OV - exec - Function _ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD

	Function: _ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_N ...	Module: exec	Source: Collapse.hpp:81-83 [...]	Coverage: 7.12%

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp: 55 - 55

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

55:     return a * b;

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp: 81 - 83

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

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

82:     RAJA_COLLAPSE(2)

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

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59

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

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

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 55 - 177

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

55:       : val(rhs.val)

[...]

177:     return value_type(val + rhs);

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/View.hpp: 79 - 110

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

79:       : layout(V.layout), data(V.data)

[...]

110:     return data[idx];

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/src/Kripke/Kernel/LPlusTimes.cpp: 57 - 57

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

57:             rhs(d,g,z) += ell_plus(d, nm) * phi_out(nm, g, z);

0x47bcc0 PUSH	%RBP

0x47bcc1 MOV	%RSP,%RBP

0x47bcc4 PUSH	%R15

0x47bcc6 PUSH	%R14

0x47bcc8 PUSH	%R13

0x47bcca PUSH	%R12

0x47bccc PUSH	%RBX

0x47bccd SUB	$0x108,%RSP

0x47bcd4 MOV	%RDX,%RBX

0x47bcd7 MOVL	$0,-0x50(%RBP)

0x47bcde MOV	(%R8),%RAX

0x47bce1 MOV	%RAX,-0x110(%RBP)

0x47bce8 MOV	0x10(%R8),%RAX

0x47bcec MOV	%RAX,-0x38(%RBP)

0x47bcf0 MOV	0x18(%R8),%RAX

0x47bcf4 MOV	%RAX,-0x30(%RBP)

0x47bcf8 MOV	0x20(%R8),%RAX

0x47bcfc MOV	%RAX,-0x108(%RBP)

0x47bd03 MOV	0x30(%R8),%RAX

0x47bd07 MOV	%RAX,-0x78(%RBP)

0x47bd0b MOV	0x38(%R8),%RAX

0x47bd0f MOV	%RAX,-0x70(%RBP)

0x47bd13 MOV	0x60(%R8),%RAX

0x47bd17 MOV	%RAX,-0x100(%RBP)

0x47bd1e MOV	0x68(%R8),%RAX

0x47bd22 MOV	%RAX,-0xf8(%RBP)

0x47bd29 MOV	0xa8(%R8),%RAX

0x47bd30 MOV	%RAX,-0x88(%RBP)

0x47bd37 MOV	(%RDI),%ESI

0x47bd39 MOV	%R9,-0xa0(%RBP)

0x47bd40 MOV	0xc0(%R8),%RAX

0x47bd47 MOV	%RAX,-0xf0(%RBP)

0x47bd4e MOV	0xf0(%R8),%R12

0x47bd55 MOV	0x110(%R8),%RAX

0x47bd5c MOV	%RAX,-0x90(%RBP)

0x47bd63 MOV	0x118(%R8),%RAX

0x47bd6a MOV	%RAX,-0x68(%RBP)

0x47bd6e MOV	0x158(%R8),%RAX

0x47bd75 MOV	%RAX,-0x48(%RBP)

0x47bd79 MOVQ	$0,-0xa8(%RBP)

0x47bd84 MOVQ	$0x1,-0x128(%RBP)

0x47bd8f SUB	$0x8,%RSP

0x47bd93 LEA	-0x128(%RBP),%RAX

0x47bd9a LEA	0xe065f(%RIP),%RDI

0x47bda1 LEA	-0x50(%RBP),%RCX

0x47bda5 LEA	-0xa8(%RBP),%R8

0x47bdac LEA	-0xa0(%RBP),%R9

0x47bdb3 MOV	%ESI,-0x4c(%RBP)

0x47bdb6 MOV	$0x22,%EDX

0x47bdbb PUSH	$0x1

0x47bdbd PUSH	$0x1

0x47bdbf PUSH	%RAX

0x47bdc0 CALL	403140 <__kmpc_for_static_init_8@plt>

0x47bdc5 ADD	$0x20,%RSP

0x47bdc9 MOV	-0xa8(%RBP),%RAX

0x47bdd0 MOV	-0xa0(%RBP),%RCX

0x47bdd7 MOV	%RAX,-0xe8(%RBP)

0x47bdde SUB	%RAX,%RCX

0x47bde1 MOV	%RCX,-0xe0(%RBP)

0x47bde8 JB	47c161

0x47bdee MOV	-0x30(%RBP),%RAX

0x47bdf2 CMP	-0x38(%RBP),%RAX

0x47bdf6 JLE	47c161

0x47bdfc MOV	-0x38(%RBP),%R10

0x47be00 MOV	%R10,%R8

0x47be03 MOV	-0x90(%RBP),%RDI

0x47be0a IMUL	%RDI,%R8

0x47be0e XOR	%R9D,%R9D

0x47be11 TEST	%RDI,%RDI

0x47be14 MOV	$0,%ECX

0x47be19 CMOVG	%RDI,%RCX

0x47be1d NOT	%R10

0x47be20 MOV	$0,%EDX

0x47be25 CMOVS	%RDI,%RDX

0x47be29 MOV	-0x30(%RBP),%RAX

0x47be2d MOV	%RAX,%RSI

0x47be30 IMUL	%RCX,%RSI

0x47be34 MOV	%RSI,-0xb8(%RBP)

0x47be3b IMUL	%R10,%RCX

0x47be3f MOV	%RCX,-0xc8(%RBP)

0x47be46 MOV	%RAX,%RCX

0x47be49 IMUL	%RDX,%RCX

0x47be4d MOV	%RCX,-0xb0(%RBP)

0x47be54 IMUL	%R10,%RDX

0x47be58 MOV	%RDX,-0xc0(%RBP)

0x47be5f ADD	%RAX,%R10

0x47be62 MOV	-0x70(%RBP),%RCX

0x47be66 MOV	-0x78(%RBP),%RDX

0x47be6a SUB	%RDX,%RCX

0x47be6d MOV	%RCX,%RAX

0x47be70 AND	$-0x2,%RAX

0x47be74 MOV	%RAX,-0x98(%RBP)

0x47be7b LEA	-0x1(%RAX),%RSI

0x47be7f LEA	(,%RDX,8),%RAX

0x47be87 LEA	(%RAX,%R8,8),%RAX

0x47be8b ADD	-0x48(%RBP),%RAX

0x47be8f MOV	%RAX,-0x60(%RBP)

0x47be93 MOV	-0x68(%RBP),%RAX

0x47be97 LEA	(,%RAX,8),%RAX

0x47be9f MOV	%RAX,-0x58(%RBP)

0x47bea3 LEA	(,%RDI,8),%RDI

0x47beab MOV	%R8,-0xd0(%RBP)

0x47beb2 LEA	(%RDX,%R8,1),%RAX

0x47beb6 MOV	%RAX,-0x80(%RBP)

0x47beba MOV	%RBX,-0xd8(%RBP)

0x47bec1 JMP	47beef

0x47bec3 NOPW	%CS:(%RAX,%RAX,1)

(1208) 0x47bed0 MOV	-0x118(%RBP),%RDX

(1208) 0x47bed7 LEA	0x1(%RDX),%R9

(1208) 0x47bedb CMP	-0xe0(%RBP),%RDX

(1208) 0x47bee2 MOV	-0xd8(%RBP),%RBX

(1208) 0x47bee9 JE	47c161

(1208) 0x47beef MOV	-0xe8(%RBP),%RAX

(1208) 0x47bef6 ADD	%R9,%RAX

(1208) 0x47bef9 MOV	%RAX,%RDX

(1208) 0x47befc OR	%RBX,%RDX

(1208) 0x47beff SHR	$0x20,%RDX

(1208) 0x47bf03 MOV	%R9,-0x118(%RBP)

(1208) 0x47bf0a JE	47bf20

(1208) 0x47bf0c CQTO

(1208) 0x47bf0e IDIV	%RBX

(1208) 0x47bf11 JMP	47bf24

0x47bf13 NOPW	%CS:(%RAX,%RAX,1)

(1208) 0x47bf20 XOR	%EDX,%EDX

(1208) 0x47bf22 DIV	%EBX

(1208) 0x47bf24 ADD	-0x110(%RBP),%RAX

(1208) 0x47bf2b ADD	-0x108(%RBP),%RDX

(1208) 0x47bf32 MOV	-0x68(%RBP),%R9

(1208) 0x47bf36 IMUL	%RDX,%R9

(1208) 0x47bf3a MOV	-0x70(%RBP),%R13

(1208) 0x47bf3e MOV	-0xd0(%RBP),%R8

(1208) 0x47bf45 ADD	%R13,%R8

(1208) 0x47bf48 ADD	-0xc8(%RBP),%R8

(1208) 0x47bf4f ADD	-0xb8(%RBP),%R8

(1208) 0x47bf56 ADD	%R9,%R8

(1208) 0x47bf59 MOV	-0x48(%RBP),%R15

(1208) 0x47bf5d LEA	(%R15,%R8,8),%R8

(1208) 0x47bf61 ADD	$-0x8,%R8

(1208) 0x47bf65 MOV	%R8,-0x40(%RBP)

(1208) 0x47bf69 MOV	-0xf8(%RBP),%RBX

(1208) 0x47bf70 IMUL	%RDX,%RBX

(1208) 0x47bf74 MOV	-0x78(%RBP),%R11

(1208) 0x47bf78 ADD	%RBX,%R11

(1208) 0x47bf7b MOV	-0x100(%RBP),%R14

(1208) 0x47bf82 IMUL	%RAX,%R14

(1208) 0x47bf86 ADD	%R14,%R11

(1208) 0x47bf89 MOV	-0x88(%RBP),%R8

(1208) 0x47bf90 MOV	%R11,-0x120(%RBP)

(1208) 0x47bf97 LEA	(%R8,%R11,8),%R11

(1208) 0x47bf9b CMP	%R11,-0x40(%RBP)

(1208) 0x47bf9f SETAEB	-0x40(%RBP)

(1208) 0x47bfa3 ADD	%R13,%RBX

(1208) 0x47bfa6 ADD	%R14,%RBX

(1208) 0x47bfa9 LEA	(%R8,%RBX,8),%RBX

(1208) 0x47bfad ADD	$-0x8,%RBX

(1208) 0x47bfb1 MOV	-0xc0(%RBP),%R8

(1208) 0x47bfb8 MOV	-0x80(%RBP),%R14

(1208) 0x47bfbc ADD	%R14,%R8

(1208) 0x47bfbf ADD	-0xb0(%RBP),%R8

(1208) 0x47bfc6 ADD	%R9,%R8

(1208) 0x47bfc9 LEA	(%R15,%R8,8),%R8

(1208) 0x47bfcd CMP	%R8,%RBX

(1208) 0x47bfd0 SETAE	%R14B

(1208) 0x47bfd4 IMUL	-0xf0(%RBP),%RAX

(1208) 0x47bfdc MOV	-0x30(%RBP),%R8

(1208) 0x47bfe0 ADD	%RAX,%R8

(1208) 0x47bfe3 LEA	(%R12,%R8,8),%R8

(1208) 0x47bfe7 ADD	$-0x8,%R8

(1208) 0x47bfeb CMP	%R11,%R8

(1208) 0x47bfee SETB	%R8B

(1208) 0x47bff2 ADD	-0x38(%RBP),%RAX

(1208) 0x47bff6 LEA	(%R12,%RAX,8),%R13

(1208) 0x47bffa CMP	%R13,%RBX

(1208) 0x47bffd SETB	%BL

(1208) 0x47c000 TEST	%R14B,-0x40(%RBP)

(1208) 0x47c004 JNE	47c110

(1208) 0x47c00a OR	%BL,%R8B

(1208) 0x47c00d JE	47c110

(1208) 0x47c013 IMUL	-0x58(%RBP),%RDX

(1208) 0x47c018 ADD	-0x60(%RBP),%RDX

(1208) 0x47c01c ADD	-0x80(%RBP),%R9

(1208) 0x47c020 XOR	%R15D,%R15D

(1208) 0x47c023 JMP	47c04a

0x47c025 NOPW	%CS:(%RAX,%RAX,1)

  (1211) 0x47c030 LEA	0x1(%R15),%R8

  (1211) 0x47c034 ADD	%RDI,%RDX

  (1211) 0x47c037 ADD	-0x90(%RBP),%R9

  (1211) 0x47c03e CMP	%R10,%R15

  (1211) 0x47c041 MOV	%R8,%R15

  (1211) 0x47c044 JE	47bed0

  (1211) 0x47c04a TEST	%RCX,%RCX

  (1211) 0x47c04d JLE	47c030

  (1211) 0x47c04f LEA	(%RAX,%R15,1),%R8

  (1211) 0x47c053 MOVSD	(%R12,%R8,8),%XMM0

  (1211) 0x47c059 CMPQ	$0,-0x98(%RBP)

  (1211) 0x47c061 JE	47c0b0

  (1211) 0x47c063 MOVAPD	%XMM0,%XMM1

  (1211) 0x47c067 UNPCKLPD	%XMM0,%XMM1

  (1211) 0x47c06b XOR	%R8D,%R8D

  (1211) 0x47c06e XCHG	%AX,%AX

    (1213) 0x47c070 MOVUPD	(%RDX,%R8,8),%XMM2

    (1213) 0x47c076 MULPD	%XMM1,%XMM2

    (1213) 0x47c07a MOVUPD	(%R11,%R8,8),%XMM3

    (1213) 0x47c080 ADDPD	%XMM2,%XMM3

    (1213) 0x47c084 MOVUPD	%XMM3,(%R11,%R8,8)

    (1213) 0x47c08a ADD	$0x2,%R8

    (1213) 0x47c08e CMP	%RSI,%R8

    (1213) 0x47c091 JLE	47c070

  (1211) 0x47c093 MOV	-0x98(%RBP),%RBX

  (1211) 0x47c09a MOV	%RBX,%R8

  (1211) 0x47c09d CMP	%RBX,%RCX

  (1211) 0x47c0a0 JE	47c030

  (1211) 0x47c0a2 JMP	47c0b3

0x47c0a4 NOPW	%CS:(%RAX,%RAX,1)

  (1211) 0x47c0b0 XOR	%R8D,%R8D

  (1211) 0x47c0b3 MOV	%RCX,%R14

  (1211) 0x47c0b6 SUB	%R8,%R14

  (1211) 0x47c0b9 MOV	-0x120(%RBP),%RBX

  (1211) 0x47c0c0 ADD	%R8,%RBX

  (1211) 0x47c0c3 MOV	-0x88(%RBP),%R13

  (1211) 0x47c0ca LEA	(%R13,%RBX,8),%R13

  (1211) 0x47c0cf ADD	%R9,%R8

  (1211) 0x47c0d2 MOV	-0x48(%RBP),%RBX

  (1211) 0x47c0d6 LEA	(%RBX,%R8,8),%R8

  (1211) 0x47c0da XOR	%EBX,%EBX

  (1211) 0x47c0dc NOPL	(%RAX)

    (1212) 0x47c0e0 MOVSD	(%R8,%RBX,8),%XMM1

    (1212) 0x47c0e6 MULSD	%XMM0,%XMM1

    (1212) 0x47c0ea ADDSD	(%R13,%RBX,8),%XMM1

    (1212) 0x47c0f1 MOVSD	%XMM1,(%R13,%RBX,8)

    (1212) 0x47c0f8 INC	%RBX

    (1212) 0x47c0fb CMP	%RBX,%R14

    (1212) 0x47c0fe JNE	47c0e0

  (1211) 0x47c100 JMP	47c030

0x47c105 NOPW	%CS:(%RAX,%RAX,1)

(1208) 0x47c110 IMUL	-0x58(%RBP),%RDX

(1208) 0x47c115 ADD	-0x60(%RBP),%RDX

(1208) 0x47c119 XOR	%R8D,%R8D

(1208) 0x47c11c JMP	47c133

0x47c11e XCHG	%AX,%AX

  (1209) 0x47c120 LEA	0x1(%R8),%R9

  (1209) 0x47c124 ADD	%RDI,%RDX

  (1209) 0x47c127 CMP	%R10,%R8

  (1209) 0x47c12a MOV	%R9,%R8

  (1209) 0x47c12d JE	47bed0

  (1209) 0x47c133 TEST	%RCX,%RCX

  (1209) 0x47c136 JLE	47c120

  (1209) 0x47c138 LEA	(%RAX,%R8,1),%R9

  (1209) 0x47c13c XOR	%EBX,%EBX

  (1209) 0x47c13e XCHG	%AX,%AX

    (1210) 0x47c140 MOVSD	(%RDX,%RBX,8),%XMM0

    (1210) 0x47c145 MULSD	(%R12,%R9,8),%XMM0

    (1210) 0x47c14b ADDSD	(%R11,%RBX,8),%XMM0

    (1210) 0x47c151 MOVSD	%XMM0,(%R11,%RBX,8)

    (1210) 0x47c157 INC	%RBX

    (1210) 0x47c15a CMP	%RBX,%RCX

    (1210) 0x47c15d JNE	47c140

  (1209) 0x47c15f JMP	47c120

0x47c161 LEA	0xe02b8(%RIP),%RDI

0x47c168 MOV	-0x4c(%RBP),%ESI

0x47c16b ADD	$0x108,%RSP

0x47c172 POP	%RBX

0x47c173 POP	%R12

0x47c175 POP	%R13

0x47c177 POP	%R14

0x47c179 POP	%R15

0x47c17b POP	%RBP

0x47c17c JMP	403050

0x47c181 NOPW	%CS:(%RAX,%RAX,1)

Path /

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

Source file and lines	Collapse.hpp:81-83
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:55
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:81-83
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp:59
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:55,177
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/View.hpp:79,110
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/src/Kripke/Kernel/LPlusTimes.cpp:57

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 19.50 to 3.35 cycles (5.81x 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

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 208 bytes. The binary function is storing 232 bytes.

General properties

nb instructions	123
nb uops	117
loop length	624
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.50 cycles
front end	19.50 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	9.25	9.25	9.00	9.00	2.50	19.33	19.33	19.33	0.00	0.00	0.00	0.00	0.00	0.00
cycles	9.25	9.25	9.00	9.00	2.50	19.33	19.33	19.33	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.50
Dispatch	19.33
Overall L1	19.50

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	10%
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 19.50 cycles. At this rate:

11% of peak load performance is reached (10.67 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (11.90 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck).

ASM code

In the binary file, the address of the function is: 47bcc0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	1	0.50
SUB $0x108,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RDX,%RBX	1	0	0	0	0	0	0	0	0	0	0.17
MOVL $0,-0x50(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV (%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x110(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x10(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x18(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x20(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x30(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x38(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x60(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x100(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x68(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xf8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xa8(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV (%RDI),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %R9,-0xa0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xc0(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xf0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xf0(%R8),%R12	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV 0x110(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x118(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x158(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOVQ $0,-0xa8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOVQ $0x1,-0x128(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
SUB $0x8,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0x128(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA 0xe065f(%RIP),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0x50(%RBP),%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0xa8(%RBP),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0xa0(%RBP),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %ESI,-0x4c(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV $0x22,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
PUSH $0x1	1	0	0	0	0	0	0	0	0	1	0.50
PUSH $0x1	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %RAX	1	0	0	0	0	0	0	0	0	1	0.50
CALL 403140 <__kmpc_for_static_init_8@plt>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0.50
ADD $0x20,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV -0xa0(%RBP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
SUB %RAX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
JB 47c161 <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x4a1>	1	0.50	0	0	0	0.50	0	0	0	1	0.50-1
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
CMP -0x38(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	1	0.33
JLE 47c161 <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x4a1>	1	0.50	0	0	0	0.50	0	0	0	1	0.50-1
MOV -0x38(%RBP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %R10,%R8	1	0	0	0	0	0	0	0	0	0	0.17
MOV -0x90(%RBP),%RDI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
IMUL %RDI,%R8	1	0	1	0	0	0	0	0	0	3	1
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0.25
TEST %RDI,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV $0,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
CMOVG %RDI,%RCX	1	0.50	0	0	0.50	0	0	0	0	1	0.50
NOT %R10	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV $0,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
CMOVS %RDI,%RDX	1	0.50	0	0	0.50	0	0	0	0	1	0.50
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0.17
IMUL %RCX,%RSI	1	0	1	0	0	0	0	0	0	3	1
MOV %RSI,-0xb8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
IMUL %R10,%RCX	1	0	1	0	0	0	0	0	0	3	1
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0.17
IMUL %RDX,%RCX	1	0	1	0	0	0	0	0	0	3	1
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
IMUL %R10,%RDX	1	0	1	0	0	0	0	0	0	3	1
MOV %RDX,-0xc0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
ADD %RAX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0x70(%RBP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV -0x78(%RBP),%RDX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
SUB %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0.17
AND $-0x2,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA (,%RDX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA (%RAX,%R8,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
ADD -0x48(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	1	0.33
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV -0x68(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
LEA (,%RAX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA (,%RDI,8),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %R8,-0xd0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA (%RDX,%R8,1),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
JMP 47beef <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x22f>	1	0.50	0	0	0	0.50	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0.09
LEA 0xe02b8(%RIP),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0x4c(%RBP),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
ADD $0x108,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	1	0.33
JMP 403050 <__kmpc_for_static_fini@plt>	1	0.50	0	0	0	0.50	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09

Source file and lines	Collapse.hpp:81-83
Module	exec

The function is defined in:

/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Layout.hpp:55
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/openmp/kernel/Collapse.hpp:81-83
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp:59
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp:55,177
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/View.hpp:79,110
/beegfs/hackathon/users/eoseret/qaas_runs/170-850-6313/intel/Kripke/build/Kripke/src/Kripke/Kernel/LPlusTimes.cpp:57

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

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 208 bytes. The binary function is storing 232 bytes.

General properties

nb instructions	123
nb uops	117
loop length	624
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	30

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	19.50 cycles
front end	19.50 cycles

Back-end

	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	FP0	FP1	FP2	FP3	FP4	FP5
uops	9.25	9.25	9.00	9.00	2.50	19.33	19.33	19.33	0.00	0.00	0.00	0.00	0.00	0.00
cycles	9.25	9.25	9.00	9.00	2.50	19.33	19.33	19.33	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

ALU0/BRU0: ALU
ALU1: ALU
ALU2: ALU
ALU3: ALU
BRU1:
AGU0 (256 bits): store address, load
AGU1 (256 bits): store address, load
AGU2 (256 bits): store address, load
FP0 (256 bits): VPU, DIV/SQRT
FP1 (256 bits): VPU, DIV/SQRT
FP2 (256 bits): VPU
FP3 (256 bits): VPU
FP4 (256 bits): FP store data
FP5 (256 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	19.50
Dispatch	19.33
Overall L1	19.50

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	10%
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 19.50 cycles. At this rate:

11% of peak load performance is reached (10.67 out of 96.00 bytes loaded per cycle (GB/s @ 1GHz))
18% of peak store performance is reached (11.90 out of 64.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Performance is limited by instruction throughput (loading/decoding program instructions to execution core) (front-end is a bottleneck).

ASM code

In the binary file, the address of the function is: 47bcc0

Instruction	Nb FU	ALU0/BRU0	ALU1	ALU2	ALU3	BRU1	AGU0	AGU1	AGU2	Latency	Recip. throughput
PUSH %RBP	1	0	0	0	0	0	0	0	0	1	0.50
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0.17
PUSH %R15	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R14	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R13	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %R12	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %RBX	1	0	0	0	0	0	0	0	0	1	0.50
SUB $0x108,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RDX,%RBX	1	0	0	0	0	0	0	0	0	0	0.17
MOVL $0,-0x50(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV (%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x110(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x10(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x18(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x20(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x30(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x38(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x60(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x100(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x68(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xf8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xa8(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV (%RDI),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %R9,-0xa0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xc0(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xf0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0xf0(%R8),%R12	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV 0x110(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x118(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV 0x158(%R8),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOVQ $0,-0xa8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOVQ $0x1,-0x128(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
SUB $0x8,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0x128(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA 0xe065f(%RIP),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0x50(%RBP),%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0xa8(%RBP),%R8	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA -0xa0(%RBP),%R9	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %ESI,-0x4c(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV $0x22,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
PUSH $0x1	1	0	0	0	0	0	0	0	0	1	0.50
PUSH $0x1	1	0	0	0	0	0	0	0	0	1	0.50
PUSH %RAX	1	0	0	0	0	0	0	0	0	1	0.50
CALL 403140 <__kmpc_for_static_init_8@plt>	2	0.50	0	0	0	0.50	0.33	0.33	0.33	0	0.50
ADD $0x20,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV -0xa0(%RBP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
SUB %RAX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RCX,-0xe0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
JB 47c161 <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x4a1>	1	0.50	0	0	0	0.50	0	0	0	1	0.50-1
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
CMP -0x38(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	1	0.33
JLE 47c161 <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x4a1>	1	0.50	0	0	0	0.50	0	0	0	1	0.50-1
MOV -0x38(%RBP),%R10	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %R10,%R8	1	0	0	0	0	0	0	0	0	0	0.17
MOV -0x90(%RBP),%RDI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
IMUL %RDI,%R8	1	0	1	0	0	0	0	0	0	3	1
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0.25
TEST %RDI,%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV $0,%ECX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
CMOVG %RDI,%RCX	1	0.50	0	0	0.50	0	0	0	0	1	0.50
NOT %R10	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV $0,%EDX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
CMOVS %RDI,%RDX	1	0.50	0	0	0.50	0	0	0	0	1	0.50
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0.17
IMUL %RCX,%RSI	1	0	1	0	0	0	0	0	0	3	1
MOV %RSI,-0xb8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
IMUL %R10,%RCX	1	0	1	0	0	0	0	0	0	3	1
MOV %RCX,-0xc8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0.17
IMUL %RDX,%RCX	1	0	1	0	0	0	0	0	0	3	1
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
IMUL %R10,%RDX	1	0	1	0	0	0	0	0	0	3	1
MOV %RDX,-0xc0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
ADD %RAX,%R10	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0x70(%RBP),%RCX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
MOV -0x78(%RBP),%RDX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
SUB %RDX,%RCX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0.17
AND $-0x2,%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA -0x1(%RAX),%RSI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA (,%RDX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
LEA (%RAX,%R8,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
ADD -0x48(%RBP),%RAX	1	0.25	0.25	0.25	0.25	0	0.33	0.33	0.33	1	0.33
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV -0x68(%RBP),%RAX	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
LEA (,%RAX,8),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA (,%RDI,8),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %R8,-0xd0(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
LEA (%RDX,%R8,1),%RAX	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
MOV %RBX,-0xd8(%RBP)	1	0	0	0	0	0	0.33	0.33	0.33	4	0.50
JMP 47beef <_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted+0x22f>	1	0.50	0	0	0	0.50	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09
XCHG %AX,%AX	0	0	0	0	0	0	0	0	0	0	0.09
LEA 0xe02b8(%RIP),%RDI	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
MOV -0x4c(%RBP),%ESI	1	0	0	0	0	0	0.33	0.33	0.33	3	0.33
ADD $0x108,%RSP	1	0.25	0.25	0.25	0.25	0	0	0	0	1	0.25
POP %RBX	1	0	0	0	0	0	0	0	0	1	0.33
POP %R12	1	0	0	0	0	0	0	0	0	1	0.33
POP %R13	1	0	0	0	0	0	0	0	0	1	0.33
POP %R14	1	0	0	0	0	0	0	0	0	1	0.33
POP %R15	1	0	0	0	0	0	0	0	0	1	0.33
POP %RBP	1	0	0	0	0	0	0	0	0	1	0.33
JMP 403050 <__kmpc_for_static_fini@plt>	1	0.50	0	0	0	0.50	0	0	0	0	1
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0.09

Name	Coverage (%)	Time (s)
▼_ZNK14LPlusTimesSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_SB_RNS8_5FieldIdJNS1_6MomentENS1_5GroupENS1_4ZoneEEEERNSC_IdJNS1_9DirectionESE_SF_EEERNSC_IdJSI_SD_EEE.extracted–	7.12	2.01
▼Loop 1208 - forall.hpp:59-59 - exec–	0.01	0
▼Loop 1211 - forall.hpp:59-59 - exec–	0.01	0
○Loop 1213 - forall.hpp:59-59 - exec	7.1	1.94
○Loop 1212 - forall.hpp:59-59 - exec	0	0
▼Loop 1209 - forall.hpp:59-59 - exec–	0	0
○Loop 1210 - forall.hpp:59-59 - exec	0	0

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL 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

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