OV - exec - Loop 391

	Loop Id: 391	Module: exec	Source: TwoBodyJastrowRef.h:393-398	Coverage: 0.03%

0x42bcc0 VMOVSD	(%R13,%RDX,8),%XMM0    [6]

0x42bcc7 VMOVSD	-0x8(%R9,%RDX,8),%XMM1    [1]

0x42bcce VFNMADD213SD	-0x8(%R10,%RDX,8),%XMM0,%XMM1    [4]

0x42bcd5 VMOVSD	%XMM1,-0x8(%R10,%RDX,8)    [4]

0x42bcdc VMOVSD	-0x8(%R11,%RDX,8),%XMM1    [2]

0x42bce3 VFNMADD213SD	-0x8(%RBX,%RDX,8),%XMM0,%XMM1    [7]

0x42bcea VMOVSD	%XMM1,-0x8(%RBX,%RDX,8)    [7]

0x42bcf0 VMOVSD	-0x8(%RCX,%RDX,8),%XMM1    [5]

0x42bcf6 VFNMADD213SD	-0x8(%R15,%RDX,8),%XMM0,%XMM1    [3]

0x42bcfd VMOVSD	%XMM1,-0x8(%R15,%RDX,8)    [3]

0x42bd04 VMOVSD	0x8(%R13,%RDX,8),%XMM0    [6]

0x42bd0b VMOVSD	(%R9,%RDX,8),%XMM1    [1]

0x42bd11 VFNMADD213SD	(%R10,%RDX,8),%XMM0,%XMM1    [4]

0x42bd17 VMOVSD	%XMM1,(%R10,%RDX,8)    [4]

0x42bd1d VMOVSD	(%R11,%RDX,8),%XMM1    [2]

0x42bd23 VFNMADD213SD	(%RBX,%RDX,8),%XMM0,%XMM1    [7]

0x42bd29 VMOVSD	%XMM1,(%RBX,%RDX,8)    [7]

0x42bd2e VMOVSD	(%RCX,%RDX,8),%XMM1    [5]

0x42bd33 VFNMADD213SD	(%R15,%RDX,8),%XMM0,%XMM1    [3]

0x42bd39 VMOVSD	%XMM1,(%R15,%RDX,8)    [3]

0x42bd3f ADD	$0x2,%RDX

0x42bd43 CMP	%RDX,%R8

0x42bd46 JNE	42bcc0

/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 393 - 398

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

393:       for (int idim = 0; idim < OHMMS_DIM; ++idim)

394:       {

395:         valT* restrict save_g   = dUat.data(idim);

396:         const valT* restrict dX = displ.data(idim);

397:         for (int jat = 0; jat < iat; jat++)

398:           save_g[jat] -= du[jat] * dX[jat];

Coverage (%)	Name	Source Location	Module
►100.00+	miniqmcreference::TwoBodyJastr[...]	TwoBodyJastrowRef.h:411	exec
○	qmcplusplus::WaveFunction::eva[...]	WaveFunction.cpp:175	exec
○	main.extracted.112	miniqmc.cpp:397	exec
○	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.56
Bottlenecks	micro-operation queue, P2, P3, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::ParticleAttrib >&, bool)
Source	TwoBodyJastrowRef.h:393-398
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	4.67
CQA cycles if no scalar integer	4.67
CQA cycles if FP arith vectorized	4.67
CQA cycles if fully vectorized	0.58
Front-end cycles	4.67
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	4.67
P3 cycles	4.67
P4 cycles	3.00
P5 cycles	0.00
P6 cycles	1.00
P7 cycles	3.00
P8 cycles	3.00
P9 cycles	3.00
P10 cycles	0.00
P11 cycles	4.67
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	23.00
Nb uops	22.00
Nb loads	14.00
Nb stores	6.00
Nb stack references	0.00
FLOP/cycle	2.57
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	6.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	34.29
Bytes prefetched	0.00
Bytes loaded	112.00
Bytes stored	48.00
Stride 0	0.00
Stride 1	7.00
Stride n	0.00
Stride unknown	0.00
Stride indirect	0.00
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	12.50
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	12.50
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	8.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.56
Bottlenecks	micro-operation queue, P2, P3, P11,
Function	miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::ParticleAttrib >&, bool)
Source	TwoBodyJastrowRef.h:393-398
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	4.67
CQA cycles if no scalar integer	4.67
CQA cycles if FP arith vectorized	4.67
CQA cycles if fully vectorized	0.58
Front-end cycles	4.67
P0 cycles	3.00
P1 cycles	3.00
P2 cycles	4.67
P3 cycles	4.67
P4 cycles	3.00
P5 cycles	0.00
P6 cycles	1.00
P7 cycles	3.00
P8 cycles	3.00
P9 cycles	3.00
P10 cycles	0.00
P11 cycles	4.67
DIV/SQRT cycles	0.00
Inter-iter dependencies cycles	1
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	23.00
Nb uops	22.00
Nb loads	14.00
Nb stores	6.00
Nb stack references	0.00
FLOP/cycle	2.57
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	6.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	34.29
Bytes prefetched	0.00
Bytes loaded	112.00
Bytes stored	48.00
Stride 0	0.00
Stride 1	7.00
Stride n	0.00
Stride unknown	0.00
Stride indirect	0.00
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	NA
Vectorization ratio add_sub	NA
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	NA
Vectorization ratio other	NA
Vector-efficiency ratio all	12.50
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	12.50
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	NA

Path /

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

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::ParticleAttrib >&, bool)
Source file and lines	TwoBodyJastrowRef.h:393-398
Module	exec

The loop is defined in /home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h:393-398.

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

gain
potential
hint
expert

Vectorization

Your loop is not vectorized. 8 data elements could be processed at once in vector registers.

By vectorizing your loop, you can lower the cost of an iteration from 4.67 to 0.58 cycles (8.00x 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:
- 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). By removing all these bottlenecks, you can lower the cost of an iteration from 4.67 to 3.00 cycles (1.56x speedup).

Workaround

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

FMA

Detected 6 FMA (fused multiply-add) operations.

Type of elements and instruction set

6 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 is composed of 12 FP arithmetical operations:

6: addition or subtraction (all inside FMA instructions)
6: multiply (all inside FMA instructions)

The binary loop is loading 112 bytes (14 double precision FP elements). The binary loop is storing 48 bytes (6 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

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	23
nb uops	22
loop length	140
used x86 registers	9
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	4.67 cycles
front end	4.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	3.00	3.00	4.67	4.67	3.00	0.00	1.00	3.00	3.00	3.00	0.00	4.67
cycles	3.00	3.00	4.67	4.67	3.00	0.00	1.00	3.00	3.00	3.00	0.00	4.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

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

Cycles summary

Front-end	4.67
Dispatch	4.67
Data deps.	1.00
Overall L1	4.67

Vectorization ratios

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

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.67 cycles. At this rate:

12% of peak load performance is reached (24.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (10.29 out of 128.00 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 4.67 to 3.00 cycles (1.56x speedup).

ASM code

In the binary file, the address of the loop is: 42bcc0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VMOVSD (%R13,%RDX,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x8(%R9,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%R10,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%R10,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD -0x8(%R11,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%RBX,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD -0x8(%RCX,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%R15,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x8(%R13,%RDX,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R9,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%R10,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%R10,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R11,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%RBX,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%RCX,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%R15,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x2,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JNE 42bcc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x980>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A

Function	miniqmcreference::TwoBodyJastrowRef >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib, std::allocator > >&, qmcplusplus::ParticleAttrib >&, bool)
Source file and lines	TwoBodyJastrowRef.h:393-398
Module	exec

gain
potential
hint
expert

Vectorization

Your loop is not vectorized. 8 data elements could be processed at once in vector registers.

By vectorizing your loop, you can lower the cost of an iteration from 4.67 to 0.58 cycles (8.00x 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:
- 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

Workaround

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

FMA

Detected 6 FMA (fused multiply-add) operations.

Type of elements and instruction set

6 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 is composed of 12 FP arithmetical operations:

6: addition or subtraction (all inside FMA instructions)
6: multiply (all inside FMA instructions)

The binary loop is loading 112 bytes (14 double precision FP elements). The binary loop is storing 48 bytes (6 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.07 FP operations per loaded or stored byte.

Unroll opportunity

Loop is data access bound.

Workaround

General properties

nb instructions	23
nb uops	22
loop length	140
used x86 registers	9
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	0

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	4.67 cycles
front end	4.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	3.00	3.00	4.67	4.67	3.00	0.00	1.00	3.00	3.00	3.00	0.00	4.67
cycles	3.00	3.00	4.67	4.67	3.00	0.00	1.00	3.00	3.00	3.00	0.00	4.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

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

Cycles summary

Front-end	4.67
Dispatch	4.67
Data deps.	1.00
Overall L1	4.67

Vectorization ratios

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

Vector efficiency ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.67 cycles. At this rate:

12% of peak load performance is reached (24.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (10.29 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 42bcc0

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
VMOVSD (%R13,%RDX,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD -0x8(%R9,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%R10,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%R10,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD -0x8(%R11,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%RBX,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD -0x8(%RCX,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD -0x8(%R15,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,-0x8(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD 0x8(%R13,%RDX,8),%XMM0	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R9,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%R10,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%R10,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R11,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%RBX,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%RCX,%RDX,8),%XMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VFNMADD213SD (%R15,%RDX,8),%XMM0,%XMM1	1	0.50	0.50	0.33	0.33	0	0	0	0	0	0	0	0.33	4	0.50	scal (12.5%)
VMOVSD %XMM1,(%R15,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD $0x2,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RDX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JNE 42bcc0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x980>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

FMA

Type of elements and instruction set

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

Arithmetic intensity

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

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

FMA

Type of elements and instruction set

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

Arithmetic intensity

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