Loop Id: 100 | Module: exec | Source: timestep.c:110-116 | Coverage: 0.01% |
---|
Loop Id: 100 | Module: exec | Source: timestep.c:110-116 | Coverage: 0.01% |
---|
0x410e20 MOVSXD (%R10,%RAX,4),%RCX [2] |
0x410e24 VMOVSD -0x10(%RDX),%XMM3 [3] |
0x410e29 VMOVSD -0x8(%RDX),%XMM4 [3] |
0x410e2e VMULSD %XMM3,%XMM3,%XMM3 |
0x410e32 VFMADD231SD %XMM4,%XMM4,%XMM3 |
0x410e37 VMOVSD (%RDX),%XMM4 [3] |
0x410e3b VFMADD213SD %XMM3,%XMM4,%XMM4 |
0x410e40 VMULSD %XMM1,%XMM4,%XMM3 |
0x410e44 SAL $0x4,%RCX |
0x410e48 VDIVSD 0x8(%R9,%RCX,1),%XMM3,%XMM3 [1] |
0x410e4f VADDSD %XMM0,%XMM3,%XMM0 |
0x410e53 INC %RAX |
0x410e56 ADD $0x18,%RDX |
0x410e5a CMP %EAX,%R8D |
0x410e5d JNE 410e20 |
/scratch_na/users/xoserete/qaas_runs/171-172-2581/intel/CoMD/build/CoMD/CoMD/src-openmp/timestep.c: 110 - 116 |
-------------------------------------------------------------------------------- |
110: for (int iOff=MAXATOMS*iBox,ii=0; ii<s->boxes->nAtoms[iBox]; ii++,iOff++) |
111: { |
112: int iSpecies = s->atoms->iSpecies[iOff]; |
113: real_t invMass = 0.5/s->species[iSpecies].mass; |
114: kenergy += ( s->atoms->p[iOff][0] * s->atoms->p[iOff][0] + |
115: s->atoms->p[iOff][1] * s->atoms->p[iOff][1] + |
116: s->atoms->p[iOff][2] * s->atoms->p[iOff][2] )*invMass; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 2.00 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | P0, |
Function | kineticEnergy.extracted |
Source | timestep.c:110-116 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 2.00 |
Front-end cycles | 2.50 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.67 |
P11 cycles | 4.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.38 - 4.40 |
Stall cycles (UFS) | 1.03 - 1.05 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 1.00 |
Nb FLOP mul | 2.00 |
Nb FLOP fma | 2.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 36.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 2.00 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | P0, |
Function | kineticEnergy.extracted |
Source | timestep.c:110-116 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 2.00 |
Front-end cycles | 2.50 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.67 |
P11 cycles | 4.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.38 - 4.40 |
Stall cycles (UFS) | 1.03 - 1.05 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 1.00 |
Nb FLOP mul | 2.00 |
Nb FLOP fma | 2.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 36.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | NA |
Path / |
Function | kineticEnergy.extracted |
Source file and lines | timestep.c:110-116 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 63 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 0.50 |
micro-operation queue | 2.50 cycles |
front end | 2.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 1.67 | 1.67 | 0.00 | 1.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.67 |
cycles | 2.50 | 2.50 | 1.67 | 1.67 | 0.00 | 1.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.67 |
Cycles executing div or sqrt instructions | 4.00 |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.38-4.40 |
Stall cycles | 1.03-1.05 |
ROB full (events) | 1.38-1.41 |
Front-end | 2.50 |
Dispatch | 2.50 |
DIV/SQRT | 4.00 |
Data deps. | 3.00 |
Overall L1 | 4.00 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | 0% |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | 12% |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD (%R10,%RAX,4),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD -0x10(%RDX),%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD -0x8(%RDX),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RDX),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD %XMM3,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
SAL $0x4,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
VDIVSD 0x8(%R9,%RCX,1),%XMM3,%XMM3 | 1 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 13-15 | 4 |
VADDSD %XMM0,%XMM3,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x18,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %EAX,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 410e20 <kineticEnergy.extracted+0x2b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | kineticEnergy.extracted |
Source file and lines | timestep.c:110-116 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 63 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
ADD-SUB / MUL ratio | 0.50 |
micro-operation queue | 2.50 cycles |
front end | 2.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 1.67 | 1.67 | 0.00 | 1.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.67 |
cycles | 2.50 | 2.50 | 1.67 | 1.67 | 0.00 | 1.00 | 2.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.67 |
Cycles executing div or sqrt instructions | 4.00 |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.38-4.40 |
Stall cycles | 1.03-1.05 |
ROB full (events) | 1.38-1.41 |
Front-end | 2.50 |
Dispatch | 2.50 |
DIV/SQRT | 4.00 |
Data deps. | 3.00 |
Overall L1 | 4.00 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | 0% |
other | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | 12% |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD (%R10,%RAX,4),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD -0x10(%RDX),%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD -0x8(%RDX),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMULSD %XMM3,%XMM3,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD231SD %XMM4,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD (%RDX),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD %XMM3,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULSD %XMM1,%XMM4,%XMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
SAL $0x4,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
VDIVSD 0x8(%R9,%RCX,1),%XMM3,%XMM3 | 1 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 13-15 | 4 |
VADDSD %XMM0,%XMM3,%XMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x18,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %EAX,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 410e20 <kineticEnergy.extracted+0x2b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |