OV - exec - Function reset_field_kernel(int, int, int, int, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&) [clone .omp

	Function: reset_field_kernel(int, int, int, int, clover::Buffer2D<double>&, clover::Buffer2D<double> ...	Module: exec	Source: reset_field.cpp:34-38 [...]	Coverage (incl. loops): 2.49% \| (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/reset_field.cpp: 34 - 38

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

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

35:   for (int j = (y_min + 1); j < (y_max + 2); j++) {

36:     for (int i = (x_min + 1); i < (x_max + 2); i++) {

37:       density0(i, j) = density1(i, j);

38:       energy0(i, j) = energy1(i, j);

0x246c20 PUSH	%RBP

0x246c21 MOV	%RSP,%RBP

0x246c24 PUSH	%R15

0x246c26 PUSH	%R14

0x246c28 PUSH	%R13

0x246c2a PUSH	%R12

0x246c2c PUSH	%RBX

0x246c2d SUB	$0x68,%RSP

0x246c31 MOV	(%RDX),%EBX

0x246c33 MOV	(%RCX),%EAX

0x246c35 INC	%EBX

0x246c37 ADD	$0x2,%EAX

0x246c3a SUB	%EBX,%EAX

0x246c3c JLE	246e86

0x246c42 MOV	(%R8),%EDX

0x246c45 MOV	(%R9),%R13D

0x246c48 INC	%EDX

0x246c4a ADD	$0x2,%R13D

0x246c4e CMP	%EDX,%R13D

0x246c51 JLE	246e86

0x246c57 SUB	%EDX,%R13D

0x246c5a MOV	%RAX,%R14

0x246c5d IMUL	%R13,%R14

0x246c61 DEC	%R14

0x246c64 MOVQ	$0,-0x68(%RBP)

0x246c6c MOV	%R14,-0x40(%RBP)

0x246c70 MOVQ	$0x1,-0x90(%RBP)

0x246c7b MOVL	$0,-0x48(%RBP)

0x246c82 MOV	(%RDI),%ESI

0x246c84 SUB	$0x8,%RSP

0x246c88 LEA	-0x90(%RBP),%RAX

0x246c8f LEA	0x180ea(%RIP),%RDI

0x246c96 LEA	-0x48(%RBP),%RCX

0x246c9a LEA	-0x68(%RBP),%R8

0x246c9e MOV	%EDX,-0x30(%RBP)

0x246ca1 LEA	-0x40(%RBP),%R9

0x246ca5 MOV	%ESI,-0x44(%RBP)

0x246ca8 MOV	$0x22,%EDX

0x246cad PUSH	$0x1

0x246caf PUSH	$0x1

0x246cb1 PUSH	%RAX

0x246cb2 CALL	25ccf0 <@plt_start@+0x530>

0x246cb7 MOV	-0x30(%RBP),%R9D

0x246cbb MOV	%R14,%R8

0x246cbe ADD	$0x20,%RSP

0x246cc2 MOV	-0x40(%RBP),%RAX

0x246cc6 CMP	%R14,%RAX

0x246cc9 CMOVL	%RAX,%R8

0x246ccd MOV	%R8,-0x40(%RBP)

0x246cd1 MOV	-0x68(%RBP),%RSI

0x246cd5 CMP	%R8,%RSI

0x246cd8 JG	246e77

0x246cde MOV	0x28(%RBP),%RAX

0x246ce2 MOV	0x20(%RBP),%RCX

0x246ce6 MOV	0x18(%RBP),%RDX

0x246cea MOV	0x10(%RBP),%RDI

0x246cee MOV	(%RDX),%R10

0x246cf1 MOV	%R10,-0x38(%RBP)

0x246cf5 MOV	0x10(%RDX),%RDX

0x246cf9 MOV	%RDX,-0x60(%RBP)

0x246cfd MOV	(%RDI),%R14

0x246d00 MOV	0x10(%RDI),%RDX

0x246d04 MOV	%RDX,-0x58(%RBP)

0x246d08 MOV	(%RAX),%R15

0x246d0b MOV	0x10(%RAX),%RAX

0x246d0f MOV	%RAX,-0x50(%RBP)

0x246d13 MOV	(%RCX),%R10

0x246d16 MOV	0x10(%RCX),%R12

0x246d1a MOV	%R8,%RAX

0x246d1d SUB	%RSI,%RAX

0x246d20 INC	%RAX

0x246d23 CMP	$0x2,%RAX

0x246d27 JAE	246d35

0x246d29 MOV	%RSI,%RCX

0x246d2c MOV	-0x38(%RBP),%RDI

0x246d30 JMP	246f08

0x246d35 MOV	%R8,-0x80(%RBP)

0x246d39 MOV	%EBX,-0x2c(%RBP)

0x246d3c MOV	%RAX,-0x78(%RBP)

0x246d40 MOV	%RAX,%R9

0x246d43 AND	$-0x2,%R9

0x246d47 LEA	(%RSI,%R9,1),%RCX

0x246d4b MOV	%R9,-0x70(%RBP)

0x246d4f MOV	%R14,-0x88(%RBP)

0x246d56 JMP	246e14

0x246d5b NOPL	(%RAX,%RAX,1)

(280) 0x246d60 CQTO

(280) 0x246d62 IDIV	%R13

(280) 0x246d65 ADD	%EBX,%EDI

(280) 0x246d67 ADD	%EBX,%EAX

(280) 0x246d69 MOV	-0x30(%RBP),%EBX

(280) 0x246d6c ADD	%EBX,%R8D

(280) 0x246d6f ADD	%EBX,%EDX

(280) 0x246d71 MOVSXD	%R8D,%R8

(280) 0x246d74 MOVSXD	%EDX,%RDX

(280) 0x246d77 MOVSXD	%EDI,%RDI

(280) 0x246d7a CLTQ

(280) 0x246d7c MOV	-0x38(%RBP),%R11

(280) 0x246d80 MOV	%R11,%RBX

(280) 0x246d83 IMUL	%RDI,%RBX

(280) 0x246d87 ADD	%R8,%RBX

(280) 0x246d8a MOV	-0x60(%RBP),%R14

(280) 0x246d8e MOVSD	(%R14,%RBX,8),%XMM0

(280) 0x246d94 IMUL	%RAX,%R11

(280) 0x246d98 ADD	%RDX,%R11

(280) 0x246d9b MOVSD	(%R14,%R11,8),%XMM1

(280) 0x246da1 MOV	-0x88(%RBP),%R14

(280) 0x246da8 MOV	%R14,%RBX

(280) 0x246dab IMUL	%RDI,%RBX

(280) 0x246daf ADD	%R8,%RBX

(280) 0x246db2 MOV	-0x58(%RBP),%R11

(280) 0x246db6 MOVSD	%XMM0,(%R11,%RBX,8)

(280) 0x246dbc MOV	%R14,%RBX

(280) 0x246dbf IMUL	%RAX,%RBX

(280) 0x246dc3 ADD	%RDX,%RBX

(280) 0x246dc6 MOVSD	%XMM1,(%R11,%RBX,8)

(280) 0x246dcc MOV	%R15,%RBX

(280) 0x246dcf IMUL	%RDI,%RBX

(280) 0x246dd3 ADD	%R8,%RBX

(280) 0x246dd6 MOV	-0x50(%RBP),%R11

(280) 0x246dda MOVSD	(%R11,%RBX,8),%XMM0

(280) 0x246de0 MOV	%R15,%RBX

(280) 0x246de3 IMUL	%RAX,%RBX

(280) 0x246de7 ADD	%RDX,%RBX

(280) 0x246dea MOVSD	(%R11,%RBX,8),%XMM1

(280) 0x246df0 IMUL	%R10,%RDI

(280) 0x246df4 ADD	%R8,%RDI

(280) 0x246df7 IMUL	%R10,%RAX

(280) 0x246dfb ADD	%RDX,%RAX

(280) 0x246dfe MOVSD	%XMM0,(%R12,%RDI,8)

(280) 0x246e04 MOVSD	%XMM1,(%R12,%RAX,8)

(280) 0x246e0a ADD	$0x2,%RSI

(280) 0x246e0e ADD	$-0x2,%R9

(280) 0x246e12 JE	246e5a

(280) 0x246e14 MOV	%RSI,%RAX

(280) 0x246e17 SHR	$0x20,%RAX

(280) 0x246e1b JE	246e30

(280) 0x246e1d MOV	%RSI,%RAX

(280) 0x246e20 CQTO

(280) 0x246e22 IDIV	%R13

(280) 0x246e25 MOV	%RDX,%R8

(280) 0x246e28 MOV	%RAX,%RDI

(280) 0x246e2b JMP	246e3c

0x246e2d NOPL	(%RAX)

(280) 0x246e30 MOV	%ESI,%EAX

(280) 0x246e32 XOR	%EDX,%EDX

(280) 0x246e34 DIV	%R13D

(280) 0x246e37 MOV	%EDX,%R8D

(280) 0x246e3a MOV	%EAX,%EDI

(280) 0x246e3c MOV	-0x2c(%RBP),%EBX

(280) 0x246e3f LEA	0x1(%RSI),%RAX

(280) 0x246e43 MOV	%RAX,%RDX

(280) 0x246e46 SHR	$0x20,%RDX

(280) 0x246e4a JNE	246d60

(280) 0x246e50 XOR	%EDX,%EDX

(280) 0x246e52 DIV	%R13D

(280) 0x246e55 JMP	246d65

0x246e5a MOV	-0x70(%RBP),%RAX

0x246e5e CMP	%RAX,-0x78(%RBP)

0x246e62 MOV	-0x2c(%RBP),%EBX

0x246e65 MOV	-0x80(%RBP),%R8

0x246e69 MOV	-0x30(%RBP),%R9D

0x246e6d MOV	-0x38(%RBP),%RDI

0x246e71 JNE	246f08

0x246e77 LEA	0x17f1a(%RIP),%RDI

0x246e7e MOV	-0x44(%RBP),%ESI

0x246e81 CALL	25cd00 <@plt_start@+0x540>

0x246e86 ADD	$0x68,%RSP

0x246e8a POP	%RBX

0x246e8b POP	%R12

0x246e8d POP	%R13

0x246e8f POP	%R14

0x246e91 POP	%R15

0x246e93 POP	%RBP

0x246e94 RET

0x246e95 NOPW	%CS:(%RAX,%RAX,1)

(279) 0x246ea0 MOV	%RCX,%RAX

(279) 0x246ea3 CQTO

(279) 0x246ea5 IDIV	%R13

(279) 0x246ea8 ADD	%EBX,%EAX

(279) 0x246eaa ADD	%R9D,%EDX

(279) 0x246ead MOVSXD	%EDX,%RDX

(279) 0x246eb0 CLTQ

(279) 0x246eb2 MOV	%RDI,%RSI

(279) 0x246eb5 IMUL	%RAX,%RSI

(279) 0x246eb9 ADD	%RDX,%RSI

(279) 0x246ebc MOV	-0x60(%RBP),%R11

(279) 0x246ec0 MOVSD	(%R11,%RSI,8),%XMM0

(279) 0x246ec6 MOV	%R14,%RSI

(279) 0x246ec9 IMUL	%RAX,%RSI

(279) 0x246ecd ADD	%RDX,%RSI

(279) 0x246ed0 MOV	-0x58(%RBP),%R11

(279) 0x246ed4 MOVSD	%XMM0,(%R11,%RSI,8)

(279) 0x246eda MOV	%R15,%RSI

(279) 0x246edd IMUL	%RAX,%RSI

(279) 0x246ee1 ADD	%RDX,%RSI

(279) 0x246ee4 MOV	-0x50(%RBP),%R11

(279) 0x246ee8 MOVSD	(%R11,%RSI,8),%XMM0

(279) 0x246eee IMUL	%R10,%RAX

(279) 0x246ef2 ADD	%RDX,%RAX

(279) 0x246ef5 MOVSD	%XMM0,(%R12,%RAX,8)

(279) 0x246efb CMP	%R8,%RCX

(279) 0x246efe LEA	0x1(%RCX),%RCX

(279) 0x246f02 JGE	246e77

(279) 0x246f08 MOV	%RCX,%RAX

(279) 0x246f0b SHR	$0x20,%RAX

(279) 0x246f0f JNE	246ea0

(279) 0x246f11 MOV	%ECX,%EAX

(279) 0x246f13 XOR	%EDX,%EDX

(279) 0x246f15 DIV	%R13D

(279) 0x246f18 JMP	246ea8

0x246f1a NOPW	(%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	reset_field.cpp:34-38
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/reset_field.cpp:34-38

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 13.25 to 0.99 cycles (13.38x 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/reset_field.cpp:34
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/reset_field.cpp:34

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/reset_field.cpp:35

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 188 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	107
nb uops	106
loop length	399
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.25 cycles
front end	13.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	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	13.25
Dispatch	11.50
Overall L1	13.25

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	10%
load	10%
store	10%
mul	12%
add-sub	7%
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 13.25 cycles. At this rate:

5% of peak load performance is reached (14.19 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.45 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 13.25 to 11.50 cycles (1.15x speedup).

ASM code

In the binary file, the address of the function is: 246c20

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 $0x68,%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),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JLE 246e86 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %EDX,%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 246e86 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %R13,%R14	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R14	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,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R14,-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,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x48(%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 -0x90(%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 0x180ea(%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 -0x48(%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 -0x68(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %EDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R14,%R8	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 %R14,%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,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R8,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R8,%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 246e77 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x257>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R10,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x58(%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	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RCX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R8,%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 246d35 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x115>	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),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 246f08 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R9,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 246e14 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x1f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%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
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x78(%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 -0x2c(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x80(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 246f08 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x17f1a(%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 $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%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	reset_field.cpp:34-38
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/reset_field.cpp:34-38

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/reset_field.cpp:34
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/reset_field.cpp:34

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/reset_field.cpp:35

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 188 bytes. The binary function is storing 112 bytes.

General properties

nb instructions	107
nb uops	106
loop length	399
used x86 registers	15
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	19

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	13.25 cycles
front end	13.25 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.67	6.67	6.67	6.67	6.67	6.67	11.50	11.50	11.50	11.50	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	13.25
Dispatch	11.50
Overall L1	13.25

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	10%
load	10%
store	10%
mul	12%
add-sub	7%
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 13.25 cycles. At this rate:

5% of peak load performance is reached (14.19 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
6% of peak store performance is reached (8.45 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: 246c20

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 $0x68,%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),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV (%RCX),%EAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
INC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JLE 246e86 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%R9),%R13D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
INC %EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD $0x2,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %EDX,%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 246e86 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x266>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
SUB %EDX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
MOV %RAX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
IMUL %R13,%R14	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R14	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,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R14,-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,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x48(%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 -0x90(%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 0x180ea(%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 -0x48(%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 -0x68(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %EDX,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R14,%R8	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 %R14,%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,%R8	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
MOV %R8,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x68(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %R8,%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 246e77 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x257>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x28(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R10,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDI),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RDI),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x58(%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	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RCX),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x10(%RCX),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV %R8,%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 246d35 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x115>	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),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 246f08 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R8,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %EBX,-0x2c(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%R9,1),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %R9,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R14,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 246e14 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x1f4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%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
MOV -0x70(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x78(%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 -0x2c(%RBP),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOV -0x80(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x30(%RBP),%R9D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 246f08 <_Z18reset_field_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_.omp_outlined+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x17f1a(%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 $0x68,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼reset_field_kernel(int, int, int, int, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&) [...–	2.49	0.97
○Loop 280 - reset_field.cpp:35-38 - exec	2.49	0.97
○Loop 279 - reset_field.cpp:35-38 - 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