OV - - Loop 351

	Loop Id: 351	Module: exec	Source: BsplineFunctor.h:236-241	Coverage: 0.96%

0x42fd7c VMOVSD	(%RDX),%XMM12    [2]

0x42fd80 VCOMISD	%XMM12,%XMM3

0x42fd85 JBE	42fd97

0x42fd87 CMP	%EAX,%R10D

0x42fd8a JE	42fd97

0x42fd8c MOVSXD	%ECX,%R11

0x42fd8f INC	%ECX

0x42fd91 VMOVSD	%XMM12,(%RSI,%R11,8)    [1]

0x42fd97 INC	%EAX

0x42fd99 VMOVSD	0x8(%RDX),%XMM13    [2]

0x42fd9e LEA	0x8(%RDX),%RDI

0x42fda2 VCOMISD	%XMM13,%XMM3

0x42fda7 JBE	42fdb8

0x42fda9 CMP	%EAX,%R10D

0x42fdac JE	42fdb8

0x42fdae MOVSXD	%ECX,%RDX

0x42fdb1 INC	%ECX

0x42fdb3 VMOVSD	%XMM13,(%RSI,%RDX,8)    [10]

0x42fdb8 VMOVSD	0x8(%RDI),%XMM14    [5]

0x42fdbd LEA	0x1(%RAX),%R11D

0x42fdc1 VCOMISD	%XMM14,%XMM3

0x42fdc6 JBE	42fdd7

0x42fdc8 CMP	%R11D,%R10D

0x42fdcb JE	42fdd7

0x42fdcd MOVSXD	%ECX,%RDX

0x42fdd0 INC	%ECX

0x42fdd2 VMOVSD	%XMM14,(%RSI,%RDX,8)    [9]

0x42fdd7 VMOVSD	0x10(%RDI),%XMM15    [5]

0x42fddc LEA	0x2(%RAX),%R11D

0x42fde0 VCOMISD	%XMM15,%XMM3

0x42fde5 JBE	42fdf6

0x42fde7 CMP	%R11D,%R10D

0x42fdea JE	42fdf6

0x42fdec MOVSXD	%ECX,%RDX

0x42fdef INC	%ECX

0x42fdf1 VMOVSD	%XMM15,(%RSI,%RDX,8)    [8]

0x42fdf6 VMOVSD	0x18(%RDI),%XMM0    [5]

0x42fdfb LEA	0x3(%RAX),%R11D

0x42fdff VCOMISD	%XMM0,%XMM3

0x42fe03 JBE	42fe14

0x42fe05 CMP	%R11D,%R10D

0x42fe08 JE	42fe14

0x42fe0a MOVSXD	%ECX,%RDX

0x42fe0d INC	%ECX

0x42fe0f VMOVSD	%XMM0,(%RSI,%RDX,8)    [7]

0x42fe14 VMOVSD	0x20(%RDI),%XMM7    [5]

0x42fe19 LEA	0x4(%RAX),%R11D

0x42fe1d VCOMISD	%XMM7,%XMM3

0x42fe21 JBE	42fe32

0x42fe23 CMP	%R11D,%R10D

0x42fe26 JE	42fe32

0x42fe28 MOVSXD	%ECX,%RDX

0x42fe2b INC	%ECX

0x42fe2d VMOVSD	%XMM7,(%RSI,%RDX,8)    [6]

0x42fe32 VMOVSD	0x28(%RDI),%XMM1    [5]

0x42fe37 LEA	0x5(%RAX),%R11D

0x42fe3b VCOMISD	%XMM1,%XMM3

0x42fe3f JBE	42fe50

0x42fe41 CMP	%R11D,%R10D

0x42fe44 JE	42fe50

0x42fe46 MOVSXD	%ECX,%RDX

0x42fe49 INC	%ECX

0x42fe4b VMOVSD	%XMM1,(%RSI,%RDX,8)    [4]

0x42fe50 VMOVSD	0x30(%RDI),%XMM2    [5]

0x42fe55 LEA	0x6(%RAX),%R11D

0x42fe59 VCOMISD	%XMM2,%XMM3

0x42fe5d JBE	42fe6e

0x42fe5f CMP	%R11D,%R10D

0x42fe62 JE	42fe6e

0x42fe64 MOVSXD	%ECX,%RDX

0x42fe67 INC	%ECX

0x42fe69 VMOVSD	%XMM2,(%RSI,%RDX,8)    [3]

0x42fe6e ADD	$0x7,%EAX

0x42fe71 LEA	0x38(%RDI),%RDX

0x42fe75 CMP	%EAX,%R12D

0x42fe78 JNE	42fd7c

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 241

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

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

237:   {

238:     real_type r = distArray[jat];

239:     // pick the distances smaller than the cutoff and avoid the reference atom

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

241:       distArrayCompressed[iCount++] = distArray[jat];

Path /

Metric	Value
CQA speedup if no scalar integer	1.41
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.16
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.29
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE
Source	BsplineFunctor.h:236-241
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	13.83
CQA cycles if no scalar integer	9.83
CQA cycles if FP arith vectorized	13.83
CQA cycles if fully vectorized	1.14
Front-end cycles	13.83
DIV/SQRT cycles	10.75
P0 cycles	10.75
P1 cycles	10.50
P2 cycles	10.50
P3 cycles	8.50
P4 cycles	5.33
P5 cycles	5.33
P6 cycles	5.33
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	76.00
Nb uops	83.00
Nb loads	8.00
Nb stores	8.00
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	9.25
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
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	10.00
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	1.41
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	12.16
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.29
Bottlenecks	micro-operation queue,
Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE
Source	BsplineFunctor.h:236-241
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	13.83
CQA cycles if no scalar integer	9.83
CQA cycles if FP arith vectorized	13.83
CQA cycles if fully vectorized	1.14
Front-end cycles	13.83
DIV/SQRT cycles	10.75
P0 cycles	10.75
P1 cycles	10.50
P2 cycles	10.50
P3 cycles	8.50
P4 cycles	5.33
P5 cycles	5.33
P6 cycles	5.33
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	76.00
Nb uops	83.00
Nb loads	8.00
Nb stores	8.00
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	9.25
Bytes prefetched	0.00
Bytes loaded	64.00
Bytes stored	64.00
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	10.00
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
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	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE
Source file and lines	BsplineFunctor.h:236-241
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:236-241.

The related source loop is not unrolled or unrolled with no peel/tail loop.
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 13.83 to 9.83 cycles (1.41x 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 10% 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 13.83 to 1.14 cycles (12.16x 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 64 bytes (8 double precision FP elements). The binary loop is storing 64 bytes (8 double precision FP elements).

General properties

nb instructions	76
nb uops	83
loop length	258
used x86 registers	8
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	13.83 cycles
front end	13.83 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	10.75	10.75	10.50	10.50	8.50	5.33	5.33	5.33	0.00	0.00	4.00	4.00	8.00	8.00
cycles	10.75	10.75	10.50	10.50	8.50	5.33	5.33	5.33	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	13.83
Dispatch	10.75
Overall L1	13.83

Vectorization ratios

INT

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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	NA (no store vectorizable/vectorized instructions)
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	10%
load	12%
store	12%
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 13.83 cycles. At this rate:

4% of peak load performance is reached (4.63 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (4.63 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 13.83 to 10.75 cycles (1.29x speedup).

ASM code

In the binary file, the address of the loop is: 42fd7c

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP2	FP3	FP4	FP5	Latency	Recip. throughput
VMOVSD (%RDX),%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM12,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fd97 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %EAX,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fd97 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM12,(%RSI,%R11,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
INC %EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x8(%RDX),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x8(%RDX),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM13,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdb8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %EAX,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdb8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM13,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x8(%RDI),%XMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x1(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM14,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x317>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x317>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM14,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x10(%RDI),%XMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x2(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM15,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdf6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x336>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdf6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x336>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM15,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x18(%RDI),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x3(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe14 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x354>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe14 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x354>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM0,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x20(%RDI),%XMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x4(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM7,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe32 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x372>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe32 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x372>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM7,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x28(%RDI),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x5(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM1,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM1,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x30(%RDI),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x6(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe6e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x3ae>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe6e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x3ae>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM2,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
ADD $0x7,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
LEA 0x38(%RDI),%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %EAX,%R12D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JNE 42fd7c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2bc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1

Function	_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE
Source file and lines	BsplineFunctor.h:236-241
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 13.83 to 9.83 cycles (1.41x 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

General properties

nb instructions	76
nb uops	83
loop length	258
used x86 registers	8
used mmx registers	0
used xmm registers	9
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	13.83 cycles
front end	13.83 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	10.75	10.75	10.50	10.50	8.50	5.33	5.33	5.33	0.00	0.00	4.00	4.00	8.00	8.00
cycles	10.75	10.75	10.50	10.50	8.50	5.33	5.33	5.33	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	13.83
Dispatch	10.75
Overall L1	13.83

Vectorization ratios

INT

all	0%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
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	NA (no store vectorizable/vectorized instructions)
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	10%
load	12%
store	12%
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 13.83 cycles. At this rate:

4% of peak load performance is reached (4.63 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
7% of peak store performance is reached (4.63 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: 42fd7c

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP2	FP3	FP4	FP5	Latency	Recip. throughput
VMOVSD (%RDX),%XMM12	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
VCOMISD %XMM12,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fd97 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %EAX,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fd97 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2d7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%R11	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM12,(%RSI,%R11,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
INC %EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD 0x8(%RDX),%XMM13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x8(%RDX),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM13,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdb8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %EAX,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdb8 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM13,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x8(%RDI),%XMM14	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x1(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM14,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x317>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdd7 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x317>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM14,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x10(%RDI),%XMM15	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x2(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM15,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fdf6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x336>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fdf6 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x336>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM15,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x18(%RDI),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x3(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM0,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe14 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x354>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe14 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x354>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM0,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x20(%RDI),%XMM7	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x4(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM7,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe32 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x372>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe32 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x372>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM7,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x28(%RDI),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x5(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM1,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe50 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x390>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM1,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
VMOVSD 0x30(%RDI),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50
LEA 0x6(%RAX),%R11D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VCOMISD %XMM2,%XMM3	2	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	6	1
JBE 42fe6e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x3ae>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
CMP %R11D,%R10D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JE 42fe6e <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x3ae>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1
MOVSXD %ECX,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
INC %ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
VMOVSD %XMM2,(%RSI,%RDX,8)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	1	1
ADD $0x7,%EAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
LEA 0x38(%RDI),%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
CMP %EAX,%R12D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	1	0.25
JNE 42fd7c <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2bc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	1	0.50-1

▶Scalability Runs Description

Run 2x1	Number processes: 2Number nodes: 1Number processes per node: 2Run Command: <executable> -g "4 2 2" -bMPI Command: mpirun -np <number_processes>Dataset: Run Directory: /beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/run/oneview_runs/compilers/gcc_2/oneview_run_1708580749I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spreadOMP_NUM_THREADS: 1
Run 2x2	OMP_NUM_THREADS: 2I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x4	OMP_NUM_THREADS: 4I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x8	OMP_NUM_THREADS: 8I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x16	OMP_NUM_THREADS: 16I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x32	OMP_NUM_THREADS: 32I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x64	OMP_NUM_THREADS: 64I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread
Run 2x96	OMP_NUM_THREADS: 96I_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_PROC_BIND: spread

(2x1) Efficiency	(2x1) Potential Speed-Up (%)	(2x2) Efficiency	(2x2) Potential Speed-Up (%)	(2x4) Efficiency	(2x4) Potential Speed-Up (%)	(2x8) Efficiency	(2x8) Potential Speed-Up (%)	(2x16) Efficiency	(2x16) Potential Speed-Up (%)	(2x32) Efficiency	(2x32) Potential Speed-Up (%)	(2x64) Efficiency	(2x64) Potential Speed-Up (%)	(2x96) Efficiency	(2x96) Potential Speed-Up (%)
1	0	0.55	0.46	0.29	0.67	0.15	0.88	0.07	0.86	0.03	0.96	0.01	1.19	0	1.26

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency

Run	Number of threads	Efficiency (ideal is 1)	Speedup	Ideal Speedup	Time (s)	Coverage (%)
2x1	2	1	1	1	0.48	0.96
2x2	4	0.55	0.92	1.6666666666667	0.54	1.02
2x4	8	0.29	0.98	3.3333333333333	0.51	0.95
2x8	16	0.15	0.86	5.6666666666667	0.56	1.04
2x16	32	0.07	0.76	11.333333333333	0.58	0.92
2x32	64	0.03	0.59	22	0.87	0.99
2x64	128	0.01	0.26	43.333333333333	2	1.2
2x96	192	0	0.17	64.666666666667	2.94	1.26

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

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code

▶Scalability Runs Description

▼Colums Filter

Speed-Up and Efficiency

▶Detailed Speed-Up and Efficiency