OV - exec - Function advec_mom_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>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer2D<double>&, clover::Buffer1D<double>&, clover::Buffer1D<double>&, int, int, int) [clone .omp

	Function: advec_mom_kernel(int, int, int, int, clover::Buffer2D<double>&, clover::Buffer2D<double>&, ...	Module: exec	Source: advec_mom.cpp:71-75 [...]	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/advec_mom.cpp: 71 - 75

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

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

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

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

74:         post_vol(i, j) = volume(i, j);

75:         pre_vol(i, j) = post_vol(i, j) + vol_flux_x(i + 1, j + 0) - vol_flux_x(i, j);

0x234ef0 PUSH	%RBP

0x234ef1 MOV	%RSP,%RBP

0x234ef4 PUSH	%R15

0x234ef6 PUSH	%R14

0x234ef8 PUSH	%R13

0x234efa PUSH	%R12

0x234efc PUSH	%RBX

0x234efd SUB	$0x98,%RSP

0x234f04 MOV	(%RDX),%EBX

0x234f06 MOV	(%RCX),%ECX

0x234f08 ADD	$0x4,%ECX

0x234f0b CMP	%EBX,%ECX

0x234f0d JL	2351d8

0x234f13 MOV	(%R8),%R10D

0x234f16 MOV	(%R9),%R13D

0x234f19 ADD	$0x4,%R13D

0x234f1d CMP	%R10D,%R13D

0x234f20 JL	2351d8

0x234f26 DEC	%EBX

0x234f28 LEA	-0x1(%R10),%R15D

0x234f2c SUB	%R15D,%R13D

0x234f2f MOV	%RCX,%R14

0x234f32 SUB	%EBX,%R14D

0x234f35 IMUL	%R13,%R14

0x234f39 DEC	%R14

0x234f3c MOVQ	$0,-0x80(%RBP)

0x234f44 MOV	%R14,-0x48(%RBP)

0x234f48 MOVQ	$0x1,-0xb8(%RBP)

0x234f53 MOVL	$0,-0x50(%RBP)

0x234f5a MOV	(%RDI),%ESI

0x234f5c SUB	$0x8,%RSP

0x234f60 LEA	-0xb8(%RBP),%RAX

0x234f67 LEA	0x29322(%RIP),%RDI

0x234f6e LEA	-0x50(%RBP),%RCX

0x234f72 LEA	-0x80(%RBP),%R8

0x234f76 LEA	-0x48(%RBP),%R9

0x234f7a MOV	%ESI,-0x4c(%RBP)

0x234f7d MOV	$0x22,%EDX

0x234f82 PUSH	$0x1

0x234f84 PUSH	$0x1

0x234f86 PUSH	%RAX

0x234f87 MOV	%R10,-0x40(%RBP)

0x234f8b CALL	25ccf0 <@plt_start@+0x530>

0x234f90 MOV	-0x40(%RBP),%R9

0x234f94 MOV	%R14,%R8

0x234f97 ADD	$0x20,%RSP

0x234f9b MOV	-0x48(%RBP),%RAX

0x234f9f CMP	%R14,%RAX

0x234fa2 CMOVL	%RAX,%R8

0x234fa6 MOV	%R8,-0x48(%RBP)

0x234faa MOV	-0x80(%RBP),%RSI

0x234fae CMP	%R8,%RSI

0x234fb1 JG	2351c9

0x234fb7 MOV	%R15,%R11

0x234fba MOV	0x28(%RBP),%RAX

0x234fbe MOV	0x20(%RBP),%RCX

0x234fc2 MOV	0x18(%RBP),%RDX

0x234fc6 MOV	0x10(%RBP),%RDI

0x234fca MOV	(%RDX),%R10

0x234fcd MOV	%R10,-0x78(%RBP)

0x234fd1 MOV	0x10(%RDX),%R14

0x234fd5 MOV	(%RDI),%R10

0x234fd8 MOV	0x10(%RDI),%R12

0x234fdc MOV	(%RAX),%RDX

0x234fdf MOV	%RDX,-0x70(%RBP)

0x234fe3 MOV	0x10(%RAX),%R15

0x234fe7 MOV	(%RCX),%RAX

0x234fea MOV	%RAX,-0x68(%RBP)

0x234fee MOV	0x10(%RCX),%RAX

0x234ff2 MOV	%RAX,-0x60(%RBP)

0x234ff6 MOV	%R8,%RAX

0x234ff9 SUB	%RSI,%RAX

0x234ffc INC	%RAX

0x234fff CMP	$0x2,%RAX

0x235003 JAE	23500d

0x235005 MOV	%RSI,%RCX

0x235008 JMP	235262

0x23500d MOV	%R14,-0x58(%RBP)

0x235011 MOV	%R11,-0x38(%RBP)

0x235015 MOV	%R8,-0x98(%RBP)

0x23501c MOV	%EBX,-0x2c(%RBP)

0x23501f MOV	%RAX,-0x90(%RBP)

0x235026 MOV	%RAX,%R9

0x235029 AND	$-0x2,%R9

0x23502d LEA	(%RSI,%R9,1),%RCX

0x235031 MOV	%R9,-0x88(%RBP)

0x235038 MOV	%R10,-0xb0(%RBP)

0x23503f MOV	%R12,-0xa8(%RBP)

0x235046 MOV	%R13,-0xa0(%RBP)

0x23504d JMP	235150

0x235052 NOPW	%CS:(%RAX,%RAX,1)

(166) 0x235060 CQTO

(166) 0x235062 IDIV	%R13

(166) 0x235065 ADD	%R11D,%R8D

(166) 0x235068 ADD	%R11D,%EAX

(166) 0x23506b LEA	(%RBX,%RDI,1),%R11D

(166) 0x23506f ADD	%EDX,%EBX

(166) 0x235071 MOVSXD	%R11D,%R11

(166) 0x235074 MOVSXD	%EBX,%RBX

(166) 0x235077 MOVSXD	%R8D,%R8

(166) 0x23507a CLTQ

(166) 0x23507c MOV	-0x78(%RBP),%R12

(166) 0x235080 MOV	%R12,%R14

(166) 0x235083 IMUL	%R8,%R14

(166) 0x235087 ADD	%R11,%R14

(166) 0x23508a MOV	-0x58(%RBP),%R10

(166) 0x23508e MOVSD	(%R10,%R14,8),%XMM0

(166) 0x235094 IMUL	%RAX,%R12

(166) 0x235098 ADD	%RBX,%R12

(166) 0x23509b MOVSD	(%R10,%R12,8),%XMM1

(166) 0x2350a1 MOV	-0xb0(%RBP),%R10

(166) 0x2350a8 MOV	%R10,%R14

(166) 0x2350ab IMUL	%R8,%R14

(166) 0x2350af ADD	%R11,%R14

(166) 0x2350b2 MOV	-0xa8(%RBP),%R12

(166) 0x2350b9 MOVSD	%XMM0,(%R12,%R14,8)

(166) 0x2350bf MOV	%R10,%R14

(166) 0x2350c2 IMUL	%RAX,%R14

(166) 0x2350c6 ADD	%RBX,%R14

(166) 0x2350c9 MOVSD	%XMM1,(%R12,%R14,8)

(166) 0x2350cf MOV	-0x40(%RBP),%R14

(166) 0x2350d3 ADD	%R14D,%EDI

(166) 0x2350d6 ADD	%R14D,%EDX

(166) 0x2350d9 MOVSXD	%EDI,%RDI

(166) 0x2350dc MOVSXD	%EDX,%RDX

(166) 0x2350df MOV	-0x70(%RBP),%R13

(166) 0x2350e3 MOV	%R13,%R14

(166) 0x2350e6 IMUL	%R8,%R14

(166) 0x2350ea ADD	%R14,%RDI

(166) 0x2350ed MOVSD	(%R15,%RDI,8),%XMM2

(166) 0x2350f3 IMUL	%RAX,%R13

(166) 0x2350f7 ADD	%R13,%RDX

(166) 0x2350fa MOVHPD	(%R15,%RDX,8),%XMM2

(166) 0x235100 ADD	%R11,%R14

(166) 0x235103 MOVSD	(%R15,%R14,8),%XMM3

(166) 0x235109 ADD	%RBX,%R13

(166) 0x23510c MOVHPD	(%R15,%R13,8),%XMM3

(166) 0x235112 MOV	-0x68(%RBP),%RDX

(166) 0x235116 IMUL	%RDX,%R8

(166) 0x23511a ADD	%R11,%R8

(166) 0x23511d IMUL	%RDX,%RAX

(166) 0x235121 ADD	%RBX,%RAX

(166) 0x235124 UNPCKLPD	%XMM1,%XMM0

(166) 0x235128 ADDPD	%XMM0,%XMM2

(166) 0x23512c SUBPD	%XMM3,%XMM2

(166) 0x235130 MOV	-0x60(%RBP),%RDX

(166) 0x235134 MOVLPD	%XMM2,(%RDX,%R8,8)

(166) 0x23513a MOVHPD	%XMM2,(%RDX,%RAX,8)

(166) 0x23513f ADD	$0x2,%RSI

(166) 0x235143 ADD	$-0x2,%R9

(166) 0x235147 MOV	-0xa0(%RBP),%R13

(166) 0x23514e JE	23519f

(166) 0x235150 MOV	%RSI,%RAX

(166) 0x235153 SHR	$0x20,%RAX

(166) 0x235157 JE	235170

(166) 0x235159 MOV	%RSI,%RAX

(166) 0x23515c CQTO

(166) 0x23515e IDIV	%R13

(166) 0x235161 MOV	%RDX,%RDI

(166) 0x235164 MOV	%RAX,%R8

(166) 0x235167 JMP	23517c

0x235169 NOPL	(%RAX)

(166) 0x235170 MOV	%ESI,%EAX

(166) 0x235172 XOR	%EDX,%EDX

(166) 0x235174 DIV	%R13D

(166) 0x235177 MOV	%EDX,%EDI

(166) 0x235179 MOV	%EAX,%R8D

(166) 0x23517c MOV	-0x2c(%RBP),%R11D

(166) 0x235180 MOV	-0x38(%RBP),%RBX

(166) 0x235184 LEA	0x1(%RSI),%RAX

(166) 0x235188 MOV	%RAX,%RDX

(166) 0x23518b SHR	$0x20,%RDX

(166) 0x23518f JNE	235060

(166) 0x235195 XOR	%EDX,%EDX

(166) 0x235197 DIV	%R13D

(166) 0x23519a JMP	235065

0x23519f MOV	-0x88(%RBP),%RAX

0x2351a6 CMP	%RAX,-0x90(%RBP)

0x2351ad MOV	-0x2c(%RBP),%EBX

0x2351b0 MOV	-0x98(%RBP),%R8

0x2351b7 MOV	-0x40(%RBP),%R9

0x2351bb MOV	-0x38(%RBP),%R11

0x2351bf MOV	-0x58(%RBP),%R14

0x2351c3 JNE	235262

0x2351c9 LEA	0x290d8(%RIP),%RDI

0x2351d0 MOV	-0x4c(%RBP),%ESI

0x2351d3 CALL	25cd00 <@plt_start@+0x540>

0x2351d8 ADD	$0x98,%RSP

0x2351df POP	%RBX

0x2351e0 POP	%R12

0x2351e2 POP	%R13

0x2351e4 POP	%R14

0x2351e6 POP	%R15

0x2351e8 POP	%RBP

0x2351e9 RET

0x2351ea NOPW	(%RAX,%RAX,1)

(165) 0x2351f0 MOV	%RCX,%RAX

(165) 0x2351f3 CQTO

(165) 0x2351f5 IDIV	%R13

(165) 0x2351f8 ADD	%EBX,%EAX

(165) 0x2351fa LEA	(%R11,%RDX,1),%ESI

(165) 0x2351fe MOVSXD	%ESI,%RSI

(165) 0x235201 CLTQ

(165) 0x235203 MOV	-0x78(%RBP),%RDI

(165) 0x235207 IMUL	%RAX,%RDI

(165) 0x23520b ADD	%RSI,%RDI

(165) 0x23520e MOVSD	(%R14,%RDI,8),%XMM0

(165) 0x235214 MOV	%R10,%RDI

(165) 0x235217 IMUL	%RAX,%RDI

(165) 0x23521b ADD	%RSI,%RDI

(165) 0x23521e MOVSD	%XMM0,(%R12,%RDI,8)

(165) 0x235224 ADD	%R9D,%EDX

(165) 0x235227 MOVSXD	%EDX,%RDX

(165) 0x23522a MOV	-0x70(%RBP),%RDI

(165) 0x23522e IMUL	%RAX,%RDI

(165) 0x235232 ADD	%RDI,%RDX

(165) 0x235235 ADDSD	(%R15,%RDX,8),%XMM0

(165) 0x23523b ADD	%RSI,%RDI

(165) 0x23523e SUBSD	(%R15,%RDI,8),%XMM0

(165) 0x235244 IMUL	-0x68(%RBP),%RAX

(165) 0x235249 ADD	%RSI,%RAX

(165) 0x23524c MOV	-0x60(%RBP),%RDX

(165) 0x235250 MOVSD	%XMM0,(%RDX,%RAX,8)

(165) 0x235255 CMP	%R8,%RCX

(165) 0x235258 LEA	0x1(%RCX),%RCX

(165) 0x23525c JGE	2351c9

(165) 0x235262 MOV	%RCX,%RAX

(165) 0x235265 SHR	$0x20,%RAX

(165) 0x235269 JNE	2351f0

(165) 0x23526b MOV	%ECX,%EAX

(165) 0x23526d XOR	%EDX,%EDX

(165) 0x23526f DIV	%R13D

(165) 0x235272 JMP	2351f8

0x235274 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	advec_mom.cpp:71-75
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/advec_mom.cpp:71-75

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 14.00 to 1.11 cycles (12.62x 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/advec_mom.cpp:71
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_mom.cpp:71

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/advec_mom.cpp:72

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 196 bytes. The binary function is storing 148 bytes.

General properties

nb instructions	113
nb uops	112
loop length	468
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	23

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.00 cycles
front end	14.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.83	6.83	6.83	6.83	6.83	6.83	12.50	12.50	12.50	12.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.83	6.83	6.83	6.83	6.83	6.83	12.50	12.50	12.50	12.50	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	14.00
Dispatch	12.50
Overall L1	14.00

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	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.00 cycles. At this rate:

5% of peak load performance is reached (14.00 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (10.57 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 14.00 to 12.50 cycles (1.12x speedup).

ASM code

In the binary file, the address of the function is: 234ef0

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 $0x98,%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),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD $0x4,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %EBX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 2351d8 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%R10D	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%)
ADD $0x4,%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 %R10D,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 2351d8 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
DEC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%R10),%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
SUB %R15D,%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 %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %EBX,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
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,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R14,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x50(%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 -0xb8(%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 0x29322(%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 -0x50(%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 -0x80(%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 -0x48(%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,-0x4c(%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
MOV %R10,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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 -0x40(%RBP),%R9	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 -0x48(%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,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x80(%RBP),%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 2351c9 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
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	N/A
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 0x10(%RDX),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RDI),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RCX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 0x10(%RCX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %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 23500d <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x11d>	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 235262 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x372>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R14,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,-0x98(%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,-0x90(%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,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 235150 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x260>	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
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x88(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x90(%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 -0x98(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 235262 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x372>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x290d8(%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 -0x4c(%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 $0x98,%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 (%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

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	advec_mom.cpp:71-75
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/advec_mom.cpp:71-75

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/advec_mom.cpp:71
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_mom.cpp:71

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/advec_mom.cpp:72

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 196 bytes. The binary function is storing 148 bytes.

General properties

nb instructions	113
nb uops	112
loop length	468
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	23

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.00 cycles
front end	14.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.83	6.83	6.83	6.83	6.83	6.83	12.50	12.50	12.50	12.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.83	6.83	6.83	6.83	6.83	6.83	12.50	12.50	12.50	12.50	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	14.00
Dispatch	12.50
Overall L1	14.00

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	10%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.00 cycles. At this rate:

5% of peak load performance is reached (14.00 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
8% of peak store performance is reached (10.57 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: 234ef0

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 $0x98,%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),%ECX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
ADD $0x4,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP %EBX,%ECX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 2351d8 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%R10D	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%)
ADD $0x4,%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 %R10D,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 2351d8 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2e8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
DEC %EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
LEA -0x1(%R10),%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
SUB %R15D,%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 %RCX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %EBX,%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
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,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R14,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x50(%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 -0xb8(%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 0x29322(%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 -0x50(%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 -0x80(%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 -0x48(%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,-0x4c(%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
MOV %R10,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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 -0x40(%RBP),%R9	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 -0x48(%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,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0x80(%RBP),%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 2351c9 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x2d9>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R15,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
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	N/A
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 0x10(%RDX),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RDI),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RDI),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RAX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RAX),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RCX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 0x10(%RCX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %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 23500d <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x11d>	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 235262 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x372>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R14,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,-0x98(%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,-0x90(%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,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 235150 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x260>	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
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0x88(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0x90(%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 -0x98(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 235262 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii.omp_outlined.6+0x372>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x290d8(%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 -0x4c(%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 $0x98,%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 (%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

Name	Coverage (%)	Time (s)
▼advec_mom_kernel(int, int, int, int, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clo...–	2.49	0.97
○Loop 166 - advec_mom.cpp:72-75 - exec	2.49	0.97
○Loop 165 - advec_mom.cpp:72-75 - 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