Loop Id: 90 | Module: exec | Source: ljForce.c:178-216 [...] | Coverage: 0.16% |
---|
Loop Id: 90 | Module: exec | Source: ljForce.c:178-216 [...] | Coverage: 0.16% |
---|
0x40ef40 INC %R14 |
0x40ef43 CMP $0x1b,%R14 |
0x40ef47 JE 40eec0 |
0x40ef4d MOV (%R9,%R14,4),%EAX |
0x40ef51 TEST %EAX,%EAX |
0x40ef53 JS 40f1a4 |
0x40ef59 MOV -0x68(%RBP),%RCX |
0x40ef5d MOVSXD (%RCX,%RAX,4),%R8 |
0x40ef61 TEST %R8,%R8 |
0x40ef64 JLE 40ef40 |
0x40ef66 SAL $0x6,%EAX |
0x40ef69 MOV -0x60(%RBP),%RCX |
0x40ef6d MOV 0x20(%RCX),%R13 |
0x40ef71 MOV 0x18(%R13),%RBX |
0x40ef75 CLTQ |
0x40ef77 MOV -0x48(%RBP),%ECX |
0x40ef7a MOV -0x44(%RBP),%EDX |
0x40ef7d CMP %EDX,%ECX |
0x40ef7f MOV %EDX,%ESI |
0x40ef81 CMOVG %ECX,%ESI |
0x40ef84 ADD -0x40(%RBP),%ESI |
0x40ef87 LEA (%RAX,%RAX,2),%RAX |
0x40ef8b LEA 0x10(%RBX,%RAX,8),%R11 |
0x40ef90 XOR %EAX,%EAX |
0x40ef92 JMP 40efcd |
(91) 0x40efc0 CMP %RSI,%RAX |
(91) 0x40efc3 LEA 0x1(%RAX),%RAX |
(91) 0x40efc7 JE 40ef40 |
(91) 0x40efcd LEA (%RAX,%RDI,1),%R15 |
(91) 0x40efd1 LEA (%R15,%R15,2),%RDX |
(91) 0x40efd5 MOV %R11,%RCX |
(91) 0x40efd8 MOV %R8,%R12 |
(91) 0x40efdb JMP 40f009 |
(92) 0x40f000 ADD $0x18,%RCX |
(92) 0x40f004 DEC %R12 |
(92) 0x40f007 JE 40efc0 |
(92) 0x40f009 VMOVUPD (%RBX,%RDX,8),%XMM11 |
(92) 0x40f00e VSUBPD -0x10(%RCX),%XMM11,%XMM11 |
(92) 0x40f013 VMULPD %XMM11,%XMM11,%XMM12 |
(92) 0x40f018 VSHUFPD $0x1,%XMM12,%XMM12,%XMM13 |
(92) 0x40f01e VADDSD %XMM12,%XMM13,%XMM13 |
(92) 0x40f023 VMOVSD 0x10(%RBX,%RDX,8),%XMM12 |
(92) 0x40f029 VSUBSD (%RCX),%XMM12,%XMM12 |
(92) 0x40f02d VFMADD231SD %XMM12,%XMM12,%XMM13 |
(92) 0x40f032 VUCOMISD %XMM2,%XMM13 |
(92) 0x40f036 JA 40f000 |
(92) 0x40f038 VUCOMISD %XMM4,%XMM13 |
(92) 0x40f03c JBE 40f000 |
(92) 0x40f03e VDIVSD %XMM13,%XMM6,%XMM13 |
(92) 0x40f043 VMULSD %XMM13,%XMM13,%XMM14 |
(92) 0x40f048 VMULSD %XMM1,%XMM13,%XMM15 |
(92) 0x40f04c VMULSD %XMM15,%XMM14,%XMM14 |
(92) 0x40f051 VADDSD %XMM7,%XMM14,%XMM15 |
(92) 0x40f055 VFNMADD213SD %XMM0,%XMM14,%XMM15 |
(92) 0x40f05a VMULSD %XMM8,%XMM15,%XMM15 |
(92) 0x40f05f MOV 0x30(%R13),%R10 |
(92) 0x40f063 VADDSD (%R10,%R15,8),%XMM15,%XMM16 |
(92) 0x40f06a VMOVSD %XMM16,(%R10,%R15,8) |
(92) 0x40f071 VMOVAPD %XMM9,%XMM16 |
(92) 0x40f077 VFMADD213SD %XMM10,%XMM14,%XMM16 |
(92) 0x40f07d VMULSD %XMM3,%XMM13,%XMM13 |
(92) 0x40f081 VMULSD %XMM14,%XMM16,%XMM14 |
(92) 0x40f087 VMULSD %XMM13,%XMM14,%XMM13 |
(92) 0x40f08c MOV 0x28(%R13),%R10 |
(92) 0x40f090 VMOVDDUP %XMM13,%XMM14 |
(92) 0x40f095 VFMADD213PD (%R10,%RDX,8),%XMM14,%XMM11 |
(92) 0x40f09b VMOVUPD %XMM11,(%R10,%RDX,8) |
(92) 0x40f0a1 VFMADD213SD 0x10(%R10,%RDX,8),%XMM13,%XMM12 |
(92) 0x40f0a8 VMOVSD %XMM12,0x10(%R10,%RDX,8) |
(92) 0x40f0af VADDSD %XMM5,%XMM15,%XMM5 |
(92) 0x40f0b3 JMP 40f000 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c: 178 - 216 |
-------------------------------------------------------------------------------- |
178: for (int jTmp=0; jTmp<nNbrBoxes; jTmp++) |
179: { |
180: int jBox = s->boxes->nbrBoxes[iBox][jTmp]; |
181: |
182: assert(jBox>=0); |
183: |
184: int nJBox = s->boxes->nAtoms[jBox]; |
185: |
186: // loop over atoms in iBox |
187: for (int iOff=MAXATOMS*iBox; iOff<(iBox*MAXATOMS+nIBox); iOff++) |
188: { |
189: |
190: // loop over atoms in jBox |
191: for (int jOff=jBox*MAXATOMS; jOff<(jBox*MAXATOMS+nJBox); jOff++) |
[...] |
197: dr[m] = s->atoms->r[iOff][m]-s->atoms->r[jOff][m]; |
198: r2+=dr[m]*dr[m]; |
199: } |
200: |
201: if ( r2 <= rCut2 && r2 > 0.0) |
202: { |
203: |
204: // Important note: |
205: // from this point on r actually refers to 1.0/r |
206: r2 = 1.0/r2; |
207: real_t r6 = s6 * (r2*r2*r2); |
208: real_t eLocal = r6 * (r6 - 1.0) - eShift; |
209: s->atoms->U[iOff] += 0.5*eLocal; |
210: ePot += 0.5*eLocal; |
211: |
212: // different formulation to avoid sqrt computation |
213: real_t fr = - 4.0*epsilon*r6*r2*(12.0*r6 - 6.0); |
214: for (int m=0; m<3; m++) |
215: { |
216: s->atoms->f[iOff][m] -= dr[m]*fr; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 13.87 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.40 |
Bottlenecks | |
Function | ljForce.extracted |
Source | ljForce.c:178-184,ljForce.c:187-187,ljForce.c:191-191,ljForce.c:197-197 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 3.50 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 2.25 |
P0 cycles | 2.08 |
P1 cycles | 2.50 |
P2 cycles | 2.50 |
P3 cycles | 0.00 |
P4 cycles | 1.95 |
P5 cycles | 2.25 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.80 |
P10 cycles | 2.50 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.69 |
Stall cycles (UFS) | 0.00 |
Nb insns | 21.25 |
Nb uops | 21.00 |
Nb loads | 7.50 |
Nb stores | 0.00 |
Nb stack references | 4.00 |
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 | 12.03 |
Bytes prefetched | 0.00 |
Bytes loaded | 43.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.75 |
Stride unknown | 1.75 |
Stride indirect | 0.75 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 9.71 |
Vector-efficiency ratio load | 9.38 |
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 | 9.84 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.55 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | micro-operation queue, P0, P6, |
Function | ljForce.extracted |
Source | ljForce.c:178-184,ljForce.c:187-187,ljForce.c:191-191,ljForce.c:197-197 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.50 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.10 |
Front-end cycles | 1.50 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.80 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.00 |
P4 cycles | 0.60 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.60 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 1.64 |
Stall cycles (UFS) | 0.00 |
Nb insns | 10.00 |
Nb uops | 9.00 |
Nb loads | 3.00 |
Nb stores | 0.00 |
Nb stack references | 1.00 |
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 | 10.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
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 | 0.00 |
Vector-efficiency ratio all | 9.38 |
Vector-efficiency ratio load | NA |
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 | 9.38 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 13.79 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.39 |
Bottlenecks | micro-operation queue, |
Function | ljForce.extracted |
Source | ljForce.c:178-184,ljForce.c:187-187,ljForce.c:191-191,ljForce.c:197-197 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.17 |
CQA cycles if no scalar integer | 4.17 |
CQA cycles if FP arith vectorized | 4.17 |
CQA cycles if fully vectorized | 0.30 |
Front-end cycles | 4.17 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 0.00 |
P4 cycles | 2.40 |
P5 cycles | 2.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.20 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 4.38 |
Stall cycles (UFS) | 0.00 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 9.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 12.48 |
Bytes prefetched | 0.00 |
Bytes loaded | 52.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 2.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 9.82 |
Vector-efficiency ratio load | 9.38 |
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 | 10.00 |
Path / |
Function | ljForce.extracted |
Source file and lines | ljForce.c:178-216 |
Module | exec |
nb instructions | 21.25 |
nb uops | 21 |
loop length | 72.50 |
used x86 registers | 9.75 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.25 | 2.00 | 2.50 | 2.50 | 0.00 | 1.95 | 2.25 | 0.00 | 0.00 | 0.00 | 1.80 | 2.50 |
cycles | 2.25 | 2.08 | 2.50 | 2.50 | 0.00 | 1.95 | 2.25 | 0.00 | 0.00 | 0.00 | 1.80 | 2.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.70 |
Stall cycles | 0.00 |
Front-end | 3.50 |
Dispatch | 2.63 |
Data deps. | 0.00 |
Overall L1 | 3.50 |
all | 0% |
load | 0% |
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 | 0% |
all | 9% |
load | 9% |
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 | 9% |
Function | ljForce.extracted |
Source file and lines | ljForce.c:178-216 |
Module | exec |
nb instructions | 10 |
nb uops | 9 |
loop length | 38 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 1.50 cycles |
front end | 1.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.80 | 1.00 | 1.00 | 0.00 | 0.60 | 1.50 | 0.00 | 0.00 | 0.00 | 0.60 | 1.00 |
cycles | 1.50 | 0.80 | 1.00 | 1.00 | 0.00 | 0.60 | 1.50 | 0.00 | 0.00 | 0.00 | 0.60 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 1.64 |
Stall cycles | 0.00 |
Front-end | 1.50 |
Dispatch | 1.50 |
Data deps. | 0.00 |
Overall L1 | 1.50 |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 9% |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 9% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP $0x1b,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JE 40eec0 <ljForce.extracted+0x180> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R9,%R14,4),%EAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %EAX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD (%RCX,%RAX,4),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R8,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 40ef40 <ljForce.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | ljForce.extracted |
Source file and lines | ljForce.c:178-216 |
Module | exec |
nb instructions | 25 |
nb uops | 25 |
loop length | 84 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 4.17 cycles |
front end | 4.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.40 | 3.00 | 3.00 | 0.00 | 2.40 | 2.50 | 0.00 | 0.00 | 0.00 | 2.20 | 3.00 |
cycles | 2.50 | 2.50 | 3.00 | 3.00 | 0.00 | 2.40 | 2.50 | 0.00 | 0.00 | 0.00 | 2.20 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 4.38 |
Stall cycles | 0.00 |
Front-end | 4.17 |
Dispatch | 3.00 |
Data deps. | 0.00 |
Overall L1 | 4.17 |
all | 0% |
load | 0% |
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 | 0% |
all | 9% |
load | 9% |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP $0x1b,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JE 40eec0 <ljForce.extracted+0x180> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R9,%R14,4),%EAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %EAX,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD (%RCX,%RAX,4),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R8,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 40ef40 <ljForce.extracted+0x200> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
SAL $0x6,%EAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x20(%RCX),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x18(%R13),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CLTQ | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
MOV -0x48(%RBP),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x44(%RBP),%EDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %EDX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EDX,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMOVG %ECX,%ESI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
ADD -0x40(%RBP),%ESI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
LEA (%RAX,%RAX,2),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA 0x10(%RBX,%RAX,8),%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 40efcd <ljForce.extracted+0x28d> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |