OV - exec - Function main.extracted.45

	Function: main.extracted.45	Module: exec	Source: stream.c:290-292	Coverage (incl. loops): 0.91% \| (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];

0x402d20 PUSH	%RBP

0x402d21 MOV	%RSP,%RBP

0x402d24 PUSH	%RBX

0x402d25 SUB	$0x28,%RSP

0x402d29 MOVL	$0,-0xc(%RBP)

0x402d30 MOV	(%RDI),%EBX

0x402d32 MOVQ	$0,-0x20(%RBP)

0x402d3a MOVQ	$0x3344ffff,-0x18(%RBP)

0x402d42 MOVQ	$0x1,-0x28(%RBP)

0x402d4a SUB	$0x8,%RSP

0x402d4e LEA	-0x28(%RBP),%RAX

0x402d52 MOV	$0x4ceb87dc0,%RDI

0x402d5c MOV	$0x401050,%R10

0x402d66 LEA	-0xc(%RBP),%RCX

0x402d6a LEA	-0x20(%RBP),%R8

0x402d6e LEA	-0x18(%RBP),%R9

0x402d72 MOV	%EBX,%ESI

0x402d74 MOV	$0x22,%EDX

0x402d79 PUSH	$0x1

0x402d7b PUSH	$0x1

0x402d7d PUSH	%RAX

0x402d7e CALL	%R10

0x402d81 ADD	$0x20,%RSP

0x402d85 MOV	-0x20(%RBP),%RSI

0x402d89 MOV	-0x18(%RBP),%RAX

0x402d8d CMP	%RAX,%RSI

0x402d90 JA	402e1a

0x402d96 MOV	%RAX,%RDI

0x402d99 SUB	%RSI,%RDI

0x402d9c INC	%RDI

0x402d9f MOV	%RDI,%RCX

0x402da2 MOV	$0x405060,%RDX

0x402dac AND	$0x7ffffffc,%RCX

0x402db3 JE	402de4

0x402db5 LEA	(,%RSI,8),%R8

0x402dbd XOR	%R9D,%R9D

(14) 0x402dc0 LEA	(%R8,%R9,8),%R10

(14) 0x402dc4 VMOVUPD	(%RDX,%R10,1),%YMM0

(14) 0x402dca VADDPD	%YMM0,%YMM0,%YMM0

(14) 0x402dce VMOVUPD	%YMM0,(%RDX,%R10,1)

(14) 0x402dd4 ADD	$0x4,%R9

(14) 0x402dd8 CMP	%RCX,%R9

(14) 0x402ddb JB	402dc0

0x402ddd CMP	%RCX,%RDI

0x402de0 JNE	402de6

0x402de2 JMP	402e1a

0x402de4 XOR	%ECX,%ECX

0x402de6 SUB	%RCX,%RAX

0x402de9 SUB	%RSI,%RAX

0x402dec INC	%RAX

0x402def ADD	%RSI,%RCX

0x402df2 SAL	$0x3,%RCX

0x402df6 XOR	%ESI,%ESI

0x402df8 NOPL	(%RAX,%RAX,1)

(13) 0x402e00 LEA	(%RCX,%RSI,8),%RDI

(13) 0x402e04 VMOVSD	(%RDX,%RDI,1),%XMM0

(13) 0x402e09 VADDSD	%XMM0,%XMM0,%XMM0

(13) 0x402e0d VMOVSD	%XMM0,(%RDX,%RDI,1)

(13) 0x402e12 INC	%RSI

(13) 0x402e15 CMP	%RSI,%RAX

(13) 0x402e18 JNE	402e00

0x402e1a MOV	$0x4ceb87de0,%RDI

0x402e24 MOV	$0x401030,%RAX

0x402e2e MOV	%EBX,%ESI

0x402e30 ADD	$0x28,%RSP

0x402e34 POP	%RBX

0x402e35 POP	%RBP

0x402e36 VZEROUPPER

0x402e39 JMP	%RAX

0x402e3b NOPL	(%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 orig_0

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 9.67 to 0.69 cycles (14.00x 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/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 28 bytes.

General properties

nb instructions	56
nb uops	58
loop length	233
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	9.67 cycles
front end	9.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	3.80	3.80	1.67	1.67	5.00	3.80	3.80	5.00	5.00	5.00	3.80	1.67
cycles	3.80	3.80	1.67	1.67	5.00	3.80	3.80	5.00	5.00	5.00	3.80	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	9.67
Dispatch	5.00
Overall L1	9.67

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	9%

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 9.67 cycles. At this rate:

1% of peak load performance is reached (2.07 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.90 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 9.67 to 5.00 cycles (1.93x speedup).

ASM code

In the binary file, the address of the function is: 402d20

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 $0x4ceb87dc0,%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	N/A
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),%RSI	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,%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%)
JA 402e1a <main.extracted.45+0xfa>	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
SUB %RSI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x405060,%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%)
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 402de4 <main.extracted.45+0xc4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%RSI,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
CMP %RCX,%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%)
JNE 402de6 <main.extracted.45+0xc6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 402e1a <main.extracted.45+0xfa>	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 %RSI,%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 %RSI,%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 %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb87de0,%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	N/A
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,%RAX,1)	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: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: 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

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 28 bytes.

General properties

nb instructions	56
nb uops	58
loop length	233
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	9.67 cycles
front end	9.67 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	3.80	3.80	1.67	1.67	5.00	3.80	3.80	5.00	5.00	5.00	3.80	1.67
cycles	3.80	3.80	1.67	1.67	5.00	3.80	3.80	5.00	5.00	5.00	3.80	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	9.67
Dispatch	5.00
Overall L1	9.67

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	9%

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 9.67 cycles. At this rate:

1% of peak load performance is reached (2.07 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
2% of peak store performance is reached (2.90 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: 402d20

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 $0x4ceb87dc0,%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	N/A
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),%RSI	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,%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%)
JA 402e1a <main.extracted.45+0xfa>	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
SUB %RSI,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
INC %RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RDI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x405060,%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%)
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 402de4 <main.extracted.45+0xc4>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (,%RSI,8),%R8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
XOR %R9D,%R9D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	scal (6.3%)
CMP %RCX,%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%)
JNE 402de6 <main.extracted.45+0xc6>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JMP 402e1a <main.extracted.45+0xfa>	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 %RSI,%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 %RSI,%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 %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
NOPL (%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV $0x4ceb87de0,%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	N/A
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,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A

Name	Coverage (%)	Time (s)
▼main.extracted.45–	0.91	0.03
○Loop 14 - stream.c:291-292 - exec	0.91	0.03
○Loop 13 - 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