OV - exec - Loop 1983

	Loop Id: 1983	Module: exec	Source: SoaDistanceTableAAOMPTarget.h:440-442 [...]	Coverage: 1.36%

0x4c23a0 MOV	(%RAX,%R8,8),%RBX    [4]

0x4c23a4 MOVSD	(%R9,%R11,8),%XMM1    [3]

0x4c23aa MOVSD	%XMM1,(%RBX,%R13,8)    [8]

0x4c23b0 MOVSD	(%R10,%R11,8),%XMM1    [7]

0x4c23b6 XORPS	%XMM0,%XMM1

0x4c23b9 MOVSD	(%RDI,%R11,8),%XMM2    [6]

0x4c23bf XORPS	%XMM0,%XMM2

0x4c23c2 MOVSD	(%RSI,%R11,8),%XMM3    [5]

0x4c23c8 MOV	-0x10(%RCX,%R8,8),%RBX    [9]

0x4c23cd MOV	(%RCX,%R8,8),%R14    [9]

0x4c23d1 MOVLPS	%XMM1,(%R14,%R13,8)    [10]

0x4c23d6 LEA	(%RBX,%R13,1),%R15

0x4c23da MOVLPS	%XMM2,(%R14,%R15,8)    [2]

0x4c23df XORPS	%XMM0,%XMM3

0x4c23e2 LEA	(,%RBX,2),%RBX

0x4c23ea ADD	%R13,%RBX

0x4c23ed MOVLPS	%XMM3,(%R14,%RBX,8)    [1]

0x4c23f2 INC	%R11

0x4c23f5 ADD	$0x5,%R8

0x4c23f9 CMP	%R11,%RDX

0x4c23fc JNE	4c23a0

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 244 - 263

--------------------------------------------------------------------------------

244:         *(_base + M * i) = rhs[i];

[...]

263:   inline Accessor operator()(size_t i) { return Accessor(myData + i, nGhosts); }

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 182 - 182

--------------------------------------------------------------------------------

182:       inverse[d] = -X[d];

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 223

--------------------------------------------------------------------------------

223:     return X[i];

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h: 440 - 442

--------------------------------------------------------------------------------

440:     for (size_t i = iat + 1; i < num_targets_; ++i)

441:     {

442:       distances_[i][iat]     = temp_r_[i];

Path /

Metric	Value
CQA speedup if no scalar integer	1.37
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.89
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	P5, P6, P7,
Function	_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi
Source	VectorSoAContainer.h:244-244,VectorSoAContainer.h:263-263,TinyVector.h:182-182,OhmmsVector.h:223-223,SoaDistanceTableAAOMPTarget.h:440-442
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	3.67
CQA cycles if no scalar integer	2.67
CQA cycles if FP arith vectorized	3.67
CQA cycles if fully vectorized	0.75
Front-end cycles	3.33
DIV/SQRT cycles	1.50
P0 cycles	1.50
P1 cycles	1.25
P2 cycles	1.25
P3 cycles	0.50
P4 cycles	3.67
P5 cycles	3.67
P6 cycles	3.67
P7 cycles	0.75
P8 cycles	0.75
P9 cycles	0.75
P10 cycles	0.75
P11 cycles	2.00
P12 cycles	2.00
P13 cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	21.00
Nb uops	20.00
Nb loads	7.00
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	24.00
Bytes prefetched	0.00
Bytes loaded	56.00
Bytes stored	32.00
Stride 0	0.00
Stride 1	4.00
Stride n	2.00
Stride unknown	3.00
Stride indirect	1.00
Vectorization ratio all	54.55
Vectorization ratio load	0.00
Vectorization ratio store	75.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	100.00
Vector-efficiency ratio all	15.91
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	25.00

Metric	Value
CQA speedup if no scalar integer	1.37
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.89
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.10
Bottlenecks	P5, P6, P7,
Function	_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi
Source	VectorSoAContainer.h:244-244,VectorSoAContainer.h:263-263,TinyVector.h:182-182,OhmmsVector.h:223-223,SoaDistanceTableAAOMPTarget.h:440-442
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	3.67
CQA cycles if no scalar integer	2.67
CQA cycles if FP arith vectorized	3.67
CQA cycles if fully vectorized	0.75
Front-end cycles	3.33
DIV/SQRT cycles	1.50
P0 cycles	1.50
P1 cycles	1.25
P2 cycles	1.25
P3 cycles	0.50
P4 cycles	3.67
P5 cycles	3.67
P6 cycles	3.67
P7 cycles	0.75
P8 cycles	0.75
P9 cycles	0.75
P10 cycles	0.75
P11 cycles	2.00
P12 cycles	2.00
P13 cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	21.00
Nb uops	20.00
Nb loads	7.00
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	24.00
Bytes prefetched	0.00
Bytes loaded	56.00
Bytes stored	32.00
Stride 0	0.00
Stride 1	4.00
Stride n	2.00
Stride unknown	3.00
Stride indirect	1.00
Vectorization ratio all	54.55
Vectorization ratio load	0.00
Vectorization ratio store	75.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	100.00
Vector-efficiency ratio all	15.91
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	25.00

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi
Source file and lines	SoaDistanceTableAAOMPTarget.h:440-442
Module	exec

The loop is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:244,263
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:182
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:440-442

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 3.67 to 2.67 cycles (1.38x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your loop is partially vectorized. Only 15% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your loop, you can lower the cost of an iteration from 3.67 to 0.75 cycles (4.89x speedup).

Details

54% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
75% of SSE/AVX stores are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 3.67 to 3.33 cycles (1.10x speedup).

Workaround

Read less array elements
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop

No data for this section

Slow data structures access

Detected data structures (typically arrays) that cannot be efficiently read/written

Details

Constant unknown stride: 3 occurrence(s)
Constant non-unit stride: 2 occurrence(s)
Irregular (variable stride) or indirect: 1 occurrence(s)

Non-unit stride (uncontiguous) accesses are not efficiently using data caches

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)
Try to remove indirect accesses. If applicable, precompute elements out of the innermost loop.

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 56 bytes. The binary loop is storing 32 bytes.

Unroll opportunity

Loop is data access bound.

Workaround

Unroll your loop if trip count is significantly higher than target unroll factor and if some data references are common to consecutive iterations. This can be done manually. Or with the unroll (resp. unroll_and_jam) directive on top of the inner (resp. surrounding) loop. You can enforce an unroll factor: #pragma unroll_and_jam N, unroll_and_jam(N), unroll N or unroll(N)

General properties

nb instructions	21
nb uops	20
loop length	94
used x86 registers	13
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	3.33 cycles
front end	3.33 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	1.50	1.50	1.25	1.25	0.50	3.67	3.67	3.67	0.75	0.75	0.75	0.75	2.00	2.00
cycles	1.50	1.50	1.25	1.25	0.50	3.67	3.67	3.67	0.75	0.75	0.75	0.75	2.00	2.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	3.33
Dispatch	3.67
Data deps.	1.00
Overall L1	3.67

Vectorization ratios

all	54%
load	0%
store	75%
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	100%

Vector efficiency ratios

all	15%
load	12%
store	12%
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	25%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 3.67 cycles. At this rate:

15% of peak load performance is reached (15.27 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
13% of peak store performance is reached (8.73 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 4c23a0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
MOV (%RAX,%R8,8),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD (%R9,%R11,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOVSD %XMM1,(%RBX,%R13,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD (%R10,%R11,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
XORPS %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOVSD (%RDI,%R11,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
XORPS %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOVSD (%RSI,%R11,8),%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOV -0x10(%RCX,%R8,8),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV (%RCX,%R8,8),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVLPS %XMM1,(%R14,%R13,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA (%RBX,%R13,1),%R15	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOVLPS %XMM2,(%R14,%R15,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
XORPS %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
LEA (,%RBX,2),%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD %R13,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOVLPS %XMM3,(%R14,%RBX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
INC %R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD $0x5,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP %R11,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 4c23a0 <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi+0x160>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1

Function	_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi
Source file and lines	SoaDistanceTableAAOMPTarget.h:440-442
Module	exec

The loop is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:244,263
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:182
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Particle/SoaDistanceTableAAOMPTarget.h:440-442

The related source loop is not unrolled or unrolled with no peel/tail loop.

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 3.67 to 2.67 cycles (1.38x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

54% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

0% of SSE/AVX loads are used in vector version.
75% of SSE/AVX stores are used in vector version.

Since your execution units are vector units, only a fully vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop streams arrays of structures (AoS), try to use structures of arrays instead (SoA): for(i) a[i].x = b[i].x; (slow, non stride 1) => for(i) a.x[i] = b.x[i]; (fast, stride 1)

Execution units bottlenecks

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 3.67 to 3.33 cycles (1.10x speedup).

Workaround

Read less array elements
Write less array elements
Provide more information to your compiler:
- hardcode the bounds of the corresponding 'for' loop

No data for this section

Slow data structures access

Detected data structures (typically arrays) that cannot be efficiently read/written

Details

Constant unknown stride: 3 occurrence(s)
Constant non-unit stride: 2 occurrence(s)
Irregular (variable stride) or indirect: 1 occurrence(s)

Non-unit stride (uncontiguous) accesses are not efficiently using data caches

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)
Try to remove indirect accesses. If applicable, precompute elements out of the innermost loop.

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This loop is probably writing/copying data or processing integer elements.

Matching between your loop (in the source code) and the binary loop

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 56 bytes. The binary loop is storing 32 bytes.

Unroll opportunity

Loop is data access bound.

Workaround

General properties

nb instructions	21
nb uops	20
loop length	94
used x86 registers	13
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	3.33 cycles
front end	3.33 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	1.50	1.50	1.25	1.25	0.50	3.67	3.67	3.67	0.75	0.75	0.75	0.75	2.00	2.00
cycles	1.50	1.50	1.25	1.25	0.50	3.67	3.67	3.67	0.75	0.75	0.75	0.75	2.00	2.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions	NA
Longest recurrence chain latency (RecMII)	1.00

Cycles summary

Front-end	3.33
Dispatch	3.67
Data deps.	1.00
Overall L1	3.67

Vectorization ratios

all	54%
load	0%
store	75%
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	100%

Vector efficiency ratios

all	15%
load	12%
store	12%
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	25%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 3.67 cycles. At this rate:

15% of peak load performance is reached (15.27 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
13% of peak store performance is reached (8.73 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the loop is: 4c23a0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
MOV (%RAX,%R8,8),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD (%R9,%R11,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOVSD %XMM1,(%RBX,%R13,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD (%R10,%R11,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
XORPS %XMM0,%XMM1	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOVSD (%RDI,%R11,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
XORPS %XMM0,%XMM2	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
MOVSD (%RSI,%R11,8),%XMM3	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOV -0x10(%RCX,%R8,8),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV (%RCX,%R8,8),%R14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVLPS %XMM1,(%R14,%R13,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA (%RBX,%R13,1),%R15	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOVLPS %XMM2,(%R14,%R15,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
XORPS %XMM0,%XMM3	1	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25
LEA (,%RBX,2),%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD %R13,%RBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOVLPS %XMM3,(%R14,%RBX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
INC %R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
ADD $0x5,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP %R11,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 4c23a0 <_ZN11qmcplusplus27SoaDistanceTableAAOMPTargetIdLj3ELi40EE6updateEi+0x160>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Slow data structures access

Details

Workaround

Type of elements and instruction set

Matching between your loop (in the source code) and the binary loop

Unroll opportunity

Workaround

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

Slow data structures access

Details

Workaround

Type of elements and instruction set

Matching between your loop (in the source code) and the binary loop

Unroll opportunity

Workaround

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code