OV - exec - Function qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<double, std::allocator<double> > const&, std::vector<double, std::allocator<double> >&)

	Function: qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus ...	Module: exec	Source: SPOSet.h:81-88 [...]	Coverage (incl. loops): 0.05% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 82 - 83

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

82:   for (int i = 0; i < n; i++)

83:     res += a[i] * b[i];

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1046 - 1046

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

1046: 	return *(this->_M_impl._M_start + __n);

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h: 81 - 88

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

81:   {

82:     assert(psi.size() == psiinv.size());

83:     for (int iat = 0; iat < VP.getTotalNum(); ++iat)

84:     {

85:       evaluate(VP, iat, psi);

86:       ratios[iat] = simd::dot(psi.data(), psiinv.data(), psi.size());

87:     }

88:   }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 178 - 178

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

178:   inline size_t size() const { return nLocal; }

0x252030 PUSH	%RBP

0x252031 MOV	%RSP,%RBP

0x252034 PUSH	%R15

0x252036 PUSH	%R14

0x252038 PUSH	%R13

0x25203a PUSH	%R12

0x25203c PUSH	%RBX

0x25203d PUSH	%RAX

0x25203e CMPQ	$0,0x260(%RSI)

0x252046 MOV	%RCX,-0x30(%RBP)

0x25204a JE	252168

0x252050 MOV	%R8,%RBX

0x252053 MOV	%RDX,%R15

0x252056 MOV	%RSI,%R12

0x252059 MOV	%RDI,%R13

0x25205c XOR	%R14D,%R14D

0x25205f JMP	25208e

0x252061 NOPW	%CS:(%RAX,%RAX,1)

(693) 0x252070 VXORPD	%XMM0,%XMM0,%XMM0

(693) 0x252074 MOV	(%RBX),%RAX

(693) 0x252077 VMOVSD	%XMM0,(%RAX,%R14,8)

(693) 0x25207d INC	%R14

(693) 0x252080 CMP	%R14,0x260(%R12)

(693) 0x252088 JBE	252168

(693) 0x25208e MOV	(%R13),%RAX

(693) 0x252092 MOV	%R13,%RDI

(693) 0x252095 MOV	%R12,%RSI

(693) 0x252098 MOV	%R14D,%EDX

(693) 0x25209b MOV	%R15,%RCX

(693) 0x25209e CALLQ	0x10(%RAX)

(693) 0x2520a1 MOV	0x8(%R15),%RDX

(693) 0x2520a5 TEST	%EDX,%EDX

(693) 0x2520a7 JLE	252070

(693) 0x2520a9 MOV	-0x30(%RBP),%RCX

(693) 0x2520ad MOV	0x18(%R15),%RAX

(693) 0x2520b1 MOV	%EDX,%EDX

(693) 0x2520b3 MOV	0x18(%RCX),%RCX

(693) 0x2520b7 CMP	$0x8,%EDX

(693) 0x2520ba JAE	2520d0

(693) 0x2520bc VXORPD	%XMM0,%XMM0,%XMM0

(693) 0x2520c0 XOR	%ESI,%ESI

(693) 0x2520c2 JMP	252150

0x2520c7 NOPW	(%RAX,%RAX,1)

(693) 0x2520d0 MOV	%EDX,%EDI

(693) 0x2520d2 MOV	%EDX,%ESI

(693) 0x2520d4 AND	$0x7,%EDI

(693) 0x2520d7 AND	$-0x8,%ESI

(693) 0x2520da VXORPD	%XMM0,%XMM0,%XMM0

(693) 0x2520de VXORPD	%XMM1,%XMM1,%XMM1

(693) 0x2520e2 VXORPD	%XMM2,%XMM2,%XMM2

(693) 0x2520e6 VXORPD	%XMM3,%XMM3,%XMM3

(693) 0x2520ea XOR	%R8D,%R8D

(693) 0x2520ed NOPL	(%RAX)

  (694) 0x2520f0 VMOVUPD	(%RCX,%R8,8),%XMM4

  (694) 0x2520f6 VMOVUPD	0x10(%RCX,%R8,8),%XMM5

  (694) 0x2520fd VMOVUPD	0x20(%RCX,%R8,8),%XMM6

  (694) 0x252104 VMOVUPD	0x30(%RCX,%R8,8),%XMM7

  (694) 0x25210b VFMADD231PD	(%RAX,%R8,8),%XMM4,%XMM0

  (694) 0x252111 VFMADD231PD	0x10(%RAX,%R8,8),%XMM5,%XMM1

  (694) 0x252118 VFMADD231PD	0x20(%RAX,%R8,8),%XMM6,%XMM2

  (694) 0x25211f VFMADD231PD	0x30(%RAX,%R8,8),%XMM7,%XMM3

  (694) 0x252126 ADD	$0x8,%R8

  (694) 0x25212a CMP	%R8,%RSI

  (694) 0x25212d JNE	2520f0

(693) 0x25212f VADDPD	%XMM0,%XMM1,%XMM0

(693) 0x252133 VADDPD	%XMM2,%XMM3,%XMM1

(693) 0x252137 VADDPD	%XMM0,%XMM1,%XMM0

(693) 0x25213b VSHUFPD	$0x1,%XMM0,%XMM0,%XMM1

(693) 0x252140 VADDSD	%XMM1,%XMM0,%XMM0

(693) 0x252144 TEST	%RDI,%RDI

(693) 0x252147 JE	252074

(693) 0x25214d NOPL	(%RAX)

  (695) 0x252150 VMOVSD	(%RCX,%RSI,8),%XMM1

  (695) 0x252155 VFMADD231SD	(%RAX,%RSI,8),%XMM1,%XMM0

  (695) 0x25215b INC	%RSI

  (695) 0x25215e CMP	%RSI,%RDX

  (695) 0x252161 JNE	252150

(693) 0x252163 JMP	252074

0x252168 ADD	$0x8,%RSP

0x25216c POP	%RBX

0x25216d POP	%R12

0x25216f POP	%R13

0x252171 POP	%R14

0x252173 POP	%R15

0x252175 POP	%RBP

0x252176 RET

0x252177 INT	$0x3

0x252178 INT	$0x3

0x252179 INT	$0x3

0x25217a INT	$0x3

0x25217b INT	$0x3

0x25217c INT	$0x3

0x25217d INT	$0x3

0x25217e INT	$0x3

0x25217f INT	$0x3

Coverage (%)	Name	Source Location	Module
►94.82+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►3.39+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:217	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_fork_call		libomp.so
○	__kmpc_fork_call		libomp.so
○	main	miniqmc.cpp:411	exec
○	__libc_start_call_main		libc.so.6
►1.06+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:135	exec
○	main.omp_outlined.64	NewTimer.h:249	exec
○	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so
○	__kmp_launch_thread		libomp.so
○	__kmp_launch_worker(void*)		libomp.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

min	med	avg	max

Percentile Index	10	20	30	40	50	60	70	80	90	100
Value

Path /

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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run aocc_4

Source file and lines	SPOSet.h:81-88
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1046
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:81-88
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:178

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 11% 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 3.13 to 0.21 cycles (15.16x 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 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

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 8 bytes. The binary function is storing 8 bytes.

General properties

nb instructions	36
nb uops	25
loop length	97
used x86 registers	13
used mmx registers	0
used xmm registers	0
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	3.13 cycles
front end	3.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	0.67	0.67	0.67	1.00	1.00	1.00	0.50	0.50	0.50	0.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	0.67	0.67	0.67	1.00	1.00	1.00	0.50	0.50	0.50	0.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.13
Dispatch	1.00
Overall L1	3.13

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

Vector efficiency ratios

all	11%
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	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.13 cycles. At this rate:

1% of peak load performance is reached (2.56 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.56 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 3.13 to 1.00 cycles (3.13x speedup).

ASM code

In the binary file, the address of the function is: 252030

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMPQ $0,0x260(%RSI)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
JE 252168 <_ZN11qmcplusplus6SPOSet17evaluateDetRatiosERKNS_18VirtualParticleSetERNS_6VectorIdSaIdEEERKS6_RSt6vectorIdS5_E+0x138>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R8,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 25208e <_ZN11qmcplusplus6SPOSet17evaluateDetRatiosERKNS_18VirtualParticleSetERNS_6VectorIdSaIdEEERKS6_RSt6vectorIdS5_E+0x5e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run aocc_4

Source file and lines	SPOSet.h:81-88
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp:82-83
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h:1046
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/SPOSet.h:81-88
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h:178

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

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

Type of elements and instruction set

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

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

The binary function does not contain any FP arithmetical operations. The binary function is loading 8 bytes. The binary function is storing 8 bytes.

General properties

nb instructions	36
nb uops	25
loop length	97
used x86 registers	13
used mmx registers	0
used xmm registers	0
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	3.13 cycles
front end	3.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	0.67	0.67	0.67	1.00	1.00	1.00	0.50	0.50	0.50	0.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	0.67	0.67	0.67	1.00	1.00	1.00	0.50	0.50	0.50	0.50	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	3.13
Dispatch	1.00
Overall L1	3.13

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

Vector efficiency ratios

all	11%
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	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 3.13 cycles. At this rate:

1% of peak load performance is reached (2.56 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.56 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the function is: 252030

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
PUSH %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CMPQ $0,0x260(%RSI)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
JE 252168 <_ZN11qmcplusplus6SPOSet17evaluateDetRatiosERKNS_18VirtualParticleSetERNS_6VectorIdSaIdEEERKS6_RSt6vectorIdS5_E+0x138>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %R8,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RSI,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RDI,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
XOR %R14D,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
JMP 25208e <_ZN11qmcplusplus6SPOSet17evaluateDetRatiosERKNS_18VirtualParticleSetERNS_6VectorIdSaIdEEERKS6_RSt6vectorIdS5_E+0x5e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
ADD $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A
INT $0x3																				N/A

Name	Coverage (%)	Time (s)
▼qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector >&, qmcplusplus::Vector > const&, std::vector >&)–	0.05	0.08
▼Loop 693 - inner_product.hpp:82-83 - exec–	0.00	0.01
○Loop 694 - inner_product.hpp:82-83 - exec	0.04	0.07
○Loop 695 - inner_product.hpp:82-83 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Type of elements and instruction set

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

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

Type of elements and instruction set

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code