Loop Id: 21 | Module: exec | Source: ljForce.c:175-216 [...] | Coverage: 0.02% |
---|
Loop Id: 21 | Module: exec | Source: ljForce.c:175-216 [...] | Coverage: 0.02% |
---|
0x406287 MOV -0x68(%RBP),%R9D |
0x40628b MOV (%R14,%RAX,4),%R8D |
0x40628f TEST %R9D,%R9D |
0x406292 JLE 4065cf |
0x406298 MOV 0x80(%R13),%R11 |
0x40629f MOV %EAX,%ESI |
0x4062a1 MOV -0x78(%RBP),%RBX |
0x4062a5 MOV %ECX,-0x70(%RBP) |
0x4062a8 SAL $0x6,%ESI |
0x4062ab LEA (%R8,%RCX,1),%R10D |
0x4062af MOV %R13,-0x80(%RBP) |
0x4062b3 VMOVSD 0xc97d(%RIP),%XMM12 |
0x4062bb MOV (%R11,%RAX,8),%RDX |
0x4062bf MOVSXD %ESI,%R9 |
0x4062c2 MOV %R10D,-0x50(%RBP) |
0x4062c6 LEA -0x1(%R10),%R10D |
0x4062ca LEA (,%R9,8),%RDI |
0x4062d2 SUB %ESI,%R10D |
0x4062d5 MOV %R14,-0x48(%RBP) |
0x4062d9 LEA (%RDX,%RBX,1),%R8 |
0x4062dd MOV %RDI,-0x58(%RBP) |
0x4062e1 LEA 0x1(%R9,%R10,1),%RBX |
0x4062e6 MOV %R12,%R9 |
0x4062e9 MOV %R8,-0x60(%RBP) |
0x4062ed SAL $0x3,%RBX |
0x4062f1 MOV %RAX,-0x88(%RBP) |
0x4062f8 MOV %ESI,-0x64(%RBP) |
(23) 0x4062fb MOV (%RDX),%R11D |
(23) 0x4062fe TEST %R11D,%R11D |
(23) 0x406301 JS 406635 |
(23) 0x406307 MOV -0x48(%RBP),%R13 |
(23) 0x40630b MOVSXD %R11D,%R12 |
(23) 0x40630e MOV -0x64(%RBP),%EAX |
(23) 0x406311 MOV (%R13,%R12,4),%R14D |
(23) 0x406316 CMP %EAX,-0x50(%RBP) |
(23) 0x406319 JLE 4065a9 |
(23) 0x40631f LEA (%R12,%R12,2),%R12 |
(23) 0x406323 MOV %RDX,-0x40(%RBP) |
(23) 0x406327 SAL $0x6,%R11D |
(23) 0x40632b LEA (%R14,%R14,2),%RCX |
(23) 0x40632f SAL $0x9,%R12 |
(23) 0x406333 MOV -0x58(%RBP),%R8 |
(23) 0x406337 LEA (%R14,%R11,1),%R13D |
(23) 0x40633b VXORPD %XMM4,%XMM4,%XMM4 |
(23) 0x40633f LEA (%R12,%RCX,8),%R14 |
(23) 0x406343 NOPL (%RAX,%RAX,1) |
(24) 0x406348 CMP %R13D,%R11D |
(24) 0x40634b JGE 406598 |
(24) 0x406351 MOV 0x20(%R15),%RDI |
(24) 0x406355 LEA (%R8,%R8,2),%R10 |
(24) 0x406359 MOV 0x18(%RDI),%RCX |
(24) 0x40635d LEA (%RCX,%R12,1),%RAX |
(24) 0x406361 LEA (%RCX,%R10,1),%RDX |
(24) 0x406365 ADD %R14,%RCX |
(24) 0x406368 MOV %RCX,%RSI |
(24) 0x40636b SUB %RAX,%RSI |
(24) 0x40636e AND $0x8,%ESI |
(24) 0x406371 JE 406430 |
(24) 0x406377 VMOVSD 0x8(%RDX),%XMM2 |
(24) 0x40637c VSUBSD 0x8(%RAX),%XMM2,%XMM0 |
(24) 0x406381 VMOVSD (%RDX),%XMM1 |
(24) 0x406385 VSUBSD (%RAX),%XMM1,%XMM1 |
(24) 0x406389 VMOVSD 0x10(%RDX),%XMM13 |
(24) 0x40638e VSUBSD 0x10(%RAX),%XMM13,%XMM2 |
(24) 0x406393 VMULSD %XMM0,%XMM0,%XMM3 |
(24) 0x406397 VFMADD231SD %XMM1,%XMM1,%XMM3 |
(24) 0x40639c VFMADD231SD %XMM2,%XMM2,%XMM3 |
(24) 0x4063a1 VCOMISD %XMM3,%XMM9 |
(24) 0x4063a5 JB 406421 |
(24) 0x4063a7 VCOMISD %XMM4,%XMM3 |
(24) 0x4063ab JBE 406421 |
(24) 0x4063ad VDIVSD %XMM3,%XMM7,%XMM15 |
(24) 0x4063b1 MOV 0x30(%RDI),%RSI |
(24) 0x4063b5 ADD %R8,%RSI |
(24) 0x4063b8 VMULSD %XMM15,%XMM15,%XMM13 |
(24) 0x4063bd VMULSD %XMM15,%XMM10,%XMM3 |
(24) 0x4063c2 VMULSD %XMM8,%XMM15,%XMM14 |
(24) 0x4063c7 VMULSD %XMM3,%XMM13,%XMM3 |
(24) 0x4063cb VSUBSD %XMM7,%XMM3,%XMM13 |
(24) 0x4063cf VFMSUB213SD -0x38(%RBP),%XMM3,%XMM13 |
(24) 0x4063d5 VMOVSD %XMM13,%XMM13,%XMM15 |
(24) 0x4063da VFMADD231SD %XMM6,%XMM13,%XMM5 |
(24) 0x4063df VMOVSD %XMM3,%XMM3,%XMM13 |
(24) 0x4063e3 VFMADD132SD %XMM11,%XMM12,%XMM13 |
(24) 0x4063e8 VFMADD213SD (%RSI),%XMM6,%XMM15 |
(24) 0x4063ed VMULSD %XMM13,%XMM3,%XMM3 |
(24) 0x4063f2 VMOVSD %XMM15,(%RSI) |
(24) 0x4063f6 MOV 0x28(%RDI),%RSI |
(24) 0x4063fa ADD %R10,%RSI |
(24) 0x4063fd VMULSD %XMM14,%XMM3,%XMM14 |
(24) 0x406402 VFNMADD213SD (%RSI),%XMM14,%XMM1 |
(24) 0x406407 VFNMADD213SD 0x8(%RSI),%XMM14,%XMM0 |
(24) 0x40640d VFNMADD213SD 0x10(%RSI),%XMM2,%XMM14 |
(24) 0x406413 VMOVSD %XMM1,(%RSI) |
(24) 0x406417 VMOVSD %XMM0,0x8(%RSI) |
(24) 0x40641c VMOVSD %XMM14,0x10(%RSI) |
(24) 0x406421 ADD $0x18,%RAX |
(24) 0x406425 CMP %RAX,%RCX |
(24) 0x406428 JE 406598 |
(24) 0x40642e XCHG %AX,%AX |
(25) 0x406430 VMOVSD 0x8(%RDX),%XMM0 |
(25) 0x406435 VSUBSD 0x8(%RAX),%XMM0,%XMM0 |
(25) 0x40643a VMOVSD (%RDX),%XMM1 |
(25) 0x40643e VSUBSD (%RAX),%XMM1,%XMM1 |
(25) 0x406442 VMOVSD 0x10(%RDX),%XMM2 |
(25) 0x406447 VSUBSD 0x10(%RAX),%XMM2,%XMM2 |
(25) 0x40644c VMULSD %XMM0,%XMM0,%XMM15 |
(25) 0x406450 VFMADD231SD %XMM1,%XMM1,%XMM15 |
(25) 0x406455 VFMADD231SD %XMM2,%XMM2,%XMM15 |
(25) 0x40645a VCOMISD %XMM15,%XMM9 |
(25) 0x40645f JB 4064db |
(25) 0x406461 VCOMISD %XMM4,%XMM15 |
(25) 0x406465 JBE 4064db |
(25) 0x406467 VDIVSD %XMM15,%XMM7,%XMM3 |
(25) 0x40646c MOV 0x30(%RDI),%RSI |
(25) 0x406470 ADD %R8,%RSI |
(25) 0x406473 VMULSD %XMM3,%XMM3,%XMM13 |
(25) 0x406477 VMULSD %XMM3,%XMM10,%XMM15 |
(25) 0x40647b VMULSD %XMM8,%XMM3,%XMM14 |
(25) 0x406480 VMULSD %XMM15,%XMM13,%XMM3 |
(25) 0x406485 VSUBSD %XMM7,%XMM3,%XMM13 |
(25) 0x406489 VFMSUB213SD -0x38(%RBP),%XMM3,%XMM13 |
(25) 0x40648f VMOVSD %XMM13,%XMM13,%XMM15 |
(25) 0x406494 VFMADD231SD %XMM6,%XMM13,%XMM5 |
(25) 0x406499 VMOVSD %XMM3,%XMM3,%XMM13 |
(25) 0x40649d VFMADD132SD %XMM11,%XMM12,%XMM13 |
(25) 0x4064a2 VFMADD213SD (%RSI),%XMM6,%XMM15 |
(25) 0x4064a7 VMULSD %XMM13,%XMM3,%XMM3 |
(25) 0x4064ac VMOVSD %XMM15,(%RSI) |
(25) 0x4064b0 MOV 0x28(%RDI),%RSI |
(25) 0x4064b4 ADD %R10,%RSI |
(25) 0x4064b7 VMULSD %XMM14,%XMM3,%XMM14 |
(25) 0x4064bc VFNMADD213SD (%RSI),%XMM14,%XMM1 |
(25) 0x4064c1 VFNMADD213SD 0x8(%RSI),%XMM14,%XMM0 |
(25) 0x4064c7 VFNMADD213SD 0x10(%RSI),%XMM2,%XMM14 |
(25) 0x4064cd VMOVSD %XMM1,(%RSI) |
(25) 0x4064d1 VMOVSD %XMM0,0x8(%RSI) |
(25) 0x4064d6 VMOVSD %XMM14,0x10(%RSI) |
(25) 0x4064db VMOVSD 0x8(%RDX),%XMM0 |
(25) 0x4064e0 VSUBSD 0x20(%RAX),%XMM0,%XMM0 |
(25) 0x4064e5 LEA 0x18(%RAX),%RSI |
(25) 0x4064e9 VMOVSD (%RDX),%XMM1 |
(25) 0x4064ed VSUBSD 0x18(%RAX),%XMM1,%XMM1 |
(25) 0x4064f2 VMOVSD 0x10(%RDX),%XMM2 |
(25) 0x4064f7 VSUBSD 0x28(%RAX),%XMM2,%XMM2 |
(25) 0x4064fc VMULSD %XMM0,%XMM0,%XMM15 |
(25) 0x406500 VFMADD231SD %XMM1,%XMM1,%XMM15 |
(25) 0x406505 VFMADD231SD %XMM2,%XMM2,%XMM15 |
(25) 0x40650a VCOMISD %XMM15,%XMM9 |
(25) 0x40650f JB 40658b |
(25) 0x406511 VCOMISD %XMM4,%XMM15 |
(25) 0x406515 JBE 40658b |
(25) 0x406517 VDIVSD %XMM15,%XMM7,%XMM3 |
(25) 0x40651c MOV 0x30(%RDI),%RAX |
(25) 0x406520 ADD %R8,%RAX |
(25) 0x406523 VMULSD %XMM3,%XMM3,%XMM13 |
(25) 0x406527 VMULSD %XMM3,%XMM10,%XMM15 |
(25) 0x40652b VMULSD %XMM8,%XMM3,%XMM14 |
(25) 0x406530 VMULSD %XMM15,%XMM13,%XMM3 |
(25) 0x406535 VSUBSD %XMM7,%XMM3,%XMM13 |
(25) 0x406539 VFMSUB213SD -0x38(%RBP),%XMM3,%XMM13 |
(25) 0x40653f VMOVSD %XMM13,%XMM13,%XMM15 |
(25) 0x406544 VFMADD231SD %XMM6,%XMM13,%XMM5 |
(25) 0x406549 VMOVSD %XMM3,%XMM3,%XMM13 |
(25) 0x40654d VFMADD132SD %XMM11,%XMM12,%XMM13 |
(25) 0x406552 VFMADD213SD (%RAX),%XMM6,%XMM15 |
(25) 0x406557 VMULSD %XMM13,%XMM3,%XMM3 |
(25) 0x40655c VMOVSD %XMM15,(%RAX) |
(25) 0x406560 MOV 0x28(%RDI),%RAX |
(25) 0x406564 ADD %R10,%RAX |
(25) 0x406567 VMULSD %XMM14,%XMM3,%XMM14 |
(25) 0x40656c VFNMADD213SD (%RAX),%XMM14,%XMM1 |
(25) 0x406571 VFNMADD213SD 0x8(%RAX),%XMM14,%XMM0 |
(25) 0x406577 VFNMADD213SD 0x10(%RAX),%XMM2,%XMM14 |
(25) 0x40657d VMOVSD %XMM1,(%RAX) |
(25) 0x406581 VMOVSD %XMM0,0x8(%RAX) |
(25) 0x406586 VMOVSD %XMM14,0x10(%RAX) |
(25) 0x40658b LEA 0x18(%RSI),%RAX |
(25) 0x40658f CMP %RAX,%RCX |
(25) 0x406592 JNE 406430 |
(24) 0x406598 ADD $0x8,%R8 |
(24) 0x40659c CMP %R8,%RBX |
(24) 0x40659f JNE 406348 |
(23) 0x4065a5 MOV -0x40(%RBP),%RDX |
(23) 0x4065a9 MOV -0x60(%RBP),%R11 |
(23) 0x4065ad ADD $0x4,%RDX |
(23) 0x4065b1 CMP %R11,%RDX |
(23) 0x4065b4 JNE 4062fb |
0x4065ba MOV -0x80(%RBP),%R13 |
0x4065be MOV -0x48(%RBP),%R14 |
0x4065c2 MOV %R9,%R12 |
0x4065c5 MOV -0x88(%RBP),%RAX |
0x4065cc MOV -0x70(%RBP),%ECX |
0x4065cf INC %RAX |
0x4065d2 ADD $0x40,%ECX |
0x4065d5 CMP %EAX,-0x6c(%RBP) |
0x4065d8 JG 406287 |
/home/eoseret/qaas_runs_CPU_9468/171-110-4860/intel/CoMD/build/CoMD/CoMD/src-openmp/ljForce.c: 175 - 216 |
-------------------------------------------------------------------------------- |
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 | 2.27 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.83 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
Bottlenecks | |
Function | ljForce._omp_fn.1 |
Source | ljForce.c:175-175,ljForce.c:178-180,ljForce.c:187-187,ljForce.c:213-213 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.83 |
CQA cycles if no scalar integer | 1.25 |
CQA cycles if FP arith vectorized | 2.83 |
CQA cycles if fully vectorized | 0.24 |
Front-end cycles | 2.83 |
DIV/SQRT cycles | 1.45 |
P0 cycles | 1.47 |
P1 cycles | 1.50 |
P2 cycles | 1.50 |
P3 cycles | 2.00 |
P4 cycles | 1.23 |
P5 cycles | 1.35 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 1.17 |
P10 cycles | 1.50 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.94 |
Stall cycles (UFS) | 0.00 |
Nb insns | 17.50 |
Nb uops | 17.00 |
Nb loads | 4.50 |
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 | 15.37 |
Bytes prefetched | 0.00 |
Bytes loaded | 26.00 |
Bytes stored | 26.00 |
Stride 0 | 1.50 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 2.50 |
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 | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 8.13 |
Vector-efficiency ratio load | 9.38 |
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 | 6.25 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.38 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.08 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
Bottlenecks | micro-operation queue, |
Function | ljForce._omp_fn.1 |
Source | ljForce.c:175-175,ljForce.c:178-180,ljForce.c:187-187,ljForce.c:213-213 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.50 |
CQA cycles if no scalar integer | 1.33 |
CQA cycles if FP arith vectorized | 4.50 |
CQA cycles if fully vectorized | 0.41 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 1.90 |
P0 cycles | 2.13 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 4.00 |
P4 cycles | 1.87 |
P5 cycles | 1.70 |
P6 cycles | 4.00 |
P7 cycles | 4.00 |
P8 cycles | 4.00 |
P9 cycles | 1.73 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.61 |
Stall cycles (UFS) | 0.00 |
Nb insns | 27.00 |
Nb uops | 27.00 |
Nb loads | 6.00 |
Nb stores | 8.00 |
Nb stack references | 10.00 |
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 | 20.44 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 52.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 4.00 |
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 | 10.00 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 10.16 |
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 | 1.17 |
Bottlenecks | micro-operation queue, |
Function | ljForce._omp_fn.1 |
Source | ljForce.c:175-175,ljForce.c:178-180,ljForce.c:187-187,ljForce.c:213-213 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.17 |
CQA cycles if no scalar integer | 1.17 |
CQA cycles if FP arith vectorized | 1.17 |
CQA cycles if fully vectorized | 0.07 |
Front-end cycles | 1.17 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
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 | 1 |
FE+BE cycles (UFS) | 1.27 |
Stall cycles (UFS) | 0.00 |
Nb insns | 8.00 |
Nb uops | 7.00 |
Nb loads | 3.00 |
Nb stores | 0.00 |
Nb stack references | 2.00 |
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 | 10.29 |
Bytes prefetched | 0.00 |
Bytes loaded | 12.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 1.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
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 | 6.25 |
Vector-efficiency ratio load | 6.25 |
Vector-efficiency ratio store | NA |
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 | 6.25 |
Path / |
Function | ljForce._omp_fn.1 |
Source file and lines | ljForce.c:175-216 |
Module | exec |
nb instructions | 17.50 |
nb uops | 17 |
loop length | 74 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0.50 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 6 |
micro-operation queue | 2.83 cycles |
front end | 2.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.45 | 1.30 | 1.50 | 1.50 | 2.00 | 1.23 | 1.35 | 2.00 | 2.00 | 2.00 | 1.17 | 1.50 |
cycles | 1.45 | 1.47 | 1.50 | 1.50 | 2.00 | 1.23 | 1.35 | 2.00 | 2.00 | 2.00 | 1.17 | 1.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.94 |
Stall cycles | 0.00 |
Front-end | 2.83 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.83 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
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 | 6% |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 12% |
load | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 8% |
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._omp_fn.1 |
Source file and lines | ljForce.c:175-216 |
Module | exec |
nb instructions | 27 |
nb uops | 27 |
loop length | 116 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.90 | 1.80 | 2.00 | 2.00 | 4.00 | 1.87 | 1.70 | 4.00 | 4.00 | 4.00 | 1.73 | 2.00 |
cycles | 1.90 | 2.13 | 2.00 | 2.00 | 4.00 | 1.87 | 1.70 | 4.00 | 4.00 | 4.00 | 1.73 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.61 |
Stall cycles | 0.00 |
Front-end | 4.50 |
Dispatch | 4.00 |
Data deps. | 1.00 |
Overall L1 | 4.50 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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) |
other | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
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 | 9% |
load | NA (no load vectorizable/vectorized instructions) |
store | 10% |
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 | 12% |
load | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 10% |
load | 12% |
store | 10% |
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 -0x68(%RBP),%R9D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R14,%RAX,4),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 4065cf <ljForce._omp_fn.1+0x40f> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x80(%R13),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %EAX,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,-0x70(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x6,%ESI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
LEA (%R8,%RCX,1),%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
MOV %R13,-0x80(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0xc97d(%RIP),%XMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R11,%RAX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD %ESI,%R9 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
MOV %R10D,-0x50(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x1(%R10),%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 |
LEA (,%R9,8),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
SUB %ESI,%R10D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %R14,-0x48(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDX,%RBX,1),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %RDI,-0x58(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x1(%R9,%R10,1),%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %R12,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R8,-0x60(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
MOV %RAX,-0x88(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %ESI,-0x64(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
Function | ljForce._omp_fn.1 |
Source file and lines | ljForce.c:175-216 |
Module | exec |
nb instructions | 8 |
nb uops | 7 |
loop length | 32 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 1.17 cycles |
front end | 1.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 1.00 | 1.00 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 1.00 |
cycles | 1.00 | 0.80 | 1.00 | 1.00 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.27 |
Stall cycles | 0.00 |
Front-end | 1.17 |
Dispatch | 1.00 |
Data deps. | 1.00 |
Overall L1 | 1.17 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 6% |
load | 6% |
store | NA (no store vectorizable/vectorized instructions) |
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 -0x68(%RBP),%R9D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R14,%RAX,4),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %R9D,%R9D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 4065cf <ljForce._omp_fn.1+0x40f> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x40,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMP %EAX,-0x6c(%RBP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JG 406287 <ljForce._omp_fn.1+0xc7> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |