OV - exec - Function build_field(global_variables&) [clone .omp

	Function: build_field(global_variables&) [clone .omp_outlined.6]	Module: exec	Source: build_field.cpp:143-148 [...]	Coverage (incl. loops): 0.02% \| (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/build_field.cpp: 143 - 148

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

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

144:     for (int j = (0); j < (yrange + 1); j++) {

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

146:         field.vol_flux_y(i, j) = 0.0;

147:         field.mass_flux_y(i, j) = 0.0;

148:         field.yarea(i, j) = 0.0;

0x239460 PUSH	%RBP

0x239461 MOV	%RSP,%RBP

0x239464 PUSH	%R15

0x239466 PUSH	%R14

0x239468 PUSH	%R13

0x23946a PUSH	%R12

0x23946c PUSH	%RBX

0x23946d SUB	$0x58,%RSP

0x239471 MOV	(%RDX),%R15D

0x239474 TEST	%R15D,%R15D

0x239477 JS	23967f

0x23947d MOV	(%RCX),%EAX

0x23947f TEST	%EAX,%EAX

0x239481 JLE	23967f

0x239487 MOV	%R8,%R14

0x23948a MOV	%EAX,-0x2c(%RBP)

0x23948d MOVSXD	%EAX,%R13

0x239490 INC	%R15

0x239493 IMUL	%R13,%R15

0x239497 DEC	%R15

0x23949a MOVQ	$0,-0x58(%RBP)

0x2394a2 MOV	%R15,-0x38(%RBP)

0x2394a6 MOVQ	$0x1,-0x80(%RBP)

0x2394ae MOVL	$0,-0x40(%RBP)

0x2394b5 MOV	(%RDI),%ESI

0x2394b7 SUB	$0x8,%RSP

0x2394bb LEA	-0x80(%RBP),%RAX

0x2394bf LEA	0x2512a(%RIP),%RDI

0x2394c6 LEA	-0x40(%RBP),%RCX

0x2394ca LEA	-0x58(%RBP),%R8

0x2394ce LEA	-0x38(%RBP),%R9

0x2394d2 MOV	%ESI,-0x3c(%RBP)

0x2394d5 MOV	$0x22,%EDX

0x2394da PUSH	$0x1

0x2394dc PUSH	$0x1

0x2394de PUSH	%RAX

0x2394df CALL	25ccf0 <@plt_start@+0x530>

0x2394e4 ADD	$0x20,%RSP

0x2394e8 MOV	-0x38(%RBP),%RAX

0x2394ec CMP	%R15,%RAX

0x2394ef CMOVL	%RAX,%R15

0x2394f3 MOV	%R15,-0x38(%RBP)

0x2394f7 MOV	-0x58(%RBP),%RSI

0x2394fb CMP	%R15,%RSI

0x2394fe JG	239670

0x239504 MOV	0x138(%R14),%RDI

0x23950b MOV	0x148(%R14),%R8

0x239512 MOV	0x160(%R14),%R10

0x239519 MOV	0x150(%R14),%RBX

0x239520 MOV	0x2d0(%R14),%R12

0x239527 MOV	0x2c0(%R14),%R14

0x23952e MOV	%R15,%RAX

0x239531 SUB	%RSI,%RAX

0x239534 INC	%RAX

0x239537 CMP	$0x2,%RAX

0x23953b JAE	239545

0x23953d MOV	%RSI,%RCX

0x239540 JMP	2396dc

0x239545 MOV	%R8,-0x48(%RBP)

0x239549 MOV	%RDI,-0x50(%RBP)

0x23954d MOV	%R15,-0x70(%RBP)

0x239551 MOV	%RAX,-0x68(%RBP)

0x239555 MOV	%RAX,%R15

0x239558 AND	$-0x2,%R15

0x23955c LEA	(%RSI,%R15,1),%RCX

0x239560 MOV	%R15,-0x60(%RBP)

0x239564 MOV	%R10,-0x78(%RBP)

0x239568 MOV	-0x48(%RBP),%R11

0x23956c JMP	239608

0x239571 NOPW	%CS:(%RAX,%RAX,1)

(191) 0x239580 CQTO

(191) 0x239582 IDIV	%R13

(191) 0x239585 MOVSXD	%R8D,%R8

(191) 0x239588 MOVSXD	%EDX,%RDX

(191) 0x23958b MOVSXD	%EDI,%R9

(191) 0x23958e CLTQ

(191) 0x239590 MOV	%R9,%RDI

(191) 0x239593 MOV	-0x50(%RBP),%R10

(191) 0x239597 IMUL	%R10,%RDI

(191) 0x23959b ADD	%R8,%RDI

(191) 0x23959e MOVQ	$0,(%R11,%RDI,8)

(191) 0x2395a6 MOV	%RAX,%RDI

(191) 0x2395a9 IMUL	%R10,%RDI

(191) 0x2395ad ADD	%RDX,%RDI

(191) 0x2395b0 MOVQ	$0,(%R11,%RDI,8)

(191) 0x2395b8 MOV	%R9,%RDI

(191) 0x2395bb IMUL	%RBX,%RDI

(191) 0x2395bf ADD	%R8,%RDI

(191) 0x2395c2 MOV	-0x78(%RBP),%R10

(191) 0x2395c6 MOVQ	$0,(%R10,%RDI,8)

(191) 0x2395ce MOV	%RAX,%RDI

(191) 0x2395d1 IMUL	%RBX,%RDI

(191) 0x2395d5 ADD	%RDX,%RDI

(191) 0x2395d8 MOVQ	$0,(%R10,%RDI,8)

(191) 0x2395e0 IMUL	%R14,%R9

(191) 0x2395e4 ADD	%R8,%R9

(191) 0x2395e7 IMUL	%R14,%RAX

(191) 0x2395eb ADD	%RDX,%RAX

(191) 0x2395ee MOVQ	$0,(%R12,%R9,8)

(191) 0x2395f6 MOVQ	$0,(%R12,%RAX,8)

(191) 0x2395fe ADD	$0x2,%RSI

(191) 0x239602 ADD	$-0x2,%R15

(191) 0x239606 JE	23965a

(191) 0x239608 MOV	%RSI,%RAX

(191) 0x23960b OR	%R13,%RAX

(191) 0x23960e SHR	$0x20,%RAX

(191) 0x239612 JE	239630

(191) 0x239614 MOV	%RSI,%RAX

(191) 0x239617 CQTO

(191) 0x239619 IDIV	%R13

(191) 0x23961c MOV	%RDX,%R8

(191) 0x23961f MOV	%RAX,%RDI

(191) 0x239622 JMP	23963c

0x239624 NOPW	%CS:(%RAX,%RAX,1)

(191) 0x239630 MOV	%ESI,%EAX

(191) 0x239632 XOR	%EDX,%EDX

(191) 0x239634 DIVL	-0x2c(%RBP)

(191) 0x239637 MOV	%EDX,%R8D

(191) 0x23963a MOV	%EAX,%EDI

(191) 0x23963c LEA	0x1(%RSI),%RAX

(191) 0x239640 MOV	%RAX,%RDX

(191) 0x239643 OR	%R13,%RDX

(191) 0x239646 SHR	$0x20,%RDX

(191) 0x23964a JNE	239580

(191) 0x239650 XOR	%EDX,%EDX

(191) 0x239652 DIVL	-0x2c(%RBP)

(191) 0x239655 JMP	239585

0x23965a MOV	-0x60(%RBP),%RAX

0x23965e CMP	%RAX,-0x68(%RBP)

0x239662 MOV	-0x70(%RBP),%R15

0x239666 MOV	-0x50(%RBP),%RDI

0x23966a MOV	-0x48(%RBP),%R8

0x23966e JNE	2396dc

0x239670 LEA	0x24f91(%RIP),%RDI

0x239677 MOV	-0x3c(%RBP),%ESI

0x23967a CALL	25cd00 <@plt_start@+0x540>

0x23967f ADD	$0x58,%RSP

0x239683 POP	%RBX

0x239684 POP	%R12

0x239686 POP	%R13

0x239688 POP	%R14

0x23968a POP	%R15

0x23968c POP	%RBP

0x23968d RET

0x23968e XCHG	%AX,%AX

(190) 0x239690 MOV	%RCX,%RAX

(190) 0x239693 CQTO

(190) 0x239695 IDIV	%R13

(190) 0x239698 MOVSXD	%EDX,%RDX

(190) 0x23969b CLTQ

(190) 0x23969d MOV	%RAX,%RSI

(190) 0x2396a0 IMUL	%RDI,%RSI

(190) 0x2396a4 ADD	%RDX,%RSI

(190) 0x2396a7 MOVQ	$0,(%R8,%RSI,8)

(190) 0x2396af MOV	%RAX,%RSI

(190) 0x2396b2 IMUL	%RBX,%RSI

(190) 0x2396b6 ADD	%RDX,%RSI

(190) 0x2396b9 MOVQ	$0,(%R10,%RSI,8)

(190) 0x2396c1 IMUL	%R14,%RAX

(190) 0x2396c5 ADD	%RDX,%RAX

(190) 0x2396c8 MOVQ	$0,(%R12,%RAX,8)

(190) 0x2396d0 LEA	0x1(%RCX),%RAX

(190) 0x2396d4 CMP	%R15,%RCX

(190) 0x2396d7 MOV	%RAX,%RCX

(190) 0x2396da JGE	239670

(190) 0x2396dc MOV	%RCX,%RAX

(190) 0x2396df OR	%R13,%RAX

(190) 0x2396e2 SHR	$0x20,%RAX

(190) 0x2396e6 JNE	239690

(190) 0x2396e8 MOV	%ECX,%EAX

(190) 0x2396ea XOR	%EDX,%EDX

(190) 0x2396ec DIVL	-0x2c(%RBP)

(190) 0x2396ef JMP	239698

0x2396f1 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	build_field.cpp:143-148
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/build_field.cpp:143-148

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 10% 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 11.13 to 0.83 cycles (13.33x 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.

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:143
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:143

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/build_field.cpp:144

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 128 bytes. The binary function is storing 92 bytes.

General properties

nb instructions	90
nb uops	89
loop length	369
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.13 cycles
front end	11.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.17	6.17	6.17	6.17	6.17	6.17	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.17	6.17	6.17	6.17	6.17	6.17	8.25	8.25	8.25	8.25	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	11.13
Dispatch	8.25
Overall L1	11.13

Vectorization ratios

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

Vector efficiency ratios

all	10%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.13 cycles. At this rate:

4% of peak load performance is reached (11.51 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.27 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 11.13 to 8.25 cycles (1.35x speedup).

ASM code

In the binary file, the address of the function is: 239460

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 $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %R15D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JS 23967f <_Z11build_fieldR16global_variables.omp_outlined.6+0x21f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23967f <_Z11build_fieldR16global_variables.omp_outlined.6+0x21f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVSXD %EAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
INC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x40(%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 -0x80(%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 0x2512a(%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 -0x40(%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 -0x58(%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 -0x38(%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,-0x3c(%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
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 -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%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,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R15,-0x38(%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),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%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 239670 <_Z11build_fieldR16global_variables.omp_outlined.6+0x210>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x138(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x148(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x160(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x150(%R14),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2d0(%R14),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2c0(%R14),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R15,%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 $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 239545 <_Z11build_fieldR16global_variables.omp_outlined.6+0xe5>	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
JMP 2396dc <_Z11build_fieldR16global_variables.omp_outlined.6+0x27c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R15,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %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 %R10,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x48(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 239608 <_Z11build_fieldR16global_variables.omp_outlined.6+0x1a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	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
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x68(%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 -0x70(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2396dc <_Z11build_fieldR16global_variables.omp_outlined.6+0x27c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x24f91(%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 -0x3c(%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 $0x58,%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
XCHG %AX,%AX	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	build_field.cpp:143-148
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/build_field.cpp:143-148

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/build_field.cpp:143
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:143

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/build_field.cpp:144

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 128 bytes. The binary function is storing 92 bytes.

General properties

nb instructions	90
nb uops	89
loop length	369
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	12

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.13 cycles
front end	11.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.17	6.17	6.17	6.17	6.17	6.17	8.25	8.25	8.25	8.25	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.17	6.17	6.17	6.17	6.17	6.17	8.25	8.25	8.25	8.25	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	11.13
Dispatch	8.25
Overall L1	11.13

Vectorization ratios

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

Vector efficiency ratios

all	10%
load	12%
store	10%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	9%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 11.13 cycles. At this rate:

4% of peak load performance is reached (11.51 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.27 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: 239460

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 $0x58,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV (%RDX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %R15D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JS 23967f <_Z11build_fieldR16global_variables.omp_outlined.6+0x21f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
TEST %EAX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JLE 23967f <_Z11build_fieldR16global_variables.omp_outlined.6+0x21f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %EAX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVSXD %EAX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
INC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
IMUL %R13,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	N/A
DEC %R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x40(%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 -0x80(%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 0x2512a(%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 -0x40(%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 -0x58(%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 -0x38(%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,-0x3c(%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
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 -0x38(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%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,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R15,-0x38(%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),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R15,%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 239670 <_Z11build_fieldR16global_variables.omp_outlined.6+0x210>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x138(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x148(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x160(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x150(%R14),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2d0(%R14),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x2c0(%R14),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R15,%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 $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 239545 <_Z11build_fieldR16global_variables.omp_outlined.6+0xe5>	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
JMP 2396dc <_Z11build_fieldR16global_variables.omp_outlined.6+0x27c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%R15	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R15,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %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 %R10,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x48(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JMP 239608 <_Z11build_fieldR16global_variables.omp_outlined.6+0x1a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	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
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x68(%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 -0x70(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x48(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2396dc <_Z11build_fieldR16global_variables.omp_outlined.6+0x27c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x24f91(%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 -0x3c(%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 $0x58,%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
XCHG %AX,%AX	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)
▼build_field(global_variables&) [clone .omp_outlined.6]–	0.02	0.01
○Loop 191 - build_field.cpp:144-148 - exec	0.02	0.01
○Loop 190 - build_field.cpp:144-148 - 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