OV - exec - Function main.omp

	Function: main.omp_outlined.14	Module: exec	Source: stream.c:271-275	Coverage (incl. loops): 0.52% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/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;

0x2032b0 PUSH	%RBP

0x2032b1 MOV	%RSP,%RBP

0x2032b4 PUSH	%R15

0x2032b6 PUSH	%R14

0x2032b8 PUSH	%R13

0x2032ba PUSH	%R12

0x2032bc PUSH	%RBX

0x2032bd SUB	$0x28,%RSP

0x2032c1 MOV	(%RDI),%EBX

0x2032c3 LEA	-0x7(%RIP),%RAX

0x2032ca MOV	$0x34a5,%R14

0x2032d4 MOVQ	$0,-0x40(%RBP)

0x2032dc MOVQ	$0x3344ffff,-0x30(%RBP)

0x2032e4 MOVQ	$0x1,-0x48(%RBP)

0x2032ec MOVL	$0,-0x34(%RBP)

0x2032f3 ADD	%RAX,%R14

0x2032f6 SUB	$0x8,%RSP

0x2032fa MOV	$-0x12a0,%RDI

0x203304 LEA	-0x48(%RBP),%RAX

0x203308 MOV	$-0x1020,%R10

0x203312 LEA	-0x34(%RBP),%RCX

0x203316 LEA	-0x40(%RBP),%R8

0x20331a LEA	-0x30(%RBP),%R9

0x20331e MOV	%EBX,%ESI

0x203320 MOV	$0x22,%EDX

0x203325 ADD	%R14,%RDI

0x203328 PUSH	$0x1

0x20332a PUSH	$0x1

0x20332c PUSH	%RAX

0x20332d CALLQ	(%R14,%R10,1)

0x203331 ADD	$0x20,%RSP

0x203335 MOV	-0x30(%RBP),%RAX

0x203339 MOV	-0x40(%RBP),%R13

0x20333d MOV	$0x3344ffff,%R15D

0x203343 CMP	$0x3344ffff,%RAX

0x203349 CMOVL	%RAX,%R15

0x20334d MOV	%R15,-0x30(%RBP)

0x203351 CMP	%R15,%R13

0x203354 JG	2034e2

0x20335a MOV	$0x334500028,%RAX

0x203364 MOV	%R15,%R12

0x203367 SUB	%R13,%R12

0x20336a XOR	%ESI,%ESI

0x20336c ADD	%R14,%RAX

0x20336f LEA	0x8(,%R12,8),%RDX

0x203377 INC	%R12

0x20337a LEA	(%RAX,%R13,8),%RDI

0x20337e MOV	$-0x1018,%RAX

0x203388 CALLQ	(%R14,%RAX,1)

0x20338c MOV	$0x28,%RAX

0x203396 MOV	$0x19a280028,%RCX

0x2033a0 CMP	$0x4,%R12

0x2033a4 JAE	2033ae

0x2033a6 MOV	%R13,%R8

0x2033a9 JMP	2034aa

0x2033ae MOV	$-0x5fb0,%RSI

0x2033b8 MOV	$-0x5fd0,%RDI

0x2033c2 CMP	$0x20,%R12

0x2033c6 JAE	2033cf

0x2033c8 XOR	%EDX,%EDX

0x2033ca JMP	20345a

0x2033cf VBROADCASTSD	(%R14,%RSI,1),%ZMM0

0x2033d6 VBROADCASTSD	(%R14,%RDI,1),%ZMM1

0x2033dd LEA	(%R14,%RAX,1),%R8

0x2033e1 LEA	(%R14,%RCX,1),%R9

0x2033e5 MOV	%R12,%RDX

0x2033e8 AND	$-0x20,%RDX

0x2033ec XOR	%R10D,%R10D

0x2033ef LEA	0xc0(%R8,%R13,8),%R8

0x2033f7 LEA	0xc0(%R9,%R13,8),%R9

0x2033ff NOP

(4) 0x203400 VMOVUPS	%ZMM0,-0xc0(%R8,%R10,8)

(4) 0x203408 VMOVUPS	%ZMM0,-0x80(%R8,%R10,8)

(4) 0x203410 VMOVUPS	%ZMM0,-0x40(%R8,%R10,8)

(4) 0x203418 VMOVUPS	%ZMM1,-0xc0(%R9,%R10,8)

(4) 0x203420 VMOVUPS	%ZMM1,-0x80(%R9,%R10,8)

(4) 0x203428 VMOVUPS	%ZMM1,-0x40(%R9,%R10,8)

(4) 0x203430 VMOVUPS	%ZMM0,(%R8,%R10,8)

(4) 0x203437 VMOVUPS	%ZMM1,(%R9,%R10,8)

(4) 0x20343e ADD	$0x20,%R10

(4) 0x203442 CMP	%R10,%RDX

(4) 0x203445 JNE	203400

0x203447 CMP	%RDX,%R12

0x20344a JE	2034e2

0x203450 TEST	$0x1c,%R12B

0x203454 JE	203511

0x20345a VBROADCASTSD	(%R14,%RSI,1),%YMM0

0x203460 VBROADCASTSD	(%R14,%RDI,1),%YMM1

0x203466 LEA	(%R14,%RAX,1),%R10

0x20346a LEA	(%R14,%RCX,1),%R11

0x20346e MOV	%R12,%R9

0x203471 AND	$-0x4,%R9

0x203475 LEA	(%R10,%R13,8),%R10

0x203479 LEA	(%R11,%R13,8),%R11

0x20347d LEA	(%R13,%R9,1),%R8

0x203482 NOPW	%CS:(%RAX,%RAX,1)

(6) 0x203490 VMOVUPS	%YMM0,(%R10,%RDX,8)

(6) 0x203496 VMOVUPS	%YMM1,(%R11,%RDX,8)

(6) 0x20349c ADD	$0x4,%RDX

(6) 0x2034a0 CMP	%RDX,%R9

(6) 0x2034a3 JNE	203490

0x2034a5 CMP	%R9,%R12

0x2034a8 JE	2034e2

0x2034aa DEC	%R8

0x2034ad ADD	%R14,%RAX

0x2034b0 MOV	$0x3ff0000000000000,%RDX

0x2034ba ADD	%R14,%RCX

0x2034bd MOV	$0x4000000000000000,%RSI

0x2034c7 NOPW	(%RAX,%RAX,1)

(5) 0x2034d0 MOV	%RDX,0x8(%RAX,%R8,8)

(5) 0x2034d5 MOV	%RSI,0x8(%RCX,%R8,8)

(5) 0x2034da INC	%R8

(5) 0x2034dd CMP	%R15,%R8

(5) 0x2034e0 JL	2034d0

0x2034e2 MOV	$-0x1288,%RDI

0x2034ec MOV	$-0x1010,%RAX

0x2034f6 MOV	%EBX,%ESI

0x2034f8 ADD	%R14,%RDI

0x2034fb VZEROUPPER

0x2034fe CALLQ	(%R14,%RAX,1)

0x203502 ADD	$0x28,%RSP

0x203506 POP	%RBX

0x203507 POP	%R12

0x203509 POP	%R13

0x20350b POP	%R14

0x20350d POP	%R15

0x20350f POP	%RBP

0x203510 RET

0x203511 ADD	%RDX,%R13

0x203514 JMP	2033a6

0x203519 NOPL	(%RAX)

Coverage (%)	Name	Source Location	Module
►99.07+	__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 orig_0

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

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/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 14.75 to 2.25 cycles (6.56x speedup).

Workaround

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

Vectorization

Your function is probably not vectorized. Only 11% 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 14.75 to 1.07 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: 3 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:275
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/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.

CMOVL: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:272
LEA: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271

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 76 bytes. The binary function is storing 36 bytes.

General properties

nb instructions	110
nb uops	118
loop length	514
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	2
used zmm registers	2
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.75 cycles
front end	14.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	11.50	11.50	11.50	11.50	11.50	11.50	5.00	5.00	5.00	5.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	11.50	11.50	11.50	11.50	11.50	11.50	5.00	5.00	5.00	5.00	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	14.75
Dispatch	11.50
Overall L1	14.75

Vectorization ratios

INT

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

all	0%
load	0%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

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	7%

Vector efficiency ratios

INT

all	11%
load	6%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	12%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	11%
load	11%
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	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.75 cycles. At this rate:

2% of peak load performance is reached (5.15 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.44 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 14.75 to 11.50 cycles (1.28x speedup).

ASM code

In the binary file, the address of the function is: 2032b0

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 %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	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 $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV (%RDI),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
LEA -0x7(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x34a5,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x34(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
ADD %RAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x12a0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x48(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1020,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x34(%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 -0x40(%RBP),%R8	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),%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	N/A
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
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
CALLQ (%R14,%R10,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	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	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV $0x3344ffff,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP $0x3344ffff,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %R15,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %R15,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV $0x334500028,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R15,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R13,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA 0x8(,%R12,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RAX,%R13,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1018,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CALLQ (%R14,%RAX,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	N/A
MOV $0x28,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a280028,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x4,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2033ae <main.omp_outlined.14+0xfe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV %R13,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2034aa <main.omp_outlined.14+0x1fa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
MOV $-0x5fb0,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x5fd0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x20,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2033cf <main.omp_outlined.14+0x11f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 20345a <main.omp_outlined.14+0x1aa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
VBROADCASTSD (%R14,%RSI,1),%ZMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
VBROADCASTSD (%R14,%RDI,1),%ZMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%R14,%RAX,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R14,%RCX,1),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R12,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x20,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xc0(%R8,%R13,8),%R8	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
LEA 0xc0(%R9,%R13,8),%R9	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RDX,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
TEST $0x1c,%R12B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JE 203511 <main.omp_outlined.14+0x261>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
VBROADCASTSD (%R14,%RSI,1),%YMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
VBROADCASTSD (%R14,%RDI,1),%YMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%R14,%RAX,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R14,%RCX,1),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R12,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R10,%R13,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R11,%R13,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R13,%R9,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
CMP %R9,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
DEC %R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x3ff0000000000000,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4000000000000000,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
MOV $-0x1288,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1010,%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	N/A
ADD %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALLQ (%R14,%RAX,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	N/A
ADD $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R13	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 %R15	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
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
ADD %RDX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 2033a6 <main.omp_outlined.14+0xf6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	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 orig_0

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

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 14.75 to 2.25 cycles (6.56x speedup).

Workaround

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

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: 3 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:275
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/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.

CMOVL: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:272
LEA: 2 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-4625/stream-scale/build/stream-scale/src/stream.c:271

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 76 bytes. The binary function is storing 36 bytes.

General properties

nb instructions	110
nb uops	118
loop length	514
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	2
used zmm registers	2
nb stack references	4

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	14.75 cycles
front end	14.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	11.50	11.50	11.50	11.50	11.50	11.50	5.00	5.00	5.00	5.00	0.00	0.00	0.00	0.00	0.00	0.00
cycles	11.50	11.50	11.50	11.50	11.50	11.50	5.00	5.00	5.00	5.00	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	14.75
Dispatch	11.50
Overall L1	14.75

Vectorization ratios

INT

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

all	0%
load	0%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	0%

INT+FP

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	7%

Vector efficiency ratios

INT

all	11%
load	6%
store	7%
mul	NA (no mul vectorizable/vectorized instructions)
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	13%

all	12%
load	12%
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)
div/sqrt	NA (no div/sqrt vectorizable/vectorized instructions)
other	12%

INT+FP

all	11%
load	11%
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	12%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.75 cycles. At this rate:

2% of peak load performance is reached (5.15 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (2.44 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: 2032b0

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 %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.50	N/A
PUSH %R12	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 $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV (%RDI),%EBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (6.3%)
LEA -0x7(%RIP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x34a5,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVQ $0,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x3344ffff,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVQ $0x1,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x34(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
ADD %RAX,%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB $0x8,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $-0x12a0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x48(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1020,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x34(%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 -0x40(%RBP),%R8	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),%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	N/A
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
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
CALLQ (%R14,%R10,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	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	scal (12.5%)
MOV -0x30(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x40(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV $0x3344ffff,%R15D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (6.3%)
CMP $0x3344ffff,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
CMOVL %RAX,%R15	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %R15,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
CMP %R15,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV $0x334500028,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R15,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %R13,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA 0x8(,%R12,8),%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RAX,%R13,8),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1018,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CALLQ (%R14,%RAX,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	N/A
MOV $0x28,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a280028,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x4,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2033ae <main.omp_outlined.14+0xfe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV %R13,%R8	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 2034aa <main.omp_outlined.14+0x1fa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
MOV $-0x5fb0,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x5fd0,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x20,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JAE 2033cf <main.omp_outlined.14+0x11f>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 20345a <main.omp_outlined.14+0x1aa>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
VBROADCASTSD (%R14,%RSI,1),%ZMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
VBROADCASTSD (%R14,%RDI,1),%ZMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%R14,%RAX,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R14,%RCX,1),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R12,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x20,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
XOR %R10D,%R10D	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
LEA 0xc0(%R8,%R13,8),%R8	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
LEA 0xc0(%R9,%R13,8),%R9	2	0	0	0.50	0.50	0	0	0.25	0.25	0.25	0.25	2	0.50	N/A
NOP	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
CMP %RDX,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
TEST $0x1c,%R12B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JE 203511 <main.omp_outlined.14+0x261>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
VBROADCASTSD (%R14,%RSI,1),%YMM0	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
VBROADCASTSD (%R14,%RDI,1),%YMM1	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
LEA (%R14,%RAX,1),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R14,%RCX,1),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R12,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R10,%R13,8),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R11,%R13,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%R13,%R9,1),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
CMP %R9,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JE 2034e2 <main.omp_outlined.14+0x232>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
DEC %R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x3ff0000000000000,%RDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
ADD %R14,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4000000000000000,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
NOPW (%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
MOV $-0x1288,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $-0x1010,%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	N/A
ADD %R14,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
VZEROUPPER	1	0	0	0	0	0	0	0	0	0	0	0	1	vect (25.0%)
CALLQ (%R14,%RAX,1)	4	0	0	0	0.33	0.33	0.33	0.50	0.50	0.50	0.50	0	2.20	N/A
ADD $0x28,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
POP %RBX	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
POP %R13	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 %R15	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
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
ADD %RDX,%R13	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 2033a6 <main.omp_outlined.14+0xf6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A

Name	Coverage (%)	Time (s)
▼main.omp_outlined.14–	0.52	0.02
○Loop 4 - stream.c:273-274 - exec	0.52	0.02
○Loop 6 - stream.c:273-274 - exec	0.00	0.00
○Loop 5 - stream.c:272-274 - exec	0.00	0.00

Report Configuration

Code clean check

Workaround

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

Code clean check

Workaround

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