OV - exec - Loop 134

0x40d578 LDR	X1, [X23, #16]

0x40d57c ADD	X21, X23, #16

0x40d580 MOVZ	X20, #0

0x40d584 ADD	X26, SP, #80

0x40d588 ADD	X23, X23, #88

0x40d58c LDR	X2, [X21, #8]

0x40d590 CMP	X1, X2

0x40d594 B.EQ	40d610

0x40d598 HINT	#0

0x40d59c HINT	#0

  (135) 0x40d5a0 LDR	X8, [X23]

  (135) 0x40d5a4 LDR	X22, [X8, X20,LSL #3]

  (135) 0x40d5a8 ORR	X0, XZR, X22

  (135) 0x40d5ac BL	479f20

  (135) 0x40d5b0 LDR	X10, [X21]

  (135) 0x40d5b4 ORR	X8, XZR, X26

  (135) 0x40d5b8 ORR	W2, WZR, W24

  (135) 0x40d5bc ORR	X1, XZR, X25

  (135) 0x40d5c0 LDR	X0, [X10, X20,LSL #3]

  (135) 0x40d5c4 LDR	X11, [X0]

  (135) 0x40d5c8 LDR	X12, [X11, #24]

  (135) 0x40d5cc BLR	X12

  (135) 0x40d5d0 LDP	D2, D1, [X19]

  (135) 0x40d5d4 ORR	X0, XZR, X22

  (135) 0x40d5d8 ADD	X20, X20, #1

  (135) 0x40d5dc LDR	D0, [X19, #16]

  (135) 0x40d5e0 LDP	D5, D4, [SP, #80]

  (135) 0x40d5e4 LDR	D3, [SP, #96]

  (135) 0x40d5e8 FADD	D6, D2, D5

  (135) 0x40d5ec FADD	D7, D1, D4

  (135) 0x40d5f0 FADD	D16, D0, D3

  (135) 0x40d5f4 STP	D6, D7, [X19]

  (135) 0x40d5f8 STR	D16, [X19, #16]

  (135) 0x40d5fc BL	47a180

  (135) 0x40d600 LDP	X13, X14, [X21]

  (135) 0x40d604 SUB	X15, X14, X13

  (135) 0x40d608 CMP	X20, X15,ASR #3

  (135) 0x40d60c B.CC	40d5a0

0x40d610 ADRP	X16,

0x40d614 LDR	X17, [X16, #4016]

0x40d618 LDR	X2, [SP, #104]

0x40d61c LDR	X1, [X17]

0x40d620 SUBS	X2, X2, X1

0x40d624 MOVZ	X1, #0

0x40d628 B.NE	40d65c

0x40d62c ORR	X0, XZR, X19

0x40d630 LDP	X19, X20, [SP, #16]

0x40d634 LDP	X21, X22, [SP, #32]

0x40d638 LDP	X23, X24, [SP, #48]

0x40d63c LDP	X25, X26, [SP, #64]

0x40d640 LDP	X29, X30, [SP], #112

0x40d644 RET

0x40d648 LDR	X0, [X23, #8]

0x40d64c LDR	X5, [X0]

0x40d650 LDR	X6, [X5, #24]

0x40d654 BLR	X6

0x40d658 B	40d578

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 94

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

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

/usr/include/c++/11/bits/refwrap.h: 338 - 338

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

338:       { return *_M_data; }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp: 189 - 197

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

189:   posT grad_iat = (iat < nelup ? Det_up->evalGrad(P, iat) : Det_dn->evalGrad(P, iat));

190:

191:   for (size_t i = 0; i < Jastrows.size(); i++)

192:   {

193:     ScopedTimer local_timer(jastrow_timers[i]);

194:     grad_iat += Jastrows[i]->evalGrad(P, iat);

195:   }

196:   return grad_iat;

197: }

/usr/include/c++/11/bits/stl_vector.h: 919 - 919

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

919:       { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); }

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249

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

242:   ScopeGuard(TIMER& t) : timer(t) { timer.start(); }

[...]

249:   ~ScopeGuard() { timer.stop(); }

Coverage (%)	Name	Source Location	Module
►100.00+	main._omp_fn.1	refwrap.h:337	exec
○	GOMP_parallel		libomp.so
○	main	miniqmc.cpp:404	exec
○	__libc_start_main		libc-2.31.so
○	_start	miniqmc.cpp:546	exec

Path /

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.28
Bottlenecks	P10, P11, P12,
Function	qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int)
Source	WaveFunction.cpp:189-191,WaveFunction.cpp:197-197,stl_vector.h:919-919
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.33
CQA cycles if no scalar integer	4.33
CQA cycles if FP arith vectorized	4.33
CQA cycles if fully vectorized	1.08
Front-end cycles	3.38
DIV/SQRT cycles	2.50
P0 cycles	2.50
P1 cycles	2.50
P2 cycles	2.50
P3 cycles	2.50
P4 cycles	2.50
P5 cycles	0.00
P6 cycles	0.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	4.33
P10 cycles	4.33
P11 cycles	4.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	29.00
Nb uops	27.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	33.23
Bytes prefetched	0.00
Bytes loaded	144.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	NA
Vectorization ratio store	NA
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	25.00
Vector-efficiency ratio load	NA
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	25.00

Metric	Value
CQA speedup if no scalar integer	1.00
CQA speedup if FP arith vectorized	1.00
CQA speedup if fully vectorized	4.00
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.28
Bottlenecks	P10, P11, P12,
Function	qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int)
Source	WaveFunction.cpp:189-191,WaveFunction.cpp:197-197,stl_vector.h:919-919
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	4.33
CQA cycles if no scalar integer	4.33
CQA cycles if FP arith vectorized	4.33
CQA cycles if fully vectorized	1.08
Front-end cycles	3.38
DIV/SQRT cycles	2.50
P0 cycles	2.50
P1 cycles	2.50
P2 cycles	2.50
P3 cycles	2.50
P4 cycles	2.50
P5 cycles	0.00
P6 cycles	0.00
P7 cycles	0.00
P8 cycles	0.00
P9 cycles	4.33
P10 cycles	4.33
P11 cycles	4.33
P12 cycles	0.00
P13 cycles	0.00
P14 cycles	0.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	29.00
Nb uops	27.00
Nb loads	NA
Nb stores	0.00
Nb stack references	0.00
FLOP/cycle	0.00
Nb FLOP add-sub	0.00
Nb FLOP mul	0.00
Nb FLOP fma	0.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	33.23
Bytes prefetched	0.00
Bytes loaded	144.00
Bytes stored	0.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	NA
Vectorization ratio store	NA
Vectorization ratio mul	NA
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	NA
Vectorization ratio other	0.00
Vector-efficiency ratio all	25.00
Vector-efficiency ratio load	NA
Vector-efficiency ratio store	NA
Vector-efficiency ratio mul	NA
Vector-efficiency ratio add_sub	25.00
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	NA
Vector-efficiency ratio other	25.00

Path /

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

Function	qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int)
Source file and lines	WaveFunction.cpp:189-197
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/usr/include/c++/11/bits/refwrap.h:338
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp:189-197
/usr/include/c++/11/bits/stl_vector.h:919
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths

gain
potential
hint
expert

Vectorization

Your loop is not vectorized. 4 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 4.33 to 1.08 cycles (4.00x speedup).

Details

All VPU 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 ftree-vectorize (included in O3) to enable loop vectorization (including 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 4.33 to 0.50 cycles (8.67x speedup).

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 144 bytes.

General properties

nb instructions	29
loop length	116
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.50	2.50	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	4.33	4.33	4.33	0.00	0.00
cycles	2.50	2.50	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	4.33	4.33	4.33	0.00	0.00

Cycles executing div or sqrt instructions

NA

Cycles summary

Front-end	3.38
Overall L1	4.33

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.33 cycles. At this rate:

34% of peak load performance is reached (33.23 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 40d648

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR X1, [X23, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X21, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X20, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X26, SP, #80	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X23, X23, #88	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X2, [X21, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X1, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 40d610 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0xf0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
ADRP X16, <4c1610>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X17, [X16, #4016]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X2, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X1, [X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUBS X2, X2, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
MOVZ X1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B.NE 40d65c <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X23, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X5, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X6, [X5, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X6	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
B 40d578 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0x58>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Function	qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int)
Source file and lines	WaveFunction.cpp:189-197
Module	exec

The loop is defined in:

/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h:94
/usr/include/c++/11/bits/refwrap.h:338
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp:189-197
/usr/include/c++/11/bits/stl_vector.h:919
/home/hbollore/qaas/qaas-runs/169-816-8620/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:242,249

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths
RecMII not computed since number of paths is unknown or > max_paths

gain
potential
hint
expert

Vectorization

Your loop is not vectorized. 4 data elements could be processed at once in vector registers. By vectorizing your loop, you can lower the cost of an iteration from 4.33 to 1.08 cycles (4.00x speedup).

Details

All VPU 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 ftree-vectorize (included in O3) to enable loop vectorization (including 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)

Expensive FP math instructions/calls

Detected performance impact from expensive FP math instructions/calls. By removing/reexpressing them, you can lower the cost of an iteration from 4.33 to 0.50 cycles (8.67x speedup).

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

The binary loop does not contain any FP arithmetical operations. The binary loop is loading 144 bytes.

General properties

nb instructions	29
loop length	116
nb stack references	0

Front-end

FIT IN UOP CACHE

front end

3.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14
uops	2.50	2.50	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	4.33	4.33	4.33	0.00	0.00
cycles	2.50	2.50	2.50	2.50	2.50	2.50	0.00	0.00	0.00	0.00	4.33	4.33	4.33	0.00	0.00

Cycles executing div or sqrt instructions

NA

Cycles summary

Front-end	3.38
Overall L1	4.33

Vectorization ratios

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

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 4.33 cycles. At this rate:

34% of peak load performance is reached (33.23 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))

ASM code

In the binary file, the address of the loop is: 40d648

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	Latency	Recip. throughput
LDR X1, [X23, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
ADD X21, X23, #16	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
MOVZ X20, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X26, SP, #80	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
ADD X23, X23, #88	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X2, [X21, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
CMP X1, X2	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
B.EQ 40d610 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0xf0>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
HINT #0
HINT #0
ADRP X16, <4c1610>	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDR X17, [X16, #4016]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X2, [SP, #104]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X1, [X17]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
SUBS X2, X2, X1	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.33
MOVZ X1, #0	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
B.NE 40d65c <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0x13c>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
ORR X0, XZR, X19	1	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0	0	1	0.25
LDP X19, X20, [SP, #16]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X21, X22, [SP, #32]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X23, X24, [SP, #48]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X25, X26, [SP, #64]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
LDP X29, X30, [SP], #112	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	1
RET	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50
LDR X0, [X23, #8]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X5, [X0]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
LDR X6, [X5, #24]	1	0	0	0	0	0	0	0	0	0	0	0.33	0.33	0.33	0	0	4	0.33
BLR X6	1	0.50	0.50	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	1	0.50
B 40d578 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi+0x58>	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0.50

Report Configuration

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code

Vectorization

Details

Workaround

Expensive FP math instructions/calls

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

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Cycles and memory resources usage

ASM code