OV - exec - Function _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1

	Function: _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS ...	Module: exec	Source: OneBodyJastrowRef.h:186-263 [...]	Coverage: 0.04%

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 273 - 273

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

273:   inline const T* restrict data(size_t i) const { return myData + i * nGhosts; }

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 169 - 169

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

169:   inline Type_t& operator[](unsigned int i) { return X[i]; }

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 186 - 263

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

186:     for (int jat = 0; jat < Nions; ++jat)

187:       lap += d2u[jat] + lapfac * du[jat];

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

189:     {

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

191:       valT s                  = valT();

192:       for (int jat = 0; jat < Nions; ++jat)

193:         s += du[jat] * dX[jat];

194:       grad[idim] = s;

[...]

256:   {

257:     UpdateMode = ORB_PBYP_PARTIAL;

258:

259:     computeU3(P, iat, P.getDistTableAB(myTableID).getTempDists().data());

260:     curLap = accumulateGL(dU.data(), d2U.data(), P.getDistTableAB(myTableID).getTempDispls(), curGrad);

261:     curAt  = std::accumulate(U.begin(), U.begin() + Nions, valT());

262:     grad_iat += curGrad;

263:     return std::exp(Vat[iat] - curAt);

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h: 140 - 141

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

140:       for (; __first != __last; ++__first)

141: 	__init = _GLIBCXX_MOVE_IF_20(__init) + *__first;

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 249

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

223:     return X[i];

[...]

249:   inline const_pointer data() const { return X; }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1169 - 1169

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

1169:       { return _M_data_ptr(this->_M_impl._M_start); }

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1028 - 1182

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

1028:       : _M_current(__i) { }

[...]

1182:     { return __lhs.base() != __rhs.base(); }

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

94:     (const_cast<T1&>(a) += b);

0x420e40 PUSH	%RBP

0x420e41 MOV	%RSP,%RBP

0x420e44 PUSH	%R15

0x420e46 PUSH	%R14

0x420e48 PUSH	%R13

0x420e4a PUSH	%R12

0x420e4c PUSH	%RBX

0x420e4d PUSH	%RAX

0x420e4e MOV	%RCX,%R14

0x420e51 MOV	%EDX,%EBX

0x420e53 MOV	%RSI,%R12

0x420e56 MOV	%RDI,%R15

0x420e59 MOVL	$0x2,0xc(%RDI)

0x420e60 MOV	0xa8(%RDI),%ESI

0x420e66 MOV	%R12,%RDI

0x420e69 CALL	462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x420e6e MOV	0x90(%RAX),%RCX

0x420e75 MOV	%R15,%RDI

0x420e78 MOV	%R12,%RSI

0x420e7b MOV	%EBX,-0x2c(%RBP)

0x420e7e MOV	%EBX,%EDX

0x420e80 CALL	423670 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>

0x420e85 MOV	0x118(%R15),%R13

0x420e8c MOV	0x130(%R15),%RBX

0x420e93 MOV	0xa8(%R15),%ESI

0x420e9a MOV	%R12,%RDI

0x420e9d CALL	462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>

0x420ea2 MOVSXD	0x90(%R15),%RCX

0x420ea9 MOV	%ECX,%EDX

0x420eab TEST	%RCX,%RCX

0x420eae JLE	420ef4

0x420eb0 MOV	$-0x2,%ESI

0x420eb5 AND	%RDX,%RSI

0x420eb8 JE	420efa

0x420eba XORPD	%XMM1,%XMM1

0x420ebe XOR	%EDI,%EDI

(269) 0x420ec0 MOVUPD	(%R13,%RDI,8),%XMM0

(269) 0x420ec7 ADDPD	%XMM0,%XMM0

(269) 0x420ecb MOVUPD	(%RBX,%RDI,8),%XMM2

(269) 0x420ed0 ADDPD	%XMM2,%XMM1

(269) 0x420ed4 ADDPD	%XMM0,%XMM1

(269) 0x420ed8 ADD	$0x2,%RDI

(269) 0x420edc CMP	%RSI,%RDI

(269) 0x420edf JB	420ec0

0x420ee1 MOVAPD	%XMM1,%XMM0

0x420ee5 UNPCKHPD	%XMM1,%XMM0

0x420ee9 ADDSD	%XMM1,%XMM0

0x420eed CMP	%RDX,%RSI

0x420ef0 JNE	420f00

0x420ef2 JMP	420f1c

0x420ef4 XORPD	%XMM0,%XMM0

0x420ef8 JMP	420f1c

0x420efa XOR	%ESI,%ESI

0x420efc XORPD	%XMM0,%XMM0

(268) 0x420f00 MOVSD	(%R13,%RSI,8),%XMM1

(268) 0x420f07 ADDSD	(%RBX,%RSI,8),%XMM0

(268) 0x420f0c ADDSD	%XMM1,%XMM1

(268) 0x420f10 ADDSD	%XMM1,%XMM0

(268) 0x420f14 INC	%RSI

(268) 0x420f17 CMP	%RSI,%RDX

(268) 0x420f1a JNE	420f00

0x420f1c MOV	0xa8(%RAX),%RSI

0x420f23 MOV	0xb8(%RAX),%RAX

0x420f2a LEA	0xc0(%R15),%R8

0x420f31 XOR	%EDI,%EDI

0x420f33 TEST	%RSI,%RSI

0x420f36 MOV	$0,%R9D

0x420f3c CMOVG	%RSI,%R9

0x420f40 LEA	(%RDX,%R9,2),%R9

0x420f44 LEA	-0x8(%RAX,%R9,8),%R9

0x420f49 CMOVS	%RSI,%RDI

0x420f4d CMP	%R8,%R9

0x420f50 JB	420fbb

0x420f52 LEA	0xd0(%R15),%R8

0x420f59 SAL	$0x4,%RDI

0x420f5d ADD	%RAX,%RDI

0x420f60 CMP	%RDI,%R8

0x420f63 JB	420fbb

0x420f65 SAL	$0x3,%RSI

0x420f69 XOR	%EDI,%EDI

0x420f6b JMP	420f8e

0x420f6d NOPL	(%RAX)

(266) 0x420f70 MOVSD	%XMM1,0xc0(%R15,%RDI,8)

(266) 0x420f7a LEA	0x1(%RDI),%R8

(266) 0x420f7e ADD	%RSI,%RAX

(266) 0x420f81 CMP	$0x2,%RDI

(266) 0x420f85 MOV	%R8,%RDI

(266) 0x420f88 JE	421171

(266) 0x420f8e XORPD	%XMM1,%XMM1

(266) 0x420f92 TEST	%EDX,%EDX

(266) 0x420f94 JLE	420f70

(266) 0x420f96 XOR	%R8D,%R8D

(266) 0x420f99 NOPL	(%RAX)

  (267) 0x420fa0 MOVSD	(%RAX,%R8,8),%XMM2

  (267) 0x420fa6 MULSD	(%R13,%R8,8),%XMM2

  (267) 0x420fad ADDSD	%XMM2,%XMM1

  (267) 0x420fb1 INC	%R8

  (267) 0x420fb4 CMP	%R8,%RDX

  (267) 0x420fb7 JNE	420fa0

(266) 0x420fb9 JMP	420f70

0x420fbb TEST	%ECX,%ECX

0x420fbd JLE	421001

0x420fbf MOV	$-0x2,%EDI

0x420fc4 AND	%RDX,%RDI

0x420fc7 JE	421015

0x420fc9 XORPD	%XMM2,%XMM2

0x420fcd XOR	%R8D,%R8D

(265) 0x420fd0 MOVUPD	(%RAX,%R8,8),%XMM1

(265) 0x420fd6 MOVUPD	(%R13,%R8,8),%XMM3

(265) 0x420fdd MULPD	%XMM1,%XMM3

(265) 0x420fe1 ADDPD	%XMM3,%XMM2

(265) 0x420fe5 ADD	$0x2,%R8

(265) 0x420fe9 CMP	%RDI,%R8

(265) 0x420fec JB	420fd0

0x420fee MOVAPD	%XMM2,%XMM1

0x420ff2 UNPCKHPD	%XMM2,%XMM1

0x420ff6 ADDSD	%XMM2,%XMM1

0x420ffa CMP	%RDX,%RDI

0x420ffd JNE	421020

0x420fff JMP	421038

0x421001 MOVQ	$0,0xc0(%R15)

0x42100c XORPD	%XMM1,%XMM1

0x421010 JMP	4210c9

0x421015 XOR	%EDI,%EDI

0x421017 XORPD	%XMM1,%XMM1

0x42101b NOPL	(%RAX,%RAX,1)

(262) 0x421020 MOVSD	(%RAX,%RDI,8),%XMM2

(262) 0x421025 MULSD	(%R13,%RDI,8),%XMM2

(262) 0x42102c ADDSD	%XMM2,%XMM1

(262) 0x421030 INC	%RDI

(262) 0x421033 CMP	%RDI,%RDX

(262) 0x421036 JNE	421020

0x421038 MOVSD	%XMM1,0xc0(%R15)

0x421041 TEST	%ECX,%ECX

0x421043 JLE	421091

0x421045 MOV	$-0x2,%EDI

0x42104a AND	%RDX,%RDI

0x42104d JE	4210a1

0x42104f LEA	(%RAX,%RSI,8),%R8

0x421053 XORPD	%XMM2,%XMM2

0x421057 XOR	%R9D,%R9D

0x42105a NOPW	(%RAX,%RAX,1)

(264) 0x421060 MOVUPD	(%R8,%R9,8),%XMM1

(264) 0x421066 MOVUPD	(%R13,%R9,8),%XMM3

(264) 0x42106d MULPD	%XMM1,%XMM3

(264) 0x421071 ADDPD	%XMM3,%XMM2

(264) 0x421075 ADD	$0x2,%R9

(264) 0x421079 CMP	%RDI,%R9

(264) 0x42107c JB	421060

0x42107e MOVAPD	%XMM2,%XMM1

0x421082 UNPCKHPD	%XMM2,%XMM1

0x421086 ADDSD	%XMM2,%XMM1

0x42108a CMP	%RDX,%RDI

0x42108d JNE	4210a7

0x42108f JMP	4210c9

0x421091 MOVQ	$0,0xc8(%R15)

0x42109c JMP	421131

0x4210a1 XOR	%EDI,%EDI

0x4210a3 XORPD	%XMM1,%XMM1

0x4210a7 LEA	(%RAX,%RSI,8),%R8

0x4210ab NOPL	(%RAX,%RAX,1)

(263) 0x4210b0 MOVSD	(%R8,%RDI,8),%XMM2

(263) 0x4210b6 MULSD	(%R13,%RDI,8),%XMM2

(263) 0x4210bd ADDSD	%XMM2,%XMM1

(263) 0x4210c1 INC	%RDI

(263) 0x4210c4 CMP	%RDI,%RDX

(263) 0x4210c7 JNE	4210b0

0x4210c9 MOVSD	%XMM1,0xc8(%R15)

0x4210d2 TEST	%EDX,%EDX

0x4210d4 JLE	421131

0x4210d6 MOV	$-0x2,%EDI

0x4210db AND	%RDX,%RDI

0x4210de JE	421137

0x4210e0 MOV	%RSI,%R8

0x4210e3 SAL	$0x4,%R8

0x4210e7 ADD	%RAX,%R8

0x4210ea XORPD	%XMM2,%XMM2

0x4210ee XOR	%R9D,%R9D

0x4210f1 NOPW	%CS:(%RAX,%RAX,1)

(261) 0x421100 MOVUPD	(%R8,%R9,8),%XMM1

(261) 0x421106 MOVUPD	(%R13,%R9,8),%XMM3

(261) 0x42110d MULPD	%XMM1,%XMM3

(261) 0x421111 ADDPD	%XMM3,%XMM2

(261) 0x421115 ADD	$0x2,%R9

(261) 0x421119 CMP	%RDI,%R9

(261) 0x42111c JB	421100

0x42111e MOVAPD	%XMM2,%XMM1

0x421122 UNPCKHPD	%XMM2,%XMM1

0x421126 ADDSD	%XMM2,%XMM1

0x42112a CMP	%RDX,%RDI

0x42112d JNE	42113d

0x42112f JMP	421168

0x421131 XORPD	%XMM1,%XMM1

0x421135 JMP	421168

0x421137 XOR	%EDI,%EDI

0x421139 XORPD	%XMM1,%XMM1

0x42113d SAL	$0x4,%RSI

0x421141 ADD	%RSI,%RAX

0x421144 NOPW	%CS:(%RAX,%RAX,1)

(260) 0x421150 MOVSD	(%RAX,%RDI,8),%XMM2

(260) 0x421155 MULSD	(%R13,%RDI,8),%XMM2

(260) 0x42115c ADDSD	%XMM2,%XMM1

(260) 0x421160 INC	%RDI

(260) 0x421163 CMP	%RDI,%RDX

(260) 0x421166 JNE	421150

0x421168 MOVSD	%XMM1,0xd0(%R15)

0x421171 MOVSD	%XMM0,0xb8(%R15)

0x42117a LEA	(,%RCX,8),%RAX

0x421182 TEST	%RAX,%RAX

0x421185 JE	42122c

0x42118b MOV	0x100(%R15),%RAX

0x421192 XORPD	%XMM1,%XMM1

0x421196 CMP	$0x8,%ECX

0x421199 JB	4211e8

0x42119b MOV	%RCX,%RDX

0x42119e SHR	$0x3,%RDX

0x4211a2 MOV	%RAX,%RSI

0x4211a5 NOPW	%CS:(%RAX,%RAX,1)

(259) 0x4211b0 MOVUPD	(%RSI),%XMM0

(259) 0x4211b4 MOVUPD	0x10(%RSI),%XMM2

(259) 0x4211b9 MOVUPD	0x20(%RSI),%XMM3

(259) 0x4211be ADDPD	%XMM0,%XMM3

(259) 0x4211c2 MOVUPD	0x30(%RSI),%XMM0

(259) 0x4211c7 ADDPD	%XMM2,%XMM0

(259) 0x4211cb ADDPD	%XMM3,%XMM0

(259) 0x4211cf MOVAPD	%XMM0,%XMM2

(259) 0x4211d3 UNPCKHPD	%XMM0,%XMM2

(259) 0x4211d7 ADDSD	%XMM0,%XMM2

(259) 0x4211db ADDSD	%XMM2,%XMM1

(259) 0x4211df ADD	$0x40,%RSI

(259) 0x4211e3 DEC	%RDX

(259) 0x4211e6 JNE	4211b0

0x4211e8 MOV	%ECX,%EDX

0x4211ea AND	$0x7,%EDX

0x4211ed DEC	%RDX

0x4211f0 CMP	$0x6,%RDX

0x4211f4 JA	421230

0x4211f6 AND	$-0x8,%RCX

0x4211fa JMP	0x517a80(,%RDX,8)

0x421201 ADDSD	0x30(%RAX,%RCX,8),%XMM1

0x421207 ADDSD	0x28(%RAX,%RCX,8),%XMM1

0x42120d ADDSD	0x20(%RAX,%RCX,8),%XMM1

0x421213 ADDSD	0x18(%RAX,%RCX,8),%XMM1

0x421219 ADDSD	0x10(%RAX,%RCX,8),%XMM1

0x42121f ADDSD	0x8(%RAX,%RCX,8),%XMM1

0x421225 ADDSD	(%RAX,%RCX,8),%XMM1

0x42122a JMP	421230

0x42122c XORPD	%XMM1,%XMM1

0x421230 MOV	-0x2c(%RBP),%EAX

0x421233 MOVSD	%XMM1,0xb0(%R15)

0x42123c MOVSD	(%R14),%XMM0

0x421241 MOVSD	0x8(%R14),%XMM2

0x421247 ADDSD	0xc0(%R15),%XMM0

0x421250 MOVSD	%XMM0,(%R14)

0x421255 ADDSD	0xc8(%R15),%XMM2

0x42125e MOVSD	%XMM2,0x8(%R14)

0x421264 MOVSD	0x10(%R14),%XMM0

0x42126a ADDSD	0xd0(%R15),%XMM0

0x421273 MOVSD	%XMM0,0x10(%R14)

0x421279 CLTQ

0x42127b MOV	0xf0(%R15),%RCX

0x421282 MOVSD	(%RCX,%RAX,8),%XMM0

0x421287 SUBSD	%XMM1,%XMM0

0x42128b CALL	4f1fd0 <exp>

0x421290 ADD	$0x8,%RSP

0x421294 POP	%RBX

0x421295 POP	%R12

0x421297 POP	%R13

0x421299 POP	%R14

0x42129b POP	%R15

0x42129d POP	%RBP

0x42129e RET

0x42129f NOP

Path /

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

Source file and lines	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94

Warnings:
Ignoring paths for analysis

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 30.67 to 11.17 cycles (2.75x speedup).

Workaround

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

Vectorization

Your function is probably not vectorized. Only 14% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your function, you can lower the cost of an iteration from 30.67 to 2.50 cycles (12.27x speedup).

Details

Store and arithmetical 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 function can use their full power.

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

Calling (and then returning from) a function prevents many compiler optimizations (like vectorization), breaks control flow (which reduces pipeline performance) and executes extra instructions to save/restore the registers used inside it, which is very expensive (dozens of cycles). Consider to inline small functions.

_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd: 1 occurrences
_ZNK11qmcplusplus11ParticleSet14getDistTableABEi: 2 occurrences
exp: 1 occurrences

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.

JMP: 1 occurrences
LEA: 1 occurrences

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

15 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 function (in the source code) and the binary function

The binary function is composed of 15 FP arithmetical operations:

15: addition or subtraction

The binary function is loading 192 bytes (24 double precision FP elements). The binary function is storing 88 bytes (11 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.05 FP operations per loaded or stored byte.

General properties

nb instructions	187
nb uops	184
loop length	765
used x86 registers	14
used mmx registers	0
used xmm registers	3
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.67 cycles
front end	30.67 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	16.50	15.00	15.00	15.00	16.50	14.33	14.33	14.33	0.00	4.00	7.50	7.50	4.00	4.00
cycles	16.50	15.00	15.00	15.00	16.50	14.33	14.33	14.33	0.00	4.00	7.50	7.50	4.00	4.00

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	30.67
Dispatch	16.50
Overall L1	30.67

Vectorization ratios

INT

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

all	35%
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	80%

INT+FP

all	22%
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	41%

Vector efficiency ratios

INT

all	10%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	16%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	14%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 30.67 cycles. At this rate:

6% of peak load performance is reached (6.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (2.87 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 30.67 to 16.50 cycles (1.86x speedup).

ASM code

In the binary file, the address of the function is: 420e40

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
MOV 0xa8(%RDI),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x90(%RAX),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 423670 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x118(%R15),%R13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x130(%R15),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xa8(%R15),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOVSXD 0x90(%R15),%RCX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33
MOV %ECX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST %RCX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 420ef4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xb4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%ESI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 420efa <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xba>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOVAPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 420f00 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xc0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 420f1c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xdc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 420f1c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xdc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0xa8(%RAX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xb8(%RAX),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
LEA 0xc0(%R15),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
TEST %RSI,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV $0,%R9D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMOVG %RSI,%R9	1	0.50	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50
LEA (%RDX,%R9,2),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA -0x8(%RAX,%R9,8),%R9	2	0	0	0.50	0.50	0	0.33	0.33	0.33	0	0	0	0	0	0	2	0.50
CMOVS %RSI,%RDI	1	0.50	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50
CMP %R8,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 420fbb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17b>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA 0xd0(%R15),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SAL $0x4,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RAX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP %RDI,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 420fbb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17b>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
SAL $0x3,%RSI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 420f8e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x14e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421001 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1c1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 421015 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d5>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 421020 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 421038 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
MOVQ $0,0xc0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 4210c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x289>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xc0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421091 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x251>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4210a1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x261>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA (%RAX,%RSI,8),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 4210a7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x267>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 4210c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x289>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
MOVQ $0,0xc8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
JMP 421131 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA (%RAX,%RSI,8),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xc8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
TEST %EDX,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421131 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 421137 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %RSI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SAL $0x4,%R8	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RAX,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 42113d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2fd>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 421168 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x328>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 421168 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x328>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SAL $0x4,%RSI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RSI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xd0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA (,%RCX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
TEST %RAX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 42122c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3ec>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV 0x100(%R15),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP $0x8,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 4211e8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SHR $0x3,%RDX	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %ECX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
AND $0x7,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
DEC %RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP $0x6,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JA 421230 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3f0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
AND $-0x8,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JMP 0x517a80(,%RDX,8)	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	1
ADDSD 0x30(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x28(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x20(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x18(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x10(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x8(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD (%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
JMP 421230 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3f0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV -0x2c(%RBP),%EAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD %XMM1,0xb0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD (%R14),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOVSD 0x8(%R14),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
ADDSD 0xc0(%R15),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM0,(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
ADDSD 0xc8(%R15),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM2,0x8(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD 0x10(%R14),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
ADDSD 0xd0(%R15),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM0,0x10(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
CLTQ
MOV 0xf0(%R15),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD (%RCX,%RAX,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
SUBSD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CALL 4f1fd0 <exp>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
ADD $0x8,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09

Source file and lines	OneBodyJastrowRef.h:186-263
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h:273
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h:169
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h:186-194,256-263
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_numeric.h:140-141
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:223,249
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1169
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h:1028,1182
/beegfs/hackathon/users/eoseret/qaas_runs/170-855-3059/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Workaround

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

Vectorization

Details

Workaround

Try another compiler or update/tune your current one
Make array accesses unit-stride:
- If your function 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

CALL instructions

Detected function call instructions.

Details

_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd: 1 occurrences
_ZNK11qmcplusplus11ParticleSet14getDistTableABEi: 2 occurrences
exp: 1 occurrences

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.

JMP: 1 occurrences
LEA: 1 occurrences

Conversion instructions

Detected expensive conversion instructions.

Details

CLTQ: 1 occurrences

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

15 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 function (in the source code) and the binary function

The binary function is composed of 15 FP arithmetical operations:

15: addition or subtraction

The binary function is loading 192 bytes (24 double precision FP elements). The binary function is storing 88 bytes (11 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.05 FP operations per loaded or stored byte.

General properties

nb instructions	187
nb uops	184
loop length	765
used x86 registers	14
used mmx registers	0
used xmm registers	3
used ymm registers	0
used zmm registers	0
nb stack references	1

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	30.67 cycles
front end	30.67 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	16.50	15.00	15.00	15.00	16.50	14.33	14.33	14.33	0.00	4.00	7.50	7.50	4.00	4.00
cycles	16.50	15.00	15.00	15.00	16.50	14.33	14.33	14.33	0.00	4.00	7.50	7.50	4.00	4.00

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	30.67
Dispatch	16.50
Overall L1	30.67

Vectorization ratios

INT

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

all	35%
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	80%

INT+FP

all	22%
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	41%

Vector efficiency ratios

INT

all	10%
load	12%
store	6%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	16%
load	12%
store	12%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	22%

INT+FP

all	14%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 30.67 cycles. At this rate:

6% of peak load performance is reached (6.26 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
4% of peak store performance is reached (2.87 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 420e40

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EDX,%EBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %RDI,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOVL $0x2,0xc(%RDI)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
MOV 0xa8(%RDI),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x90(%RAX),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R15,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
MOV %EBX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 423670 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERNS1_11ParticleSetEiPKd>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOV 0x118(%R15),%R13	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0x130(%R15),%RBX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xa8(%R15),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CALL 462dd0 <_ZNK11qmcplusplus11ParticleSet14getDistTableABEi>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
MOVSXD 0x90(%R15),%RCX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.33
MOV %ECX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
TEST %RCX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 420ef4 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xb4>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%ESI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 420efa <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xba>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOVAPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 420f00 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xc0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 420f1c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xdc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 420f1c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0xdc>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV 0xa8(%RAX),%RSI	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOV 0xb8(%RAX),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
LEA 0xc0(%R15),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
TEST %RSI,%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
MOV $0,%R9D	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMOVG %RSI,%R9	1	0.50	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50
LEA (%RDX,%R9,2),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
LEA -0x8(%RAX,%R9,8),%R9	2	0	0	0.50	0.50	0	0.33	0.33	0.33	0	0	0	0	0	0	2	0.50
CMOVS %RSI,%RDI	1	0.50	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1	0.50
CMP %R8,%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 420fbb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17b>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA 0xd0(%R15),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
SAL $0x4,%RDI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RAX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP %RDI,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 420fbb <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x17b>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
SAL $0x3,%RSI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
JMP 420f8e <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x14e>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421001 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1c1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 421015 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1d5>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 421020 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1e0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 421038 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x1f8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
MOVQ $0,0xc0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 4210c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x289>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xc0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
TEST %ECX,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421091 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x251>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 4210a1 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x261>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
LEA (%RAX,%RSI,8),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 4210a7 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x267>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 4210c9 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x289>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
MOVQ $0,0xc8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	4	0.50
JMP 421131 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
LEA (%RAX,%RSI,8),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xc8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
TEST %EDX,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JLE 421131 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f1>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV $-0x2,%EDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
AND %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 421137 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2f7>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %RSI,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SAL $0x4,%R8	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RAX,%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
XORPD %XMM2,%XMM2	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVAPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
UNPCKHPD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	1	0.40
ADDSD %XMM2,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CMP %RDX,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JNE 42113d <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x2fd>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
JMP 421168 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x328>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
JMP 421168 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x328>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SAL $0x4,%RSI	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ADD %RSI,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOVSD %XMM1,0xd0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD %XMM0,0xb8(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
LEA (,%RCX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
TEST %RAX,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JE 42122c <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3ec>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV 0x100(%R15),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
CMP $0x8,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JB 4211e8 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3a8>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
SHR $0x3,%RDX	1	0	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09
MOV %ECX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
AND $0x7,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
DEC %RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
CMP $0x6,%RDX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JA 421230 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3f0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50-1
AND $-0x8,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
JMP 0x517a80(,%RDX,8)	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	1
ADDSD 0x30(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x28(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x20(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x18(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x10(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD 0x8(%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
ADDSD (%RAX,%RCX,8),%XMM1	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
JMP 421230 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x3f0>	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	0	1
XORPD %XMM1,%XMM1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17
MOV -0x2c(%RBP),%EAX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD %XMM1,0xb0(%R15)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD (%R14),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
MOVSD 0x8(%R14),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
ADDSD 0xc0(%R15),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM0,(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
ADDSD 0xc8(%R15),%XMM2	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM2,0x8(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
MOVSD 0x10(%R14),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
ADDSD 0xd0(%R15),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0.50	0.50	0	0	3	0.50
MOVSD %XMM0,0x10(%R14)	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0.50	0.50	1	1
CLTQ
MOV 0xf0(%R15),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	3	0.33
MOVSD (%RCX,%RAX,8),%XMM0	1	0	0	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	1	0.50
SUBSD %XMM1,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	0.50
CALL 4f1fd0 <exp>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0	0	0	0	0	0	0.50
ADD $0x8,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33
RET	1	0.50	0	0	0	0.50	0	0	0	0	0	0	0	0	0	1	0.50
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09

Name	Coverage (%)	Time (s)
▼_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE–	0.04	0.08
○Loop 264 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.02
○Loop 265 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.02
○Loop 269 - OneBodyJastrowRef.h:186-187 - exec	0.01	0.01
○Loop 261 - OneBodyJastrowRef.h:192-193 - exec	0.01	0.01
○Loop 259 - stl_numeric.h:140-141 - exec	0	0
○Loop 263 - OneBodyJastrowRef.h:192-193 - exec	0	0
○Loop 260 - OneBodyJastrowRef.h:192-193 - exec	0	0
○Loop 268 - OneBodyJastrowRef.h:186-187 - exec	0	0
○Loop 262 - OneBodyJastrowRef.h:192-193 - exec	0	0
▼Loop 266 - OneBodyJastrowRef.h:186-194 - exec–	0	0
○Loop 267 - OneBodyJastrowRef.h:192-193 - exec	0	0

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

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

CALL instructions

Details

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

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

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code