OV - exec - Function generate_chunk(int, global_variables&) [clone .omp

	Function: generate_chunk(int, global_variables&) [clone .omp_outlined]	Module: exec	Source: generate_chunk.cpp:74-80 [...]	Coverage (incl. loops): 0.04% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 69 - 69

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

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp: 74 - 80

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

74: #pragma omp parallel for simd collapse(2)

75:   for (int j = (0); j < (yrange); j++) {

76:     for (int i = (0); i < (xrange); i++) {

77:       field.energy0(i, j) = state_energy[0];

78:       field.density0(i, j) = state_density[0];

79:       field.xvel0(i, j) = state_xvel[0];

80:       field.yvel0(i, j) = state_yvel[0];

0x23e370 MOV	(%RDX),%EDX

0x23e372 TEST	%EDX,%EDX

0x23e374 JLE	23e778

0x23e37a PUSH	%RBP

0x23e37b MOV	%RSP,%RBP

0x23e37e PUSH	%R15

0x23e380 PUSH	%R14

0x23e382 PUSH	%R13

0x23e384 PUSH	%R12

0x23e386 PUSH	%RBX

0x23e387 SUB	$0xb8,%RSP

0x23e38e MOV	(%RCX),%R13D

0x23e391 TEST	%R13D,%R13D

0x23e394 JLE	23e767

0x23e39a MOV	%R9,%R15

0x23e39d MOV	%R8,%R14

0x23e3a0 MOVSXD	%R13D,%RBX

0x23e3a3 MOV	%RDX,%R12

0x23e3a6 IMUL	%RBX,%R12

0x23e3aa DEC	%R12

0x23e3ad MOVQ	$0,-0xa0(%RBP)

0x23e3b8 MOV	%R12,-0x40(%RBP)

0x23e3bc MOVQ	$0x1,-0xd8(%RBP)

0x23e3c7 MOVL	$0,-0x4c(%RBP)

0x23e3ce MOV	(%RDI),%ESI

0x23e3d0 SUB	$0x8,%RSP

0x23e3d4 LEA	-0xd8(%RBP),%RAX

0x23e3db LEA	0x2047e(%RIP),%RDI

0x23e3e2 LEA	-0x4c(%RBP),%RCX

0x23e3e6 LEA	-0xa0(%RBP),%R8

0x23e3ed LEA	-0x40(%RBP),%R9

0x23e3f1 MOV	%ESI,-0x44(%RBP)

0x23e3f4 MOV	$0x22,%EDX

0x23e3f9 PUSH	$0x1

0x23e3fb PUSH	$0x1

0x23e3fd PUSH	%RAX

0x23e3fe CALL	25ccf0 <@plt_start@+0x530>

0x23e403 MOV	%R12,%RDI

0x23e406 ADD	$0x20,%RSP

0x23e40a MOV	-0x40(%RBP),%RAX

0x23e40e CMP	%R12,%RAX

0x23e411 CMOVL	%RAX,%RDI

0x23e415 MOV	%RDI,-0x40(%RBP)

0x23e419 MOV	-0xa0(%RBP),%RSI

0x23e420 CMP	%RDI,%RSI

0x23e423 JG	23e758

0x23e429 MOV	0x20(%RBP),%RAX

0x23e42d MOV	0x18(%RBP),%RCX

0x23e431 MOV	0x10(%RBP),%RDX

0x23e435 MOV	0x8(%R15),%R8

0x23e439 MOV	0x40(%R14),%R10

0x23e43d MOV	0x30(%R14),%R11

0x23e441 MOV	0x8(%RDX),%R12

0x23e445 MOV	(%R14),%R15

0x23e448 MOV	0x10(%R14),%R9

0x23e44c MOV	0x8(%RCX),%RCX

0x23e450 MOV	%RCX,-0x38(%RBP)

0x23e454 MOV	0xb8(%R14),%RCX

0x23e45b MOV	%RCX,-0x98(%RBP)

0x23e462 MOV	0xa8(%R14),%RCX

0x23e469 MOV	%RCX,-0x90(%RBP)

0x23e470 MOV	0x8(%RAX),%RAX

0x23e474 MOV	%RAX,-0x88(%RBP)

0x23e47b MOV	0xe8(%R14),%RAX

0x23e482 MOV	%RAX,-0x80(%RBP)

0x23e486 MOV	0xd8(%R14),%RAX

0x23e48d MOV	%RAX,-0x78(%RBP)

0x23e491 MOV	%RDI,%RAX

0x23e494 SUB	%RSI,%RAX

0x23e497 INC	%RAX

0x23e49a CMP	$0x4,%RAX

0x23e49e MOV	%R8,-0x30(%RBP)

0x23e4a2 JAE	23e4b0

0x23e4a4 MOV	%RSI,%RCX

0x23e4a7 MOV	-0x38(%RBP),%R14

0x23e4ab JMP	23e807

0x23e4b0 MOV	%R9,-0x58(%RBP)

0x23e4b4 MOV	%R15,-0x60(%RBP)

0x23e4b8 MOV	%R11,-0x68(%RBP)

0x23e4bc MOV	%R10,-0x70(%RBP)

0x23e4c0 MOV	%RDI,-0xb8(%RBP)

0x23e4c7 MOV	%RAX,-0xb0(%RBP)

0x23e4ce AND	$-0x4,%RAX

0x23e4d2 LEA	(%RSI,%RAX,1),%RCX

0x23e4d6 MOV	%RAX,-0xa8(%RBP)

0x23e4dd MOV	%RAX,%RDX

0x23e4e0 MOV	%R13D,-0x48(%RBP)

0x23e4e4 MOV	%RBX,-0xc8(%RBP)

0x23e4eb MOV	%R12,-0xc0(%RBP)

0x23e4f2 JMP	23e67a

0x23e4f7 NOPW	(%RAX,%RAX,1)

(226) 0x23e500 CQTO

(226) 0x23e502 IDIV	%RBX

(226) 0x23e505 MOVSD	(%R8),%XMM0

(226) 0x23e50a MOVSXD	%R15D,%R8

(226) 0x23e50d MOVSXD	%R10D,%R10

(226) 0x23e510 MOVSXD	%R14D,%R14

(226) 0x23e513 MOVSXD	%EDX,%RDX

(226) 0x23e516 MOVSXD	%EDI,%R15

(226) 0x23e519 MOVSXD	%R9D,%R9

(226) 0x23e51c MOVSXD	%R11D,%R11

(226) 0x23e51f CLTQ

(226) 0x23e521 MOV	%R15,%R13

(226) 0x23e524 MOV	-0x68(%RBP),%RBX

(226) 0x23e528 IMUL	%RBX,%R13

(226) 0x23e52c ADD	%R8,%R13

(226) 0x23e52f MOV	-0x70(%RBP),%R12

(226) 0x23e533 MOVSD	%XMM0,(%R12,%R13,8)

(226) 0x23e539 MOV	%R9,%R13

(226) 0x23e53c IMUL	%RBX,%R13

(226) 0x23e540 ADD	%R10,%R13

(226) 0x23e543 MOVSD	%XMM0,(%R12,%R13,8)

(226) 0x23e549 MOV	%R11,%R13

(226) 0x23e54c IMUL	%RBX,%R13

(226) 0x23e550 ADD	%R14,%R13

(226) 0x23e553 MOVSD	%XMM0,(%R12,%R13,8)

(226) 0x23e559 MOV	%RAX,%R13

(226) 0x23e55c IMUL	%RBX,%R13

(226) 0x23e560 ADD	%RDX,%R13

(226) 0x23e563 MOVSD	%XMM0,(%R12,%R13,8)

(226) 0x23e569 MOV	-0xc0(%RBP),%R12

(226) 0x23e570 MOVSD	(%R12),%XMM0

(226) 0x23e576 MOV	%R15,%R13

(226) 0x23e579 MOV	-0x60(%RBP),%RBX

(226) 0x23e57d IMUL	%RBX,%R13

(226) 0x23e581 ADD	%R8,%R13

(226) 0x23e584 MOV	-0x58(%RBP),%RDI

(226) 0x23e588 MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e58e MOV	%R9,%R13

(226) 0x23e591 IMUL	%RBX,%R13

(226) 0x23e595 ADD	%R10,%R13

(226) 0x23e598 MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e59e MOV	%R11,%R13

(226) 0x23e5a1 IMUL	%RBX,%R13

(226) 0x23e5a5 ADD	%R14,%R13

(226) 0x23e5a8 MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e5ae MOV	%RAX,%R13

(226) 0x23e5b1 IMUL	%RBX,%R13

(226) 0x23e5b5 ADD	%RDX,%R13

(226) 0x23e5b8 MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e5be MOV	-0x38(%RBP),%RDI

(226) 0x23e5c2 MOVSD	(%RDI),%XMM0

(226) 0x23e5c6 MOV	%R15,%R13

(226) 0x23e5c9 MOV	-0x90(%RBP),%RBX

(226) 0x23e5d0 IMUL	%RBX,%R13

(226) 0x23e5d4 ADD	%R8,%R13

(226) 0x23e5d7 MOV	-0x98(%RBP),%RDI

(226) 0x23e5de MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e5e4 MOV	%R9,%R13

(226) 0x23e5e7 IMUL	%RBX,%R13

(226) 0x23e5eb ADD	%R10,%R13

(226) 0x23e5ee MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e5f4 MOV	%R11,%R13

(226) 0x23e5f7 IMUL	%RBX,%R13

(226) 0x23e5fb ADD	%R14,%R13

(226) 0x23e5fe MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e604 MOV	%RAX,%R13

(226) 0x23e607 IMUL	%RBX,%R13

(226) 0x23e60b ADD	%RDX,%R13

(226) 0x23e60e MOVSD	%XMM0,(%RDI,%R13,8)

(226) 0x23e614 MOV	-0x78(%RBP),%RDI

(226) 0x23e618 IMUL	%RDI,%R15

(226) 0x23e61c ADD	%R8,%R15

(226) 0x23e61f IMUL	%RDI,%R9

(226) 0x23e623 ADD	%R10,%R9

(226) 0x23e626 IMUL	%RDI,%R11

(226) 0x23e62a ADD	%R14,%R11

(226) 0x23e62d IMUL	%RDI,%RAX

(226) 0x23e631 ADD	%RDX,%RAX

(226) 0x23e634 MOV	-0x88(%RBP),%RDX

(226) 0x23e63b MOVSD	(%RDX),%XMM0

(226) 0x23e63f MOV	-0x80(%RBP),%RDX

(226) 0x23e643 MOVSD	%XMM0,(%RDX,%R15,8)

(226) 0x23e649 MOVSD	%XMM0,(%RDX,%R9,8)

(226) 0x23e64f MOVSD	%XMM0,(%RDX,%R11,8)

(226) 0x23e655 MOVSD	%XMM0,(%RDX,%RAX,8)

(226) 0x23e65a ADD	$0x4,%RSI

(226) 0x23e65e MOV	-0xd0(%RBP),%RDX

(226) 0x23e665 ADD	$-0x4,%RDX

(226) 0x23e669 MOV	-0x48(%RBP),%R13D

(226) 0x23e66d MOV	-0xc8(%RBP),%RBX

(226) 0x23e674 JE	23e729

(226) 0x23e67a MOV	%RSI,%RAX

(226) 0x23e67d OR	%RBX,%RAX

(226) 0x23e680 SHR	$0x20,%RAX

(226) 0x23e684 MOV	%RDX,-0xd0(%RBP)

(226) 0x23e68b JE	23e6a0

(226) 0x23e68d MOV	%RSI,%RAX

(226) 0x23e690 CQTO

(226) 0x23e692 IDIV	%RBX

(226) 0x23e695 MOV	%RDX,%R15

(226) 0x23e698 MOV	%RAX,%RDI

(226) 0x23e69b JMP	23e6ac

0x23e69d NOPL	(%RAX)

(226) 0x23e6a0 MOV	%ESI,%EAX

(226) 0x23e6a2 XOR	%EDX,%EDX

(226) 0x23e6a4 DIV	%R13D

(226) 0x23e6a7 MOV	%EDX,%R15D

(226) 0x23e6aa MOV	%EAX,%EDI

(226) 0x23e6ac MOV	-0x30(%RBP),%R8

(226) 0x23e6b0 LEA	0x1(%RSI),%RAX

(226) 0x23e6b4 MOV	%RAX,%RDX

(226) 0x23e6b7 OR	%RBX,%RDX

(226) 0x23e6ba SHR	$0x20,%RDX

(226) 0x23e6be JE	23e6d0

(226) 0x23e6c0 CQTO

(226) 0x23e6c2 IDIV	%RBX

(226) 0x23e6c5 MOV	%RDX,%R10

(226) 0x23e6c8 MOV	%RAX,%R9

(226) 0x23e6cb JMP	23e6db

0x23e6cd NOPL	(%RAX)

(226) 0x23e6d0 XOR	%EDX,%EDX

(226) 0x23e6d2 DIV	%R13D

(226) 0x23e6d5 MOV	%EDX,%R10D

(226) 0x23e6d8 MOV	%EAX,%R9D

(226) 0x23e6db LEA	0x2(%RSI),%RAX

(226) 0x23e6df MOV	%RAX,%RDX

(226) 0x23e6e2 OR	%RBX,%RDX

(226) 0x23e6e5 SHR	$0x20,%RDX

(226) 0x23e6e9 JE	23e700

(226) 0x23e6eb CQTO

(226) 0x23e6ed IDIV	%RBX

(226) 0x23e6f0 MOV	%RDX,%R14

(226) 0x23e6f3 MOV	%RAX,%R11

(226) 0x23e6f6 JMP	23e70b

0x23e6f8 NOPL	(%RAX,%RAX,1)

(226) 0x23e700 XOR	%EDX,%EDX

(226) 0x23e702 DIV	%R13D

(226) 0x23e705 MOV	%EDX,%R14D

(226) 0x23e708 MOV	%EAX,%R11D

(226) 0x23e70b LEA	0x3(%RSI),%RAX

(226) 0x23e70f MOV	%RAX,%RDX

(226) 0x23e712 OR	%RBX,%RDX

(226) 0x23e715 SHR	$0x20,%RDX

(226) 0x23e719 JNE	23e500

(226) 0x23e71f XOR	%EDX,%EDX

(226) 0x23e721 DIV	%R13D

(226) 0x23e724 JMP	23e505

0x23e729 MOV	-0xa8(%RBP),%RAX

0x23e730 CMP	%RAX,-0xb0(%RBP)

0x23e737 MOV	-0xb8(%RBP),%RDI

0x23e73e MOV	-0x70(%RBP),%R10

0x23e742 MOV	-0x68(%RBP),%R11

0x23e746 MOV	-0x60(%RBP),%R15

0x23e74a MOV	-0x58(%RBP),%R9

0x23e74e MOV	-0x38(%RBP),%R14

0x23e752 JNE	23e807

0x23e758 LEA	0x20119(%RIP),%RDI

0x23e75f MOV	-0x44(%RBP),%ESI

0x23e762 CALL	25cd00 <@plt_start@+0x540>

0x23e767 ADD	$0xb8,%RSP

0x23e76e POP	%RBX

0x23e76f POP	%R12

0x23e771 POP	%R13

0x23e773 POP	%R14

0x23e775 POP	%R15

0x23e777 POP	%RBP

0x23e778 RET

0x23e779 NOPL	(%RAX)

(225) 0x23e780 MOV	%RCX,%RAX

(225) 0x23e783 CQTO

(225) 0x23e785 IDIV	%RBX

(225) 0x23e788 MOV	-0x30(%RBP),%RSI

(225) 0x23e78c MOV	%R10,%R8

(225) 0x23e78f MOVSD	(%RSI),%XMM0

(225) 0x23e793 MOVSXD	%EDX,%RDX

(225) 0x23e796 CLTQ

(225) 0x23e798 MOV	%RAX,%RSI

(225) 0x23e79b IMUL	%R11,%RSI

(225) 0x23e79f ADD	%RDX,%RSI

(225) 0x23e7a2 MOVSD	%XMM0,(%R10,%RSI,8)

(225) 0x23e7a8 MOVSD	(%R12),%XMM0

(225) 0x23e7ae MOV	%RAX,%RSI

(225) 0x23e7b1 IMUL	%R15,%RSI

(225) 0x23e7b5 ADD	%RDX,%RSI

(225) 0x23e7b8 MOVSD	%XMM0,(%R9,%RSI,8)

(225) 0x23e7be MOVSD	(%R14),%XMM0

(225) 0x23e7c3 MOV	%RAX,%RSI

(225) 0x23e7c6 IMUL	-0x90(%RBP),%RSI

(225) 0x23e7ce ADD	%RDX,%RSI

(225) 0x23e7d1 MOV	-0x98(%RBP),%R8

(225) 0x23e7d8 MOVSD	%XMM0,(%R8,%RSI,8)

(225) 0x23e7de IMUL	-0x78(%RBP),%RAX

(225) 0x23e7e3 ADD	%RDX,%RAX

(225) 0x23e7e6 MOV	-0x88(%RBP),%RDX

(225) 0x23e7ed MOVSD	(%RDX),%XMM0

(225) 0x23e7f1 MOV	-0x80(%RBP),%RDX

(225) 0x23e7f5 MOVSD	%XMM0,(%RDX,%RAX,8)

(225) 0x23e7fa CMP	%RDI,%RCX

(225) 0x23e7fd LEA	0x1(%RCX),%RCX

(225) 0x23e801 JGE	23e758

(225) 0x23e807 MOV	%RCX,%RAX

(225) 0x23e80a OR	%RBX,%RAX

(225) 0x23e80d SHR	$0x20,%RAX

(225) 0x23e811 JNE	23e780

(225) 0x23e817 MOV	%ECX,%EAX

(225) 0x23e819 XOR	%EDX,%EDX

(225) 0x23e81b DIV	%R13D

(225) 0x23e81e JMP	23e788

0x23e823 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module

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 orig_0

Source file and lines	generate_chunk.cpp:74-80
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:74-80

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 14.13 to 1.28 cycles (11.02x 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.

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:74
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp: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.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:75

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 224 bytes. The binary function is storing 172 bytes.

General properties

nb instructions	116
nb uops	113
loop length	514
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	25

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.13 cycles
front end	14.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.00	6.00	6.00	6.00	6.00	6.00	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.00	6.00	6.00	6.00	6.00	6.00	13.75	13.75	13.75	13.75	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	14.13
Dispatch	13.75
Overall L1	14.13

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	11%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.13 cycles. At this rate:

6% of peak load performance is reached (15.86 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.18 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).

ASM code

In the binary file, the address of the function is: 23e370

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RDX),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EDX,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23e778 <_Z14generate_chunkiR16global_variables.omp_outlined+0x408>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
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 $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RCX),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
TEST %R13D,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23e767 <_Z14generate_chunkiR16global_variables.omp_outlined+0x3f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R9,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSXD %R13D,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %RBX,%R12	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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%)
MOV %R12,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x4c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 -0xd8(%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 0x2047e(%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 -0x4c(%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 -0x40(%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,-0x44(%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 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	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 -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%RDI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RDI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 23e758 <_Z14generate_chunkiR16global_variables.omp_outlined+0x3e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%R15),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x40(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x30(%R14),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RDX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R14),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb8(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xa8(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	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 0xe8(%R14),%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 0xd8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	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%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x4,%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 %R8,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 23e4b0 <_Z14generate_chunkiR16global_variables.omp_outlined+0x140>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 23e807 <_Z14generate_chunkiR16global_variables.omp_outlined+0x497>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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%)
AND $-0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	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 %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13D,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 23e67a <_Z14generate_chunkiR16global_variables.omp_outlined+0x30a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	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
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xb0(%RBP)	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%)
MOV -0xb8(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x70(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x68(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x60(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x38(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 23e807 <_Z14generate_chunkiR16global_variables.omp_outlined+0x497>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x20119(%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 -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0xb8,%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
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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run orig_0

Source file and lines	generate_chunk.cpp:74-80
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:74-80

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

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:74
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp: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.

CMOVL: 1 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:75

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 224 bytes. The binary function is storing 172 bytes.

General properties

nb instructions	116
nb uops	113
loop length	514
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	25

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.13 cycles
front end	14.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.00	6.00	6.00	6.00	6.00	6.00	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.00	6.00	6.00	6.00	6.00	6.00	13.75	13.75	13.75	13.75	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	14.13
Dispatch	13.75
Overall L1	14.13

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	11%
store	11%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.13 cycles. At this rate:

6% of peak load performance is reached (15.86 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.18 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).

ASM code

In the binary file, the address of the function is: 23e370

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	Latency	Recip. throughput	Vectorization
MOV (%RDX),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EDX,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23e778 <_Z14generate_chunkiR16global_variables.omp_outlined+0x408>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
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 $0xb8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RCX),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
TEST %R13D,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23e767 <_Z14generate_chunkiR16global_variables.omp_outlined+0x3f7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R9,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVSXD %R13D,%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %RBX,%R12	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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%)
MOV %R12,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x4c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 -0xd8(%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 0x2047e(%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 -0x4c(%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 -0x40(%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,-0x44(%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 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
MOV %R12,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	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 -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%RDI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %RDI,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RDI,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 23e758 <_Z14generate_chunkiR16global_variables.omp_outlined+0x3e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x8(%R15),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x40(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x30(%R14),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RDX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%R14),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x8(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xb8(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xa8(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x8(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	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 0xe8(%R14),%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 0xd8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	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%)
MOV %RDI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x4,%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 %R8,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 23e4b0 <_Z14generate_chunkiR16global_variables.omp_outlined+0x140>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 23e807 <_Z14generate_chunkiR16global_variables.omp_outlined+0x497>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R9,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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%)
AND $-0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RAX,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	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 %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13D,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 23e67a <_Z14generate_chunkiR16global_variables.omp_outlined+0x30a>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPL (%RAX)	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
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xb0(%RBP)	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%)
MOV -0xb8(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x70(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x68(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x60(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x58(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x38(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 23e807 <_Z14generate_chunkiR16global_variables.omp_outlined+0x497>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x20119(%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 -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0xb8,%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
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

Name	Coverage (%)	Time (s)
▼generate_chunk(int, global_variables&) [clone .omp_outlined]–	0.04	0.02
○Loop 226 - generate_chunk.cpp:75-80 - exec	0.04	0.02
○Loop 225 - generate_chunk.cpp:75-80 - 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