OV - exec - Function main.extracted.60

	Function: main.extracted.60	Module: exec	Source: stream.c:342-344	Coverage (incl. loops): 27.64% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-365-2841/stream/build/stream/src/stream.c: 342 - 344

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

342: #pragma omp parallel for

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

344: 	    c[j] = a[j]+b[j];

0x4034c0 PUSH	%RBP

0x4034c1 MOV	%RSP,%RBP

0x4034c4 PUSH	%R14

0x4034c6 PUSH	%RBX

0x4034c7 SUB	$0x20,%RSP

0x4034cb MOVL	$0,-0x14(%RBP)

0x4034d2 MOV	(%RDI),%EBX

0x4034d4 MOVQ	$0,-0x28(%RBP)

0x4034dc MOVQ	$0x3344ffff,-0x20(%RBP)

0x4034e4 MOVQ	$0x1,-0x30(%RBP)

0x4034ec SUB	$0x8,%RSP

0x4034f0 LEA	-0x30(%RBP),%RAX

0x4034f4 LEA	-0x28(%RBP),%R8

0x4034f8 MOV	$0x4ceb891e0,%RDI

0x403502 MOV	$0x401050,%R10

0x40350c LEA	-0x14(%RBP),%RCX

0x403510 LEA	-0x20(%RBP),%R9

0x403514 MOV	%EBX,%ESI

0x403516 MOV	$0x22,%EDX

0x40351b PUSH	$0x1

0x40351d PUSH	$0x1

0x40351f PUSH	%RAX

0x403520 CALL	%R10

0x403523 ADD	$0x20,%RSP

0x403527 MOV	-0x28(%RBP),%R8

0x40352b MOV	-0x20(%RBP),%RAX

0x40352f CMP	%RAX,%R8

0x403532 JA	4035de

0x403538 MOV	%RAX,%R9

0x40353b SUB	%R8,%R9

0x40353e MOV	$0x19a686060,%RDX

0x403548 MOV	$0x406060,%RSI

0x403552 MOV	$0x334906060,%RDI

0x40355c INC	%R9

0x40355f MOV	%R9,%RCX

0x403562 AND	$0x7ffffffc,%RCX

0x403569 JE	4035a6

0x40356b LEA	(,%R8,8),%R10

0x403573 XOR	%R11D,%R11D

0x403576 NOPW	%CS:(%RAX,%RAX,1)

(20) 0x403580 LEA	(%R10,%R11,8),%R14

(20) 0x403584 ADD	$0x4,%R11

(20) 0x403588 VMOVUPD	(%RDX,%R14,1),%YMM0

(20) 0x40358e VADDPD	(%RSI,%R14,1),%YMM0,%YMM0

(20) 0x403594 VMOVUPD	%YMM0,(%RDI,%R14,1)

(20) 0x40359a CMP	%RCX,%R11

(20) 0x40359d JB	403580

0x40359f CMP	%RCX,%R9

0x4035a2 JNE	4035a8

0x4035a4 JMP	4035de

0x4035a6 XOR	%ECX,%ECX

0x4035a8 SUB	%RCX,%RAX

0x4035ab ADD	%R8,%RCX

0x4035ae SUB	%R8,%RAX

0x4035b1 SAL	$0x3,%RCX

0x4035b5 XOR	%R8D,%R8D

0x4035b8 INC	%RAX

0x4035bb NOPL	(%RAX,%RAX,1)

(19) 0x4035c0 LEA	(%RCX,%R8,8),%R9

(19) 0x4035c4 INC	%R8

(19) 0x4035c7 VMOVSD	(%RDX,%R9,1),%XMM0

(19) 0x4035cd VADDSD	(%RSI,%R9,1),%XMM0,%XMM0

(19) 0x4035d3 VMOVSD	%XMM0,(%RDI,%R9,1)

(19) 0x4035d9 CMP	%R8,%RAX

(19) 0x4035dc JNE	4035c0

0x4035de MOV	$0x4ceb89200,%RDI

0x4035e8 MOV	$0x401030,%RAX

0x4035f2 MOV	%EBX,%ESI

0x4035f4 ADD	$0x20,%RSP

0x4035f8 POP	%RBX

0x4035f9 POP	%R14

0x4035fb POP	%RBP

0x4035fc VZEROUPPER

0x4035ff JMP	%RAX

0x403601 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module
►100.00+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.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 icx_4

Source file and lines	stream.c:342-344
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-365-2841/stream/build/stream/src/stream.c:342-344.

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 7.38 to 0.54 cycles (13.75x 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: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-365-2841/stream/build/stream/src/stream.c:342

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 28 bytes.

General properties

nb instructions	61
nb uops	59
loop length	275
used x86 registers	13
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	7.38 cycles
front end	7.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.50	5.50	5.50	5.50	5.50	5.50	2.00	2.00	2.00	2.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	5.50	5.50	5.50	5.50	5.50	5.50	2.00	2.00	2.00	2.00	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	7.38
Dispatch	5.50
Overall L1	7.38

Vectorization ratios

all	4%
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	6%

Vector efficiency ratios

all	10%
load	6%
store	6%
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 7.38 cycles. At this rate:

1% of peak load performance is reached (2.71 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.80 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 7.38 to 5.50 cycles (1.34x speedup).

ASM code

In the binary file, the address of the function is: 4034c0

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 %R14	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 $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVL $0,-0x14(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOVQ $0,-0x28(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x20(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 -0x30(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x28(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4ceb891e0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x401050,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
LEA -0x14(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x20(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	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	scal (6.3%)
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 %R10	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	2	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 -0x28(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JA 4035de <main.extracted.60+0x11e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x19a686060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x406060,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x334906060,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R9,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $0x7ffffffc,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 4035a6 <main.extracted.60+0xe6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA (,%R8,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
CMP %RCX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JNE 4035a8 <main.extracted.60+0xe8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
JMP 4035de <main.extracted.60+0x11e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
SUB %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SAL $0x3,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	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
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
MOV $0x4ceb89200,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x401030,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP %RAX	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	0.13	N/A

The code analyzed by CQA in that panel excludes loops and represents 0.00% of application time for run icx_4

Source file and lines	stream.c:342-344
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: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-365-2841/stream/build/stream/src/stream.c:342

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 28 bytes.

General properties

nb instructions	61
nb uops	59
loop length	275
used x86 registers	13
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	7.38 cycles
front end	7.38 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	5.50	5.50	5.50	5.50	5.50	5.50	2.00	2.00	2.00	2.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	5.50	5.50	5.50	5.50	5.50	5.50	2.00	2.00	2.00	2.00	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	7.38
Dispatch	5.50
Overall L1	7.38

Vectorization ratios

all	4%
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	6%

Vector efficiency ratios

all	10%
load	6%
store	6%
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 7.38 cycles. At this rate:

1% of peak load performance is reached (2.71 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (3.80 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: 4034c0

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 %R14	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 $0x20,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVL $0,-0x14(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
MOVQ $0,-0x28(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x20(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
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 -0x30(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x28(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4ceb891e0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x401050,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
LEA -0x14(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x20(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	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	scal (6.3%)
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 %R10	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	2	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 -0x28(%RBP),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x20(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JA 4035de <main.extracted.60+0x11e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV %RAX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
SUB %R8,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x19a686060,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x406060,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x334906060,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %R9,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (12.5%)
AND $0x7ffffffc,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 4035a6 <main.extracted.60+0xe6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA (,%R8,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
CMP %RCX,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JNE 4035a8 <main.extracted.60+0xe8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
JMP 4035de <main.extracted.60+0x11e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %RCX,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R8,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
SUB %R8,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SAL $0x3,%RCX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
XOR %R8D,%R8D	1	0	0	0	0	0	0	0	0	0	0	0	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
NOPL (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
MOV $0x4ceb89200,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x401030,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
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
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP %RAX	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	0.13	N/A

Name	Coverage (%)	Time (s)
▼main.extracted.60–	27.64	5.51
○Loop 20 - stream.c:343-344 - exec	27.64	5.43
○Loop 19 - stream.c:343-344 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

CALL 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

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