OV - exec - Function main.extracted.40

	Function: main.extracted.40	Module: exec	Source: stream.c:271-276	Coverage (incl. loops): 0.74% \| (excl. loops): 0.00%

/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/src/stream.c: 271 - 276

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

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;

276: 	}

0x4028a0 PUSH	%RBP

0x4028a1 MOV	%RSP,%RBP

0x4028a4 PUSH	%R15

0x4028a6 PUSH	%R14

0x4028a8 PUSH	%R13

0x4028aa PUSH	%R12

0x4028ac PUSH	%RBX

0x4028ad SUB	$0x28,%RSP

0x4028b1 MOVL	$0,-0x2c(%RBP)

0x4028b8 MOV	(%RDI),%EBX

0x4028ba MOVQ	$0,-0x40(%RBP)

0x4028c2 MOVQ	$0x3344ffff,-0x38(%RBP)

0x4028ca MOVQ	$0x1,-0x48(%RBP)

0x4028d2 SUB	$0x8,%RSP

0x4028d6 LEA	-0x48(%RBP),%RAX

0x4028da MOV	$0x401050,%R10

0x4028e4 MOV	$0x4ceb88d50,%RDI

0x4028ee LEA	-0x2c(%RBP),%RCX

0x4028f2 LEA	-0x40(%RBP),%R8

0x4028f6 LEA	-0x38(%RBP),%R9

0x4028fa MOV	%EBX,%ESI

0x4028fc MOV	$0x22,%EDX

0x402901 PUSH	$0x1

0x402903 PUSH	$0x1

0x402905 PUSH	%RAX

0x402906 CALL	%R10

0x402909 ADD	$0x20,%RSP

0x40290d MOV	-0x40(%RBP),%RAX

0x402911 MOV	-0x38(%RBP),%R10

0x402915 SUB	%RAX,%R10

0x402918 JB	402b85

0x40291e LEA	0x1(%R10),%R9

0x402922 MOV	$0x3ff0000000000000,%RCX

0x40292c MOV	$0x4000000000000000,%RDX

0x402936 MOV	$0x406060,%RSI

0x402940 MOV	$0x19a686060,%RDI

0x40294a MOV	$0x334906060,%R8

0x402954 CMP	$0x7,%R10

0x402958 JB	402a12

0x40295e LEA	0x38(,%RAX,8),%R14

0x402966 MOV	%R9,%R11

0x402969 SHR	$0x3,%R11

0x40296d NOPL	(%RAX)

(9) 0x402970 LEA	-0x38(%R14,%RSI,1),%R15

(9) 0x402975 LEA	-0x38(%R14,%RDI,1),%R12

(9) 0x40297a LEA	-0x38(%R14,%R8,1),%R13

(9) 0x40297f ADD	$0x40,%R14

(9) 0x402983 DEC	%R11

(9) 0x402986 MOV	%RCX,(%R15)

(9) 0x402989 MOV	%RDX,(%R12)

(9) 0x40298d MOVQ	$0,(%R13)

(9) 0x402995 MOV	%RCX,0x8(%R15)

(9) 0x402999 MOV	%RDX,0x8(%R12)

(9) 0x40299e MOVQ	$0,0x8(%R13)

(9) 0x4029a6 MOV	%RCX,0x10(%R15)

(9) 0x4029aa MOV	%RDX,0x10(%R12)

(9) 0x4029af MOVQ	$0,0x10(%R13)

(9) 0x4029b7 MOV	%RCX,0x18(%R15)

(9) 0x4029bb MOV	%RDX,0x18(%R12)

(9) 0x4029c0 MOVQ	$0,0x18(%R13)

(9) 0x4029c8 MOV	%RCX,0x20(%R15)

(9) 0x4029cc MOV	%RDX,0x20(%R12)

(9) 0x4029d1 MOVQ	$0,0x20(%R13)

(9) 0x4029d9 MOV	%RCX,0x28(%R15)

(9) 0x4029dd MOV	%RDX,0x28(%R12)

(9) 0x4029e2 MOVQ	$0,0x28(%R13)

(9) 0x4029ea MOV	%RCX,0x30(%R15)

(9) 0x4029ee MOV	%RDX,0x30(%R12)

(9) 0x4029f3 MOVQ	$0,0x30(%R13)

(9) 0x4029fb MOV	%RCX,0x38(%R15)

(9) 0x4029ff MOV	%RDX,0x38(%R12)

(9) 0x402a04 MOVQ	$0,0x38(%R13)

(9) 0x402a0c JNE	402970

0x402a12 AND	$0x7ffffff8,%R9D

0x402a19 SUB	%R9,%R10

0x402a1c CMP	$0x6,%R10

0x402a20 JA	402b85

0x402a26 MOV	$0x4040d0,%R11

0x402a30 JMP	(%R11,%R10,8)

0x402a34 ADD	%R9,%RAX

0x402a37 JMP	402b75

0x402a3c ADD	%R9,%RAX

0x402a3f JMP	402abd

0x402a41 ADD	%R9,%RAX

0x402a44 JMP	402b19

0x402a49 ADD	%R9,%RAX

0x402a4c JMP	402aeb

0x402a51 ADD	%R9,%RAX

0x402a54 JMP	402b47

0x402a59 ADD	%R9,%RAX

0x402a5c JMP	402a8f

0x402a5e ADD	%R9,%RAX

0x402a61 MOV	$0x406090,%R10

0x402a6b MOV	$0x19a686090,%R11

0x402a75 MOV	%RCX,(%R10,%RAX,8)

0x402a79 MOV	$0x334906090,%R10

0x402a83 MOV	%RDX,(%R11,%RAX,8)

0x402a87 MOVQ	$0,(%R10,%RAX,8)

0x402a8f MOV	$0x406088,%R9

0x402a99 MOV	$0x19a686088,%R11

0x402aa3 MOV	$0x334906088,%R10

0x402aad MOV	%RCX,(%R9,%RAX,8)

0x402ab1 MOV	%RDX,(%R11,%RAX,8)

0x402ab5 MOVQ	$0,(%R10,%RAX,8)

0x402abd MOV	$0x406080,%R9

0x402ac7 MOV	$0x19a686080,%R11

0x402ad1 MOV	$0x334906080,%R10

0x402adb MOV	%RCX,(%R9,%RAX,8)

0x402adf MOV	%RDX,(%R11,%RAX,8)

0x402ae3 MOVQ	$0,(%R10,%RAX,8)

0x402aeb MOV	$0x406078,%R9

0x402af5 MOV	$0x19a686078,%R11

0x402aff MOV	$0x334906078,%R10

0x402b09 MOV	%RCX,(%R9,%RAX,8)

0x402b0d MOV	%RDX,(%R11,%RAX,8)

0x402b11 MOVQ	$0,(%R10,%RAX,8)

0x402b19 MOV	$0x406070,%R9

0x402b23 MOV	$0x19a686070,%R11

0x402b2d MOV	$0x334906070,%R10

0x402b37 MOV	%RCX,(%R9,%RAX,8)

0x402b3b MOV	%RDX,(%R11,%RAX,8)

0x402b3f MOVQ	$0,(%R10,%RAX,8)

0x402b47 MOV	$0x406068,%R9

0x402b51 MOV	$0x19a686068,%R11

0x402b5b MOV	$0x334906068,%R10

0x402b65 MOV	%RCX,(%R9,%RAX,8)

0x402b69 MOV	%RDX,(%R11,%RAX,8)

0x402b6d MOVQ	$0,(%R10,%RAX,8)

0x402b75 MOV	%RCX,(%RSI,%RAX,8)

0x402b79 MOV	%RDX,(%RDI,%RAX,8)

0x402b7d MOVQ	$0,(%R8,%RAX,8)

0x402b85 MOV	$0x4ceb88d70,%RDI

0x402b8f MOV	$0x401030,%RAX

0x402b99 MOV	%EBX,%ESI

0x402b9b ADD	$0x28,%RSP

0x402b9f POP	%RBX

0x402ba0 POP	%R12

0x402ba2 POP	%R13

0x402ba4 POP	%R14

0x402ba6 POP	%R15

0x402ba8 POP	%RBP

0x402ba9 JMP	%RAX

0x402bab 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 icx_10

Source file and lines	stream.c:271-276
Module	exec

The function is defined in /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/src/stream.c:271-276.

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is not vectorized. Only 9% 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 14.13 to 1.01 cycles (14.02x speedup).

Details

All 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/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/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.

JMP: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/src/stream.c:276

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 28 bytes. The binary function is storing 196 bytes.

General properties

nb instructions	113
nb uops	113
loop length	622
used x86 registers	16
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	14.13 cycles
front end	14.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	10.67	10.67	10.67	10.67	10.67	10.67	7.50	7.50	7.50	7.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	10.67	10.67	10.67	10.67	10.67	10.67	7.50	7.50	7.50	7.50	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	14.13
Dispatch	10.67
Overall L1	14.13

Vectorization ratios

all	0%
load	0%
store	0%
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%

Vector efficiency ratios

all	9%
load	6%
store	9%
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	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.13 cycles. At this rate:

0% of peak load performance is reached (1.98 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.88 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 14.13 to 10.67 cycles (1.32x speedup).

ASM code

In the binary file, the address of the function is: 4028a0

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	N/A
MOVL $0,-0x2c(%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,-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,-0x38(%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%)
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 -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 $0x401050,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4ceb88d50,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x2c(%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 -0x38(%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	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 -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JB 402b85 <main.extracted.40+0x2e5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA 0x1(%R10),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x3ff0000000000000,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x4000000000000000,%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	N/A
MOV $0x19a686060,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906060,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x7,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JB 402a12 <main.extracted.40+0x172>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA 0x38(,%RAX,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R9,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x3,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
AND $0x7ffffff8,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %R9,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x6,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JA 402b85 <main.extracted.40+0x2e5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV $0x4040d0,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP (%R11,%R10,8)	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	1	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b75 <main.extracted.40+0x2d5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402abd <main.extracted.40+0x21d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b19 <main.extracted.40+0x279>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402aeb <main.extracted.40+0x24b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b47 <main.extracted.40+0x2a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402a8f <main.extracted.40+0x1ef>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x406090,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686090,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $0x334906090,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406088,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686088,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906088,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406080,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686080,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906080,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406078,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686078,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906078,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406070,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686070,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906070,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406068,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686068,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906068,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RCX,(%RSI,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%RDI,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R8,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x4ceb88d70,%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	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	N/A
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
JMP %RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%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_10

Source file and lines	stream.c:271-276
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/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/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.

JMP: 1 occurrences►
- /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/177-365-3092/stream-add/build/stream-add/src/stream.c:276

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 28 bytes. The binary function is storing 196 bytes.

General properties

nb instructions	113
nb uops	113
loop length	622
used x86 registers	16
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	14.13 cycles
front end	14.13 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	10.67	10.67	10.67	10.67	10.67	10.67	7.50	7.50	7.50	7.50	0.00	0.00	0.00	0.00	0.00	0.00
cycles	10.67	10.67	10.67	10.67	10.67	10.67	7.50	7.50	7.50	7.50	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	14.13
Dispatch	10.67
Overall L1	14.13

Vectorization ratios

all	0%
load	0%
store	0%
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%

Vector efficiency ratios

all	9%
load	6%
store	9%
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	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each call to the function takes 14.13 cycles. At this rate:

0% of peak load performance is reached (1.98 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
10% of peak store performance is reached (13.88 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: 4028a0

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	N/A
MOVL $0,-0x2c(%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,-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,-0x38(%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%)
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 -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 $0x401050,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x4ceb88d50,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA -0x2c(%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 -0x38(%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	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 -0x40(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0x38(%RBP),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
SUB %RAX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JB 402b85 <main.extracted.40+0x2e5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA 0x1(%R10),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x3ff0000000000000,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV $0x4000000000000000,%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	N/A
MOV $0x19a686060,%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906060,%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x7,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JB 402a12 <main.extracted.40+0x172>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
LEA 0x38(,%RAX,8),%R14	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %R9,%R11	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x3,%R11	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.33	N/A
NOPL (%RAX)	0	0	0	0	0	0	0	0	0	0	0	0	0.13	N/A
AND $0x7ffffff8,%R9D	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
SUB %R9,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x6,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JA 402b85 <main.extracted.40+0x2e5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.33-1	N/A
MOV $0x4040d0,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP (%R11,%R10,8)	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	1	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b75 <main.extracted.40+0x2d5>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402abd <main.extracted.40+0x21d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b19 <main.extracted.40+0x279>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402aeb <main.extracted.40+0x24b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402b47 <main.extracted.40+0x2a7>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JMP 402a8f <main.extracted.40+0x1ef>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0.50	N/A
ADD %R9,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x406090,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686090,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV $0x334906090,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406088,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686088,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906088,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406080,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686080,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906080,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406078,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686078,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906078,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406070,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686070,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906070,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x406068,%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x19a686068,%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV $0x334906068,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOV %RCX,(%R9,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%R11,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R10,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RCX,(%RSI,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RDX,(%RDI,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0,(%R8,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x4ceb88d70,%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	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	N/A
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
JMP %RAX	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPL (%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.40–	0.74	0.04
○Loop 9 - stream.c:272-276 - exec	0.74	0.04

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