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

	Function: advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D<double>&, clover::Buffer1 ...	Module: exec	Source: advec_cell.cpp:136-140 [...]	Coverage (incl. loops): 1.44% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp: 136 - 140

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

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

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

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

139:           pre_vol(i, j) = volume(i, j) + (vol_flux_y(i + 0, j + 1) - vol_flux_y(i, j) + vol_flux_x(i + 1, j + 0) - vol_flux_x(i, j));

140:           post_vol(i, j) = pre_vol(i, j) - (vol_flux_y(i + 0, j + 1) - vol_flux_y(i, j));

/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]; }

0x231c70 PUSH	%RBP

0x231c71 MOV	%RSP,%RBP

0x231c74 PUSH	%R15

0x231c76 PUSH	%R14

0x231c78 PUSH	%R13

0x231c7a PUSH	%R12

0x231c7c PUSH	%RBX

0x231c7d SUB	$0xc8,%RSP

0x231c84 MOV	(%RDX),%R14D

0x231c87 MOV	(%RCX),%R15D

0x231c8a ADD	$0x4,%R15D

0x231c8e CMP	%R14D,%R15D

0x231c91 JL	232018

0x231c97 MOV	(%R8),%EAX

0x231c9a MOV	(%R9),%R13D

0x231c9d ADD	$0x4,%R13D

0x231ca1 CMP	%EAX,%R13D

0x231ca4 JL	232018

0x231caa LEA	-0x1(%R14),%R12D

0x231cae MOV	%RAX,-0x38(%RBP)

0x231cb2 LEA	-0x1(%RAX),%EBX

0x231cb5 SUB	%EBX,%R13D

0x231cb8 SUB	%R12D,%R15D

0x231cbb IMUL	%R13,%R15

0x231cbf DEC	%R15

0x231cc2 MOVQ	$0,-0xa8(%RBP)

0x231ccd MOV	%R15,-0x40(%RBP)

0x231cd1 MOVQ	$0x1,-0xe8(%RBP)

0x231cdc MOVL	$0,-0x48(%RBP)

0x231ce3 MOV	(%RDI),%ESI

0x231ce5 SUB	$0x8,%RSP

0x231ce9 LEA	-0xe8(%RBP),%RAX

0x231cf0 LEA	0x2c3a1(%RIP),%RDI

0x231cf7 LEA	-0x48(%RBP),%RCX

0x231cfb LEA	-0xa8(%RBP),%R8

0x231d02 LEA	-0x40(%RBP),%R9

0x231d06 MOV	%ESI,-0x44(%RBP)

0x231d09 MOV	$0x22,%EDX

0x231d0e PUSH	$0x1

0x231d10 PUSH	$0x1

0x231d12 PUSH	%RAX

0x231d13 CALL	25ccf0 <@plt_start@+0x530>

0x231d18 ADD	$0x20,%RSP

0x231d1c MOV	-0x40(%RBP),%RAX

0x231d20 CMP	%R15,%RAX

0x231d23 CMOVL	%RAX,%R15

0x231d27 MOV	%R15,-0x40(%RBP)

0x231d2b MOV	-0xa8(%RBP),%RSI

0x231d32 CMP	%R15,%RSI

0x231d35 JG	232009

0x231d3b MOV	%RBX,%R11

0x231d3e MOV	%R12,%R10

0x231d41 MOV	0x30(%RBP),%RAX

0x231d45 MOV	0x28(%RBP),%RCX

0x231d49 MOV	0x20(%RBP),%RDX

0x231d4d MOV	0x18(%RBP),%RDI

0x231d51 MOV	0x10(%RBP),%R8

0x231d55 MOV	(%RDI),%R9

0x231d58 MOV	%R9,-0xa0(%RBP)

0x231d5f MOV	0x10(%RDI),%RDI

0x231d63 MOV	%RDI,-0x98(%RBP)

0x231d6a MOV	(%RDX),%RDI

0x231d6d MOV	%RDI,-0x90(%RBP)

0x231d74 MOV	0x10(%RDX),%RBX

0x231d78 MOV	(%RCX),%RDX

0x231d7b MOV	%RDX,-0x88(%RBP)

0x231d82 MOV	0x10(%RCX),%RCX

0x231d86 MOV	%RCX,-0x80(%RBP)

0x231d8a MOV	(%R8),%RCX

0x231d8d MOV	%RCX,-0x78(%RBP)

0x231d91 MOV	0x10(%R8),%RCX

0x231d95 MOV	%RCX,-0x70(%RBP)

0x231d99 MOV	(%RAX),%RCX

0x231d9c MOV	%RCX,-0x68(%RBP)

0x231da0 MOV	0x10(%RAX),%RAX

0x231da4 MOV	%RAX,-0x60(%RBP)

0x231da8 MOV	%R15,%RAX

0x231dab SUB	%RSI,%RAX

0x231dae INC	%RAX

0x231db1 CMP	$0x2,%RAX

0x231db5 JAE	231dbf

0x231db7 MOV	%RSI,%RCX

0x231dba JMP	2320f4

0x231dbf MOV	%R11,-0x50(%RBP)

0x231dc3 MOV	%R10,-0x30(%RBP)

0x231dc7 MOV	%R15,-0xc0(%RBP)

0x231dce MOV	%R14,-0x58(%RBP)

0x231dd2 MOV	%RAX,-0xb8(%RBP)

0x231dd9 MOV	%RAX,%RCX

0x231ddc AND	$-0x2,%RCX

0x231de0 LEA	(%RSI,%RCX,1),%RAX

0x231de4 MOV	%RAX,-0xc8(%RBP)

0x231deb MOV	%RCX,-0xb0(%RBP)

0x231df2 MOV	%RCX,%RDX

0x231df5 MOV	%R13,-0xd0(%RBP)

0x231dfc JMP	231f90

0x231e01 NOPW	%CS:(%RAX,%RAX,1)

(152) 0x231e10 CQTO

(152) 0x231e12 IDIV	%R13

(152) 0x231e15 LEA	(%R9,%R8,1),%R10D

(152) 0x231e19 LEA	(%R9,%RAX,1),%R11D

(152) 0x231e1d MOV	-0x50(%RBP),%R14

(152) 0x231e21 LEA	(%R14,%RDI,1),%R9D

(152) 0x231e25 ADD	%EDX,%R14D

(152) 0x231e28 MOVSXD	%R9D,%R13

(152) 0x231e2b MOVSXD	%R14D,%R9

(152) 0x231e2e MOVSXD	%R10D,%R10

(152) 0x231e31 MOVSXD	%R11D,%R14

(152) 0x231e34 MOV	-0xa0(%RBP),%R15

(152) 0x231e3b MOV	%R15,%R11

(152) 0x231e3e IMUL	%R10,%R11

(152) 0x231e42 IMUL	%R14,%R15

(152) 0x231e46 ADD	%R13,%R11

(152) 0x231e49 ADD	%R9,%R15

(152) 0x231e4c MOV	-0x98(%RBP),%R12

(152) 0x231e53 MOVSD	(%R12,%R11,8),%XMM0

(152) 0x231e59 MOVHPD	(%R12,%R15,8),%XMM0

(152) 0x231e5f MOV	-0x58(%RBP),%R11

(152) 0x231e63 ADD	%R11D,%R8D

(152) 0x231e66 ADD	%R11D,%EAX

(152) 0x231e69 MOVSXD	%R8D,%R8

(152) 0x231e6c CLTQ

(152) 0x231e6e MOV	-0x90(%RBP),%R12

(152) 0x231e75 IMUL	%R12,%R8

(152) 0x231e79 IMUL	%R12,%RAX

(152) 0x231e7d ADD	%R13,%R8

(152) 0x231e80 ADD	%R9,%RAX

(152) 0x231e83 MOVSD	(%RBX,%R8,8),%XMM2

(152) 0x231e89 MOVHPD	(%RBX,%RAX,8),%XMM2

(152) 0x231e8e MOV	%R12,%R11

(152) 0x231e91 IMUL	%R10,%R11

(152) 0x231e95 MOV	-0x38(%RBP),%R15

(152) 0x231e99 ADD	%R15D,%EDI

(152) 0x231e9c ADD	%R15D,%EDX

(152) 0x231e9f MOVSXD	%EDI,%RDI

(152) 0x231ea2 MOVSXD	%EDX,%RDX

(152) 0x231ea5 MOV	-0x88(%RBP),%RCX

(152) 0x231eac MOV	%RCX,%R15

(152) 0x231eaf IMUL	%R10,%R15

(152) 0x231eb3 ADD	%R15,%RDI

(152) 0x231eb6 MOV	-0x80(%RBP),%RSI

(152) 0x231eba MOVSD	(%RSI,%RDI,8),%XMM1

(152) 0x231ebf IMUL	%R14,%RCX

(152) 0x231ec3 ADD	%RCX,%RDX

(152) 0x231ec6 MOVHPD	(%RSI,%RDX,8),%XMM1

(152) 0x231ecb MOV	%R12,%RDX

(152) 0x231ece IMUL	%R14,%RDX

(152) 0x231ed2 ADD	%R13,%R11

(152) 0x231ed5 ADD	%R9,%RDX

(152) 0x231ed8 MOVSD	(%RBX,%R11,8),%XMM3

(152) 0x231ede MOVHPD	(%RBX,%RDX,8),%XMM3

(152) 0x231ee3 ADD	%R13,%R15

(152) 0x231ee6 MOVSD	(%RSI,%R15,8),%XMM4

(152) 0x231eec SUBPD	%XMM3,%XMM2

(152) 0x231ef0 ADDPD	%XMM2,%XMM1

(152) 0x231ef4 ADD	%R9,%RCX

(152) 0x231ef7 MOVHPD	(%RSI,%RCX,8),%XMM4

(152) 0x231efc SUBPD	%XMM4,%XMM1

(152) 0x231f00 ADDPD	%XMM0,%XMM1

(152) 0x231f04 MOV	-0x78(%RBP),%RCX

(152) 0x231f08 MOV	%RCX,%RDI

(152) 0x231f0b IMUL	%R10,%RDI

(152) 0x231f0f ADD	%R13,%RDI

(152) 0x231f12 MOV	-0x70(%RBP),%RSI

(152) 0x231f16 MOVLPD	%XMM1,(%RSI,%RDI,8)

(152) 0x231f1b MOV	%RCX,%RDI

(152) 0x231f1e IMUL	%R14,%RDI

(152) 0x231f22 ADD	%R9,%RDI

(152) 0x231f25 MOVHPD	%XMM1,(%RSI,%RDI,8)

(152) 0x231f2a MOVSD	(%RBX,%R8,8),%XMM0

(152) 0x231f30 MOVHPD	(%RBX,%RAX,8),%XMM0

(152) 0x231f35 MOVSD	(%RBX,%R11,8),%XMM2

(152) 0x231f3b MOVHPD	(%RBX,%RDX,8),%XMM2

(152) 0x231f40 MOV	-0x68(%RBP),%RAX

(152) 0x231f44 IMUL	%RAX,%R10

(152) 0x231f48 ADD	%R13,%R10

(152) 0x231f4b IMUL	%RAX,%R14

(152) 0x231f4f ADD	%R9,%R14

(152) 0x231f52 SUBPD	%XMM2,%XMM0

(152) 0x231f56 SUBPD	%XMM0,%XMM1

(152) 0x231f5a MOV	-0x60(%RBP),%RAX

(152) 0x231f5e MOVLPD	%XMM1,(%RAX,%R10,8)

(152) 0x231f64 MOVHPD	%XMM1,(%RAX,%R14,8)

(152) 0x231f6a MOV	-0xe0(%RBP),%RSI

(152) 0x231f71 ADD	$0x2,%RSI

(152) 0x231f75 MOV	-0xd8(%RBP),%RDX

(152) 0x231f7c ADD	$-0x2,%RDX

(152) 0x231f80 MOV	-0xd0(%RBP),%R13

(152) 0x231f87 MOV	-0xc8(%RBP),%RCX

(152) 0x231f8e JE	231fe2

(152) 0x231f90 MOV	%RSI,%RAX

(152) 0x231f93 SHR	$0x20,%RAX

(152) 0x231f97 MOV	%RDX,-0xd8(%RBP)

(152) 0x231f9e JE	231fb0

(152) 0x231fa0 MOV	%RSI,%RAX

(152) 0x231fa3 CQTO

(152) 0x231fa5 IDIV	%R13

(152) 0x231fa8 MOV	%RDX,%RDI

(152) 0x231fab MOV	%RAX,%R8

(152) 0x231fae JMP	231fbc

(152) 0x231fb0 MOV	%ESI,%EAX

(152) 0x231fb2 XOR	%EDX,%EDX

(152) 0x231fb4 DIV	%R13D

(152) 0x231fb7 MOV	%EDX,%EDI

(152) 0x231fb9 MOV	%EAX,%R8D

(152) 0x231fbc MOV	-0x30(%RBP),%R9

(152) 0x231fc0 LEA	0x1(%RSI),%RAX

(152) 0x231fc4 MOV	%RAX,%RDX

(152) 0x231fc7 SHR	$0x20,%RDX

(152) 0x231fcb MOV	%RSI,-0xe0(%RBP)

(152) 0x231fd2 JNE	231e10

(152) 0x231fd8 XOR	%EDX,%EDX

(152) 0x231fda DIV	%R13D

(152) 0x231fdd JMP	231e15

0x231fe2 MOV	-0xb0(%RBP),%RAX

0x231fe9 CMP	%RAX,-0xb8(%RBP)

0x231ff0 MOV	-0x58(%RBP),%R14

0x231ff4 MOV	-0xc0(%RBP),%R15

0x231ffb MOV	-0x30(%RBP),%R10

0x231fff MOV	-0x50(%RBP),%R11

0x232003 JNE	2320f4

0x232009 LEA	0x2c0a0(%RIP),%RDI

0x232010 MOV	-0x44(%RBP),%ESI

0x232013 CALL	25cd00 <@plt_start@+0x540>

0x232018 ADD	$0xc8,%RSP

0x23201f POP	%RBX

0x232020 POP	%R12

0x232022 POP	%R13

0x232024 POP	%R14

0x232026 POP	%R15

0x232028 POP	%RBP

0x232029 RET

0x23202a NOPW	(%RAX,%RAX,1)

(151) 0x232030 MOV	%RCX,%RAX

(151) 0x232033 CQTO

(151) 0x232035 IDIV	%R13

(151) 0x232038 MOV	%RCX,%R12

(151) 0x23203b MOV	-0x38(%RBP),%RCX

(151) 0x23203f LEA	(%R10,%RAX,1),%EDI

(151) 0x232043 LEA	(%R11,%RDX,1),%ESI

(151) 0x232047 MOVSXD	%ESI,%RSI

(151) 0x23204a MOVSXD	%EDI,%RDI

(151) 0x23204d ADD	%R14D,%EAX

(151) 0x232050 CLTQ

(151) 0x232052 MOV	-0x90(%RBP),%R8

(151) 0x232059 IMUL	%R8,%RAX

(151) 0x23205d ADD	%RSI,%RAX

(151) 0x232060 MOVSD	(%RBX,%RAX,8),%XMM0

(151) 0x232065 IMUL	%RDI,%R8

(151) 0x232069 ADD	%RSI,%R8

(151) 0x23206c SUBSD	(%RBX,%R8,8),%XMM0

(151) 0x232072 ADD	%ECX,%EDX

(151) 0x232074 MOVSXD	%EDX,%RDX

(151) 0x232077 MOV	-0x88(%RBP),%R9

(151) 0x23207e IMUL	%RDI,%R9

(151) 0x232082 ADD	%R9,%RDX

(151) 0x232085 MOV	-0x80(%RBP),%RCX

(151) 0x232089 ADDSD	(%RCX,%RDX,8),%XMM0

(151) 0x23208e ADD	%RSI,%R9

(151) 0x232091 SUBSD	(%RCX,%R9,8),%XMM0

(151) 0x232097 MOV	-0xa0(%RBP),%RDX

(151) 0x23209e IMUL	%RDI,%RDX

(151) 0x2320a2 ADD	%RSI,%RDX

(151) 0x2320a5 MOV	-0x98(%RBP),%R9

(151) 0x2320ac ADDSD	(%R9,%RDX,8),%XMM0

(151) 0x2320b2 MOV	-0x78(%RBP),%RDX

(151) 0x2320b6 IMUL	%RDI,%RDX

(151) 0x2320ba ADD	%RSI,%RDX

(151) 0x2320bd MOV	-0x70(%RBP),%RCX

(151) 0x2320c1 MOVSD	%XMM0,(%RCX,%RDX,8)

(151) 0x2320c6 MOVSD	(%RBX,%RAX,8),%XMM1

(151) 0x2320cb SUBSD	(%RBX,%R8,8),%XMM1

(151) 0x2320d1 IMUL	-0x68(%RBP),%RDI

(151) 0x2320d6 ADD	%RSI,%RDI

(151) 0x2320d9 SUBSD	%XMM1,%XMM0

(151) 0x2320dd MOV	-0x60(%RBP),%RAX

(151) 0x2320e1 MOVSD	%XMM0,(%RAX,%RDI,8)

(151) 0x2320e6 CMP	%R15,%R12

(151) 0x2320e9 LEA	0x1(%R12),%RCX

(151) 0x2320ee JGE	232009

(151) 0x2320f4 MOV	%RCX,%RAX

(151) 0x2320f7 SHR	$0x20,%RAX

(151) 0x2320fb JNE	232030

(151) 0x232101 MOV	%ECX,%EAX

(151) 0x232103 XOR	%EDX,%EDX

(151) 0x232105 DIV	%R13D

(151) 0x232108 JMP	232038

0x23210d NOPL	(%RAX)

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_cell.cpp:136-140
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/advec_cell.cpp:136-140
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

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 14.63 to 1.25 cycles (11.70x 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_cell.cpp:136
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:136

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_cell.cpp:137

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 208 bytes. The binary function is storing 184 bytes.

General properties

nb instructions	117
nb uops	117
loop length	497
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	28

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.63 cycles
front end	14.63 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	13.75	13.75	13.75	13.75	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	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.63
Dispatch	13.75
Overall L1	14.63

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	11%
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 14.63 cycles. At this rate:

5% of peak load performance is reached (14.22 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.58 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 14.63 to 13.75 cycles (1.06x speedup).

ASM code

In the binary file, the address of the function is: 231c70

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 $0xc8,%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),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
ADD $0x4,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 232018 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x3a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EAX	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 %EAX,%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 232018 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x3a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%R14),%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x1(%RAX),%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
SUB %EBX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB %R12D,%R15D	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,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R15	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,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-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,-0xe8(%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 -0xe8(%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 0x2c3a1(%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 -0xa8(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
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 %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	scal (12.5%)
MOV %R15,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xa8(%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 232009 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x399>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R12,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDI),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R9,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x90(%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),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x88(%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),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%R8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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(%R8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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(%RAX),%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 %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 231dbf <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x14f>	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 2320f4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x484>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R11,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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 %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 231f90 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x320>	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
MOV -0xb0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xb8(%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 -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xc0(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x50(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2320f4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x484>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2c0a0(%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 $0xc8,%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
NOPL (%RAX)	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_cell.cpp:136-140
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/advec_cell.cpp:136-140
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69

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_cell.cpp:136
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:136

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_cell.cpp:137

Type of elements and instruction set

No instructions are processing arithmetic or math operations on FP elements. This function is probably writing/copying data or processing integer elements.

Matching between your function (in the source code) and the binary function

The binary function does not contain any FP arithmetical operations. The binary function is loading 208 bytes. The binary function is storing 184 bytes.

General properties

nb instructions	117
nb uops	117
loop length	497
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	28

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.63 cycles
front end	14.63 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	13.75	13.75	13.75	13.75	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	13.75	13.75	13.75	13.75	0.00	0.00	0.00	0.00	0.00	0.00

Execution ports to units layout:

P0: ALU
P1: ALU
P2: ALU
P3: ALU, BRU
P4: ALU, BRU
P5: ALU, BRU
P6 (512 bits): store address, load
P7 (512 bits): store address, load
P8 (512 bits): store address, load
P9 (512 bits): store address, load
P10 (512 bits): VPU, DIV/SQRT
P11 (512 bits): VPU, DIV/SQRT
P12 (512 bits): VPU
P13 (512 bits): VPU
P14 (512 bits): FP store data
P15 (512 bits): FP store data

Cycles executing div or sqrt instructions

Cycles summary

Front-end	14.63
Dispatch	13.75
Overall L1	14.63

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	11%
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 14.63 cycles. At this rate:

5% of peak load performance is reached (14.22 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
9% of peak store performance is reached (12.58 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: 231c70

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 $0xc8,%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),%R14D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RCX),%R15D	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
ADD $0x4,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP %R14D,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
JL 232018 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x3a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%EAX	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 %EAX,%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 232018 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x3a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA -0x1(%R14),%R12D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x1(%RAX),%EBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
SUB %EBX,%R13D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
SUB %R12D,%R15D	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,%R15	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %R15	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,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %R15,-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,-0xe8(%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 -0xe8(%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 0x2c3a1(%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 -0xa8(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH $0x1	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %RAX	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
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 %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	scal (12.5%)
MOV %R15,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xa8(%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 232009 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x399>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R12,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV 0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x28(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x20(%RBP),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x18(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x10(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV (%RDI),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %R9,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x10(%RDI),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%RDX),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDI,-0x90(%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),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV (%RCX),%RDX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RDX,-0x88(%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),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV (%R8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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(%R8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-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(%RAX),%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 %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 231dbf <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x14f>	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 2320f4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x484>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R11,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
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 %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R13,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 231f90 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x320>	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
MOV -0xb0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xb8(%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 -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xc0(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x50(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2320f4 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined.8+0x484>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2c0a0(%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 $0xc8,%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
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼advec_cell_kernel(int, int, int, int, int, int, clover::Buffer1D&, clover::Buffer1D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D&, clover::Buffer2D–	1.44	0.56
○Loop 152 - advec_cell.cpp:137-140 - exec	1.44	0.56
○Loop 151 - advec_cell.cpp:137-140 - 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