Loop Id: 58 | Module: exec | Source: haloExchange.c:621-629 | Coverage: 2.85% |
---|
Loop Id: 58 | Module: exec | Source: haloExchange.c:621-629 | Coverage: 2.85% |
---|
0x40a7b0 MOV (%R8,%RDX,4),%EDI [4] |
0x40a7b4 MOV %EDI,(%RCX) [5] |
0x40a7b6 MOV (%R9,%RDX,4),%EDI [1] |
0x40a7ba MOV %EDI,0x4(%RCX) [5] |
0x40a7bd VMOVUPS (%R12,%RAX,1),%XMM0 [2] |
0x40a7c3 VBROADCASTSD 0x10(%R12,%RAX,1),%YMM1 [2] |
0x40a7ca VBLENDPS $0x30,%YMM1,%YMM0,%YMM0 |
0x40a7d0 VBROADCASTSD (%R13,%RAX,1),%YMM1 [3] |
0x40a7d7 VBLENDPS $-0x40,%YMM1,%YMM0,%YMM0 |
0x40a7dd VMOVUPS %YMM0,0x8(%RCX) [5] |
0x40a7e2 VMOVUPS 0x8(%R13,%RAX,1),%XMM0 [3] |
0x40a7e9 VMOVUPS %XMM0,0x28(%RCX) [5] |
0x40a7ee INC %RDX |
0x40a7f1 ADD $0x18,%RAX |
0x40a7f5 ADD $0x38,%RCX |
0x40a7f9 CMP %R15,%RDX |
0x40a7fc JL 40a7b0 |
/scratch_na/users/xoserete/qaas_runs/171-172-4338/intel/CoMD/build/CoMD/CoMD/src-openmp/haloExchange.c: 621 - 629 |
-------------------------------------------------------------------------------- |
621: for (int ii=begin, iTmp=0; ii<end; ++ii, ++iTmp) |
622: { |
623: tmp[iTmp].gid = atoms->gid[ii]; |
624: tmp[iTmp].type = atoms->iSpecies[ii]; |
625: tmp[iTmp].rx = atoms->r[ii][0]; |
626: tmp[iTmp].ry = atoms->r[ii][1]; |
627: tmp[iTmp].rz = atoms->r[ii][2]; |
628: tmp[iTmp].px = atoms->p[ii][0]; |
629: tmp[iTmp].py = atoms->p[ii][1]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.60 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 5.55 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | micro-operation queue, |
Function | sortAtomsInCell |
Source | haloExchange.c:621-629 |
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 | 2.67 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.48 |
Front-end cycles | 2.67 |
DIV/SQRT cycles | 0.83 |
P0 cycles | 1.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 2.00 |
P4 cycles | 0.67 |
P5 cycles | 0.50 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.79 |
Stall cycles (UFS) | 0.00 |
Nb insns | 17.00 |
Nb uops | 16.00 |
Nb loads | 6.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
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 | 42.00 |
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 | 50.00 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 22.92 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 21.88 |
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 | 31.25 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.60 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 5.55 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | micro-operation queue, |
Function | sortAtomsInCell |
Source | haloExchange.c:621-629 |
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 | 2.67 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 0.48 |
Front-end cycles | 2.67 |
DIV/SQRT cycles | 0.83 |
P0 cycles | 1.00 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 2.00 |
P4 cycles | 0.67 |
P5 cycles | 0.50 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.79 |
Stall cycles (UFS) | 0.00 |
Nb insns | 17.00 |
Nb uops | 16.00 |
Nb loads | 6.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
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 | 42.00 |
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 | 50.00 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 22.92 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 21.88 |
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 | 31.25 |
Path / |
Function | sortAtomsInCell |
Source file and lines | haloExchange.c:621-629 |
Module | exec |
nb instructions | 17 |
nb uops | 16 |
loop length | 78 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.67 cycles |
front end | 2.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.83 | 1.00 | 2.00 | 2.00 | 2.00 | 0.67 | 0.50 | 2.00 | 2.00 | 2.00 | 0.00 | 2.00 |
cycles | 0.83 | 1.00 | 2.00 | 2.00 | 2.00 | 0.67 | 0.50 | 2.00 | 2.00 | 2.00 | 0.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.79 |
Stall cycles | 0.00 |
Front-end | 2.67 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.67 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 75% |
load | 50% |
store | 100% |
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 | 50% |
all | 50% |
load | 33% |
store | 50% |
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 | 50% |
all | 6% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 31% |
load | 18% |
store | 37% |
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 | 31% |
all | 22% |
load | 14% |
store | 21% |
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 | 31% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R8,%RDX,4),%EDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %EDI,(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%R9,%RDX,4),%EDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %EDI,0x4(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS (%R12,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VBROADCASTSD 0x10(%R12,%RAX,1),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.33 |
VBLENDPS $0x30,%YMM1,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VBROADCASTSD (%R13,%RAX,1),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.33 |
VBLENDPS $-0x40,%YMM1,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVUPS %YMM0,0x8(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPS 0x8(%R13,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS %XMM0,0x28(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x18,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x38,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R15,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 40a7b0 <sortAtomsInCell+0x70> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | sortAtomsInCell |
Source file and lines | haloExchange.c:621-629 |
Module | exec |
nb instructions | 17 |
nb uops | 16 |
loop length | 78 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.67 cycles |
front end | 2.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.83 | 1.00 | 2.00 | 2.00 | 2.00 | 0.67 | 0.50 | 2.00 | 2.00 | 2.00 | 0.00 | 2.00 |
cycles | 0.83 | 1.00 | 2.00 | 2.00 | 2.00 | 0.67 | 0.50 | 2.00 | 2.00 | 2.00 | 0.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.79 |
Stall cycles | 0.00 |
Front-end | 2.67 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.67 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 75% |
load | 50% |
store | 100% |
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 | 50% |
all | 50% |
load | 33% |
store | 50% |
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 | 50% |
all | 6% |
load | 6% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 31% |
load | 18% |
store | 37% |
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 | 31% |
all | 22% |
load | 14% |
store | 21% |
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 | 31% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R8,%RDX,4),%EDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %EDI,(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV (%R9,%RDX,4),%EDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %EDI,0x4(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVUPS (%R12,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VBROADCASTSD 0x10(%R12,%RAX,1),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.33 |
VBLENDPS $0x30,%YMM1,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VBROADCASTSD (%R13,%RAX,1),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.33 |
VBLENDPS $-0x40,%YMM1,%YMM0,%YMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVUPS %YMM0,0x8(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPS 0x8(%R13,%RAX,1),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPS %XMM0,0x28(%RCX) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x18,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x38,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R15,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 40a7b0 <sortAtomsInCell+0x70> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |