Loop Id: 84 | Module: exec | Source: ljForce.c:178-216 [...] | Coverage: 0.26% |
---|
Loop Id: 84 | Module: exec | Source: ljForce.c:178-216 [...] | Coverage: 0.26% |
---|
0x40d5c0 INC %R10 |
0x40d5c3 CMP $0x1b,%R10 |
0x40d5c7 MOV -0x80(%RBP),%RDX |
0x40d5cb JE 40d540 |
0x40d5d1 MOV (%RDX,%R10,4),%EAX |
0x40d5d5 TEST %EAX,%EAX |
0x40d5d7 JS 40d7fd |
0x40d5dd MOV -0x60(%RBP),%RCX |
0x40d5e1 MOVSXD (%RCX,%RAX,4),%RDX |
0x40d5e5 TEST %RDX,%RDX |
0x40d5e8 JLE 40d5c0 |
0x40d5ea SAL $0x6,%EAX |
0x40d5ed MOV -0x58(%RBP),%RCX |
0x40d5f1 MOV 0x20(%RCX),%R14 |
0x40d5f5 MOV 0x18(%R14),%R12 |
0x40d5f9 CLTQ |
0x40d5fb ADD %RAX,%RDX |
0x40d5fe LEA 0x1(%RAX),%RCX |
0x40d602 CMP %RCX,%RDX |
0x40d605 CMOVLE %RCX,%RDX |
0x40d609 SUB %RAX,%RDX |
0x40d60c LEA (%RAX,%RAX,2),%RAX |
0x40d610 LEA 0x10(%R12,%RAX,8),%R15 |
0x40d615 XOR %EBX,%EBX |
0x40d617 JMP 40d64d |
(85) 0x40d640 CMP %R9,%RBX |
(85) 0x40d643 LEA 0x1(%RBX),%RBX |
(85) 0x40d647 JE 40d5c0 |
(85) 0x40d64d LEA (%RBX,%RDI,1),%RSI |
(85) 0x40d651 LEA (%RSI,%RSI,2),%RCX |
(85) 0x40d655 LEA (%R12,%RCX,8),%RAX |
(85) 0x40d659 MOV %R15,%R13 |
(85) 0x40d65c MOV %RDX,%R11 |
(85) 0x40d65f JMP 40d689 |
(86) 0x40d680 ADD $0x18,%R13 |
(86) 0x40d684 DEC %R11 |
(86) 0x40d687 JE 40d640 |
(86) 0x40d689 VMOVUPD (%RAX),%XMM11 |
(86) 0x40d68d VSUBPD -0x10(%R13),%XMM11,%XMM11 |
(86) 0x40d693 VMULPD %XMM11,%XMM11,%XMM12 |
(86) 0x40d698 VSHUFPD $0x1,%XMM12,%XMM12,%XMM13 |
(86) 0x40d69e VADDSD %XMM12,%XMM13,%XMM13 |
(86) 0x40d6a3 VMOVSD 0x10(%RAX),%XMM12 |
(86) 0x40d6a8 VSUBSD (%R13),%XMM12,%XMM12 |
(86) 0x40d6ae VFMADD231SD %XMM12,%XMM12,%XMM13 |
(86) 0x40d6b3 VUCOMISD %XMM2,%XMM13 |
(86) 0x40d6b7 JA 40d680 |
(86) 0x40d6b9 VUCOMISD %XMM4,%XMM13 |
(86) 0x40d6bd JBE 40d680 |
(86) 0x40d6bf VDIVSD %XMM13,%XMM6,%XMM13 |
(86) 0x40d6c4 VMULSD %XMM13,%XMM13,%XMM14 |
(86) 0x40d6c9 VMULSD %XMM1,%XMM13,%XMM15 |
(86) 0x40d6cd VMULSD %XMM15,%XMM14,%XMM14 |
(86) 0x40d6d2 VADDSD %XMM7,%XMM14,%XMM15 |
(86) 0x40d6d6 VFNMADD213SD %XMM0,%XMM14,%XMM15 |
(86) 0x40d6db VMULSD %XMM8,%XMM15,%XMM15 |
(86) 0x40d6e0 MOV 0x30(%R14),%R8 |
(86) 0x40d6e4 VADDSD (%R8,%RSI,8),%XMM15,%XMM16 |
(86) 0x40d6eb VMOVSD %XMM16,(%R8,%RSI,8) |
(86) 0x40d6f2 VMOVAPD %XMM9,%XMM16 |
(86) 0x40d6f8 VFMADD213SD %XMM10,%XMM14,%XMM16 |
(86) 0x40d6fe VMULSD %XMM3,%XMM13,%XMM13 |
(86) 0x40d702 VMULSD %XMM14,%XMM16,%XMM14 |
(86) 0x40d708 VMULSD %XMM13,%XMM14,%XMM13 |
(86) 0x40d70d MOV 0x28(%R14),%R8 |
(86) 0x40d711 VMOVDDUP %XMM13,%XMM14 |
(86) 0x40d716 VFMADD213PD (%R8,%RCX,8),%XMM14,%XMM11 |
(86) 0x40d71c VMOVUPD %XMM11,(%R8,%RCX,8) |
(86) 0x40d722 VFMADD213SD 0x10(%R8,%RCX,8),%XMM13,%XMM12 |
(86) 0x40d729 VMOVSD %XMM12,0x10(%R8,%RCX,8) |
(86) 0x40d730 VADDSD %XMM5,%XMM15,%XMM5 |
(86) 0x40d734 JMP 40d680 |
/home/eoseret/qaas_runs_CPU_9468/171-148-3214/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 | 13.89 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.48 |
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 | 3.54 |
CQA cycles if no scalar integer | 3.54 |
CQA cycles if FP arith vectorized | 3.54 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 3.54 |
DIV/SQRT cycles | 2.40 |
P0 cycles | 2.23 |
P1 cycles | 2.08 |
P2 cycles | 2.08 |
P3 cycles | 0.00 |
P4 cycles | 2.10 |
P5 cycles | 2.25 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.10 |
P10 cycles | 2.08 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.75 |
Stall cycles (UFS) | 0.00 |
Nb insns | 21.50 |
Nb uops | 21.25 |
Nb loads | 6.25 |
Nb stores | 0.00 |
Nb stack references | 2.75 |
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 | 12.24 |
Bytes prefetched | 0.00 |
Bytes loaded | 42.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.75 |
Stride unknown | 2.50 |
Stride indirect | 0.75 |
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 | 10.16 |
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 | 10.16 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.67 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
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 | 1.67 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 1.67 |
CQA cycles if fully vectorized | 0.11 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.80 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
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 | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 1.89 |
Stall cycles (UFS) | 0.02 |
Nb insns | 11.00 |
Nb uops | 10.00 |
Nb loads | 4.00 |
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 | 14.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 24.00 |
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 | 1.54 |
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 | 2.70 |
P0 cycles | 2.70 |
P1 cycles | 2.33 |
P2 cycles | 2.33 |
P3 cycles | 0.00 |
P4 cycles | 2.60 |
P5 cycles | 2.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 2.60 |
P10 cycles | 2.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 4.37 |
Stall cycles (UFS) | 0.00 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 7.00 |
Nb stores | 0.00 |
Nb stack references | 3.00 |
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 | 11.52 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 3.00 |
Stride indirect | 1.00 |
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 | 10.42 |
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 | 10.42 |
Path / |
Function | ljForce.extracted |
Source file and lines | ljForce.c:178-216 |
Module | exec |
nb instructions | 21.50 |
nb uops | 21.25 |
loop length | 77.25 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2.75 |
micro-operation queue | 3.54 cycles |
front end | 3.54 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.40 | 2.15 | 2.08 | 2.08 | 0.00 | 2.10 | 2.25 | 0.00 | 0.00 | 0.00 | 2.10 | 2.08 |
cycles | 2.40 | 2.23 | 2.08 | 2.08 | 0.00 | 2.10 | 2.25 | 0.00 | 0.00 | 0.00 | 2.10 | 2.08 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.75 |
Stall cycles | 0.00 |
LM full (events) | 0.02 |
Front-end | 3.54 |
Dispatch | 2.40 |
Data deps. | 0.00 |
Overall L1 | 3.54 |
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 | 10% |
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 | 10% |
Function | ljForce.extracted |
Source file and lines | ljForce.c:178-216 |
Module | exec |
nb instructions | 11 |
nb uops | 10 |
loop length | 42 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.80 | 1.33 | 1.33 | 0.00 | 0.60 | 1.50 | 0.00 | 0.00 | 0.00 | 0.60 | 1.33 |
cycles | 1.50 | 0.80 | 1.33 | 1.33 | 0.00 | 0.60 | 1.50 | 0.00 | 0.00 | 0.00 | 0.60 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 1.89 |
Stall cycles | 0.02 |
LM full (events) | 0.08 |
Front-end | 1.67 |
Dispatch | 1.50 |
Data deps. | 0.00 |
Overall L1 | 1.67 |
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 %R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP $0x1b,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE 40d540 <ljForce.extracted+0x1a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%RDX,%R10,4),%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 40d7fd <ljForce.extracted+0x45d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 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 |
MOVSXD (%RCX,%RAX,4),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RDX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 40d5c0 <ljForce.extracted+0x220> | 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 | 89 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 4.17 cycles |
front end | 4.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.70 | 2.60 | 2.33 | 2.33 | 0.00 | 2.60 | 2.50 | 0.00 | 0.00 | 0.00 | 2.60 | 2.33 |
cycles | 2.70 | 2.70 | 2.33 | 2.33 | 0.00 | 2.60 | 2.50 | 0.00 | 0.00 | 0.00 | 2.60 | 2.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 4.37 |
Stall cycles | 0.00 |
Front-end | 4.17 |
Dispatch | 2.70 |
Data deps. | 0.00 |
Overall L1 | 4.17 |
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 | 10% |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP $0x1b,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JE 40d540 <ljForce.extracted+0x1a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%RDX,%R10,4),%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 40d7fd <ljForce.extracted+0x45d> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 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 |
MOVSXD (%RCX,%RAX,4),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
TEST %RDX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
JLE 40d5c0 <ljForce.extracted+0x220> | 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 -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x20(%RCX),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x18(%R14),%R12 | 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 |
ADD %RAX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA 0x1(%RAX),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RCX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMOVLE %RCX,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
SUB %RAX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
LEA (%RAX,%RAX,2),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA 0x10(%R12,%RAX,8),%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 40d64d <ljForce.extracted+0x2ad> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |