Loop Id: 45 | Module: exec | Source: haloExchange.c:380-389 | Coverage: 0.02% |
---|
Loop Id: 45 | Module: exec | Source: haloExchange.c:380-389 | Coverage: 0.02% |
---|
0x406ba0 MOV (%R10,%R15,4),%ECX [3] |
0x406ba4 MOV %ECX,(%R13) [5] |
0x406ba8 MOV (%R11,%R15,4),%ECX [1] |
0x406bac MOV %ECX,0x4(%R13) [5] |
0x406bb0 VADDPD -0x10(%RBX,%RDX,4),%XMM0,%XMM2 [4] |
0x406bb6 VMOVUPD %XMM2,0x8(%R13) [5] |
0x406bbc VADDSD (%RBX,%RDX,4),%XMM1,%XMM2 [4] |
0x406bc1 VMOVSD %XMM2,0x18(%R13) [5] |
0x406bc7 VMOVUPS -0x10(%R14,%RDX,4),%XMM2 [2] |
0x406bce VMOVUPS %XMM2,0x20(%R13) [5] |
0x406bd4 VMOVSD (%R14,%RDX,4),%XMM2 [2] |
0x406bda VMOVSD %XMM2,0x30(%R13) [5] |
0x406be0 INC %R15 |
0x406be3 ADD $0x38,%R13 |
0x406be7 INC %EDI |
0x406be9 ADD $0x6,%RDX |
0x406bed CMP %R12,%R15 |
0x406bf0 JL 406ba0 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c: 380 - 389 |
-------------------------------------------------------------------------------- |
380: for (int ii=iOff; ii<iOff+s->boxes->nAtoms[iBox]; ++ii) |
381: { |
382: buf[nBuf].gid = s->atoms->gid[ii]; |
383: buf[nBuf].type = s->atoms->iSpecies[ii]; |
384: buf[nBuf].rx = s->atoms->r[ii][0] + shift[0]; |
385: buf[nBuf].ry = s->atoms->r[ii][1] + shift[1]; |
386: buf[nBuf].rz = s->atoms->r[ii][2] + shift[2]; |
387: buf[nBuf].px = s->atoms->p[ii][0]; |
388: buf[nBuf].py = s->atoms->p[ii][1]; |
389: buf[nBuf].pz = s->atoms->p[ii][2]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.58 |
CQA speedup if FP arith vectorized | 1.06 |
CQA speedup if fully vectorized | 7.24 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.06 |
Bottlenecks | micro-operation queue, |
Function | loadAtomsBuffer |
Source | haloExchange.c:380-389 |
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 | 3.17 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 3.00 |
CQA cycles if fully vectorized | 0.44 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 0.70 |
P0 cycles | 1.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 3.00 |
P4 cycles | 1.00 |
P5 cycles | 0.70 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 0.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 18.00 |
Nb uops | 17.00 |
Nb loads | 6.00 |
Nb stores | 6.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.95 |
Nb FLOP add-sub | 3.00 |
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 | 35.37 |
Bytes prefetched | 0.00 |
Bytes loaded | 56.00 |
Bytes stored | 56.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 3.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 30.77 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 33.33 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 33.33 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 13.94 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 14.58 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 14.58 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.58 |
CQA speedup if FP arith vectorized | 1.06 |
CQA speedup if fully vectorized | 7.24 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.06 |
Bottlenecks | micro-operation queue, |
Function | loadAtomsBuffer |
Source | haloExchange.c:380-389 |
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 | 3.17 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 3.00 |
CQA cycles if fully vectorized | 0.44 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 0.70 |
P0 cycles | 1.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 3.00 |
P4 cycles | 1.00 |
P5 cycles | 0.70 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 0.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 18.00 |
Nb uops | 17.00 |
Nb loads | 6.00 |
Nb stores | 6.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.95 |
Nb FLOP add-sub | 3.00 |
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 | 35.37 |
Bytes prefetched | 0.00 |
Bytes loaded | 56.00 |
Bytes stored | 56.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 3.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 30.77 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 33.33 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 33.33 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 13.94 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 14.58 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 14.58 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | loadAtomsBuffer |
Source file and lines | haloExchange.c:380-389 |
Module | exec |
nb instructions | 18 |
nb uops | 17 |
loop length | 82 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.70 | 1.00 | 2.00 | 2.00 | 3.00 | 1.00 | 0.70 | 3.00 | 3.00 | 3.00 | 0.60 | 2.00 |
cycles | 0.70 | 1.00 | 2.00 | 2.00 | 3.00 | 1.00 | 0.70 | 3.00 | 3.00 | 3.00 | 0.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.31 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 3.00 |
Data deps. | 1.00 |
Overall L1 | 3.17 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 30% |
load | 33% |
store | 33% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 6% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma 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 | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 13% |
load | 14% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 14% |
fma | NA (no fma vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R10,%R15,4),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%R11,%R15,4),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,0x4(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VADDPD -0x10(%RBX,%RDX,4),%XMM0,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %XMM2,0x8(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VADDSD (%RBX,%RDX,4),%XMM1,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVSD %XMM2,0x18(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS -0x10(%R14,%RDX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS %XMM2,0x20(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD (%R14,%RDX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM2,0x30(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x38,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x6,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R12,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 406ba0 <loadAtomsBuffer+0xc0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | loadAtomsBuffer |
Source file and lines | haloExchange.c:380-389 |
Module | exec |
nb instructions | 18 |
nb uops | 17 |
loop length | 82 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.70 | 1.00 | 2.00 | 2.00 | 3.00 | 1.00 | 0.70 | 3.00 | 3.00 | 3.00 | 0.60 | 2.00 |
cycles | 0.70 | 1.00 | 2.00 | 2.00 | 3.00 | 1.00 | 0.70 | 3.00 | 3.00 | 3.00 | 0.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.31 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 3.00 |
Data deps. | 1.00 |
Overall L1 | 3.17 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 30% |
load | 33% |
store | 33% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 6% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma 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 | 18% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 13% |
load | 14% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 14% |
fma | NA (no fma vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R10,%R15,4),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%R11,%R15,4),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,0x4(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VADDPD -0x10(%RBX,%RDX,4),%XMM0,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD %XMM2,0x8(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VADDSD (%RBX,%RDX,4),%XMM1,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVSD %XMM2,0x18(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS -0x10(%R14,%RDX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS %XMM2,0x20(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD (%R14,%RDX,4),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD %XMM2,0x30(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x38,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD $0x6,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R12,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 406ba0 <loadAtomsBuffer+0xc0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |