OV - exec - Function void Kripke::DispatchHelper<Kripke::ArchT_OpenMP>::operator()<Kripke::LayoutT_DGZ, LTimesSdom, Kripke::SdomId&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Direction>&>(Kripke::LayoutT_DGZ, LTimesSdom const&, Kripke::SdomId&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Set const&, Kripke::Core::Field<double, Kripke::Direction, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Group, Kripke::Zone>&, Kripke::Core::Field<double, Kripke::Moment, Kripke::Direction>&) const [clone .extracted]

	Function: void Kripke::DispatchHelper<Kripke::ArchT_OpenMP>::operator()<Kripke::LayoutT_DGZ, LTimesS ...	Module: exec	Source: Collapse.hpp:74-76 [...]	Coverage (incl. loops): 2.16% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp: 137 - 137

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

137:     for (decltype(distance_it) i = 0; i < distance_it; ++i) {

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 190 - 190

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

190:          strides[RangeInts]*indices // it's not stride one

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp: 131 - 131

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

131:         m_end(begin > end ? m_begin : iterator(end))

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 216 - 269

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

216:     return val - rhs.val;

[...]

269:     return value_type(val + rhs);

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/TypedViewBase.hpp: 189 - 189

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

189:         return data[stripIndexType(layout(args...))];

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp: 62 - 62

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

62:            phi(nm,g,z) += ell(nm, d) * psi(d, g, z);

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 74 - 76

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

74: #pragma omp parallel for private(i0, i1) firstprivate(privatizer) \

75:     RAJA_COLLAPSE(2)

76:     for (i0 = 0; i0 < l0; ++i0) {

0x483f30 PUSH	%RBP

0x483f31 MOV	%RSP,%RBP

0x483f34 PUSH	%R15

0x483f36 PUSH	%R14

0x483f38 PUSH	%R13

0x483f3a PUSH	%R12

0x483f3c PUSH	%RBX

0x483f3d SUB	$0x128,%RSP

0x483f44 MOVL	$0,-0x68(%RBP)

0x483f4b TEST	%R9,%R9

0x483f4e JS	4844f1

0x483f54 MOV	%RDX,%R15

0x483f57 MOV	(%R8),%RAX

0x483f5a MOV	%RAX,-0x128(%RBP)

0x483f61 MOV	0x10(%R8),%R12

0x483f65 MOV	0x18(%R8),%R13

0x483f69 MOV	0x20(%R8),%RAX

0x483f6d MOV	%RAX,-0x120(%RBP)

0x483f74 MOV	0x30(%R8),%RAX

0x483f78 MOV	%RAX,-0x58(%RBP)

0x483f7c MOV	0x38(%R8),%R14

0x483f80 MOV	0x48(%R8),%RAX

0x483f84 MOV	%RAX,-0x50(%RBP)

0x483f88 MOV	0x68(%R8),%RAX

0x483f8c MOV	%RAX,-0x118(%RBP)

0x483f93 MOV	0x70(%R8),%RAX

0x483f97 MOV	%RAX,-0x110(%RBP)

0x483f9e MOV	0xb0(%R8),%RBX

0x483fa5 MOV	0xd0(%R8),%RAX

0x483fac MOV	%RAX,-0x60(%RBP)

0x483fb0 MOV	0xf8(%R8),%RAX

0x483fb7 MOV	%RAX,-0x38(%RBP)

0x483fbb MOV	0x118(%R8),%RAX

0x483fc2 MOV	%RAX,-0x48(%RBP)

0x483fc6 MOV	0x120(%R8),%RAX

0x483fcd MOV	%RAX,-0x80(%RBP)

0x483fd1 MOV	(%RDI),%ESI

0x483fd3 MOV	%R9,-0x98(%RBP)

0x483fda MOVQ	$0,-0xa0(%RBP)

0x483fe5 MOVQ	$0x1,-0x148(%RBP)

0x483ff0 SUB	$0x8,%RSP

0x483ff4 LEA	-0x148(%RBP),%RAX

0x483ffb LEA	0xae62e(%RIP),%RDI

0x484002 LEA	-0x68(%RBP),%RCX

0x484006 LEA	-0xa0(%RBP),%R8

0x48400d LEA	-0x98(%RBP),%R9

0x484014 MOV	%ESI,-0x64(%RBP)

0x484017 MOV	$0x22,%EDX

0x48401c PUSH	$0x1

0x48401e PUSH	$0x1

0x484020 PUSH	%RAX

0x484021 CALL	403140 <__kmpc_for_static_init_8@plt>

0x484026 ADD	$0x20,%RSP

0x48402a MOV	-0xa0(%RBP),%RAX

0x484031 MOV	-0x98(%RBP),%RCX

0x484038 MOV	%RAX,-0x108(%RBP)

0x48403f SUB	%RAX,%RCX

0x484042 MOV	%RCX,-0x100(%RBP)

0x484049 JB	4844d1

0x48404f SUB	%R12,%R13

0x484052 SUB	-0x58(%RBP),%R14

0x484056 XOR	%EAX,%EAX

0x484058 TEST	%R14,%R14

0x48405b MOV	$0,%EDI

0x484060 CMOVG	%R14,%RDI

0x484064 TEST	%R13,%R13

0x484067 CMOVLE	%RAX,%R13

0x48406b JLE	4844d1

0x484071 MOV	%R12,%RSI

0x484074 MOV	-0x48(%RBP),%RDX

0x484078 IMUL	%RDX,%RSI

0x48407c XOR	%R8D,%R8D

0x48407f TEST	%RDX,%RDX

0x484082 MOV	$0,%EAX

0x484087 CMOVG	%RDX,%RAX

0x48408b MOV	$0,%ECX

0x484090 CMOVS	%RDX,%RCX

0x484094 MOV	%R13,%R9

0x484097 MOV	%RAX,-0xe8(%RBP)

0x48409e IMUL	%RAX,%R9

0x4840a2 MOV	%R9,-0xd8(%RBP)

0x4840a9 MOV	%R13,%RAX

0x4840ac MOV	%RCX,-0xe0(%RBP)

0x4840b3 IMUL	%RCX,%RAX

0x4840b7 MOV	%RAX,-0xd0(%RBP)

0x4840be MOV	-0x60(%RBP),%RAX

0x4840c2 IMUL	%RAX,%R12

0x4840c6 MOV	%R12,-0xf0(%RBP)

0x4840cd TEST	%RAX,%RAX

0x4840d0 MOV	$0,%ECX

0x4840d5 CMOVG	%RAX,%RCX

0x4840d9 MOV	$0,%R9D

0x4840df CMOVS	%RAX,%R9

0x4840e3 MOV	%R13,%RAX

0x4840e6 MOV	%RCX,-0xc8(%RBP)

0x4840ed IMUL	%RCX,%RAX

0x4840f1 MOV	%RAX,-0xb8(%RBP)

0x4840f8 MOV	%R13,%RAX

0x4840fb MOV	%R9,-0xc0(%RBP)

0x484102 IMUL	%R9,%RAX

0x484106 MOV	%RAX,-0xb0(%RBP)

0x48410d DEC	%R13

0x484110 MOV	%RDI,%RAX

0x484113 SHR	$0x2,%RAX

0x484117 MOV	%RAX,-0x138(%RBP)

0x48411e MOV	$0x7ffffffffffffffc,%RAX

0x484128 AND	%RDI,%RAX

0x48412b MOV	%RAX,-0xa8(%RBP)

0x484132 MOV	%EDI,%EAX

0x484134 AND	$0x3,%EAX

0x484137 MOV	%RAX,-0x140(%RBP)

0x48413e MOV	-0x58(%RBP),%RCX

0x484142 LEA	(,%RCX,8),%RAX

0x48414a MOV	%RSI,-0x90(%RBP)

0x484151 LEA	(%RAX,%RSI,8),%RAX

0x484155 ADD	-0x38(%RBP),%RAX

0x484159 MOV	%RAX,-0x78(%RBP)

0x48415d LEA	(%RDI,%RCX,1),%RAX

0x484161 MOV	%RAX,-0x88(%RBP)

0x484168 MOV	-0x80(%RBP),%RAX

0x48416c LEA	(,%RAX,8),%RAX

0x484174 MOV	%RAX,-0x70(%RBP)

0x484178 LEA	(,%RDX,8),%R10

0x484180 MOV	%R15,-0xf8(%RBP)

0x484187 JMP	4841af

0x484189 NOPL	(%RAX)

(1687) 0x484190 MOV	-0x130(%RBP),%RCX

(1687) 0x484197 LEA	0x1(%RCX),%R8

(1687) 0x48419b CMP	-0x100(%RBP),%RCX

(1687) 0x4841a2 MOV	-0xf8(%RBP),%R15

(1687) 0x4841a9 JE	4844d1

(1687) 0x4841af MOV	-0x108(%RBP),%RAX

(1687) 0x4841b6 ADD	%R8,%RAX

(1687) 0x4841b9 MOV	%RAX,%RCX

(1687) 0x4841bc OR	%R15,%RCX

(1687) 0x4841bf SHR	$0x20,%RCX

(1687) 0x4841c3 MOV	%R8,-0x130(%RBP)

(1687) 0x4841ca JE	4841e0

(1687) 0x4841cc CQTO

(1687) 0x4841ce IDIV	%R15

(1687) 0x4841d1 MOV	%RAX,%R12

(1687) 0x4841d4 JMP	4841e8

0x4841d6 NOPW	%CS:(%RAX,%RAX,1)

(1687) 0x4841e0 XOR	%EDX,%EDX

(1687) 0x4841e2 DIV	%R15D

(1687) 0x4841e5 MOV	%EAX,%R12D

(1687) 0x4841e8 MOV	-0x38(%RBP),%RSI

(1687) 0x4841ec ADD	-0x128(%RBP),%R12

(1687) 0x4841f3 ADD	-0x120(%RBP),%RDX

(1687) 0x4841fa MOV	-0x80(%RBP),%RAX

(1687) 0x4841fe IMUL	%RDX,%RAX

(1687) 0x484202 MOV	-0x90(%RBP),%RCX

(1687) 0x484209 MOV	-0x88(%RBP),%R8

(1687) 0x484210 ADD	%R8,%RCX

(1687) 0x484213 ADD	%RAX,%RCX

(1687) 0x484216 SUB	-0xe8(%RBP),%RCX

(1687) 0x48421d ADD	-0xd8(%RBP),%RCX

(1687) 0x484224 LEA	(%RSI,%RCX,8),%RCX

(1687) 0x484228 ADD	$-0x8,%RCX

(1687) 0x48422c MOV	%RCX,-0x40(%RBP)

(1687) 0x484230 MOV	-0x110(%RBP),%R9

(1687) 0x484237 IMUL	%RDX,%R9

(1687) 0x48423b MOV	-0x58(%RBP),%RCX

(1687) 0x48423f LEA	(%RCX,%R9,1),%R11

(1687) 0x484243 MOV	-0x118(%RBP),%R15

(1687) 0x48424a IMUL	%R12,%R15

(1687) 0x48424e ADD	%R15,%R11

(1687) 0x484251 MOV	-0x50(%RBP),%RSI

(1687) 0x484255 LEA	(%RSI,%R11,8),%R8

(1687) 0x484259 CMP	%R8,-0x40(%RBP)

(1687) 0x48425d SETAEB	-0x29(%RBP)

(1687) 0x484261 ADD	-0x88(%RBP),%R9

(1687) 0x484268 ADD	%R15,%R9

(1687) 0x48426b LEA	(%RSI,%R9,8),%R15

(1687) 0x48426f ADD	$-0x8,%R15

(1687) 0x484273 MOV	-0x90(%RBP),%RSI

(1687) 0x48427a ADD	%RCX,%RAX

(1687) 0x48427d ADD	%RSI,%RAX

(1687) 0x484280 MOV	%RAX,-0x40(%RBP)

(1687) 0x484284 MOV	%RAX,%R9

(1687) 0x484287 SUB	-0xe0(%RBP),%R9

(1687) 0x48428e ADD	-0xd0(%RBP),%R9

(1687) 0x484295 MOV	-0x38(%RBP),%RAX

(1687) 0x484299 LEA	(%RAX,%R9,8),%R9

(1687) 0x48429d CMP	%R9,%R15

(1687) 0x4842a0 SETAE	%CL

(1687) 0x4842a3 ADD	-0xf0(%RBP),%R12

(1687) 0x4842aa MOV	%R12,%R9

(1687) 0x4842ad SUB	-0xc8(%RBP),%R9

(1687) 0x4842b4 ADD	-0xb8(%RBP),%R9

(1687) 0x4842bb LEA	(%RBX,%R9,8),%R9

(1687) 0x4842bf CMP	%R8,%R9

(1687) 0x4842c2 SETB	%R9B

(1687) 0x4842c6 MOV	%R12,%RAX

(1687) 0x4842c9 SUB	-0xc0(%RBP),%RAX

(1687) 0x4842d0 ADD	-0xb0(%RBP),%RAX

(1687) 0x4842d7 LEA	(%RBX,%RAX,8),%RAX

(1687) 0x4842db CMP	%RAX,%R15

(1687) 0x4842de SETB	%R15B

(1687) 0x4842e2 TEST	%CL,-0x29(%RBP)

(1687) 0x4842e5 JNE	484470

(1687) 0x4842eb OR	%R15B,%R9B

(1687) 0x4842ee JE	484470

(1687) 0x4842f4 MOV	-0xa8(%RBP),%RAX

(1687) 0x4842fb ADD	%RAX,-0x40(%RBP)

(1687) 0x4842ff ADD	%RAX,%R11

(1687) 0x484302 IMUL	-0x70(%RBP),%RDX

(1687) 0x484307 ADD	-0x78(%RBP),%RDX

(1687) 0x48430b XOR	%R9D,%R9D

(1687) 0x48430e JMP	484378

  (1690) 0x484310 MOV	-0x48(%RBP),%RCX

  (1690) 0x484314 IMUL	%R9,%RCX

  (1690) 0x484318 ADD	-0x40(%RBP),%RCX

  (1690) 0x48431c MOV	-0x38(%RBP),%RSI

  (1690) 0x484320 MOVSD	0x10(%RSI,%RCX,8),%XMM1

  (1690) 0x484326 MULSD	%XMM0,%XMM1

  (1690) 0x48432a MOV	-0x50(%RBP),%RAX

  (1690) 0x48432e ADDSD	0x10(%RAX,%R11,8),%XMM1

  (1690) 0x484335 MOVSD	%XMM1,0x10(%RAX,%R11,8)

  (1690) 0x48433c MOVSD	0x8(%RSI,%RCX,8),%XMM1

  (1690) 0x484342 MULSD	%XMM0,%XMM1

  (1690) 0x484346 ADDSD	0x8(%RAX,%R11,8),%XMM1

  (1690) 0x48434d MOVSD	%XMM1,0x8(%RAX,%R11,8)

  (1690) 0x484354 MULSD	(%RSI,%RCX,8),%XMM0

  (1690) 0x484359 ADDSD	(%RAX,%R11,8),%XMM0

  (1690) 0x48435f MOVSD	%XMM0,(%RAX,%R11,8)

  (1690) 0x484365 LEA	0x1(%R9),%RAX

  (1690) 0x484369 ADD	%R10,%RDX

  (1690) 0x48436c CMP	%R13,%R9

  (1690) 0x48436f MOV	%RAX,%R9

  (1690) 0x484372 JE	484190

  (1690) 0x484378 TEST	%R14,%R14

  (1690) 0x48437b JLE	484365

  (1690) 0x48437d MOV	-0x60(%RBP),%RAX

  (1690) 0x484381 IMUL	%R9,%RAX

  (1690) 0x484385 ADD	%R12,%RAX

  (1690) 0x484388 MOVSD	(%RBX,%RAX,8),%XMM0

  (1690) 0x48438d CMP	$0x4,%RDI

  (1690) 0x484391 JB	48441a

  (1690) 0x484397 MOV	$0x18,%R15D

  (1690) 0x48439d MOV	-0x138(%RBP),%RCX

  (1690) 0x4843a4 NOPW	%CS:(%RAX,%RAX,1)

    (1691) 0x4843b0 MOVSD	-0x18(%RDX,%R15,1),%XMM1

    (1691) 0x4843b7 MULSD	%XMM0,%XMM1

    (1691) 0x4843bb ADDSD	-0x18(%R8,%R15,1),%XMM1

    (1691) 0x4843c2 MOVSD	%XMM1,-0x18(%R8,%R15,1)

    (1691) 0x4843c9 MOVSD	-0x10(%RDX,%R15,1),%XMM1

    (1691) 0x4843d0 MULSD	%XMM0,%XMM1

    (1691) 0x4843d4 ADDSD	-0x10(%R8,%R15,1),%XMM1

    (1691) 0x4843db MOVSD	%XMM1,-0x10(%R8,%R15,1)

    (1691) 0x4843e2 MOVSD	-0x8(%RDX,%R15,1),%XMM1

    (1691) 0x4843e9 MULSD	%XMM0,%XMM1

    (1691) 0x4843ed ADDSD	-0x8(%R8,%R15,1),%XMM1

    (1691) 0x4843f4 MOVSD	%XMM1,-0x8(%R8,%R15,1)

    (1691) 0x4843fb MOVSD	(%RDX,%R15,1),%XMM1

    (1691) 0x484401 MULSD	%XMM0,%XMM1

    (1691) 0x484405 ADDSD	(%R8,%R15,1),%XMM1

    (1691) 0x48440b MOVSD	%XMM1,(%R8,%R15,1)

    (1691) 0x484411 ADD	$0x20,%R15

    (1691) 0x484415 DEC	%RCX

    (1691) 0x484418 JNE	4843b0

  (1690) 0x48441a MOV	-0x140(%RBP),%RAX

  (1690) 0x484421 CMP	$0x1,%EAX

  (1690) 0x484424 JE	484451

  (1690) 0x484426 CMP	$0x3,%EAX

  (1690) 0x484429 JE	484310

  (1690) 0x48442f CMP	$0x2,%EAX

  (1690) 0x484432 MOV	-0x38(%RBP),%RSI

  (1690) 0x484436 JNE	484365

  (1690) 0x48443c MOV	-0x48(%RBP),%RCX

  (1690) 0x484440 IMUL	%R9,%RCX

  (1690) 0x484444 ADD	-0x40(%RBP),%RCX

  (1690) 0x484448 MOV	-0x50(%RBP),%RAX

  (1690) 0x48444c JMP	48433c

  (1690) 0x484451 MOV	-0x48(%RBP),%RCX

  (1690) 0x484455 IMUL	%R9,%RCX

  (1690) 0x484459 ADD	-0x40(%RBP),%RCX

  (1690) 0x48445d MOV	-0x50(%RBP),%RAX

  (1690) 0x484461 MOV	-0x38(%RBP),%RSI

  (1690) 0x484465 JMP	484354

0x48446a NOPW	(%RAX,%RAX,1)

(1687) 0x484470 IMUL	-0x70(%RBP),%RDX

(1687) 0x484475 ADD	-0x78(%RBP),%RDX

(1687) 0x484479 XOR	%ECX,%ECX

(1687) 0x48447b JMP	484493

0x48447d NOPL	(%RAX)

  (1688) 0x484480 LEA	0x1(%RCX),%RAX

  (1688) 0x484484 ADD	%R10,%RDX

  (1688) 0x484487 CMP	%R13,%RCX

  (1688) 0x48448a MOV	%RAX,%RCX

  (1688) 0x48448d JE	484190

  (1688) 0x484493 TEST	%R14,%R14

  (1688) 0x484496 JLE	484480

  (1688) 0x484498 MOV	-0x60(%RBP),%RSI

  (1688) 0x48449c IMUL	%RCX,%RSI

  (1688) 0x4844a0 ADD	%R12,%RSI

  (1688) 0x4844a3 XOR	%R9D,%R9D

  (1688) 0x4844a6 NOPW	%CS:(%RAX,%RAX,1)

    (1689) 0x4844b0 MOVSD	(%RDX,%R9,8),%XMM0

    (1689) 0x4844b6 MULSD	(%RBX,%RSI,8),%XMM0

    (1689) 0x4844bb ADDSD	(%R8,%R9,8),%XMM0

    (1689) 0x4844c1 MOVSD	%XMM0,(%R8,%R9,8)

    (1689) 0x4844c7 INC	%R9

    (1689) 0x4844ca CMP	%R9,%RDI

    (1689) 0x4844cd JNE	4844b0

  (1688) 0x4844cf JMP	484480

0x4844d1 LEA	0xae178(%RIP),%RDI

0x4844d8 MOV	-0x64(%RBP),%ESI

0x4844db ADD	$0x128,%RSP

0x4844e2 POP	%RBX

0x4844e3 POP	%R12

0x4844e5 POP	%R13

0x4844e7 POP	%R14

0x4844e9 POP	%R15

0x4844eb POP	%RBP

0x4844ec JMP	403050

0x4844f1 ADD	$0x128,%RSP

0x4844f8 POP	%RBX

0x4844f9 POP	%R12

0x4844fb POP	%R13

0x4844fd POP	%R14

0x4844ff POP	%R15

0x484501 POP	%RBP

0x484502 RET

0x484503 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►97.05+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.40+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	LTimes	Collapse.hpp:74	exec
○	SteadyStateSolver	SteadyStateSolver.cpp:62	exec
○	main	kripke.cpp:504	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start	kripke.cpp:0	exec

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 icx_10

Source file and lines	Collapse.hpp:74-76
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:137
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:190
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:216,269
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/TypedViewBase.hpp:189
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74-76

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 18.50 to 1.50 cycles (12.33x 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

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.

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74

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.

CMOVG: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
CMOVLE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131

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 184 bytes. The binary function is storing 264 bytes.

General properties

nb instructions	148
nb uops	148
loop length	690
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	18.50 cycles
front end	18.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	9.83	9.83	9.83	9.83	9.83	9.83	14.75	14.75	14.75	14.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	9.83	9.83	9.83	9.83	9.83	9.83	14.75	14.75	14.75	14.75	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	18.50
Dispatch	14.75
Overall L1	18.50

Vectorization ratios

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

all	11%
load	12%
store	11%
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 18.50 cycles. At this rate:

3% of peak load performance is reached (9.95 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.27 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 18.50 to 14.75 cycles (1.25x speedup).

ASM code

In the binary file, the address of the function is: 483f30

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVL $0,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
TEST %R9,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JS 4844f1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5c1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV (%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x18(%R8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x20(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x30(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x38(%R8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x48(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x68(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x118(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x70(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb0(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd0(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf8(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x118(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x120(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x148(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x148(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0xae62e(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x68(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xa0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x98(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x64(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	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	1	0.50	N/A
CALL 403140 <__kmpc_for_static_init_8@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	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	1	0.17	N/A
MOV -0xa0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x98(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JB 4844d1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5a1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %R12,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
SUB -0x58(%RBP),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
TEST %R14,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %R14,%RDI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
TEST %R13,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVLE %RAX,%R13	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
JLE 4844d1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5a1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x48(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RDX,%RSI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
TEST %RDX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %RDX,%RAX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV $0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVS %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R13,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RAX,%R9	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
MOV %R9,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RCX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RAX,%R12	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
MOV %R12,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %RAX,%RCX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV $0,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMOVS %RAX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RCX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %R9,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
DEC %R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RAX,-0x138(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $0x7ffffffffffffffc,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
AND %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EDI,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%RCX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RSI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%RAX,%RSI,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD -0x38(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%RDI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%RAX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%RDX,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R15,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 4841af <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x27f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	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	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
LEA 0xae178(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x64(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
JMP 403050 <__kmpc_for_static_fini@plt>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_10

Source file and lines	Collapse.hpp:74-76
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/pattern/kernel/For.hpp:137
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:190
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:216,269
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/TypedViewBase.hpp:189
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
/home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74-76

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

CALL instructions

Detected function call instructions.

Details

__kmpc_for_static_init_8@plt: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:74

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.

CMOVG: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp:62
CMOVLE: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-940-2141/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/RangeSegment.hpp:131

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 184 bytes. The binary function is storing 264 bytes.

General properties

nb instructions	148
nb uops	148
loop length	690
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	34

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	18.50 cycles
front end	18.50 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	9.83	9.83	9.83	9.83	9.83	9.83	14.75	14.75	14.75	14.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	9.83	9.83	9.83	9.83	9.83	9.83	14.75	14.75	14.75	14.75	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	18.50
Dispatch	14.75
Overall L1	18.50

Vectorization ratios

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

all	11%
load	12%
store	11%
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 18.50 cycles. At this rate:

3% of peak load performance is reached (9.95 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.27 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: 483f30

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	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	0.17	N/A
PUSH %R15	1	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	1	0.50	N/A
PUSH %R13	1	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	1	0.50	N/A
PUSH %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
SUB $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVL $0,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
TEST %R9,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JS 4844f1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5c1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RDX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV (%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%R8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x18(%R8),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x20(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x120(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x30(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x38(%R8),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x48(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x68(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x118(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x70(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb0(%R8),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd0(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf8(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x118(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x120(%R8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R9,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x148(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x148(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0xae62e(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x68(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xa0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x98(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x64(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	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	1	0.50	N/A
CALL 403140 <__kmpc_for_static_init_8@plt>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	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	1	0.17	N/A
MOV -0xa0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x98(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
SUB %RAX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JB 4844d1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5a1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %R12,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
SUB -0x58(%RBP),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
TEST %R14,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%EDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %R14,%RDI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
TEST %R13,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVLE %RAX,%R13	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
JLE 4844d1 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x5a1>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R12,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x48(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RDX,%RSI	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
TEST %RDX,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %RDX,%RAX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV $0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVS %RDX,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R13,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RAX,%R9	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
MOV %R9,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RCX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
IMUL %RAX,%R12	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
MOV %R12,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
TEST %RAX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMOVG %RAX,%RCX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV $0,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMOVS %RAX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %RCX,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R9,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
IMUL %R9,%RAX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
MOV %RAX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
DEC %R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RAX,-0x138(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $0x7ffffffffffffffc,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
AND %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EDI,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x140(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x58(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%RCX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RSI,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%RAX,%RSI,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
ADD -0x38(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%RDI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x80(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
LEA (,%RAX,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (,%RDX,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R15,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 4841af <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE10LTimesSdomJRNS_6SdomIdERKNS_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS_9DirectionENS_5GroupENS_4ZoneEEEERNSC_IdJNS_6MomentESE_SF_EEERNSC_IdJSI_SD_EEEEEEvT_RKT0_DpOT1_.extracted+0x27f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	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	0.09	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
LEA 0xae178(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x64(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
JMP 403050 <__kmpc_for_static_fini@plt>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
ADD $0x128,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	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	1	0.33	N/A
POP %R13	1	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	1	0.33	N/A
POP %R15	1	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	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼void Kripke::DispatchHelper::operator()–	2.16	0.45
▼Loop 1687 - For.hpp:137-137 - exec–	0.01	0.01
▼Loop 1690 - LTimes.cpp:62-62 - exec–	0.03	0.01
○Loop 1691 - For.hpp:137-137 - exec	2.13	0.44
▼Loop 1688 - For.hpp:137-137 - exec–	0.00	0.00
○Loop 1689 - For.hpp:137-137 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

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

CALL instructions

Details

Complex instructions

Details

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