OV - exec - Function main.omp

	Function: main.omp_outlined.18	Module: exec	Source: stream.c:290-292	Coverage (incl. loops): 1.01% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c: 290 - 292

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

290: #pragma omp parallel for

291:     for (j = 0; j < STREAM_ARRAY_SIZE; j++)

292: 		a[j] = 2.0E0 * a[j];

0x2031f0 PUSH	%RBP

0x2031f1 MOV	%RSP,%RBP

0x2031f4 PUSH	%R14

0x2031f6 PUSH	%RBX

0x2031f7 SUB	$0x20,%RSP

0x2031fb MOVQ	$0,-0x28(%RBP)

0x203203 MOVQ	$0x3344ffff,-0x18(%RBP)

0x20320b LEA	0x31ce(%RIP),%RBX

0x203212 MOVQ	$0x1,-0x30(%RBP)

0x20321a MOVL	$0,-0x1c(%RBP)

0x203221 MOV	(%RDI),%R14D

0x203224 SUB	$0x8,%RSP

0x203228 LEA	-0x30(%RBP),%RAX

0x20322c MOV	$0x1108,%RDI

0x203236 ADD	%RBX,%RDI

0x203239 LEA	-0x1c(%RBP),%RCX

0x20323d LEA	-0x28(%RBP),%R8

0x203241 LEA	-0x18(%RBP),%R9

0x203245 MOV	%R14D,%ESI

0x203248 MOV	$0x22,%EDX

0x20324d PUSH	$0x1

0x20324f PUSH	$0x1

0x203251 PUSH	%RAX

0x203252 CALL	2041d0 <@plt_start@+0x80>

0x203257 ADD	$0x20,%RSP

0x20325b MOV	-0x18(%RBP),%RCX

0x20325f CMP	$0x3344ffff,%RCX

0x203266 MOV	$0x3344ffff,%EAX

0x20326b CMOVL	%RCX,%RAX

0x20326f MOV	%RAX,-0x18(%RBP)

0x203273 MOV	-0x28(%RBP),%RCX

0x203277 CMP	%RAX,%RCX

0x20327a JG	203328

0x203280 MOV	%RAX,%RSI

0x203283 SUB	%RCX,%RSI

0x203286 INC	%RSI

0x203289 MOV	$0x11a0,%RDX

0x203293 CMP	$0x10,%RSI

0x203297 JB	203304

0x203299 MOV	%RSI,%RDI

0x20329c AND	$-0x10,%RDI

0x2032a0 LEA	(%RBX,%RDX,1),%R8

0x2032a4 LEA	0x60(%R8,%RCX,8),%R8

0x2032a9 ADD	%RDI,%RCX

0x2032ac XOR	%R9D,%R9D

0x2032af NOP

(5) 0x2032b0 VMOVUPD	-0x60(%R8,%R9,8),%YMM0

(5) 0x2032b7 VMOVUPD	-0x40(%R8,%R9,8),%YMM1

(5) 0x2032be VMOVUPD	-0x20(%R8,%R9,8),%YMM2

(5) 0x2032c5 VMOVUPD	(%R8,%R9,8),%YMM3

(5) 0x2032cb VADDPD	%YMM0,%YMM0,%YMM0

(5) 0x2032cf VADDPD	%YMM1,%YMM1,%YMM1

(5) 0x2032d3 VADDPD	%YMM2,%YMM2,%YMM2

(5) 0x2032d7 VADDPD	%YMM3,%YMM3,%YMM3

(5) 0x2032db VMOVUPD	%YMM0,-0x60(%R8,%R9,8)

(5) 0x2032e2 VMOVUPD	%YMM1,-0x40(%R8,%R9,8)

(5) 0x2032e9 VMOVUPD	%YMM2,-0x20(%R8,%R9,8)

(5) 0x2032f0 VMOVUPD	%YMM3,(%R8,%R9,8)

(5) 0x2032f6 ADD	$0x10,%R9

(5) 0x2032fa CMP	%R9,%RDI

(5) 0x2032fd JNE	2032b0

0x2032ff CMP	%RDI,%RSI

0x203302 JE	203328

0x203304 DEC	%RCX

0x203307 ADD	%RBX,%RDX

0x20330a NOPW	(%RAX,%RAX,1)

(4) 0x203310 VMOVSD	0x8(%RDX,%RCX,8),%XMM0

(4) 0x203316 VADDSD	%XMM0,%XMM0,%XMM0

(4) 0x20331a VMOVSD	%XMM0,0x8(%RDX,%RCX,8)

(4) 0x203320 INC	%RCX

(4) 0x203323 CMP	%RAX,%RCX

(4) 0x203326 JL	203310

0x203328 MOV	$0x1120,%RAX

0x203332 ADD	%RAX,%RBX

0x203335 MOV	%RBX,%RDI

0x203338 MOV	%R14D,%ESI

0x20333b VZEROUPPER

0x20333e CALL	2041f0 <@plt_start@+0xa0>

0x203343 ADD	$0x20,%RSP

0x203347 POP	%RBX

0x203348 POP	%R14

0x20334a POP	%RBP

0x20334b RET

0x20334c NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►99.22+	__kmp_invoke_microtask		libomp.so
○	__kmp_invoke_task_func		libomp.so

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 aocc_8

Source file and lines	stream.c:290-292
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290-292.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is probably 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 11.00 to 0.80 cycles (13.81x speedup).

Details

Store and arithmetical 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►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290

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.

VZEROUPPER: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290

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 20 bytes. The binary function is storing 36 bytes.

General properties

nb instructions	63
nb uops	66
loop length	249
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.00 cycles
front end	11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.30	4.20	2.33	2.33	6.50	4.20	4.10	6.50	6.50	6.50	4.20	2.33
cycles	4.30	4.20	2.33	2.33	6.50	4.20	4.10	6.50	6.50	6.50	4.20	2.33

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

Cycles summary

Front-end	11.00
Dispatch	6.50
Overall L1	11.00

Vectorization ratios

all	5%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Vector efficiency ratios

all	10%
load	6%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
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 11.00 cycles. At this rate:

0% of peak load performance is reached (1.82 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.27 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 11.00 to 6.50 cycles (1.69x speedup).

ASM code

In the binary file, the address of the function is: 2031f0

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 %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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 %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x28(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x18(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA 0x31ce(%RIP),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0x1,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0,-0x1c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV (%RDI),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x1108,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RBX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1c(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x28(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x18(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 2041d0 <@plt_start@+0x80>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x18(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x3344ffff,%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%)
MOV $0x3344ffff,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVL %RCX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %RAX,-0x18(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x28(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%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%)
JG 203328 <main.omp_outlined.18+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RCX,%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%)
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x11a0,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
CMP $0x10,%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%)
JB 203304 <main.omp_outlined.18+0x114>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x10,%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
LEA (%RBX,%RDX,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x60(%R8,%RCX,8),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDI,%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%)
JE 203328 <main.omp_outlined.18+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RBX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x1120,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 2041f0 <@plt_start@+0xa0>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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 %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

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run aocc_8

Source file and lines	stream.c:290-292
Module	exec

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►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290

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.

VZEROUPPER: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix04.benchmarkcenter.megware.com/177-373-7189/stream-copy/build/stream-copy/src/stream.c:290

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 20 bytes. The binary function is storing 36 bytes.

General properties

nb instructions	63
nb uops	66
loop length	249
used x86 registers	11
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	11.00 cycles
front end	11.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.30	4.20	2.33	2.33	6.50	4.20	4.10	6.50	6.50	6.50	4.20	2.33
cycles	4.30	4.20	2.33	2.33	6.50	4.20	4.10	6.50	6.50	6.50	4.20	2.33

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

Cycles summary

Front-end	11.00
Dispatch	6.50
Overall L1	11.00

Vectorization ratios

all	5%
load	0%
store	0%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	11%

Vector efficiency ratios

all	10%
load	6%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
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 11.00 cycles. At this rate:

0% of peak load performance is reached (1.82 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.27 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: 2031f0

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 %RSP,%RBP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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 %RBX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
SUB $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x28(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x18(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
LEA 0x31ce(%RIP),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOVQ $0x1,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOVL $0,-0x1c(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (6.3%)
MOV (%RDI),%R14D	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x1108,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RBX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
LEA -0x1c(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x28(%RBP),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x18(%RBP),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
MOV $0x22,%EDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH $0x1	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
PUSH %RAX	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	5-12	0.50	N/A
CALL 2041d0 <@plt_start@+0x80>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x18(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP $0x3344ffff,%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%)
MOV $0x3344ffff,%EAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMOVL %RCX,%RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %RAX,-0x18(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x28(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%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%)
JG 203328 <main.omp_outlined.18+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RCX,%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%)
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x11a0,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
CMP $0x10,%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%)
JB 203304 <main.omp_outlined.18+0x114>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x10,%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
LEA (%RBX,%RDX,1),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0x60(%R8,%RCX,8),%R8	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOP	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RDI,%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%)
JE 203328 <main.omp_outlined.18+0x138>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
DEC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
ADD %RBX,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x1120,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RBX,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R14D,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALL 2041f0 <@plt_start@+0xa0>	2	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	0	1	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
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 %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

Name	Coverage (%)	Time (s)
▼main.omp_outlined.18–	1.01	0.03
○Loop 5 - stream.c:292-292 - exec	1.01	0.03
○Loop 4 - stream.c:291-292 - 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