OV - exec - Loop 602

	Loop Id: 602	Module: exec	Source: BsplineFunctor.h:291-298	Coverage: 0.01%

0x454cd4 VMOVSD	(%RDX,%R11,8),%XMM11    [20]

0x454cda VCOMISD	%XMM11,%XMM8

0x454cdf JBE	454cf8

0x454ce1 LEA	(%R14,%R11,1),%EAX

0x454ce5 CMP	%ECX,%EAX

0x454ce7 JE	454cf8

0x454ce9 MOVSXD	%EBX,%R12

0x454cec INC	%EBX

0x454cee MOV	%R11D,(%RDI,%R12,4)    [18]

0x454cf2 VMOVSD	%XMM11,(%R8,%R12,8)    [9]

0x454cf8 INC	%R11

0x454cfb VMOVSD	(%RDX,%R11,8),%XMM6    [15]

0x454d01 VCOMISD	%XMM6,%XMM8

0x454d05 JBE	454d1e

0x454d07 LEA	(%R14,%R11,1),%EAX

0x454d0b CMP	%ECX,%EAX

0x454d0d JE	454d1e

0x454d0f MOVSXD	%EBX,%R12

0x454d12 INC	%EBX

0x454d14 MOV	%R11D,(%RDI,%R12,4)    [17]

0x454d18 VMOVSD	%XMM6,(%R8,%R12,8)    [8]

0x454d1e LEA	0x1(%R11),%R12

0x454d22 VMOVSD	(%RDX,%R12,8),%XMM4    [7]

0x454d28 VCOMISD	%XMM4,%XMM8

0x454d2c JBE	454d45

0x454d2e LEA	(%R14,%R12,1),%EAX

0x454d32 CMP	%ECX,%EAX

0x454d34 JE	454d45

0x454d36 MOVSXD	%EBX,%RAX

0x454d39 INC	%EBX

0x454d3b MOV	%R12D,(%RDI,%RAX,4)    [14]

0x454d3f VMOVSD	%XMM4,(%R8,%RAX,8)    [5]

0x454d45 LEA	0x2(%R11),%R12

0x454d49 VMOVSD	(%RDX,%R12,8),%XMM5    [7]

0x454d4f VCOMISD	%XMM5,%XMM8

0x454d53 JBE	454d6c

0x454d55 LEA	(%R14,%R12,1),%EAX

0x454d59 CMP	%ECX,%EAX

0x454d5b JE	454d6c

0x454d5d MOVSXD	%EBX,%RAX

0x454d60 INC	%EBX

0x454d62 MOV	%R12D,(%RDI,%RAX,4)    [13]

0x454d66 VMOVSD	%XMM5,(%R8,%RAX,8)    [4]

0x454d6c LEA	0x3(%R11),%R12

0x454d70 VMOVSD	(%RDX,%R12,8),%XMM12    [7]

0x454d76 VCOMISD	%XMM12,%XMM8

0x454d7b JBE	454d94

0x454d7d LEA	(%R14,%R12,1),%EAX

0x454d81 CMP	%ECX,%EAX

0x454d83 JE	454d94

0x454d85 MOVSXD	%EBX,%RAX

0x454d88 INC	%EBX

0x454d8a MOV	%R12D,(%RDI,%RAX,4)    [12]

0x454d8e VMOVSD	%XMM12,(%R8,%RAX,8)    [3]

0x454d94 LEA	0x4(%R11),%R12

0x454d98 VMOVSD	(%RDX,%R12,8),%XMM2    [7]

0x454d9e VCOMISD	%XMM2,%XMM8

0x454da2 JBE	454dbb

0x454da4 LEA	(%R14,%R12,1),%EAX

0x454da8 CMP	%ECX,%EAX

0x454daa JE	454dbb

0x454dac MOVSXD	%EBX,%RAX

0x454daf INC	%EBX

0x454db1 MOV	%R12D,(%RDI,%RAX,4)    [11]

0x454db5 VMOVSD	%XMM2,(%R8,%RAX,8)    [2]

0x454dbb LEA	0x5(%R11),%R12

0x454dbf VMOVSD	(%RDX,%R12,8),%XMM13    [7]

0x454dc5 VCOMISD	%XMM13,%XMM8

0x454dca JBE	454de3

0x454dcc LEA	(%R14,%R12,1),%EAX

0x454dd0 CMP	%ECX,%EAX

0x454dd2 JE	454de3

0x454dd4 MOVSXD	%EBX,%RAX

0x454dd7 INC	%EBX

0x454dd9 MOV	%R12D,(%RDI,%RAX,4)    [10]

0x454ddd VMOVSD	%XMM13,(%R8,%RAX,8)    [1]

0x454de3 LEA	0x6(%R11),%R12

0x454de7 VMOVSD	(%RDX,%R12,8),%XMM0    [7]

0x454ded VCOMISD	%XMM0,%XMM8

0x454df1 JBE	454e0a

0x454df3 LEA	(%R14,%R12,1),%EAX

0x454df7 CMP	%ECX,%EAX

0x454df9 JE	454e0a

0x454dfb MOVSXD	%EBX,%RAX

0x454dfe INC	%EBX

0x454e00 MOV	%R12D,(%RDI,%RAX,4)    [6]

0x454e04 VMOVSD	%XMM0,(%R8,%RAX,8)    [16]

0x454e0a ADD	$0x7,%R11

0x454e0e CMP	%R11,0x158(%RSP)    [19]

0x454e16 JNE	454cd4

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 298

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

291:   for (int jat = 0; jat < iLimit; jat++)

292:   {

293:     real_type r = distArray[jat];

294:     if (r < cutoff_radius && iStart + jat != iat)

295:     {

296:       distIndices[iCount]         = jat;

297:       distArrayCompressed[iCount] = r;

298:       iCount++;

Path /

Metric	Value
CQA speedup if no scalar integer	1.64
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.63
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.32
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE
Source	BsplineFunctor.h:291-298
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	16.17
CQA cycles if no scalar integer	9.83
CQA cycles if FP arith vectorized	16.17
CQA cycles if fully vectorized	1.28
Front-end cycles	16.17
DIV/SQRT cycles	12.25
P0 cycles	12.25
P1 cycles	12.00
P2 cycles	12.00
P3 cycles	8.50
P4 cycles	8.33
P5 cycles	8.33
P6 cycles	8.33
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	4.00
P10 cycles	4.00
P11 cycles	8.00
P12 cycles	8.00
P13 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	97.00
Nb loads	9.00
Nb stores	16.00
Nb stack references	1.00
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	10.39
Bytes prefetched	0.00
Bytes loaded	72.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	9.38
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	9.38
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	6.25
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.38

Metric	Value
CQA speedup if no scalar integer	1.64
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.63
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.32
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE
Source	BsplineFunctor.h:291-298
Source loop unroll info	multi-versionned
Source loop unroll confidence level	max
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	16.17
CQA cycles if no scalar integer	9.83
CQA cycles if FP arith vectorized	16.17
CQA cycles if fully vectorized	1.28
Front-end cycles	16.17
DIV/SQRT cycles	12.25
P0 cycles	12.25
P1 cycles	12.00
P2 cycles	12.00
P3 cycles	8.50
P4 cycles	8.33
P5 cycles	8.33
P6 cycles	8.33
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	4.00
P10 cycles	4.00
P11 cycles	8.00
P12 cycles	8.00
P13 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	90.00
Nb uops	97.00
Nb loads	9.00
Nb stores	16.00
Nb stack references	1.00
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	10.39
Bytes prefetched	0.00
Bytes loaded	72.00
Bytes stored	96.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	9.38
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	9.38
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	6.25
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	9.38

Path /

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

Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE
Source file and lines	BsplineFunctor.h:291-298
Module	exec

The loop is defined in /beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h:291-298.

The related source loop is multi-versionned.
Warnings:

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 6561 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 16.17 to 9.83 cycles (1.64x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 9% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your loop, you can lower the cost of an iteration from 16.17 to 1.28 cycles (12.63x speedup).

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
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

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VCOMISD: 8 occurrences

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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 72 bytes (9 double precision FP elements). The binary loop is storing 96 bytes (12 double precision FP elements).

Unroll opportunity

Loop is potentially 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 by recompiling with -funroll-loops and/or -floop-unroll-and-jam. Or with the unroll (resp. unroll_and_jam) directive on top of the inner (resp. surrounding) loop. You can enforce an unroll factor: #pragma GCC unroll N

General properties

nb instructions	90
nb uops	97
loop length	328
used x86 registers	10
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	16.17 cycles
front end	16.17 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	12.25	12.25	12.00	12.00	8.50	8.33	8.33	8.33	0.00	0.00	4.00	4.00	8.00	8.00
cycles	12.25	12.25	12.00	12.00	8.50	8.33	8.33	8.33	0.00	0.00	4.00	4.00	8.00	8.00

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

Cycles summary

Front-end	16.17
Dispatch	12.25
Overall L1	16.17

Vectorization ratios

INT

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	6%
load	NA (no load vectorizable/vectorized instructions)
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	6%

all	12%
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	12%

INT+FP

all	9%
load	12%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 16.17 cycles. At this rate:

4% of peak load performance is reached (4.45 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (5.94 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck). By removing all these bottlenecks, you can lower the cost of an iteration from 16.17 to 12.25 cycles (1.32x speedup).

ASM code

In the binary file, the address of the loop is: 454cd4

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP2	FP3	FP4	FP5	Latency	Recip. throughput
VMOVSD (%RDX,%R11,8),%XMM11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM11,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454cf8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x538>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R11,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454cf8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x538>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R11D,(%RDI,%R12,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM11,(%R8,%R12,8)	1	0	0	0	0	0	0.33	0.33	0.33	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	1	0.25
VMOVSD (%RDX,%R11,8),%XMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM6,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d1e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x55e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R11,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d1e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x55e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R11D,(%RDI,%R12,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM6,(%R8,%R12,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x1(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM4,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d45 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x585>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d45 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x585>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM4,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x2(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM5,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d6c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5ac>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d6c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5ac>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM5,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x3(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM12,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5d4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5d4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM12,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x4(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM2,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454dbb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5fb>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454dbb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5fb>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM2,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x5(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM13,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454de3 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x623>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454de3 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x623>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM13,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x6(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM0,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454e0a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x64a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454e0a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x64a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM0,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
ADD $0x7,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %R11,0x158(%RSP)	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	1	0.33
JNE 454cd4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x514>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1

Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE
Source file and lines	BsplineFunctor.h:291-298
Module	exec

Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 6561 paths individually, rerun with max-paths=6561
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 16.17 to 9.83 cycles (1.64x speedup).

Workaround

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

Vectorization

Details

All SSE/AVX instructions are used in scalar version (process only one data element in vector registers). Since your execution units are vector units, only a vectorized loop can use their full power.

Workaround

Try another compiler or update/tune your current one
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

Found no such bottlenecks but see expert reports for more complex bottlenecks.

No data for this section

Complex instructions

Detected COMPLEX INSTRUCTIONS.

Details

These instructions generate more than one micro-operation and only one of them can be decoded during a cycle and the extra micro-operations increase pressure on execution units.

VCOMISD: 8 occurrences

Type of elements and instruction set

8 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

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

Unroll opportunity

Loop is potentially data access bound.

Workaround

General properties

nb instructions	90
nb uops	97
loop length	328
used x86 registers	10
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	16.17 cycles
front end	16.17 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	12.25	12.25	12.00	12.00	8.50	8.33	8.33	8.33	0.00	0.00	4.00	4.00	8.00	8.00
cycles	12.25	12.25	12.00	12.00	8.50	8.33	8.33	8.33	0.00	0.00	4.00	4.00	8.00	8.00

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

Cycles summary

Front-end	16.17
Dispatch	12.25
Overall L1	16.17

Vectorization ratios

INT

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
other	0%

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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

Vector efficiency ratios

INT

all	6%
load	NA (no load vectorizable/vectorized instructions)
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
other	6%

all	12%
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	12%

INT+FP

all	9%
load	12%
store	9%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	6%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 16.17 cycles. At this rate:

4% of peak load performance is reached (4.45 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (5.94 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 454cd4

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP2	FP3	FP4	FP5	Latency	Recip. throughput
VMOVSD (%RDX,%R11,8),%XMM11	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM11,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454cf8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x538>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R11,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454cf8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x538>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R11D,(%RDI,%R12,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM11,(%R8,%R12,8)	1	0	0	0	0	0	0.33	0.33	0.33	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	1	0.25
VMOVSD (%RDX,%R11,8),%XMM6	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM6,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d1e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x55e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R11,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d1e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x55e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R11D,(%RDI,%R12,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM6,(%R8,%R12,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x1(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM4	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM4,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d45 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x585>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d45 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x585>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM4,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x2(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM5	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM5,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d6c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5ac>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d6c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5ac>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM5,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x3(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM12,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454d94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5d4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454d94 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5d4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM12,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x4(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM2,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454dbb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5fb>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454dbb <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x5fb>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM2,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x5(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM13,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454de3 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x623>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454de3 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x623>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM13,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
LEA 0x6(%R11),%R12	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD (%RDX,%R12,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM0,%XMM8	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 454e0a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x64a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
LEA (%R14,%R12,1),%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %ECX,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 454e0a <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x64a>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %EBX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %EBX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
MOV %R12D,(%RDI,%RAX,4)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	4	0.50
VMOVSD %XMM0,(%R8,%RAX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
ADD $0x7,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %R11,0x158(%RSP)	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	1	0.33
JNE 454cd4 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9recomputeERNS1_11ParticleSetE+0x514>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

Complex instructions

Details

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

Complex instructions

Details

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