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
LEA (%R12,%R13,1),%ECX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD 0x30(%R14),%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOVSXD %ECX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LEA (%RCX,%RCX,2),%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
VMOVSD (%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VUCOMISD %XMM0,%XMM1 | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0.50 | 6 | 1 |
JBE 20fbd0 <updateLinkCells+0xe0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |
MOV (%R14),%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 |
VMOVUPD 0x8(%RAX,%RCX,8),%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVQ 0x4(%R14),%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VSUBPD 0x20(%R14),%XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCMPPD $0x1,0x38(%R14),%XMM0,%K2 | 2 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMULPD 0x68(%R14),%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VROUNDPD $0x9,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VCVTTPD2DQ %XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 |
VPCMPEQD %XMM1,%XMM2,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VPADDD %XMM0,%XMM2,%XMM1{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 1 | 0.25 |
VMOVDQA32 %XMM1,%XMM2{%K2} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVD %XMM2,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 5 | 1 |
VPEXTRD $0x1,%XMM2,%ECX | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0.50 | 0.50 | 6 | 1 |
CALL 20f6b0 <getBoxFromTuple> | 2 | 0.50 | 0 | 0 | 0 | 0.50 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RCX,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
JE 20fb80 <updateLinkCells+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 |