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:44-48 [...]	Coverage (incl. loops): 1.49% \| (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: 44 - 48

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

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

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

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

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

48:           post_vol(i, j) = pre_vol(i, j) - (vol_flux_x(i + 1, j + 0) - vol_flux_x(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]; }

0x22fe30 PUSH	%RBP

0x22fe31 MOV	%RSP,%RBP

0x22fe34 PUSH	%R15

0x22fe36 PUSH	%R14

0x22fe38 PUSH	%R13

0x22fe3a PUSH	%R12

0x22fe3c PUSH	%RBX

0x22fe3d SUB	$0xc8,%RSP

0x22fe44 MOV	(%RDX),%EAX

0x22fe46 MOV	(%RCX),%R15D

0x22fe49 ADD	$0x4,%R15D

0x22fe4d MOV	%RAX,-0x48(%RBP)

0x22fe51 CMP	%EAX,%R15D

0x22fe54 JL	2301e5

0x22fe5a MOV	(%R8),%ECX

0x22fe5d MOV	(%R9),%R13D

0x22fe60 ADD	$0x4,%R13D

0x22fe64 CMP	%ECX,%R13D

0x22fe67 JL	2301e5

0x22fe6d MOV	-0x48(%RBP),%RAX

0x22fe71 LEA	-0x1(%RAX),%R14D

0x22fe75 MOV	%RCX,-0x40(%RBP)

0x22fe79 LEA	-0x1(%RCX),%EBX

0x22fe7c SUB	%EBX,%R13D

0x22fe7f SUB	%R14D,%R15D

0x22fe82 IMUL	%R13,%R15

0x22fe86 DEC	%R15

0x22fe89 MOVQ	$0,-0xa8(%RBP)

0x22fe94 MOV	%R15,-0x50(%RBP)

0x22fe98 MOVQ	$0x1,-0xe8(%RBP)

0x22fea3 MOVL	$0,-0x58(%RBP)

0x22feaa MOV	(%RDI),%ESI

0x22feac SUB	$0x8,%RSP

0x22feb0 LEA	-0xe8(%RBP),%RAX

0x22feb7 LEA	0x2e0ba(%RIP),%RDI

0x22febe LEA	-0x58(%RBP),%RCX

0x22fec2 LEA	-0xa8(%RBP),%R8

0x22fec9 LEA	-0x50(%RBP),%R9

0x22fecd MOV	%ESI,-0x54(%RBP)

0x22fed0 MOV	$0x22,%EDX

0x22fed5 PUSH	$0x1

0x22fed7 PUSH	$0x1

0x22fed9 PUSH	%RAX

0x22feda CALL	25ccf0 <@plt_start@+0x530>

0x22fedf ADD	$0x20,%RSP

0x22fee3 MOV	-0x50(%RBP),%RAX

0x22fee7 CMP	%R15,%RAX

0x22feea CMOVL	%RAX,%R15

0x22feee MOV	%R15,-0x50(%RBP)

0x22fef2 MOV	-0xa8(%RBP),%RSI

0x22fef9 CMP	%R15,%RSI

0x22fefc JG	2301d6

0x22ff02 MOV	%RBX,%R10

0x22ff05 MOV	%R14,%R9

0x22ff08 MOV	0x30(%RBP),%RAX

0x22ff0c MOV	0x28(%RBP),%RCX

0x22ff10 MOV	0x20(%RBP),%RDX

0x22ff14 MOV	0x18(%RBP),%RDI

0x22ff18 MOV	0x10(%RBP),%R8

0x22ff1c MOV	(%RDI),%R11

0x22ff1f MOV	0x10(%RDI),%RDI

0x22ff23 MOV	%RDI,-0xa0(%RBP)

0x22ff2a MOV	(%RDX),%RDI

0x22ff2d MOV	%RDI,-0x98(%RBP)

0x22ff34 MOV	0x10(%RDX),%RBX

0x22ff38 MOV	(%RCX),%RDX

0x22ff3b MOV	%RDX,-0x90(%RBP)

0x22ff42 MOV	0x10(%RCX),%RCX

0x22ff46 MOV	%RCX,-0x88(%RBP)

0x22ff4d MOV	(%R8),%RCX

0x22ff50 MOV	%RCX,-0x80(%RBP)

0x22ff54 MOV	0x10(%R8),%RCX

0x22ff58 MOV	%RCX,-0x78(%RBP)

0x22ff5c MOV	(%RAX),%RCX

0x22ff5f MOV	%RCX,-0x70(%RBP)

0x22ff63 MOV	0x10(%RAX),%RAX

0x22ff67 MOV	%RAX,-0x68(%RBP)

0x22ff6b MOV	%R15,%RAX

0x22ff6e SUB	%RSI,%RAX

0x22ff71 INC	%RAX

0x22ff74 CMP	$0x2,%RAX

0x22ff78 JAE	22ff82

0x22ff7a MOV	%RSI,%RCX

0x22ff7d JMP	2302c6

0x22ff82 MOV	%R11,-0x60(%RBP)

0x22ff86 MOV	%R10,-0x30(%RBP)

0x22ff8a MOV	%R9,-0x38(%RBP)

0x22ff8e MOV	%RAX,-0xb8(%RBP)

0x22ff95 MOV	%RAX,%RCX

0x22ff98 AND	$-0x2,%RCX

0x22ff9c LEA	(%RSI,%RCX,1),%RAX

0x22ffa0 MOV	%RAX,-0xc0(%RBP)

0x22ffa7 MOV	%RCX,-0xb0(%RBP)

0x22ffae MOV	%RCX,%RDX

0x22ffb1 MOV	%R15,-0xd0(%RBP)

0x22ffb8 MOV	%R13,-0xc8(%RBP)

0x22ffbf JMP	230152

0x22ffc4 NOPW	%CS:(%RAX,%RAX,1)

(144) 0x22ffd0 CQTO

(144) 0x22ffd2 IDIV	%R13

(144) 0x22ffd5 LEA	(%R9,%RDI,1),%R11D

(144) 0x22ffd9 LEA	(%R9,%RAX,1),%R14D

(144) 0x22ffdd LEA	(%R10,%R8,1),%R9D

(144) 0x22ffe1 LEA	(%R10,%RDX,1),%R15D

(144) 0x22ffe5 MOVSXD	%R9D,%R13

(144) 0x22ffe8 MOVSXD	%R15D,%R9

(144) 0x22ffeb MOVSXD	%R11D,%R11

(144) 0x22ffee MOVSXD	%R14D,%R14

(144) 0x22fff1 MOV	-0x60(%RBP),%R12

(144) 0x22fff5 MOV	%R12,%R15

(144) 0x22fff8 IMUL	%R11,%R15

(144) 0x22fffc IMUL	%R14,%R12

(144) 0x230000 ADD	%R13,%R15

(144) 0x230003 ADD	%R9,%R12

(144) 0x230006 MOV	-0xa0(%RBP),%R10

(144) 0x23000d MOVSD	(%R10,%R15,8),%XMM0

(144) 0x230013 MOVHPD	(%R10,%R12,8),%XMM0

(144) 0x230019 MOV	-0x40(%RBP),%R10

(144) 0x23001d ADD	%R10D,%R8D

(144) 0x230020 ADD	%R10D,%EDX

(144) 0x230023 MOVSXD	%R8D,%R12

(144) 0x230026 MOVSXD	%EDX,%RDX

(144) 0x230029 MOV	-0x98(%RBP),%R15

(144) 0x230030 MOV	%R15,%R8

(144) 0x230033 IMUL	%R11,%R8

(144) 0x230037 IMUL	%R14,%R15

(144) 0x23003b ADD	%R8,%R12

(144) 0x23003e ADD	%R15,%RDX

(144) 0x230041 MOVSD	(%RBX,%R12,8),%XMM2

(144) 0x230047 MOVHPD	(%RBX,%RDX,8),%XMM2

(144) 0x23004c ADD	%R13,%R8

(144) 0x23004f ADD	%R9,%R15

(144) 0x230052 MOVSD	(%RBX,%R8,8),%XMM3

(144) 0x230058 MOVHPD	(%RBX,%R15,8),%XMM3

(144) 0x23005e MOV	-0x48(%RBP),%R10

(144) 0x230062 ADD	%R10D,%EDI

(144) 0x230065 MOVSXD	%EDI,%RDI

(144) 0x230068 MOV	-0x90(%RBP),%RCX

(144) 0x23006f IMUL	%RCX,%RDI

(144) 0x230073 ADD	%R13,%RDI

(144) 0x230076 MOV	-0x88(%RBP),%RSI

(144) 0x23007d MOVSD	(%RSI,%RDI,8),%XMM1

(144) 0x230082 SUBPD	%XMM3,%XMM2

(144) 0x230086 ADD	%R10D,%EAX

(144) 0x230089 CLTQ

(144) 0x23008b IMUL	%RCX,%RAX

(144) 0x23008f ADD	%R9,%RAX

(144) 0x230092 MOVHPD	(%RSI,%RAX,8),%XMM1

(144) 0x230097 ADDPD	%XMM2,%XMM1

(144) 0x23009b MOV	%RCX,%RAX

(144) 0x23009e IMUL	%R11,%RAX

(144) 0x2300a2 ADD	%R13,%RAX

(144) 0x2300a5 MOVSD	(%RSI,%RAX,8),%XMM2

(144) 0x2300aa IMUL	%R14,%RCX

(144) 0x2300ae ADD	%R9,%RCX

(144) 0x2300b1 MOVHPD	(%RSI,%RCX,8),%XMM2

(144) 0x2300b6 SUBPD	%XMM2,%XMM1

(144) 0x2300ba ADDPD	%XMM0,%XMM1

(144) 0x2300be MOV	-0x80(%RBP),%RCX

(144) 0x2300c2 MOV	%RCX,%RAX

(144) 0x2300c5 IMUL	%R11,%RAX

(144) 0x2300c9 ADD	%R13,%RAX

(144) 0x2300cc MOV	-0x78(%RBP),%RSI

(144) 0x2300d0 MOVLPD	%XMM1,(%RSI,%RAX,8)

(144) 0x2300d5 MOV	%RCX,%RAX

(144) 0x2300d8 IMUL	%R14,%RAX

(144) 0x2300dc ADD	%R9,%RAX

(144) 0x2300df MOVHPD	%XMM1,(%RSI,%RAX,8)

(144) 0x2300e4 MOVSD	(%RBX,%R12,8),%XMM0

(144) 0x2300ea MOVHPD	(%RBX,%RDX,8),%XMM0

(144) 0x2300ef MOVSD	(%RBX,%R8,8),%XMM2

(144) 0x2300f5 MOVHPD	(%RBX,%R15,8),%XMM2

(144) 0x2300fb MOV	-0x70(%RBP),%RAX

(144) 0x2300ff IMUL	%RAX,%R11

(144) 0x230103 ADD	%R13,%R11

(144) 0x230106 IMUL	%RAX,%R14

(144) 0x23010a ADD	%R9,%R14

(144) 0x23010d SUBPD	%XMM2,%XMM0

(144) 0x230111 SUBPD	%XMM0,%XMM1

(144) 0x230115 MOV	-0x68(%RBP),%RAX

(144) 0x230119 MOVLPD	%XMM1,(%RAX,%R11,8)

(144) 0x23011f MOVHPD	%XMM1,(%RAX,%R14,8)

(144) 0x230125 MOV	-0xe0(%RBP),%RSI

(144) 0x23012c ADD	$0x2,%RSI

(144) 0x230130 MOV	-0xd8(%RBP),%RDX

(144) 0x230137 ADD	$-0x2,%RDX

(144) 0x23013b MOV	-0xd0(%RBP),%R15

(144) 0x230142 MOV	-0xc8(%RBP),%R13

(144) 0x230149 MOV	-0xc0(%RBP),%RCX

(144) 0x230150 JE	2301b6

(144) 0x230152 MOV	%RSI,%RAX

(144) 0x230155 SHR	$0x20,%RAX

(144) 0x230159 MOV	%RDX,-0xd8(%RBP)

(144) 0x230160 JE	230180

(144) 0x230162 MOV	%RSI,%RAX

(144) 0x230165 CQTO

(144) 0x230167 IDIV	%R13

(144) 0x23016a MOV	%RDX,%R8

(144) 0x23016d MOV	%RAX,%RDI

(144) 0x230170 JMP	23018c

0x230172 NOPW	%CS:(%RAX,%RAX,1)

(144) 0x230180 MOV	%ESI,%EAX

(144) 0x230182 XOR	%EDX,%EDX

(144) 0x230184 DIV	%R13D

(144) 0x230187 MOV	%EDX,%R8D

(144) 0x23018a MOV	%EAX,%EDI

(144) 0x23018c MOV	-0x38(%RBP),%R9

(144) 0x230190 MOV	-0x30(%RBP),%R10

(144) 0x230194 LEA	0x1(%RSI),%RAX

(144) 0x230198 MOV	%RAX,%RDX

(144) 0x23019b SHR	$0x20,%RDX

(144) 0x23019f MOV	%RSI,-0xe0(%RBP)

(144) 0x2301a6 JNE	22ffd0

(144) 0x2301ac XOR	%EDX,%EDX

(144) 0x2301ae DIV	%R13D

(144) 0x2301b1 JMP	22ffd5

0x2301b6 MOV	-0xb0(%RBP),%RAX

0x2301bd CMP	%RAX,-0xb8(%RBP)

0x2301c4 MOV	-0x38(%RBP),%R9

0x2301c8 MOV	-0x30(%RBP),%R10

0x2301cc MOV	-0x60(%RBP),%R11

0x2301d0 JNE	2302c6

0x2301d6 LEA	0x2ddb3(%RIP),%RDI

0x2301dd MOV	-0x54(%RBP),%ESI

0x2301e0 CALL	25cd00 <@plt_start@+0x540>

0x2301e5 ADD	$0xc8,%RSP

0x2301ec POP	%RBX

0x2301ed POP	%R12

0x2301ef POP	%R13

0x2301f1 POP	%R14

0x2301f3 POP	%R15

0x2301f5 POP	%RBP

0x2301f6 RET

0x2301f7 NOPW	(%RAX,%RAX,1)

(143) 0x230200 MOV	%RCX,%RAX

(143) 0x230203 CQTO

(143) 0x230205 IDIV	%R13

(143) 0x230208 MOV	%RCX,%R14

(143) 0x23020b MOV	-0x40(%RBP),%RCX

(143) 0x23020f LEA	(%R9,%RAX,1),%EDI

(143) 0x230213 LEA	(%R10,%RDX,1),%ESI

(143) 0x230217 MOVSXD	%ESI,%RSI

(143) 0x23021a MOVSXD	%EDI,%RDI

(143) 0x23021d ADD	%ECX,%EDX

(143) 0x23021f MOVSXD	%EDX,%R8

(143) 0x230222 MOV	-0x98(%RBP),%RDX

(143) 0x230229 IMUL	%RDI,%RDX

(143) 0x23022d ADD	%RDX,%R8

(143) 0x230230 MOVSD	(%RBX,%R8,8),%XMM0

(143) 0x230236 ADD	%RSI,%RDX

(143) 0x230239 SUBSD	(%RBX,%RDX,8),%XMM0

(143) 0x23023e ADD	-0x48(%RBP),%EAX

(143) 0x230241 CLTQ

(143) 0x230243 MOV	-0x90(%RBP),%RCX

(143) 0x23024a IMUL	%RCX,%RAX

(143) 0x23024e ADD	%RSI,%RAX

(143) 0x230251 MOV	-0x88(%RBP),%R12

(143) 0x230258 ADDSD	(%R12,%RAX,8),%XMM0

(143) 0x23025e MOV	%RCX,%RAX

(143) 0x230261 IMUL	%RDI,%RAX

(143) 0x230265 ADD	%RSI,%RAX

(143) 0x230268 SUBSD	(%R12,%RAX,8),%XMM0

(143) 0x23026e MOV	%R11,%RAX

(143) 0x230271 IMUL	%RDI,%RAX

(143) 0x230275 ADD	%RSI,%RAX

(143) 0x230278 MOV	-0xa0(%RBP),%R12

(143) 0x23027f ADDSD	(%R12,%RAX,8),%XMM0

(143) 0x230285 MOV	-0x80(%RBP),%RAX

(143) 0x230289 IMUL	%RDI,%RAX

(143) 0x23028d ADD	%RSI,%RAX

(143) 0x230290 MOV	-0x78(%RBP),%RCX

(143) 0x230294 MOVSD	%XMM0,(%RCX,%RAX,8)

(143) 0x230299 MOVSD	(%RBX,%R8,8),%XMM1

(143) 0x23029f SUBSD	(%RBX,%RDX,8),%XMM1

(143) 0x2302a4 IMUL	-0x70(%RBP),%RDI

(143) 0x2302a9 ADD	%RSI,%RDI

(143) 0x2302ac SUBSD	%XMM1,%XMM0

(143) 0x2302b0 MOV	-0x68(%RBP),%RAX

(143) 0x2302b4 MOVSD	%XMM0,(%RAX,%RDI,8)

(143) 0x2302b9 CMP	%R15,%R14

(143) 0x2302bc LEA	0x1(%R14),%RCX

(143) 0x2302c0 JGE	2301d6

(143) 0x2302c6 MOV	%RCX,%RAX

(143) 0x2302c9 SHR	$0x20,%RAX

(143) 0x2302cd JNE	230200

(143) 0x2302d3 MOV	%ECX,%EAX

(143) 0x2302d5 XOR	%EDX,%EDX

(143) 0x2302d7 DIV	%R13D

(143) 0x2302da JMP	230208

0x2302df NOP

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:44-48
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:44-48
/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:44
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:44

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:45

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	118
nb uops	117
loop length	505
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	10%

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: 22fe30

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),%EAX	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%)
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %EAX,%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 2301e5 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%ECX	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 %ECX,%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 2301e5 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	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
LEA -0x1(%RAX),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RCX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x1(%RCX),%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 %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%)
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,-0x50(%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,-0x58(%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 0x2e0ba(%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 -0x58(%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 -0x50(%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,-0x54(%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 -0x50(%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,-0x50(%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 2301d6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3a6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R14,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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,-0xa0(%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,-0x98(%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,-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(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x88(%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,-0x80(%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,-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),%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 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,-0x68(%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 22ff82 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x152>	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 2302c6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x496>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R11,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0x38(%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,-0xc0(%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 %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 230152 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -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 -0x38(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 -0x60(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2302c6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x496>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2ddb3(%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 -0x54(%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
NOP	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:44-48
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:44-48
/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:44
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_cell.cpp:44

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:45

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	118
nb uops	117
loop length	505
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	10%

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: 22fe30

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),%EAX	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%)
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %EAX,%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 2301e5 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV (%R8),%ECX	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 %ECX,%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 2301e5 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3b5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	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
LEA -0x1(%RAX),%R14D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RCX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA -0x1(%RCX),%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 %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%)
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,-0x50(%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,-0x58(%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 0x2e0ba(%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 -0x58(%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 -0x50(%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,-0x54(%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 -0x50(%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,-0x50(%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 2301d6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x3a6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RBX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
MOV %R14,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
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),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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,-0xa0(%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,-0x98(%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,-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(%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RCX,-0x88(%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,-0x80(%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,-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),%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 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,-0x68(%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 22ff82 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x152>	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 2302c6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x496>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %R11,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R10,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0x38(%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,-0xc0(%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 %R15,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JMP 230152 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x322>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -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 -0x38(%RBP),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
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 -0x60(%RBP),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
JNE 2302c6 <_Z17advec_cell_kerneliiiiiiRN6clover8Buffer1DIdEES2_RNS_8Buffer2DIdEES5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_S5_.omp_outlined+0x496>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x2ddb3(%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 -0x54(%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
NOP	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–	1.49	0.58
○Loop 144 - advec_cell.cpp:45-48 - exec	1.49	0.58
○Loop 143 - advec_cell.cpp:45-48 - 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