OV - exec - Function qmcplusplus::TimerType<std::chrono::_V2::system

	Function: qmcplusplus::TimerType<std::chrono::_V2::system_clock>::stop()	Module: exec	Source: NewTimer.cpp:86-120 [...]	Coverage (incl. loops): 0.01% \| (excl. loops): 0.01%

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_tree.h: 316 - 1905

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

316:       { return __x._M_node == __y._M_node; }

[...]

735:       { return static_cast<_Link_type>(this->_M_impl._M_header._M_parent); }

[...]

780:       { return static_cast<_Link_type>(__x->_M_left); }

[...]

788:       { return static_cast<_Link_type>(__x->_M_right); }

[...]

1904:       while (__x != 0)

1905: 	if (!_M_impl._M_key_compare(_S_key(__x), __k))

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono: 227 - 666

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

227: 	      static_cast<_CR>(__d.count()) / static_cast<_CR>(_CF::den)));

[...]

666: 	return __cd(__cd(__lhs).count() - __cd(__rhs).count());

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp: 86 - 120

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

86:   if (active)

[...]

99:     for (int level = omp_get_level(); level > 0; level--)

100:       if (omp_get_ancestor_thread_num(level) != 0)

101:         is_true_master = false;

102:     if (is_true_master)

103:     {

104:       std::chrono::duration<double> elapsed = CLOCK::now() - start_time;

105:       total_time += elapsed.count();

106:       num_calls++;

107:

108:       per_stack_total_time[current_stack_key] += elapsed.count();

109:       per_stack_num_calls[current_stack_key] += 1;

110:

111:       if (manager)

112:         manager->pop_timer(this);

[...]

120: }

/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 119 - 121

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

119:       if (!(this->long_buckets[j] == rhs.long_buckets[j]))

120:       {

121:         return this->long_buckets[j] < rhs.long_buckets[j];

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h: 499 - 501

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

499: 	if (__i == end() || key_comp()(__k, (*__i).first))

500: #if __cplusplus >= 201103L

501: 	  __i = _M_t._M_emplace_hint_unique(__i, std::piecewise_construct,

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/tuple: 193 - 193

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

193:       : _M_head_impl(__h) { }

0x2a2400 CMPB	$0,0x38(%RDI)

0x2a2404 JE	2a25ed

0x2a240a PUSH	%RBP

0x2a240b MOV	%RSP,%RBP

0x2a240e PUSH	%R15

0x2a2410 PUSH	%R14

0x2a2412 PUSH	%R12

0x2a2414 PUSH	%RBX

0x2a2415 SUB	$0x20,%RSP

0x2a2419 MOV	%RDI,%RBX

0x2a241c CALL	2f7240 <@plt_start@+0x600>

0x2a2421 TEST	%EAX,%EAX

0x2a2423 JLE	2a2459

0x2a2425 MOV	$0x1,%R15B

0x2a2428 MOV	%EAX,%R14D

0x2a242b XOR	%R12D,%R12D

0x2a242e XCHG	%AX,%AX

(1528) 0x2a2430 MOV	%R14D,%EDI

(1528) 0x2a2433 CALL	2f7250 <@plt_start@+0x610>

(1528) 0x2a2438 TEST	%EAX,%EAX

(1528) 0x2a243a MOVZX	%R15B,%R15D

(1528) 0x2a243e LEA	-0x1(%R14),%EAX

(1528) 0x2a2442 CMOVNE	%R12D,%R15D

(1528) 0x2a2446 CMP	$0x1,%R14D

(1528) 0x2a244a MOV	%EAX,%R14D

(1528) 0x2a244d JG	2a2430

0x2a244f TEST	$0x1,%R15B

0x2a2453 JE	2a25e1

0x2a2459 CALL	2f7260 <@plt_start@+0x620>

0x2a245e SUB	(%RBX),%RAX

0x2a2461 LEA	0x50(%RBX),%R14

0x2a2465 LEA	0x70(%RBX),%RSI

0x2a2469 VCVTSI2SD	%RAX,%XMM0,%XMM0

0x2a246e VMULSD	-0x9e296(%RIP),%XMM0,%XMM1

0x2a2476 VADDSD	0x8(%RBX),%XMM1,%XMM0

0x2a247b VMOVSD	%XMM0,0x8(%RBX)

0x2a2480 INCQ	0x10(%RBX)

0x2a2484 MOV	0x78(%RBX),%RDI

0x2a2488 TEST	%RDI,%RDI

0x2a248b JE	2a24fd

0x2a248d MOV	0x50(%RBX),%RCX

0x2a2491 MOV	0x58(%RBX),%RDX

0x2a2495 MOV	%RSI,%RAX

0x2a2498 JMP	2a24af

0x2a249a NOPW	(%RAX,%RAX,1)

(1527) 0x2a24a0 LEA	0x10(%RDI),%R8

(1527) 0x2a24a4 MOV	%RDI,%RAX

(1527) 0x2a24a7 MOV	(%R8),%RDI

(1527) 0x2a24aa TEST	%RDI,%RDI

(1527) 0x2a24ad JE	2a24db

(1527) 0x2a24af MOV	0x20(%RDI),%R8

(1527) 0x2a24b3 MOV	%RCX,%R9

(1527) 0x2a24b6 CMP	%RCX,%R8

(1527) 0x2a24b9 JNE	2a24c7

(1527) 0x2a24bb MOV	0x28(%RDI),%R8

(1527) 0x2a24bf MOV	%RDX,%R9

(1527) 0x2a24c2 CMP	%RDX,%R8

(1527) 0x2a24c5 JE	2a24a0

(1527) 0x2a24c7 CMP	%R9,%R8

(1527) 0x2a24ca JGE	2a24a0

(1527) 0x2a24cc ADD	$0x18,%RDI

(1527) 0x2a24d0 MOV	%RDI,%R8

(1527) 0x2a24d3 MOV	(%R8),%RDI

(1527) 0x2a24d6 TEST	%RDI,%RDI

(1527) 0x2a24d9 JNE	2a24af

0x2a24db CMP	%RSI,%RAX

0x2a24de JE	2a24fd

0x2a24e0 MOV	0x20(%RAX),%RDI

0x2a24e4 CMP	%RDI,%RCX

0x2a24e7 JNE	2a24f5

0x2a24e9 MOV	0x28(%RAX),%RDI

0x2a24ed MOV	%RDX,%RCX

0x2a24f0 CMP	%RDI,%RDX

0x2a24f3 JE	2a2523

0x2a24f5 MOV	%RAX,%RSI

0x2a24f8 CMP	%RDI,%RCX

0x2a24fb JGE	2a2523

0x2a24fd LEA	0x68(%RBX),%RDI

0x2a2501 LEA	-0x98880(%RIP),%RDX

0x2a2508 LEA	-0x30(%RBP),%RCX

0x2a250c LEA	-0x21(%RBP),%R8

0x2a2510 MOV	%R14,-0x30(%RBP)

0x2a2514 VMOVSD	%XMM1,-0x38(%RBP)

0x2a2519 CALL	2a25f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_dESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>

0x2a251e VMOVSD	-0x38(%RBP),%XMM1

0x2a2523 VADDSD	0x38(%RAX),%XMM1,%XMM0

0x2a2528 LEA	0xa0(%RBX),%RSI

0x2a252f VMOVSD	%XMM0,0x38(%RAX)

0x2a2534 MOV	0xa8(%RBX),%RDI

0x2a253b TEST	%RDI,%RDI

0x2a253e JE	2a25ad

0x2a2540 MOV	0x50(%RBX),%RCX

0x2a2544 MOV	0x58(%RBX),%RDX

0x2a2548 MOV	%RSI,%RAX

0x2a254b JMP	2a255f

0x2a254d NOPL	(%RAX)

(1526) 0x2a2550 LEA	0x10(%RDI),%R8

(1526) 0x2a2554 MOV	%RDI,%RAX

(1526) 0x2a2557 MOV	(%R8),%RDI

(1526) 0x2a255a TEST	%RDI,%RDI

(1526) 0x2a255d JE	2a258b

(1526) 0x2a255f MOV	0x20(%RDI),%R8

(1526) 0x2a2563 MOV	%RCX,%R9

(1526) 0x2a2566 CMP	%RCX,%R8

(1526) 0x2a2569 JNE	2a2577

(1526) 0x2a256b MOV	0x28(%RDI),%R8

(1526) 0x2a256f MOV	%RDX,%R9

(1526) 0x2a2572 CMP	%RDX,%R8

(1526) 0x2a2575 JE	2a2550

(1526) 0x2a2577 CMP	%R9,%R8

(1526) 0x2a257a JGE	2a2550

(1526) 0x2a257c ADD	$0x18,%RDI

(1526) 0x2a2580 MOV	%RDI,%R8

(1526) 0x2a2583 MOV	(%R8),%RDI

(1526) 0x2a2586 TEST	%RDI,%RDI

(1526) 0x2a2589 JNE	2a255f

0x2a258b CMP	%RSI,%RAX

0x2a258e JE	2a25ad

0x2a2590 MOV	0x20(%RAX),%RDI

0x2a2594 CMP	%RDI,%RCX

0x2a2597 JNE	2a25a5

0x2a2599 MOV	0x28(%RAX),%RDI

0x2a259d MOV	%RDX,%RCX

0x2a25a0 CMP	%RDI,%RDX

0x2a25a3 JE	2a25cc

0x2a25a5 MOV	%RAX,%RSI

0x2a25a8 CMP	%RDI,%RCX

0x2a25ab JGE	2a25cc

0x2a25ad LEA	0x98(%RBX),%RDI

0x2a25b4 LEA	-0x98933(%RIP),%RDX

0x2a25bb LEA	-0x30(%RBP),%RCX

0x2a25bf LEA	-0x21(%RBP),%R8

0x2a25c3 MOV	%R14,-0x30(%RBP)

0x2a25c7 CALL	2a29f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_lESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>

0x2a25cc INCQ	0x38(%RAX)

0x2a25d0 MOV	0x48(%RBX),%RDI

0x2a25d4 TEST	%RDI,%RDI

0x2a25d7 JE	2a25e1

0x2a25d9 MOV	%RBX,%RSI

0x2a25dc CALL	2a7eb0 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINSt6chrono3_V212system_clockEEEE9pop_timerEPS5_>

0x2a25e1 ADD	$0x20,%RSP

0x2a25e5 POP	%RBX

0x2a25e6 POP	%R12

0x2a25e8 POP	%R14

0x2a25ea POP	%R15

0x2a25ec POP	%RBP

0x2a25ed RET

0x2a25ee INT	$0x3

0x2a25ef INT	$0x3

Coverage (%)	Name	Source Location	Module
►14.64+	qmcplusplus::ParticleSet::acce[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	miniqmc.cpp:452	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
►12.63+	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
►9.61+	main.omp_outlined.64	miniqmc.cpp:452	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
►5.14+	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:134	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
►4.58+	__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
►4.13+	qmcplusplus::ParticleSet::upda[...]	stl_vector.h:919	exec
○	qmcplusplus::NonLocalPP<double[...]	NonLocalPP.hpp:134	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
○3.91	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableABOMPTarget.h:377	exec
►3.35+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:177	exec
○	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:183	exec
○	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	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
►3.02+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►3.02+	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
►2.79+	qmcplusplus::WaveFunction::rat[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►2.01+	qmcplusplus::WaveFunction::acc[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►2.01+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:183	exec
○	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	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
►1.79+	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
○1.68	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableAAOMPTarget.h:445	exec
►1.56+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:177	exec
○	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:183	exec
○	qmcplusplus::SPOSet::evaluateD[...]	OhmmsVector.h:178	exec
○	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
○1.34	qmcplusplus::SoaDistanceTableA[...]	SoaDistanceTableABOMPTarget.h:233	exec
►1.23+	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:91	exec
○	qmcplusplus::WaveFunction::eva[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►1.23+	miniqmcreference::einspline_sp[...]	einspline_spo_ref.hpp:219	exec
○	miniqmcreference::DiracDetermi[...]	DiracDeterminantRef.cpp:100	exec
○	qmcplusplus::WaveFunction::rat[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►1.12+	qmcplusplus::WaveFunction::acc[...]	stl_vector.h:919	exec
○	main.omp_outlined.64	stl_vector.h:1046	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
►1.12+	main.omp_outlined.64	stl_vector.h:1046	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
►1.01+	qmcplusplus::ParticleSet::acce[...]	ParticleSet.cpp:395	exec
○	main.omp_outlined.64	miniqmc.cpp:452	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 0.01% of application time for run orig_0

Source file and lines	NewTimer.cpp:86-120
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_tree.h:316,735,780,788,1904-1905
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227,666
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:86,99-112,120
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:119-121
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:499-501
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/tuple:193

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 12.63 to 4.67 cycles (2.71x speedup).

Workaround

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

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 12.63 to 0.58 cycles (21.92x 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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

qmcplusplus::TimerManager
>::pop_timer(qmcplusplus::TimerType
*): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:112
std::_Rb_tree_iterator
const, double> > std::_Rb_tree
, std::pair
const, double>, std::_Select1st
const, double> >, std::less >, std::allocator const, double> > >::_M_emplace_hint_unique const&>, std::tuple<> >(std::_Rb_tree_const_iterator const, double> >, std::piecewise_construct_t const&, std::tuple const&>&&, std::tuple<>&&): 1 occurrences►
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:501
std::_Rb_tree_iterator
const, long> > std::_Rb_tree
, std::pair
const, long>, std::_Select1st
const, long> >, std::less >, std::allocator const, long> > >::_M_emplace_hint_unique const&>, std::tuple<> >(std::_Rb_tree_const_iterator const, long> >, std::piecewise_construct_t const&, std::tuple const&>&&, std::tuple<>&&): 1 occurrences►
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:501
unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:99
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:104

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.

VCVTSI2SD: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227

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

3 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 3 FP arithmetical operations:

2: addition or subtraction
1: multiply

The binary function is loading 145 bytes (18 double precision FP elements). The binary function is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	100
nb uops	101
loop length	347
used x86 registers	12
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	3
ADD-SUB / MUL ratio	2.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.63 cycles
front end	12.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.83	8.83	8.83	8.83	8.83	8.83	7.25	7.25	7.25	7.25	0.50	0.50	1.50	1.50	1.50	1.50
cycles	8.83	8.83	8.83	8.83	8.83	8.83	7.25	7.25	7.25	7.25	0.50	0.50	1.50	1.50	1.50	1.50

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	12.63
Dispatch	8.83
Overall L1	12.63

Vectorization ratios

INT

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)
other	0%

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

INT+FP

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

Vector efficiency ratios

INT

all	11%
load	10%
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)
other	11%

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

INT+FP

all	11%
load	11%
store	12%
mul	12%
add-sub	12%
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 12.63 cycles. At this rate:

4% of peak load performance is reached (11.49 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.44 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 12.63 to 8.83 cycles (1.43x speedup).

ASM code

In the binary file, the address of the function is: 2a2400

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
CMPB $0,0x38(%RDI)	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 (1.6%)
JE 2a25ed <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ed>	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
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 %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
SUB $0x20,%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
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f7240 <@plt_start@+0x600>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
TEST %EAX,%EAX	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	scal (6.3%)
JLE 2a2459 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x59>	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 $0x1,%R15B	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
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
TEST $0x1,%R15B	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
JE 2a25e1 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1e1>	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
CALL 2f7260 <@plt_start@+0x620>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
SUB (%RBX),%RAX	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	N/A
LEA 0x50(%RBX),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x70(%RBX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VCVTSI2SD %RAX,%XMM0,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (12.5%)
VMULSD -0x9e296(%RIP),%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VADDSD 0x8(%RBX),%XMM1,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,0x8(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
INCQ 0x10(%RBX)	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	0.50	scal (12.5%)
MOV 0x78(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a24fd <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xfd>	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 0x50(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x58(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2a24af <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xaf>	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 (%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
CMP %RSI,%RAX	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	scal (12.5%)
JE 2a24fd <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xfd>	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 0x20(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RCX	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	scal (12.5%)
JNE 2a24f5 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xf5>	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 0x28(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RDX	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	scal (12.5%)
JE 2a2523 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x123>	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 %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RCX	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	scal (12.5%)
JGE 2a2523 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x123>	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
LEA 0x68(%RBX),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x98880(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x21(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R14,-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%)
VMOVSD %XMM1,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
CALL 2a25f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_dESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x38(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD 0x38(%RAX),%XMM1,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
LEA 0xa0(%RBX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD %XMM0,0x38(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV 0xa8(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a25ad <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ad>	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 0x50(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x58(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2a255f <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x15f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RSI,%RAX	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	scal (12.5%)
JE 2a25ad <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ad>	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 0x20(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RCX	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	scal (12.5%)
JNE 2a25a5 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1a5>	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 0x28(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RDX	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	scal (12.5%)
JE 2a25cc <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1cc>	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 %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RCX	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	scal (12.5%)
JGE 2a25cc <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1cc>	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
LEA 0x98(%RBX),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x98933(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x21(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R14,-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%)
CALL 2a29f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_lESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
INCQ 0x38(%RAX)	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	0.50	scal (12.5%)
MOV 0x48(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a25e1 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1e1>	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 %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 2a7eb0 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINSt6chrono3_V212system_clockEEEE9pop_timerEPS5_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
ADD $0x20,%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 %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

The code analyzed by CQA in that panel excludes loops and represents 0.01% of application time for run orig_0

Source file and lines	NewTimer.cpp:86-120
Module	exec

The function is defined in:

/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_tree.h:316,735,780,788,1904-1905
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227,666
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:86,99-112,120
/home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h:119-121
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:499-501
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/tuple:193

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 12.63 to 4.67 cycles (2.71x speedup).

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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

CALL instructions

Detected function call instructions.

Details

qmcplusplus::TimerManager
>::pop_timer(qmcplusplus::TimerType
*): 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:112
std::_Rb_tree_iterator
const, double> > std::_Rb_tree
, std::pair
const, double>, std::_Select1st
const, double> >, std::less >, std::allocator const, double> > >::_M_emplace_hint_unique const&>, std::tuple<> >(std::_Rb_tree_const_iterator const, double> >, std::piecewise_construct_t const&, std::tuple const&>&&, std::tuple<>&&): 1 occurrences►
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:501
std::_Rb_tree_iterator
const, long> > std::_Rb_tree
, std::pair
const, long>, std::_Select1st
const, long> >, std::less >, std::allocator const, long> > >::_M_emplace_hint_unique const&>, std::tuple<> >(std::_Rb_tree_const_iterator const, long> >, std::piecewise_construct_t const&, std::tuple const&>&&, std::tuple<>&&): 1 occurrences►
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_map.h:501
unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:99
- /home/eoseret/qaas_runs_ZEN5/173-938-0042/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp:104

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.

VCVTSI2SD: 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227

Conversion instructions

Detected expensive conversion instructions.

Details

VCVTSI2SD (INT32/64 to FP64, scalar): 1 occurrences►
- /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/chrono:227

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

3 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 3 FP arithmetical operations:

2: addition or subtraction
1: multiply

The binary function is loading 145 bytes (18 double precision FP elements). The binary function is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.01 FP operations per loaded or stored byte.

General properties

nb instructions	100
nb uops	101
loop length	347
used x86 registers	12
used mmx registers	0
used xmm registers	2
used ymm registers	0
used zmm registers	0
nb stack references	3
ADD-SUB / MUL ratio	2.00

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	12.63 cycles
front end	12.63 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	8.83	8.83	8.83	8.83	8.83	8.83	7.25	7.25	7.25	7.25	0.50	0.50	1.50	1.50	1.50	1.50
cycles	8.83	8.83	8.83	8.83	8.83	8.83	7.25	7.25	7.25	7.25	0.50	0.50	1.50	1.50	1.50	1.50

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	12.63
Dispatch	8.83
Overall L1	12.63

Vectorization ratios

INT

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)
other	0%

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

INT+FP

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

Vector efficiency ratios

INT

all	11%
load	10%
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)
other	11%

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

INT+FP

all	11%
load	11%
store	12%
mul	12%
add-sub	12%
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 12.63 cycles. At this rate:

4% of peak load performance is reached (11.49 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.44 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: 2a2400

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
CMPB $0,0x38(%RDI)	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 (1.6%)
JE 2a25ed <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ed>	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
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 %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
SUB $0x20,%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
MOV %RDI,%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CALL 2f7240 <@plt_start@+0x600>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
TEST %EAX,%EAX	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	scal (6.3%)
JLE 2a2459 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x59>	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 $0x1,%R15B	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
MOV %EAX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
XOR %R12D,%R12D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	scal (6.3%)
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
TEST $0x1,%R15B	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
JE 2a25e1 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1e1>	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
CALL 2f7260 <@plt_start@+0x620>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
SUB (%RBX),%RAX	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	N/A
LEA 0x50(%RBX),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA 0x70(%RBX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VCVTSI2SD %RAX,%XMM0,%XMM0	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	3	1	scal (12.5%)
VMULSD -0x9e296(%RIP),%XMM0,%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
VADDSD 0x8(%RBX),%XMM1,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
VMOVSD %XMM0,0x8(%RBX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
INCQ 0x10(%RBX)	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	0.50	scal (12.5%)
MOV 0x78(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a24fd <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xfd>	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 0x50(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x58(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2a24af <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xaf>	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 (%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
CMP %RSI,%RAX	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	scal (12.5%)
JE 2a24fd <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xfd>	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 0x20(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RCX	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	scal (12.5%)
JNE 2a24f5 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0xf5>	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 0x28(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RDX	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	scal (12.5%)
JE 2a2523 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x123>	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 %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RCX	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	scal (12.5%)
JGE 2a2523 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x123>	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
LEA 0x68(%RBX),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x98880(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x21(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R14,-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%)
VMOVSD %XMM1,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
CALL 2a25f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_dESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
VMOVSD -0x38(%RBP),%XMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
VADDSD 0x38(%RAX),%XMM1,%XMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
LEA 0xa0(%RBX),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VMOVSD %XMM0,0x38(%RAX)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
MOV 0xa8(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a25ad <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ad>	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 0x50(%RBX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV 0x58(%RBX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	scal (12.5%)
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2a255f <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x15f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RSI,%RAX	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	scal (12.5%)
JE 2a25ad <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1ad>	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 0x20(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RCX	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	scal (12.5%)
JNE 2a25a5 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1a5>	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 0x28(%RAX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RDX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RDX	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	scal (12.5%)
JE 2a25cc <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1cc>	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 %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CMP %RDI,%RCX	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	scal (12.5%)
JGE 2a25cc <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1cc>	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
LEA 0x98(%RBX),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x98933(%RIP),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x30(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
LEA -0x21(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %R14,-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%)
CALL 2a29f0 <_ZNSt8_Rb_treeIN11qmcplusplus13StackKeyParamILi2EEESt4pairIKS2_lESt10_Select1stIS5_ESt4lessIS2_ESaIS5_EE22_M_emplace_hint_uniqueIJRKSt21piecewise_construct_tSt5tupleIJRS4_EESG_IJEEEEESt17_Rb_tree_iteratorIS5_ESt23_Rb_tree_const_iteratorIS5_EDpOT_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
INCQ 0x38(%RAX)	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	0.50	scal (12.5%)
MOV 0x48(%RBX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
TEST %RDI,%RDI	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	scal (12.5%)
JE 2a25e1 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv+0x1e1>	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 %RBX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
CALL 2a7eb0 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINSt6chrono3_V212system_clockEEEE9pop_timerEPS5_>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0	0	0	0	0	0	0.50	N/A
ADD $0x20,%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 %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

Name	Coverage (%)	Time (s)
▼qmcplusplus::TimerType::stop()–	0.01	0.02
○Loop 1527 - stl_tree.h:780-1905 - exec	0.00	0.05
○Loop 1526 - stl_tree.h:780-1905 - exec	0.00	0.03
○Loop 1528 - NewTimer.cpp:99-100 - exec	0.00	0.01

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

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

FMA

Workaround

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