OV - exec - Function main._omp

	Function: main._omp_fn.2	Module: exec	Source: stream.c:271-275	Coverage (incl. loops): 0.70% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c: 271 - 275

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

271: #pragma omp parallel for

272:     for (j=0; j<STREAM_ARRAY_SIZE; j++) {

273: 	    a[j] = 1.0;

274: 	    b[j] = 2.0;

275: 	    c[j] = 0.0;

0x402750 PUSH	%RBP

0x402751 MOV	$0x401060,%RAX

0x40275b MOV	%RSP,%RBP

0x40275e PUSH	%R14

0x402760 PUSH	%R13

0x402762 PUSH	%R12

0x402764 MOV	$0x401030,%R12

0x40276e PUSH	%RBX

0x40276f CALL	%RAX

0x402771 MOVSXD	%EAX,%RBX

0x402774 CALL	%R12

0x402777 MOVSXD	%EAX,%RCX

0x40277a MOV	$0x33450000,%EAX

0x40277f CQTO

0x402781 IDIV	%RBX

0x402784 CMP	%RDX,%RCX

0x402787 JL	402ad8

0x40278d IMUL	%RAX,%RCX

0x402791 ADD	%RCX,%RDX

0x402794 LEA	(%RAX,%RDX,1),%R11

0x402798 CMP	%R11,%RDX

0x40279b JGE	402abc

0x4027a1 LEA	-0x1(%RAX),%RSI

0x4027a5 MOV	%RDX,%R14

0x4027a8 CMP	$0x6,%RSI

0x4027ac JBE	402ae8

0x4027b2 MOV	%RAX,%R10

0x4027b5 MOV	$0x404700,%R9

0x4027bf SHR	$0x3,%R10

0x4027c3 VMOVAPD	(%R9),%ZMM2

0x4027c9 SAL	$0x6,%R10

0x4027cd MOV	$0x404740,%R9

0x4027d7 VMOVAPD	(%R9),%ZMM1

0x4027dd LEA	-0x40(%R10),%R9

0x4027e1 SHR	$0x6,%R9

0x4027e5 LEA	(,%RDX,8),%RSI

0x4027ed MOV	$0x334906100,%RBX

0x4027f7 MOV	$0x19a686100,%R12

0x402801 MOV	$0x406100,%R13

0x40280b INC	%R9

0x40280e LEA	(%RBX,%RSI,1),%R8

0x402812 LEA	(%R12,%RSI,1),%RDI

0x402816 XOR	%ECX,%ECX

0x402818 ADD	%R13,%RSI

0x40281b VXORPD	%XMM0,%XMM0,%XMM0

0x40281f AND	$0x7,%R9D

0x402823 JE	40290b

0x402829 CMP	$0x1,%R9

0x40282d JE	4028e9

0x402833 CMP	$0x2,%R9

0x402837 JE	4028d0

0x40283d CMP	$0x3,%R9

0x402841 JE	4028b7

0x402843 CMP	$0x4,%R9

0x402847 JE	40289e

0x402849 CMP	$0x5,%R9

0x40284d JE	402885

0x40284f CMP	$0x6,%R9

0x402853 JE	40286c

0x402855 VMOVUPD	%ZMM2,(%R8)

0x40285b MOV	$0x40,%ECX

0x402860 VMOVUPD	%ZMM1,(%RDI)

0x402866 VMOVUPD	%ZMM0,(%RSI)

0x40286c VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x402873 VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x40287a VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x402881 ADD	$0x40,%RCX

0x402885 VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x40288c VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x402893 VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x40289a ADD	$0x40,%RCX

0x40289e VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x4028a5 VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x4028ac VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x4028b3 ADD	$0x40,%RCX

0x4028b7 VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x4028be VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x4028c5 VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x4028cc ADD	$0x40,%RCX

0x4028d0 VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x4028d7 VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x4028de VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x4028e5 ADD	$0x40,%RCX

0x4028e9 VMOVUPD	%ZMM2,(%R8,%RCX,1)

0x4028f0 VMOVUPD	%ZMM1,(%RDI,%RCX,1)

0x4028f7 VMOVUPD	%ZMM0,(%RSI,%RCX,1)

0x4028fe ADD	$0x40,%RCX

0x402902 CMP	%R10,%RCX

0x402905 JE	4029d8

(4) 0x40290b VMOVUPD	%ZMM2,(%R8,%RCX,1)

(4) 0x402912 VMOVUPD	%ZMM1,(%RDI,%RCX,1)

(4) 0x402919 VMOVUPD	%ZMM0,(%RSI,%RCX,1)

(4) 0x402920 VMOVUPD	%ZMM2,0x40(%R8,%RCX,1)

(4) 0x402928 VMOVUPD	%ZMM1,0x40(%RDI,%RCX,1)

(4) 0x402930 VMOVUPD	%ZMM0,0x40(%RSI,%RCX,1)

(4) 0x402938 VMOVUPD	%ZMM2,0x80(%R8,%RCX,1)

(4) 0x402940 VMOVUPD	%ZMM1,0x80(%RDI,%RCX,1)

(4) 0x402948 VMOVUPD	%ZMM0,0x80(%RSI,%RCX,1)

(4) 0x402950 VMOVUPD	%ZMM2,0xc0(%R8,%RCX,1)

(4) 0x402958 VMOVUPD	%ZMM1,0xc0(%RDI,%RCX,1)

(4) 0x402960 VMOVUPD	%ZMM0,0xc0(%RSI,%RCX,1)

(4) 0x402968 VMOVUPD	%ZMM2,0x100(%R8,%RCX,1)

(4) 0x402970 VMOVUPD	%ZMM1,0x100(%RDI,%RCX,1)

(4) 0x402978 VMOVUPD	%ZMM0,0x100(%RSI,%RCX,1)

(4) 0x402980 VMOVUPD	%ZMM2,0x140(%R8,%RCX,1)

(4) 0x402988 VMOVUPD	%ZMM1,0x140(%RDI,%RCX,1)

(4) 0x402990 VMOVUPD	%ZMM0,0x140(%RSI,%RCX,1)

(4) 0x402998 VMOVUPD	%ZMM2,0x180(%R8,%RCX,1)

(4) 0x4029a0 VMOVUPD	%ZMM1,0x180(%RDI,%RCX,1)

(4) 0x4029a8 VMOVUPD	%ZMM0,0x180(%RSI,%RCX,1)

(4) 0x4029b0 VMOVUPD	%ZMM2,0x1c0(%R8,%RCX,1)

(4) 0x4029b8 VMOVUPD	%ZMM1,0x1c0(%RDI,%RCX,1)

(4) 0x4029c0 VMOVUPD	%ZMM0,0x1c0(%RSI,%RCX,1)

(4) 0x4029c8 ADD	$0x200,%RCX

(4) 0x4029cf CMP	%R10,%RCX

(4) 0x4029d2 JNE	40290b

0x4029d8 MOV	%RAX,%RDI

0x4029db AND	$-0x8,%RDI

0x4029df ADD	%RDI,%RDX

0x4029e2 CMP	%RDI,%RAX

0x4029e5 JE	402ac8

0x4029eb SUB	%RDI,%RAX

0x4029ee LEA	-0x1(%RAX),%RSI

0x4029f2 CMP	$0x2,%RSI

0x4029f6 JBE	402a45

0x4029f8 ADD	%R14,%RDI

0x4029fb MOV	$0x404740,%R8

0x402a05 MOV	$0x404700,%R14

0x402a0f VMOVAPD	(%R14),%YMM3

0x402a14 VMOVAPD	(%R8),%YMM4

0x402a19 SAL	$0x3,%RDI

0x402a1d VXORPD	%XMM5,%XMM5,%XMM5

0x402a21 VMOVUPD	%YMM3,(%RBX,%RDI,1)

0x402a26 VMOVUPD	%YMM4,(%R12,%RDI,1)

0x402a2c VMOVUPD	%YMM5,(%R13,%RDI,1)

0x402a33 MOV	%RAX,%RDI

0x402a36 AND	$-0x4,%RDI

0x402a3a ADD	%RDI,%RDX

0x402a3d TEST	$0x3,%AL

0x402a3f JE	402ac8

0x402a45 MOV	$0x404700,%RAX

0x402a4f MOV	$0x404740,%R10

0x402a59 MOV	$0x404918,%R9

0x402a63 VMOVSD	(%RAX),%XMM6

0x402a67 VMOVSD	(%R10),%XMM7

0x402a6c VMOVSD	(%R9),%XMM8

0x402a71 LEA	0x1(%RDX),%RCX

0x402a75 VMOVSD	%XMM6,(%RBX,%RDX,8)

0x402a7a VMOVSD	%XMM7,(%R12,%RDX,8)

0x402a80 VMOVSD	%XMM8,(%R13,%RDX,8)

0x402a87 CMP	%RCX,%R11

0x402a8a JLE	402ac8

0x402a8c ADD	$0x2,%RDX

0x402a90 VMOVSD	%XMM6,(%RBX,%RCX,8)

0x402a95 VMOVSD	%XMM7,(%R12,%RCX,8)

0x402a9b VMOVSD	%XMM8,(%R13,%RCX,8)

0x402aa2 CMP	%RDX,%R11

0x402aa5 JLE	402ac8

0x402aa7 VMOVSD	%XMM6,(%RBX,%RDX,8)

0x402aac VMOVSD	%XMM7,(%R12,%RDX,8)

0x402ab2 VMOVSD	%XMM8,(%R13,%RDX,8)

0x402ab9 VZEROUPPER

0x402abc POP	%RBX

0x402abd POP	%R12

0x402abf POP	%R13

0x402ac1 POP	%R14

0x402ac3 POP	%RBP

0x402ac4 RET

0x402ac5 NOPL	(%RAX)

0x402ac8 VZEROUPPER

0x402acb POP	%RBX

0x402acc POP	%R12

0x402ace POP	%R13

0x402ad0 POP	%R14

0x402ad2 POP	%RBP

0x402ad3 RET

0x402ad4 NOPL	(%RAX)

0x402ad8 INC	%RAX

0x402adb XOR	%EDX,%EDX

0x402add JMP	40278d

0x402ae2 NOPW	(%RAX,%RAX,1)

0x402ae8 XOR	%EDI,%EDI

0x402aea MOV	$0x334906100,%RBX

0x402af4 MOV	$0x19a686100,%R12

0x402afe MOV	$0x406100,%R13

0x402b08 JMP	4029eb

0x402b0d NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
○98.96	gomp_thread_start	team.c:130	libgomp.so.1.0.0
○1.04	GOMP_parallel	libgomp.h:982	libgomp.so.1.0.0

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 gcc_2

Source file and lines	stream.c:271-275
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271-275.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Code clean check

Detected a slowdown caused by scalar integer instructions (typically used for address computation). By removing them, you can lower the cost of an iteration from 28.00 to 16.50 cycles (1.70x speedup).

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Your function is partially vectorized. Only 49% of vector register length is used (average across all SSE/AVX instructions). By fully vectorizing your function, you can lower the cost of an iteration from 28.00 to 23.01 cycles (1.22x speedup).

Details

52% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

57% of SSE/AVX loads are used in vector version.
72% of SSE/AVX stores are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
20% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

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.

IDIV: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271
VZEROUPPER: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:275
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

Vector unaligned load/store instructions

Detected 3 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 3 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:273
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:274
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:275

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

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 216 bytes. The binary function is storing 1512 bytes.

General properties

nb instructions	160
nb uops	168
loop length	755
used x86 registers	15
used mmx registers	0
used xmm registers	5
used ymm registers	3
used zmm registers	3
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	28.00 cycles
front end	28.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	14.50	14.40	6.33	6.33	20.00	14.40	14.30	20.00	20.00	20.00	14.40	6.33
cycles	14.50	14.40	6.33	6.33	20.00	14.40	14.30	20.00	20.00	20.00	14.40	6.33

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

10.00

Cycles summary

Front-end	28.00
Dispatch	20.00
DIV/SQRT	10.00
Overall L1	28.00

Vectorization ratios

INT

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

all	71%
load	57%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	52%
load	57%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	20%

Vector efficiency ratios

INT

all	13%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	65%
load	48%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	49%
load	48%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 28.00 cycles. At this rate:

4% of peak load performance is reached (7.71 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
42% of peak store performance is reached (54.00 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 28.00 to 20.00 cycles (1.40x speedup).

ASM code

In the binary file, the address of the function is: 402750

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x401060,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x401030,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL %RAX	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
MOVSXD %EAX,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
CALL %R12	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
MOVSXD %EAX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV $0x33450000,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %RBX	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
CMP %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JL 402ad8 <main._omp_fn.2+0x388>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %RAX,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RAX,%RDX,1),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R11,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 402abc <main._omp_fn.2+0x36c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RAX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x6,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 402ae8 <main._omp_fn.2+0x398>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x404700,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
SHR $0x3,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VMOVAPD (%R9),%ZMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $0x404740,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVAPD (%R9),%ZMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
LEA -0x40(%R10),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (,%RDX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x334906100,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x19a686100,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x406100,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RBX,%RSI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R12,%RSI,1),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 40290b <main._omp_fn.2+0x1bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028e9 <main._omp_fn.2+0x199>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028d0 <main._omp_fn.2+0x180>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028b7 <main._omp_fn.2+0x167>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40289e <main._omp_fn.2+0x14e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 402885 <main._omp_fn.2+0x135>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40286c <main._omp_fn.2+0x11c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD %ZMM2,(%R8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
MOV $0x40,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD %ZMM1,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R10,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4029d8 <main._omp_fn.2+0x288>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %RDI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %RDI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 402a45 <main._omp_fn.2+0x2f5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R14,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x404740,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404700,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVAPD (%R14),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD (%R8),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
SAL $0x3,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVUPD %YMM3,(%RBX,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
VMOVUPD %YMM4,(%R12,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
VMOVUPD %YMM5,(%R13,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %RDI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x404700,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404740,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404918,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVSD (%RAX),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R10),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R9),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
LEA 0x1(%RDX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM6,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RCX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $0x2,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM6,(%RBX,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RDX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD %XMM6,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40278d <main._omp_fn.2+0x3d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x334906100,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x19a686100,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x406100,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
JMP 4029eb <main._omp_fn.2+0x29b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run gcc_2

Source file and lines	stream.c:271-275
Module	exec

gain
potential
hint
expert

Code clean check

Workaround

Try to reorganize arrays of structures to structures of arrays
Consider to permute loops (see vectorization gain report)

Vectorization

Details

52% of SSE/AVX instructions are used in vector version (process two or more data elements in vector registers):

57% of SSE/AVX loads are used in vector version.
72% of SSE/AVX stores are used in vector version.
0% of SSE/AVX divide and square root instructions are used in vector version.
20% of SSE/AVX instructions that are not load, store, addition, subtraction nor multiply instructions are used in vector version.

Since your execution units are vector units, only a fully 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

unknown: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

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.

IDIV: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271
VZEROUPPER: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:275
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

Vector unaligned load/store instructions

Detected 3 optimal vector unaligned load/store instructions.

Details

VMOVUPD: 3 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:273
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:274
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:275

Workaround

Use vector aligned instructions:

align your arrays on 64 bytes boundaries: replace { void *p = malloc (size); } with { void *p; posix_memalign (&p, 64, size); }.
inform your compiler that your arrays are vector aligned: if array 'foo' is 64 bytes-aligned, define a pointer 'p_foo' as __builtin_assume_aligned (foo, 64) and use it instead of 'foo' in the loop.

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix05.benchmarkcenter.megware.com/177-373-7249/stream-triad/build/stream-triad/src/stream.c:271

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

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 216 bytes. The binary function is storing 1512 bytes.

General properties

nb instructions	160
nb uops	168
loop length	755
used x86 registers	15
used mmx registers	0
used xmm registers	5
used ymm registers	3
used zmm registers	3
nb stack references	0

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	28.00 cycles
front end	28.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	14.50	14.40	6.33	6.33	20.00	14.40	14.30	20.00	20.00	20.00	14.40	6.33
cycles	14.50	14.40	6.33	6.33	20.00	14.40	14.30	20.00	20.00	20.00	14.40	6.33

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

10.00

Cycles summary

Front-end	28.00
Dispatch	20.00
DIV/SQRT	10.00
Overall L1	28.00

Vectorization ratios

INT

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

all	71%
load	57%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	100%

INT+FP

all	52%
load	57%
store	72%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	20%

Vector efficiency ratios

INT

all	13%
load	NA (no load vectorizable/vectorized instructions)
store	NA (no store vectorizable/vectorized instructions)
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	65%
load	48%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	25%

INT+FP

all	49%
load	48%
store	71%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	NA (no add-sub vectorizable/vectorized instructions)
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	15%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 28.00 cycles. At this rate:

4% of peak load performance is reached (7.71 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
42% of peak store performance is reached (54.00 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: 402750

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
PUSH %RBP	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x401060,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
PUSH %R14	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R13	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %R12	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
MOV $0x401030,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
PUSH %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL %RAX	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
MOVSXD %EAX,%RBX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
CALL %R12	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
MOVSXD %EAX,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
MOV $0x33450000,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %RBX	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
CMP %RDX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JL 402ad8 <main._omp_fn.2+0x388>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
IMUL %RAX,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RCX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA (%RAX,%RDX,1),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %R11,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JGE 402abc <main._omp_fn.2+0x36c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA -0x1(%RAX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x6,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 402ae8 <main._omp_fn.2+0x398>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV $0x404700,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
SHR $0x3,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VMOVAPD (%R9),%ZMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
SAL $0x6,%R10	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $0x404740,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVAPD (%R9),%ZMM1	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.50	vect (100.0%)
LEA -0x40(%R10),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x6,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
LEA (,%RDX,8),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x334906100,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x19a686100,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x406100,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
INC %R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA (%RBX,%RSI,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA (%R12,%RSI,1),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R13,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VXORPD %XMM0,%XMM0,%XMM0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
AND $0x7,%R9D	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
JE 40290b <main._omp_fn.2+0x1bb>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028e9 <main._omp_fn.2+0x199>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028d0 <main._omp_fn.2+0x180>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x3,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4028b7 <main._omp_fn.2+0x167>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x4,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40289e <main._omp_fn.2+0x14e>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x5,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 402885 <main._omp_fn.2+0x135>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x6,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 40286c <main._omp_fn.2+0x11c>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVUPD %ZMM2,(%R8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
MOV $0x40,%ECX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVUPD %ZMM1,(%RDI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVUPD %ZMM2,(%R8,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM1,(%RDI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
VMOVUPD %ZMM0,(%RSI,%RCX,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	1	vect (100.0%)
ADD $0x40,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R10,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 4029d8 <main._omp_fn.2+0x288>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x8,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %RDI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP %RDI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SUB %RDI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1(%RAX),%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JBE 402a45 <main._omp_fn.2+0x2f5>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD %R14,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV $0x404740,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404700,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVAPD (%R14),%YMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
VMOVAPD (%R8),%YMM4	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	0-1	0.33	vect (50.0%)
SAL $0x3,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VXORPD %XMM5,%XMM5,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
VMOVUPD %YMM3,(%RBX,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
VMOVUPD %YMM4,(%R12,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
VMOVUPD %YMM5,(%R13,%RDI,1)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0-1	0.50	vect (50.0%)
MOV %RAX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x4,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
ADD %RDI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
TEST $0x3,%AL	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	2	0.20	N/A
JE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV $0x404700,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404740,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x404918,%R9	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
VMOVSD (%RAX),%XMM6	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R10),%XMM7	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD (%R9),%XMM8	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
LEA 0x1(%RDX),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD %XMM6,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RCX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
ADD $0x2,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
VMOVSD %XMM6,(%RBX,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RCX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP %RDX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JLE 402ac8 <main._omp_fn.2+0x378>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
VMOVSD %XMM6,(%RBX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM7,(%R12,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD %XMM8,(%R13,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
POP %RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
POP %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
RET	1	0.50	0	0.33	0.33	0	0	0.50	0	0	0	0	0.33	0	2.13	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 40278d <main._omp_fn.2+0x3d>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x334906100,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x19a686100,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x406100,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
JMP 4029eb <main._omp_fn.2+0x29b>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼main._omp_fn.2–	0.70	0.03
○Loop 4 - stream.c:273-275 - exec	0.70	0.03

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

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

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

CALL instructions

Details

Complex instructions

Details

Vector unaligned load/store instructions

Details

Workaround

Conversion instructions

Details

Workaround

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