Loop Id: 89 | Module: exec | Source: ljForce.c:172-216 [...] | Coverage: 0.01% |
---|
Loop Id: 89 | Module: exec | Source: ljForce.c:172-216 [...] | Coverage: 0.01% |
---|
0x40eec0 MOV -0x80(%RBP),%RCX |
0x40eec4 INC %RCX |
0x40eec7 ADD $0x40,%EDI |
0x40eeca CMP -0x58(%RBP),%RCX |
0x40eece JE 40edc4 |
0x40eed4 MOV %EDI,%EDI |
0x40eed6 MOV -0x68(%RBP),%RAX |
0x40eeda MOV (%RAX,%RCX,4),%ESI |
0x40eedd MOV -0x78(%RBP),%RAX |
0x40eee1 MOV (%RAX,%RCX,8),%R9 |
0x40eee5 TEST %ESI,%ESI |
0x40eee7 MOV %RCX,-0x80(%RBP) |
0x40eeeb JLE 40f0c0 |
0x40eef1 MOV %ECX,%EAX |
0x40eef3 SAL $0x6,%EAX |
0x40eef6 ADD %EAX,%ESI |
0x40eef8 MOV %ESI,-0x48(%RBP) |
0x40eefb LEA 0x1(%RDI),%EAX |
0x40eefe MOV %EAX,-0x44(%RBP) |
0x40ef01 MOV %EDI,%EAX |
0x40ef03 NOT %EAX |
0x40ef05 MOV %EAX,-0x40(%RBP) |
0x40ef08 XOR %R14D,%R14D |
0x40ef0b JMP 40ef4d |
(90) 0x40ef40 INC %R14 |
(90) 0x40ef43 CMP $0x1b,%R14 |
(90) 0x40ef47 JE 40eec0 |
(90) 0x40ef4d MOV (%R9,%R14,4),%EAX |
(90) 0x40ef51 TEST %EAX,%EAX |
(90) 0x40ef53 JS 40f1a4 |
(90) 0x40ef59 MOV -0x68(%RBP),%RCX |
(90) 0x40ef5d MOVSXD (%RCX,%RAX,4),%R8 |
(90) 0x40ef61 TEST %R8,%R8 |
(90) 0x40ef64 JLE 40ef40 |
(90) 0x40ef66 SAL $0x6,%EAX |
(90) 0x40ef69 MOV -0x60(%RBP),%RCX |
(90) 0x40ef6d MOV 0x20(%RCX),%R13 |
(90) 0x40ef71 MOV 0x18(%R13),%RBX |
(90) 0x40ef75 CLTQ |
(90) 0x40ef77 MOV -0x48(%RBP),%ECX |
(90) 0x40ef7a MOV -0x44(%RBP),%EDX |
(90) 0x40ef7d CMP %EDX,%ECX |
(90) 0x40ef7f MOV %EDX,%ESI |
(90) 0x40ef81 CMOVG %ECX,%ESI |
(90) 0x40ef84 ADD -0x40(%RBP),%ESI |
(90) 0x40ef87 LEA (%RAX,%RAX,2),%RAX |
(90) 0x40ef8b LEA 0x10(%RBX,%RAX,8),%R11 |
(90) 0x40ef90 XOR %EAX,%EAX |
(90) 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 |
0x40f0c0 CMPL $0,(%R9) |
0x40f0c4 JS 40f1a4 |
0x40f0ca CMPL $0,0x4(%R9) |
0x40f0cf JS 40f1a4 |
0x40f0d5 CMPL $0,0x8(%R9) |
0x40f0da JS 40f1a4 |
0x40f0e0 CMPL $0,0xc(%R9) |
0x40f0e5 JS 40f1a4 |
0x40f0eb CMPL $0,0x10(%R9) |
0x40f0f0 JS 40f1a4 |
0x40f0f6 CMPL $0,0x14(%R9) |
0x40f0fb JS 40f1a4 |
0x40f101 CMPL $0,0x18(%R9) |
0x40f106 JS 40f1a4 |
0x40f10c CMPL $0,0x1c(%R9) |
0x40f111 JS 40f1a4 |
0x40f117 CMPL $0,0x20(%R9) |
0x40f11c JS 40f1a4 |
0x40f122 CMPL $0,0x24(%R9) |
0x40f127 JS 40f1a4 |
0x40f129 CMPL $0,0x28(%R9) |
0x40f12e JS 40f1a4 |
0x40f130 CMPL $0,0x2c(%R9) |
0x40f135 JS 40f1a4 |
0x40f137 CMPL $0,0x30(%R9) |
0x40f13c JS 40f1a4 |
0x40f13e CMPL $0,0x34(%R9) |
0x40f143 JS 40f1a4 |
0x40f145 CMPL $0,0x38(%R9) |
0x40f14a JS 40f1a4 |
0x40f14c CMPL $0,0x3c(%R9) |
0x40f151 JS 40f1a4 |
0x40f153 CMPL $0,0x40(%R9) |
0x40f158 JS 40f1a4 |
0x40f15a CMPL $0,0x44(%R9) |
0x40f15f JS 40f1a4 |
0x40f161 CMPL $0,0x48(%R9) |
0x40f166 JS 40f1a4 |
0x40f168 CMPL $0,0x4c(%R9) |
0x40f16d JS 40f1a4 |
0x40f16f CMPL $0,0x50(%R9) |
0x40f174 JS 40f1a4 |
0x40f176 CMPL $0,0x54(%R9) |
0x40f17b JS 40f1a4 |
0x40f17d CMPL $0,0x58(%R9) |
0x40f182 JS 40f1a4 |
0x40f184 CMPL $0,0x5c(%R9) |
0x40f189 JS 40f1a4 |
0x40f18b CMPL $0,0x60(%R9) |
0x40f190 JS 40f1a4 |
0x40f192 CMPL $0,0x64(%R9) |
0x40f197 JS 40f1a4 |
0x40f199 CMPL $0,0x68(%R9) |
0x40f19e JNS 40eec0 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c: 172 - 216 |
-------------------------------------------------------------------------------- |
172: #pragma omp parallel for reduction(+:ePot) |
173: for (int iBox=0; iBox<s->boxes->nLocalBoxes; iBox++) |
174: { |
175: int nIBox = s->boxes->nAtoms[iBox]; |
176: |
177: // loop over neighbors of iBox |
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 | 15.70 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.34 |
Bottlenecks | |
Function | ljForce.extracted |
Source | ljForce.c:172-175,ljForce.c:180-182,ljForce.c:187-187 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 8.83 |
CQA cycles if no scalar integer | 8.83 |
CQA cycles if FP arith vectorized | 8.83 |
CQA cycles if fully vectorized | 0.56 |
Front-end cycles | 7.17 |
DIV/SQRT cycles | 7.85 |
P0 cycles | 5.60 |
P1 cycles | 6.17 |
P2 cycles | 6.17 |
P3 cycles | 1.25 |
P4 cycles | 5.60 |
P5 cycles | 7.85 |
P6 cycles | 1.25 |
P7 cycles | 1.25 |
P8 cycles | 1.25 |
P9 cycles | 5.60 |
P10 cycles | 6.17 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 11.24 |
Stall cycles (UFS) | 3.94 |
Nb insns | 43.00 |
Nb uops | 43.00 |
Nb loads | 18.50 |
Nb stores | 2.50 |
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 | 13.10 |
Bytes prefetched | 0.00 |
Bytes loaded | 90.00 |
Bytes stored | 14.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.50 |
Stride indirect | 0.50 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 7.34 |
Vector-efficiency ratio load | 9.49 |
Vector-efficiency ratio store | 10.16 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 6.36 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.48 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.58 |
Bottlenecks | micro-operation queue, |
Function | ljForce.extracted |
Source | ljForce.c:172-175,ljForce.c:180-182,ljForce.c:187-187 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.17 |
CQA cycles if no scalar integer | 3.17 |
CQA cycles if FP arith vectorized | 3.17 |
CQA cycles if fully vectorized | 0.22 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 1.20 |
P0 cycles | 1.20 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 2.00 |
P4 cycles | 1.20 |
P5 cycles | 1.20 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 1.20 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 3.32 |
Stall cycles (UFS) | 0.00 |
Nb insns | 19.00 |
Nb uops | 19.00 |
Nb loads | 4.00 |
Nb stores | 4.00 |
Nb stack references | 6.00 |
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 | 15.16 |
Bytes prefetched | 0.00 |
Bytes loaded | 28.00 |
Bytes stored | 20.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
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 | 8.04 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 7.81 |
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 | 6.25 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 16.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.30 |
Bottlenecks | P0, P6, |
Function | ljForce.extracted |
Source | ljForce.c:172-175,ljForce.c:180-182,ljForce.c:187-187 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 14.50 |
CQA cycles if no scalar integer | 14.50 |
CQA cycles if FP arith vectorized | 14.50 |
CQA cycles if fully vectorized | 0.91 |
Front-end cycles | 11.17 |
DIV/SQRT cycles | 14.50 |
P0 cycles | 10.00 |
P1 cycles | 11.00 |
P2 cycles | 11.00 |
P3 cycles | 0.50 |
P4 cycles | 10.00 |
P5 cycles | 14.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 10.00 |
P10 cycles | 11.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | 19.17 |
Stall cycles (UFS) | 7.88 |
Nb insns | 67.00 |
Nb uops | 67.00 |
Nb loads | 33.00 |
Nb stores | 1.00 |
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 | 11.03 |
Bytes prefetched | 0.00 |
Bytes loaded | 152.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
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 | 0.00 |
Vector-efficiency ratio all | 6.64 |
Vector-efficiency ratio load | 6.47 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 6.47 |
Path / |
Function | ljForce.extracted |
Source file and lines | ljForce.c:172-216 |
Module | exec |
nb instructions | 43 |
nb uops | 43 |
loop length | 167 |
used x86 registers | 6.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 7.17 cycles |
front end | 7.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 7.85 | 5.60 | 6.17 | 6.17 | 1.25 | 5.60 | 7.85 | 1.25 | 1.25 | 1.25 | 5.60 | 6.17 |
cycles | 7.85 | 5.60 | 6.17 | 6.17 | 1.25 | 5.60 | 7.85 | 1.25 | 1.25 | 1.25 | 5.60 | 6.17 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 11.25 |
Stall cycles | 3.94 |
LM full (events) | 4.53 |
Front-end | 7.17 |
Dispatch | 8.25 |
Data deps. | 2.00 |
Overall L1 | 8.83 |
all | 0% |
load | 0% |
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 | 0% |
all | 7% |
load | 9% |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 6% |
Function | ljForce.extracted |
Source file and lines | ljForce.c:172-216 |
Module | exec |
nb instructions | 19 |
nb uops | 19 |
loop length | 57 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 6 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.20 | 1.20 | 1.33 | 1.33 | 2.00 | 1.20 | 1.20 | 2.00 | 2.00 | 2.00 | 1.20 | 1.33 |
cycles | 1.20 | 1.20 | 1.33 | 1.33 | 2.00 | 1.20 | 1.20 | 2.00 | 2.00 | 2.00 | 1.20 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 3.32 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 2.00 |
Data deps. | 2.00 |
Overall L1 | 3.17 |
all | 0% |
load | 0% |
store | 0% |
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 | 8% |
load | 12% |
store | 7% |
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 | 6% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RCX,4),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x78(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
MOV %RCX,-0x80(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JLE 40f0c0 <ljForce.extracted+0x380> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %ECX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SAL $0x6,%EAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
ADD %EAX,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %ESI,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%RDI),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV %EAX,-0x44(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %EDI,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
NOT %EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %EAX,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 40ef4d <ljForce.extracted+0x20d> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | ljForce.extracted |
Source file and lines | ljForce.c:172-216 |
Module | exec |
nb instructions | 67 |
nb uops | 67 |
loop length | 277 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 11.17 cycles |
front end | 11.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 14.50 | 10.00 | 11.00 | 11.00 | 0.50 | 10.00 | 14.50 | 0.50 | 0.50 | 0.50 | 10.00 | 11.00 |
cycles | 14.50 | 10.00 | 11.00 | 11.00 | 0.50 | 10.00 | 14.50 | 0.50 | 0.50 | 0.50 | 10.00 | 11.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
FE+BE cycles | 19.17 |
Stall cycles | 7.88 |
LM full (events) | 9.06 |
Front-end | 11.17 |
Dispatch | 14.50 |
Data deps. | 2.00 |
Overall L1 | 14.50 |
all | 0% |
load | 0% |
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 | 0% |
all | 6% |
load | 6% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 6% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x80(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x40,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP -0x58(%RBP),%RCX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 40edc4 <ljForce.extracted+0x84> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RCX,4),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x78(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %ESI,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
MOV %RCX,-0x80(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JLE 40f0c0 <ljForce.extracted+0x380> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x4(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x8(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0xc(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x10(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x14(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x18(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x1c(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x20(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x24(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x28(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x2c(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x30(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x34(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x38(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x3c(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x40(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x44(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x48(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x4c(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x50(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x54(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x58(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x5c(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x60(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x64(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JS 40f1a4 <ljForce.extracted+0x464> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPL $0,0x68(%R9) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JNS 40eec0 <ljForce.extracted+0x180> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |