OV - exec - Function main.extracted.50

	Function: main.extracted.50	Module: exec	Source: stream.c:318-320	Coverage (incl. loops): 19.09% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c: 318 - 320

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

318: #pragma omp parallel for

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

320: 	    c[j] = a[j];

0x402ef0 PUSH	%RBP

0x402ef1 MOV	%RSP,%RBP

0x402ef4 PUSH	%RBX

0x402ef5 SUB	$0x28,%RSP

0x402ef9 MOVL	$0,-0xc(%RBP)

0x402f00 MOV	(%RDI),%EBX

0x402f02 MOVQ	$0,-0x20(%RBP)

0x402f0a MOVQ	$0x3344ffff,-0x18(%RBP)

0x402f12 MOVQ	$0x1,-0x28(%RBP)

0x402f1a SUB	$0x8,%RSP

0x402f1e LEA	-0x28(%RBP),%RAX

0x402f22 MOV	$0x4ceb89120,%RDI

0x402f2c MOV	$0x401050,%R10

0x402f36 LEA	-0xc(%RBP),%RCX

0x402f3a LEA	-0x20(%RBP),%R8

0x402f3e LEA	-0x18(%RBP),%R9

0x402f42 MOV	%EBX,%ESI

0x402f44 MOV	$0x22,%EDX

0x402f49 PUSH	$0x1

0x402f4b PUSH	$0x1

0x402f4d PUSH	%RAX

0x402f4e CALL	%R10

0x402f51 ADD	$0x20,%RSP

0x402f55 MOV	-0x20(%RBP),%RDI

0x402f59 MOV	-0x18(%RBP),%RAX

0x402f5d CMP	%RAX,%RDI

0x402f60 JA	402ff8

0x402f66 MOV	%RAX,%R8

0x402f69 SUB	%RDI,%R8

0x402f6c INC	%R8

0x402f6f MOV	%R8,%RCX

0x402f72 MOV	$0x406060,%RDX

0x402f7c MOV	$0x334906060,%RSI

0x402f86 AND	$0x7ffffffc,%RCX

0x402f8d JE	402fc0

0x402f8f LEA	(,%RDI,8),%R9

0x402f97 XOR	%R10D,%R10D

0x402f9a NOPW	(%RAX,%RAX,1)

(16) 0x402fa0 LEA	(%R9,%R10,8),%R11

(16) 0x402fa4 VMOVUPS	(%RDX,%R11,1),%YMM0

(16) 0x402faa VMOVUPS	%YMM0,(%RSI,%R11,1)

(16) 0x402fb0 ADD	$0x4,%R10

(16) 0x402fb4 CMP	%RCX,%R10

(16) 0x402fb7 JB	402fa0

0x402fb9 CMP	%RCX,%R8

0x402fbc JNE	402fc2

0x402fbe JMP	402ff8

0x402fc0 XOR	%ECX,%ECX

0x402fc2 SUB	%RCX,%RAX

0x402fc5 SUB	%RDI,%RAX

0x402fc8 INC	%RAX

0x402fcb ADD	%RDI,%RCX

0x402fce SAL	$0x3,%RCX

0x402fd2 XOR	%EDI,%EDI

0x402fd4 NOPW	%CS:(%RAX,%RAX,1)

(15) 0x402fe0 LEA	(%RCX,%RDI,8),%R8

(15) 0x402fe4 VMOVSD	(%RDX,%R8,1),%XMM0

(15) 0x402fea VMOVSD	%XMM0,(%RSI,%R8,1)

(15) 0x402ff0 INC	%RDI

(15) 0x402ff3 CMP	%RDI,%RAX

(15) 0x402ff6 JNE	402fe0

0x402ff8 MOV	$0x4ceb89140,%RDI

0x403002 MOV	$0x401030,%RAX

0x40300c MOV	%EBX,%ESI

0x40300e ADD	$0x28,%RSP

0x403012 POP	%RBX

0x403013 POP	%RBP

0x403014 VZEROUPPER

0x403017 JMP	%RAX

0x403019 NOPL	(%RAX)

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 orig_0

Source file and lines	stream.c:318-320
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318-320.

Warnings:
get_cqa_results:

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 10.00 to 0.73 cycles (13.65x 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/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318

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/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318

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	58
nb uops	60
loop length	255
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	10.00 cycles
front end	10.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.00	4.00	1.67	1.67	5.00	4.00	4.00	5.00	5.00	5.00	4.00	1.67
cycles	4.00	4.00	1.67	1.67	5.00	4.00	4.00	5.00	5.00	5.00	4.00	1.67

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	10.00
Dispatch	5.00
Overall L1	10.00

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 10.00 cycles. At this rate:

1% of peak load performance is reached (2.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.80 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 10.00 to 5.00 cycles (2.00x speedup).

ASM code

In the binary file, the address of the function is: 402ef0

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 %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 $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0,-0xc(%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),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x20(%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%)
MOVQ $0x1,-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%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x28(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb89120,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x401050,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
LEA -0xc(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x20(%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 %EBX,%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	scal (6.3%)
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 %R10	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x20(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x18(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 402ff8 <main.extracted.50+0x108>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RDI,%R8	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 %R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x406060,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
MOV $0x334906060,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
AND $0x7ffffffc,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 402fc0 <main.extracted.50+0xd0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RCX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 402fc2 <main.extracted.50+0xd2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 402ff8 <main.extracted.50+0x108>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	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
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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	scal (12.5%)
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb89140,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x401030,%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 %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x28,%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 %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP %RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	1.75	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 orig_0

Source file and lines	stream.c:318-320
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318-320.

Warnings:
get_cqa_results:

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: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318

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/isix02.benchmarkcenter.megware.com/177-373-7005/stream/build/stream/src/stream.c:318

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	58
nb uops	60
loop length	255
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	10.00 cycles
front end	10.00 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	4.00	4.00	1.67	1.67	5.00	4.00	4.00	5.00	5.00	5.00	4.00	1.67
cycles	4.00	4.00	1.67	1.67	5.00	4.00	4.00	5.00	5.00	5.00	4.00	1.67

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	10.00
Dispatch	5.00
Overall L1	10.00

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 10.00 cycles. At this rate:

1% of peak load performance is reached (2.00 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.80 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: 402ef0

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 %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 $0x28,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOVL $0,-0xc(%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),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (6.3%)
MOVQ $0,-0x20(%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%)
MOVQ $0x1,-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%)
SUB $0x8,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA -0x28(%RBP),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb89120,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x401050,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
LEA -0xc(%RBP),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA -0x20(%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 %EBX,%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	scal (6.3%)
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 %R10	2	0.50	0	0	0	0.50	0	0.50	0.50	0.50	0.50	0	0	0	2.14	N/A
ADD $0x20,%RSP	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x20(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x18(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
CMP %RAX,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JA 402ff8 <main.extracted.50+0x108>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SUB %RDI,%R8	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 %R8	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV %R8,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x406060,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
MOV $0x334906060,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	scal (12.5%)
AND $0x7ffffffc,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	scal (12.5%)
JE 402fc0 <main.extracted.50+0xd0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%RDI,8),%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
NOPW (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RCX,%R8	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JNE 402fc2 <main.extracted.50+0xd2>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 402ff8 <main.extracted.50+0x108>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	5.84	N/A
XOR %ECX,%ECX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
SUB %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	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
INC %RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	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	scal (12.5%)
SAL $0x3,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	scal (12.5%)
XOR %EDI,%EDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb89140,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
MOV $0x401030,%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 %EBX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
ADD $0x28,%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 %RBP	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1-6	0.33	N/A
VZEROUPPER	2	0	0	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
JMP %RAX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	1.75	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.extracted.50–	19.09	3.11
○Loop 16 - stream.c:319-320 - exec	19.09	2.87
○Loop 15 - stream.c:319-320 - 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