Loop Id: 68 | Module: exec | Source: initAtoms.c:126-133 | Coverage: 0.02% |
---|
Loop Id: 68 | Module: exec | Source: initAtoms.c:126-133 | Coverage: 0.02% |
---|
0x40b720 MOVSXD (%R11,%R8,4),%R15 [3] |
0x40b724 SAL $0x4,%R15 |
0x40b728 MOVSXD 0x4(%R11,%R8,4),%RBX [3] |
0x40b72d SAL $0x4,%RBX |
0x40b731 VMOVSD 0x8(%R9,%R15,1),%XMM6 [4] |
0x40b738 VMOVDDUP 0x8(%R9,%RBX,1),%XMM7 [1] |
0x40b73f VPERMT2PD %YMM7,%YMM1,%YMM6 |
0x40b745 VFMADD213PD -0x20(%R13),%YMM4,%YMM6 [2] |
0x40b74b VMOVUPD %YMM6,-0x20(%R13) [2] |
0x40b751 VFMADD213PD (%R13),%XMM5,%XMM7 [2] |
0x40b757 VMOVUPD %XMM7,(%R13) [2] |
0x40b75d ADD $0x2,%R8 |
0x40b761 ADD $0x30,%R13 |
0x40b765 ADD $-0x2,%R12D |
0x40b769 JNE 40b720 |
/home/eoseret/qaas_runs_CPU_9468/171-110-4860/intel/CoMD/build/CoMD/CoMD/src-openmp/initAtoms.c: 126 - 133 |
-------------------------------------------------------------------------------- |
126: for (int iOff=MAXATOMS*iBox, ii=0; ii<s->boxes->nAtoms[iBox]; ++ii, ++iOff) |
127: { |
128: int iSpecies = s->atoms->iSpecies[iOff]; |
129: real_t mass = s->species[iSpecies].mass; |
130: |
131: s->atoms->p[iOff][0] += mass * vShift[0]; |
132: s->atoms->p[iOff][1] += mass * vShift[1]; |
133: s->atoms->p[iOff][2] += mass * vShift[2]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.17 |
CQA speedup if FP arith vectorized | 1.56 |
CQA speedup if fully vectorized | 4.62 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.17 |
Bottlenecks | micro-operation queue, |
Function | setVcm.extracted |
Source | initAtoms.c:126-133 |
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 | 2.33 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.51 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.50 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 1.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.58 - 2.60 |
Stall cycles (UFS) | 0.00 - 0.01 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 6.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 5.14 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 6.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 51.43 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 48.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 71.43 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 32.14 |
Vector-efficiency ratio load | 25.00 |
Vector-efficiency ratio store | 37.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 37.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.17 |
CQA speedup if FP arith vectorized | 1.56 |
CQA speedup if fully vectorized | 4.62 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.17 |
Bottlenecks | micro-operation queue, |
Function | setVcm.extracted |
Source | initAtoms.c:126-133 |
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 | 2.33 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 1.50 |
CQA cycles if fully vectorized | 0.51 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 1.50 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 1.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.58 - 2.60 |
Stall cycles (UFS) | 0.00 - 0.01 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 6.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 5.14 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 6.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 51.43 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 48.00 |
Stride 0 | 0.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 2.00 |
Vectorization ratio all | 71.43 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 32.14 |
Vector-efficiency ratio load | 25.00 |
Vector-efficiency ratio store | 37.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 37.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 50.00 |
Path / |
Function | setVcm.extracted |
Source file and lines | initAtoms.c:126-133 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 75 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 4 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.50 | 2.00 | 2.00 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 0.00 | 2.00 |
cycles | 2.00 | 1.50 | 2.00 | 2.00 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 0.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.58-2.60 |
Stall cycles | 0.00-0.01 |
Front-end | 2.33 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.33 |
all | 71% |
load | 50% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 32% |
load | 25% |
store | 37% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 37% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD (%R11,%R8,4),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SAL $0x4,%R15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
MOVSXD 0x4(%R11,%R8,4),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SAL $0x4,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
VMOVSD 0x8(%R9,%R15,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP 0x8(%R9,%RBX,1),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VPERMT2PD %YMM7,%YMM1,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VFMADD213PD -0x20(%R13),%YMM4,%YMM6 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %YMM6,-0x20(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VFMADD213PD (%R13),%XMM5,%XMM7 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM7,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x2,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x30,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $-0x2,%R12D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 40b720 <setVcm.extracted+0x1a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | setVcm.extracted |
Source file and lines | initAtoms.c:126-133 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 75 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 4 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 1.50 | 2.00 | 2.00 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 0.00 | 2.00 |
cycles | 2.00 | 1.50 | 2.00 | 2.00 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 0.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.58-2.60 |
Stall cycles | 0.00-0.01 |
Front-end | 2.33 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.33 |
all | 71% |
load | 50% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 32% |
load | 25% |
store | 37% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 37% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD (%R11,%R8,4),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SAL $0x4,%R15 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
MOVSXD 0x4(%R11,%R8,4),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SAL $0x4,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
VMOVSD 0x8(%R9,%R15,1),%XMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP 0x8(%R9,%RBX,1),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VPERMT2PD %YMM7,%YMM1,%YMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VFMADD213PD -0x20(%R13),%YMM4,%YMM6 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %YMM6,-0x20(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VFMADD213PD (%R13),%XMM5,%XMM7 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM7,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x2,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x30,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $-0x2,%R12D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 40b720 <setVcm.extracted+0x1a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |