Loop Id: 94 | Module: exec | Source: timestep.c:74-78 | Coverage: 0.32% |
---|
Loop Id: 94 | Module: exec | Source: timestep.c:74-78 | Coverage: 0.32% |
---|
0x40ed70 VMOVUPD (%R10,%R14,1),%XMM2 [1] |
0x40ed76 VFMADD213PD (%R9,%R14,1),%XMM1,%XMM2 [2] |
0x40ed7c VMOVUPD %XMM2,(%R9,%R14,1) [2] |
0x40ed82 VMOVSD 0x10(%R10,%R14,1),%XMM2 [1] |
0x40ed89 VFMADD213SD 0x10(%R9,%R14,1),%XMM0,%XMM2 [2] |
0x40ed90 VMOVSD %XMM2,0x10(%R9,%R14,1) [2] |
0x40ed97 ADD $0x18,%R14 |
0x40ed9b DEC %R8D |
0x40ed9e JNE 40ed70 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/timestep.c: 74 - 78 |
-------------------------------------------------------------------------------- |
74: for (int iOff=MAXATOMS*iBox,ii=0; ii<s->boxes->nAtoms[iBox]; ii++,iOff++) |
75: { |
76: s->atoms->p[iOff][0] += dt*s->atoms->f[iOff][0]; |
77: s->atoms->p[iOff][1] += dt*s->atoms->f[iOff][1]; |
78: s->atoms->p[iOff][2] += dt*s->atoms->f[iOff][2]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.11 |
CQA speedup if FP arith vectorized | 1.25 |
CQA speedup if fully vectorized | 6.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.25 |
Bottlenecks | micro-operation queue, |
Function | advanceVelocity.extracted |
Source | timestep.c:74-78 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 1.67 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.33 |
CQA cycles if fully vectorized | 0.28 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 1.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.83 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 4.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 3.60 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 43.20 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 50.00 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 18.75 |
Vector-efficiency ratio load | 18.75 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.11 |
CQA speedup if FP arith vectorized | 1.25 |
CQA speedup if fully vectorized | 6.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.25 |
Bottlenecks | micro-operation queue, |
Function | advanceVelocity.extracted |
Source | timestep.c:74-78 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | high |
Unroll/vectorization loop type | peel/tail |
Unroll factor | 1 |
CQA cycles | 1.67 |
CQA cycles if no scalar integer | 1.50 |
CQA cycles if FP arith vectorized | 1.33 |
CQA cycles if fully vectorized | 0.28 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 1.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.83 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 4.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 3.60 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 43.20 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 24.00 |
Stride 0 | 0.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 50.00 |
Vectorization ratio load | 50.00 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 18.75 |
Vector-efficiency ratio load | 18.75 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | advanceVelocity.extracted |
Source file and lines | timestep.c:74-78 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 48 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 1.00 | 1.33 | 1.33 | 1.00 | 0.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 1.33 |
cycles | 1.00 | 1.00 | 1.33 | 1.33 | 1.00 | 0.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.83 |
Stall cycles | 0.00 |
Front-end | 1.67 |
Dispatch | 1.33 |
Data deps. | 1.00 |
Overall L1 | 1.67 |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 18% |
load | 18% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R10,%R14,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD213PD (%R9,%R14,1),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM2,(%R9,%R14,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD 0x10(%R10,%R14,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD 0x10(%R9,%R14,1),%XMM0,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVSD %XMM2,0x10(%R9,%R14,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 40ed70 <advanceVelocity.extracted+0x400> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | advanceVelocity.extracted |
Source file and lines | timestep.c:74-78 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 48 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 1.00 | 1.33 | 1.33 | 1.00 | 0.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 1.33 |
cycles | 1.00 | 1.00 | 1.33 | 1.33 | 1.00 | 0.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.83 |
Stall cycles | 0.00 |
Front-end | 1.67 |
Dispatch | 1.33 |
Data deps. | 1.00 |
Overall L1 | 1.67 |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 18% |
load | 18% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R10,%R14,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD213PD (%R9,%R14,1),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM2,(%R9,%R14,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD 0x10(%R10,%R14,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD213SD 0x10(%R9,%R14,1),%XMM0,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVSD %XMM2,0x10(%R9,%R14,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x18,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 40ed70 <advanceVelocity.extracted+0x400> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |