OV - exec - Function build_field(global_variables&) [clone .omp

	Function: build_field(global_variables&) [clone .omp_outlined]	Module: exec	Source: build_field.cpp:100-113 [...]	Coverage (incl. loops): 0.09% \| (excl. loops): 0.00%

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 69 - 69

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

69:   T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; }

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp: 100 - 113

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

100: #pragma omp parallel for simd collapse(2)

101:     for (int j = (0); j < (yrange + 1); j++) {

102:       for (int i = (0); i < (xrange + 1); i++) {

103:         field.work_array1(i, j) = 0.0;

104:         field.work_array2(i, j) = 0.0;

105:         field.work_array3(i, j) = 0.0;

106:         field.work_array4(i, j) = 0.0;

107:         field.work_array5(i, j) = 0.0;

108:         field.work_array6(i, j) = 0.0;

109:         field.work_array7(i, j) = 0.0;

110:         field.xvel0(i, j) = 0.0;

111:         field.xvel1(i, j) = 0.0;

112:         field.yvel0(i, j) = 0.0;

113:         field.yvel1(i, j) = 0.0;

0x2386b0 PUSH	%RBP

0x2386b1 MOV	%RSP,%RBP

0x2386b4 PUSH	%R15

0x2386b6 PUSH	%R14

0x2386b8 PUSH	%R13

0x2386ba PUSH	%R12

0x2386bc PUSH	%RBX

0x2386bd SUB	$0x108,%RSP

0x2386c4 MOVSXD	(%RDX),%RBX

0x2386c7 MOVSXD	(%RCX),%R12

0x2386ca MOV	%R12D,%EAX

0x2386cd OR	%EBX,%EAX

0x2386cf JS	238b8f

0x2386d5 MOV	%R8,%R14

0x2386d8 INC	%R12

0x2386db INC	%RBX

0x2386de IMUL	%R12,%RBX

0x2386e2 DEC	%RBX

0x2386e5 MOVQ	$0,-0xd0(%RBP)

0x2386f0 MOV	%RBX,-0x40(%RBP)

0x2386f4 MOVQ	$0x1,-0x128(%RBP)

0x2386ff MOVL	$0,-0x48(%RBP)

0x238706 MOV	(%RDI),%ESI

0x238708 SUB	$0x8,%RSP

0x23870c LEA	-0x128(%RBP),%RAX

0x238713 LEA	0x25dfe(%RIP),%RDI

0x23871a LEA	-0x48(%RBP),%RCX

0x23871e LEA	-0xd0(%RBP),%R8

0x238725 LEA	-0x40(%RBP),%R9

0x238729 MOV	%ESI,-0x44(%RBP)

0x23872c MOV	$0x22,%EDX

0x238731 PUSH	$0x1

0x238733 PUSH	$0x1

0x238735 PUSH	%RAX

0x238736 CALL	25ccf0 <@plt_start@+0x530>

0x23873b ADD	$0x20,%RSP

0x23873f MOV	-0x40(%RBP),%RAX

0x238743 CMP	%RBX,%RAX

0x238746 CMOVL	%RAX,%RBX

0x23874a MOV	%RBX,-0x40(%RBP)

0x23874e MOV	-0xd0(%RBP),%RSI

0x238755 CMP	%RBX,%RSI

0x238758 JG	238b80

0x23875e MOV	0x178(%R14),%RCX

0x238765 MOV	0x168(%R14),%RDI

0x23876c MOV	0x190(%R14),%R8

0x238773 MOV	0x180(%R14),%R13

0x23877a MOV	0x1a8(%R14),%RAX

0x238781 MOV	%RAX,-0xc0(%RBP)

0x238788 MOV	0x198(%R14),%RAX

0x23878f MOV	%RAX,-0xb8(%RBP)

0x238796 MOV	0x1c0(%R14),%R10

0x23879d MOV	0x1b0(%R14),%R11

0x2387a4 MOV	0x1d8(%R14),%RAX

0x2387ab MOV	%RAX,-0xb0(%RBP)

0x2387b2 MOV	0x1c8(%R14),%RAX

0x2387b9 MOV	%RAX,-0xa8(%RBP)

0x2387c0 MOV	0x1f0(%R14),%RAX

0x2387c7 MOV	%RAX,-0x58(%RBP)

0x2387cb MOV	0x1e0(%R14),%RAX

0x2387d2 MOV	%RAX,-0xa0(%RBP)

0x2387d9 MOV	0x208(%R14),%RAX

0x2387e0 MOV	%RAX,-0x98(%RBP)

0x2387e7 MOV	0x1f8(%R14),%RAX

0x2387ee MOV	%RAX,-0x90(%RBP)

0x2387f5 MOV	0xa8(%R14),%R15

0x2387fc MOV	0xb8(%R14),%RAX

0x238803 MOV	%RAX,-0x88(%RBP)

0x23880a MOV	0xd0(%R14),%RAX

0x238811 MOV	%RAX,-0x80(%RBP)

0x238815 MOV	0xc0(%R14),%RAX

0x23881c MOV	%RAX,-0x78(%RBP)

0x238820 MOV	0xe8(%R14),%R9

0x238827 MOV	0xd8(%R14),%RAX

0x23882e MOV	%RAX,-0x70(%RBP)

0x238832 MOV	0x100(%R14),%RAX

0x238839 MOV	%RAX,-0x68(%RBP)

0x23883d MOV	0xf0(%R14),%RAX

0x238844 MOV	%RAX,-0x60(%RBP)

0x238848 MOV	%RBX,%RAX

0x23884b SUB	%RSI,%RAX

0x23884e INC	%RAX

0x238851 CMP	$0x2,%RAX

0x238855 MOV	%RCX,-0x38(%RBP)

0x238859 MOV	%R8,-0x30(%RBP)

0x23885d MOV	%R13,-0xc8(%RBP)

0x238864 JAE	238872

0x238866 MOV	%RSI,%RCX

0x238869 MOV	-0x58(%RBP),%R14

0x23886d JMP	238cd9

0x238872 MOV	%RDI,-0x50(%RBP)

0x238876 MOV	%RBX,-0xf0(%RBP)

0x23887d MOV	%RAX,-0xe0(%RBP)

0x238884 MOV	%RAX,%RCX

0x238887 AND	$-0x2,%RCX

0x23888b LEA	(%RSI,%RCX,1),%RAX

0x23888f MOV	%RAX,-0xe8(%RBP)

0x238896 MOV	%RCX,-0xd8(%RBP)

0x23889d MOV	%RCX,%RDX

0x2388a0 MOV	%R10,-0x118(%RBP)

0x2388a7 MOV	%R11,-0x110(%RBP)

0x2388ae MOV	%R12,-0x108(%RBP)

0x2388b5 MOV	%R15,-0x100(%RBP)

0x2388bc MOV	%R9,-0xf8(%RBP)

0x2388c3 MOV	-0xc8(%RBP),%R13

0x2388ca MOV	-0x30(%RBP),%RCX

0x2388ce JMP	238b02

0x2388d3 NOPW	%CS:(%RAX,%RAX,1)

(185) 0x2388e0 CQTO

(185) 0x2388e2 IDIV	%R12

(185) 0x2388e5 MOVSXD	%R8D,%R8

(185) 0x2388e8 MOVSXD	%EDX,%RDX

(185) 0x2388eb MOVSXD	%EDI,%RBX

(185) 0x2388ee CLTQ

(185) 0x2388f0 MOV	%RBX,%RDI

(185) 0x2388f3 MOV	-0x50(%RBP),%R9

(185) 0x2388f7 IMUL	%R9,%RDI

(185) 0x2388fb ADD	%R8,%RDI

(185) 0x2388fe MOV	-0x38(%RBP),%R15

(185) 0x238902 MOVQ	$0,(%R15,%RDI,8)

(185) 0x23890a MOV	%RAX,%RDI

(185) 0x23890d IMUL	%R9,%RDI

(185) 0x238911 ADD	%RDX,%RDI

(185) 0x238914 MOVQ	$0,(%R15,%RDI,8)

(185) 0x23891c MOV	%RBX,%RDI

(185) 0x23891f IMUL	%R13,%RDI

(185) 0x238923 ADD	%R8,%RDI

(185) 0x238926 MOVQ	$0,(%RCX,%RDI,8)

(185) 0x23892e MOV	%RAX,%RDI

(185) 0x238931 IMUL	%R13,%RDI

(185) 0x238935 ADD	%RDX,%RDI

(185) 0x238938 MOVQ	$0,(%RCX,%RDI,8)

(185) 0x238940 MOV	%RBX,%RDI

(185) 0x238943 MOV	-0xb8(%RBP),%R11

(185) 0x23894a IMUL	%R11,%RDI

(185) 0x23894e ADD	%R8,%RDI

(185) 0x238951 MOV	-0xc0(%RBP),%R10

(185) 0x238958 MOVQ	$0,(%R10,%RDI,8)

(185) 0x238960 MOV	%RAX,%RDI

(185) 0x238963 IMUL	%R11,%RDI

(185) 0x238967 ADD	%RDX,%RDI

(185) 0x23896a MOVQ	$0,(%R10,%RDI,8)

(185) 0x238972 MOV	%RBX,%RDI

(185) 0x238975 MOV	-0x110(%RBP),%R11

(185) 0x23897c IMUL	%R11,%RDI

(185) 0x238980 ADD	%R8,%RDI

(185) 0x238983 MOV	-0x118(%RBP),%R10

(185) 0x23898a MOVQ	$0,(%R10,%RDI,8)

(185) 0x238992 MOV	%RAX,%RDI

(185) 0x238995 IMUL	%R11,%RDI

(185) 0x238999 ADD	%RDX,%RDI

(185) 0x23899c MOVQ	$0,(%R10,%RDI,8)

(185) 0x2389a4 MOV	%RBX,%RDI

(185) 0x2389a7 MOV	-0xa8(%RBP),%R12

(185) 0x2389ae IMUL	%R12,%RDI

(185) 0x2389b2 ADD	%R8,%RDI

(185) 0x2389b5 MOV	-0xb0(%RBP),%R14

(185) 0x2389bc MOVQ	$0,(%R14,%RDI,8)

(185) 0x2389c4 MOV	%RAX,%RDI

(185) 0x2389c7 IMUL	%R12,%RDI

(185) 0x2389cb ADD	%RDX,%RDI

(185) 0x2389ce MOVQ	$0,(%R14,%RDI,8)

(185) 0x2389d6 MOV	%RBX,%RDI

(185) 0x2389d9 MOV	-0xa0(%RBP),%R12

(185) 0x2389e0 IMUL	%R12,%RDI

(185) 0x2389e4 ADD	%R8,%RDI

(185) 0x2389e7 MOV	-0x58(%RBP),%R14

(185) 0x2389eb MOVQ	$0,(%R14,%RDI,8)

(185) 0x2389f3 MOV	%RAX,%RDI

(185) 0x2389f6 IMUL	%R12,%RDI

(185) 0x2389fa ADD	%RDX,%RDI

(185) 0x2389fd MOVQ	$0,(%R14,%RDI,8)

(185) 0x238a05 MOV	%RBX,%RDI

(185) 0x238a08 MOV	-0x90(%RBP),%R15

(185) 0x238a0f IMUL	%R15,%RDI

(185) 0x238a13 ADD	%R8,%RDI

(185) 0x238a16 MOV	-0x98(%RBP),%R12

(185) 0x238a1d MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a25 MOV	%RAX,%RDI

(185) 0x238a28 IMUL	%R15,%RDI

(185) 0x238a2c ADD	%RDX,%RDI

(185) 0x238a2f MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a37 MOV	%RBX,%RDI

(185) 0x238a3a MOV	-0x100(%RBP),%R15

(185) 0x238a41 IMUL	%R15,%RDI

(185) 0x238a45 ADD	%R8,%RDI

(185) 0x238a48 MOV	-0x88(%RBP),%R12

(185) 0x238a4f MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a57 MOV	%RAX,%RDI

(185) 0x238a5a IMUL	%R15,%RDI

(185) 0x238a5e ADD	%RDX,%RDI

(185) 0x238a61 MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a69 MOV	%RBX,%RDI

(185) 0x238a6c MOV	-0x78(%RBP),%R9

(185) 0x238a70 IMUL	%R9,%RDI

(185) 0x238a74 ADD	%R8,%RDI

(185) 0x238a77 MOV	-0x80(%RBP),%R12

(185) 0x238a7b MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a83 MOV	%RAX,%RDI

(185) 0x238a86 IMUL	%R9,%RDI

(185) 0x238a8a ADD	%RDX,%RDI

(185) 0x238a8d MOVQ	$0,(%R12,%RDI,8)

(185) 0x238a95 MOV	%RBX,%RDI

(185) 0x238a98 MOV	-0x70(%RBP),%R12

(185) 0x238a9c IMUL	%R12,%RDI

(185) 0x238aa0 ADD	%R8,%RDI

(185) 0x238aa3 MOV	-0xf8(%RBP),%R9

(185) 0x238aaa MOVQ	$0,(%R9,%RDI,8)

(185) 0x238ab2 MOV	%RAX,%RDI

(185) 0x238ab5 IMUL	%R12,%RDI

(185) 0x238ab9 ADD	%RDX,%RDI

(185) 0x238abc MOVQ	$0,(%R9,%RDI,8)

(185) 0x238ac4 MOV	-0x60(%RBP),%RDI

(185) 0x238ac8 IMUL	%RDI,%RBX

(185) 0x238acc ADD	%R8,%RBX

(185) 0x238acf IMUL	%RDI,%RAX

(185) 0x238ad3 ADD	%RDX,%RAX

(185) 0x238ad6 MOV	-0x68(%RBP),%RDX

(185) 0x238ada MOVQ	$0,(%RDX,%RBX,8)

(185) 0x238ae2 MOVQ	$0,(%RDX,%RAX,8)

(185) 0x238aea ADD	$0x2,%RSI

(185) 0x238aee MOV	-0x120(%RBP),%RDX

(185) 0x238af5 ADD	$-0x2,%RDX

(185) 0x238af9 MOV	-0x108(%RBP),%R12

(185) 0x238b00 JE	238b5a

(185) 0x238b02 MOV	%RSI,%RAX

(185) 0x238b05 OR	%R12,%RAX

(185) 0x238b08 SHR	$0x20,%RAX

(185) 0x238b0c MOV	%RDX,-0x120(%RBP)

(185) 0x238b13 JE	238b30

(185) 0x238b15 MOV	%RSI,%RAX

(185) 0x238b18 CQTO

(185) 0x238b1a IDIV	%R12

(185) 0x238b1d MOV	%RDX,%R8

(185) 0x238b20 MOV	%RAX,%RDI

(185) 0x238b23 JMP	238b3c

0x238b25 NOPW	%CS:(%RAX,%RAX,1)

(185) 0x238b30 MOV	%ESI,%EAX

(185) 0x238b32 XOR	%EDX,%EDX

(185) 0x238b34 DIV	%R12D

(185) 0x238b37 MOV	%EDX,%R8D

(185) 0x238b3a MOV	%EAX,%EDI

(185) 0x238b3c LEA	0x1(%RSI),%RAX

(185) 0x238b40 MOV	%RAX,%RDX

(185) 0x238b43 OR	%R12,%RDX

(185) 0x238b46 SHR	$0x20,%RDX

(185) 0x238b4a JNE	2388e0

(185) 0x238b50 XOR	%EDX,%EDX

(185) 0x238b52 DIV	%R12D

(185) 0x238b55 JMP	2388e5

0x238b5a MOV	-0xd8(%RBP),%RAX

0x238b61 CMP	%RAX,-0xe0(%RBP)

0x238b68 MOV	-0xf0(%RBP),%RBX

0x238b6f MOV	-0x50(%RBP),%RDI

0x238b73 MOV	-0xe8(%RBP),%RCX

0x238b7a JNE	238cd9

0x238b80 LEA	0x259a9(%RIP),%RDI

0x238b87 MOV	-0x44(%RBP),%ESI

0x238b8a CALL	25cd00 <@plt_start@+0x540>

0x238b8f ADD	$0x108,%RSP

0x238b96 POP	%RBX

0x238b97 POP	%R12

0x238b99 POP	%R13

0x238b9b POP	%R14

0x238b9d POP	%R15

0x238b9f POP	%RBP

0x238ba0 RET

0x238ba1 NOPW	%CS:(%RAX,%RAX,1)

(184) 0x238bb0 MOV	%RCX,%RAX

(184) 0x238bb3 CQTO

(184) 0x238bb5 IDIV	%R12

(184) 0x238bb8 MOV	%RCX,%R8

(184) 0x238bbb MOV	-0x30(%RBP),%RCX

(184) 0x238bbf MOV	-0x38(%RBP),%R13

(184) 0x238bc3 MOVSXD	%EDX,%RDX

(184) 0x238bc6 CLTQ

(184) 0x238bc8 MOV	%RAX,%RSI

(184) 0x238bcb IMUL	%RDI,%RSI

(184) 0x238bcf ADD	%RDX,%RSI

(184) 0x238bd2 MOVQ	$0,(%R13,%RSI,8)

(184) 0x238bdb MOV	%RAX,%RSI

(184) 0x238bde IMUL	-0xc8(%RBP),%RSI

(184) 0x238be6 ADD	%RDX,%RSI

(184) 0x238be9 MOVQ	$0,(%RCX,%RSI,8)

(184) 0x238bf1 MOV	%RAX,%RSI

(184) 0x238bf4 IMUL	-0xb8(%RBP),%RSI

(184) 0x238bfc ADD	%RDX,%RSI

(184) 0x238bff MOV	-0xc0(%RBP),%R13

(184) 0x238c06 MOVQ	$0,(%R13,%RSI,8)

(184) 0x238c0f MOV	%RAX,%RSI

(184) 0x238c12 IMUL	%R11,%RSI

(184) 0x238c16 ADD	%RDX,%RSI

(184) 0x238c19 MOVQ	$0,(%R10,%RSI,8)

(184) 0x238c21 MOV	%RAX,%RSI

(184) 0x238c24 IMUL	-0xa8(%RBP),%RSI

(184) 0x238c2c ADD	%RDX,%RSI

(184) 0x238c2f MOV	-0xb0(%RBP),%R13

(184) 0x238c36 MOVQ	$0,(%R13,%RSI,8)

(184) 0x238c3f MOV	%RAX,%RSI

(184) 0x238c42 IMUL	-0xa0(%RBP),%RSI

(184) 0x238c4a ADD	%RDX,%RSI

(184) 0x238c4d MOVQ	$0,(%R14,%RSI,8)

(184) 0x238c55 MOV	%RAX,%RSI

(184) 0x238c58 IMUL	-0x90(%RBP),%RSI

(184) 0x238c60 ADD	%RDX,%RSI

(184) 0x238c63 MOV	-0x98(%RBP),%R13

(184) 0x238c6a MOVQ	$0,(%R13,%RSI,8)

(184) 0x238c73 MOV	%RAX,%RSI

(184) 0x238c76 IMUL	%R15,%RSI

(184) 0x238c7a ADD	%RDX,%RSI

(184) 0x238c7d MOV	-0x88(%RBP),%R13

(184) 0x238c84 MOVQ	$0,(%R13,%RSI,8)

(184) 0x238c8d MOV	%RAX,%RSI

(184) 0x238c90 IMUL	-0x78(%RBP),%RSI

(184) 0x238c95 ADD	%RDX,%RSI

(184) 0x238c98 MOV	-0x80(%RBP),%R13

(184) 0x238c9c MOVQ	$0,(%R13,%RSI,8)

(184) 0x238ca5 MOV	%RAX,%RSI

(184) 0x238ca8 IMUL	-0x70(%RBP),%RSI

(184) 0x238cad ADD	%RDX,%RSI

(184) 0x238cb0 MOVQ	$0,(%R9,%RSI,8)

(184) 0x238cb8 IMUL	-0x60(%RBP),%RAX

(184) 0x238cbd ADD	%RDX,%RAX

(184) 0x238cc0 MOV	-0x68(%RBP),%RDX

(184) 0x238cc4 MOVQ	$0,(%RDX,%RAX,8)

(184) 0x238ccc CMP	%RBX,%R8

(184) 0x238ccf LEA	0x1(%R8),%RCX

(184) 0x238cd3 JGE	238b80

(184) 0x238cd9 MOV	%RCX,%RAX

(184) 0x238cdc OR	%R12,%RAX

(184) 0x238cdf SHR	$0x20,%RAX

(184) 0x238ce3 JNE	238bb0

(184) 0x238ce9 MOV	%ECX,%EAX

(184) 0x238ceb XOR	%EDX,%EDX

(184) 0x238ced DIV	%R12D

(184) 0x238cf0 JMP	238bb8

0x238cf5 NOPW	%CS:(%RAX,%RAX,1)

Coverage (%)	Name	Source Location	Module

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	build_field.cpp:100-113
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100-113

Warnings:
Ignoring paths for analysis

gain
potential
hint
expert

Vectorization

Your function is 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 17.75 to 1.70 cycles (10.42x 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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.75 to 15.88 cycles (1.12x speedup).

Workaround

Read less array elements
Write less array elements

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: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100

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►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:101

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 272 bytes. The binary function is storing 256 bytes.

General properties

nb instructions	128
nb uops	127
loop length	668
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	32

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.88 cycles
front end	15.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.17	6.17	6.17	6.17	6.17	6.17	17.75	17.75	17.75	17.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.17	6.17	6.17	6.17	6.17	6.17	17.75	17.75	17.75	17.75	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	15.88
Dispatch	17.75
Overall L1	17.75

Vectorization ratios

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

Vector efficiency ratios

all	11%
load	11%
store	11%
mul	12%
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 17.75 cycles. At this rate:

5% of peak load performance is reached (15.32 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.42 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 2386b0

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 $0x108,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVSXD (%RDX),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (6.3%)
MOVSXD (%RCX),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (6.3%)
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
OR %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JS 238b8f <_Z11build_fieldR16global_variables.omp_outlined+0x4df>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	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	scal (12.5%)
INC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
IMUL %R12,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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	N/A
LEA -0x128(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x25dfe(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xd0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	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
CMP %RBX,%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,%RBX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xd0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 238b80 <_Z11build_fieldR16global_variables.omp_outlined+0x4d0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x178(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x168(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x190(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x180(%R14),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1a8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x198(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1c0(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1b0(%R14),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1d8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1c8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1f0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1e0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x208(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1f8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xa8(%R14),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xb8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xd0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xc0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xe8(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x100(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 238872 <_Z11build_fieldR16global_variables.omp_outlined+0x1c2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 238cd9 <_Z11build_fieldR16global_variables.omp_outlined+0x629>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,-0x118(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xc8(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 238b02 <_Z11build_fieldR16global_variables.omp_outlined+0x452>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xd8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xe0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0xf0(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xe8(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 238cd9 <_Z11build_fieldR16global_variables.omp_outlined+0x629>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x259a9(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x108,%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	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	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	build_field.cpp:100-113
Module	exec

The function is defined in:

/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:69
/home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100-113

Warnings:
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

Performance is limited by:

reading data from caches/RAM (load units are a bottleneck)
writing data to caches/RAM (the store unit is a bottleneck)

By removing all these bottlenecks, you can lower the cost of an iteration from 17.75 to 15.88 cycles (1.12x speedup).

Workaround

Read less array elements
Write less array elements

No data for this section

CALL instructions

Detected function call instructions.

Details

unknown: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:100

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►
- /home/eoseret/qaas_runs_ZEN5/173-937-4090/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/build_field.cpp:101

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 272 bytes. The binary function is storing 256 bytes.

General properties

nb instructions	128
nb uops	127
loop length	668
used x86 registers	16
used mmx registers	0
used xmm registers	0
used ymm registers	0
used zmm registers	0
nb stack references	32

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	15.88 cycles
front end	15.88 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	6.17	6.17	6.17	6.17	6.17	6.17	17.75	17.75	17.75	17.75	0.00	0.00	0.00	0.00	0.00	0.00
cycles	6.17	6.17	6.17	6.17	6.17	6.17	17.75	17.75	17.75	17.75	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	15.88
Dispatch	17.75
Overall L1	17.75

Vectorization ratios

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

Vector efficiency ratios

all	11%
load	11%
store	11%
mul	12%
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 17.75 cycles. At this rate:

5% of peak load performance is reached (15.32 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
11% of peak store performance is reached (14.42 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

Found no such bottlenecks.

ASM code

In the binary file, the address of the function is: 2386b0

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 $0x108,%RSP	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
MOVSXD (%RDX),%RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (6.3%)
MOVSXD (%RCX),%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (6.3%)
MOV %R12D,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
OR %EBX,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
JS 238b8f <_Z11build_fieldR16global_variables.omp_outlined+0x4df>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %R8,%R14	1	0	0	0	0	0	0	0	0	0	0	0	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	scal (12.5%)
INC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
IMUL %R12,%RBX	1	0.33	0.33	0.33	0	0	0	0	0	0	0	3	0.33	scal (12.5%)
DEC %RBX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOVQ $0,-0xd0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOVQ $0x1,-0x128(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOVL $0,-0x48(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV (%RDI),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	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	N/A
LEA -0x128(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA 0x25dfe(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x48(%RBP),%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0xd0(%RBP),%R8	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
LEA -0x40(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %ESI,-0x44(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (6.3%)
MOV $0x22,%EDX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	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
CALL 25ccf0 <@plt_start@+0x530>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	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
CMP %RBX,%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,%RBX	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	1	0.33	scal (12.5%)
MOV %RBX,-0x40(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xd0(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RBX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
JG 238b80 <_Z11build_fieldR16global_variables.omp_outlined+0x4d0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV 0x178(%R14),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x168(%R14),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV 0x190(%R14),%R8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x180(%R14),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1a8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xc0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x198(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1c0(%R14),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1b0(%R14),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0x1d8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1c8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1f0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1e0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0xa0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x208(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x98(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x1f8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x90(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xa8(%R14),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xb8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xd0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xc0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x78(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xe8(%R14),%R9	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV 0xd8(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x70(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0x100(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x68(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV 0xf0(%R14),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV %RAX,-0x60(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RSI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
INC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	scal (12.5%)
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R8,-0x30(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R13,-0xc8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
JAE 238872 <_Z11build_fieldR16global_variables.omp_outlined+0x1c2>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x58(%RBP),%R14	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 238cd9 <_Z11build_fieldR16global_variables.omp_outlined+0x629>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
MOV %RDI,-0x50(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RBX,-0xf0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,-0xe0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x2,%RCX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.17	N/A
LEA (%RSI,%RCX,1),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV %RAX,-0xe8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,-0xd8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %RCX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R10,-0x118(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R11,-0x110(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R12,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R15,-0x100(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV %R9,-0xf8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	4	0.50	scal (12.5%)
MOV -0xc8(%RBP),%R13	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JMP 238b02 <_Z11build_fieldR16global_variables.omp_outlined+0x452>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	1	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xd8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CMP %RAX,-0xe0(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	1	0.25	scal (12.5%)
MOV -0xf0(%RBP),%RBX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	scal (12.5%)
MOV -0x50(%RBP),%RDI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
MOV -0xe8(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
JNE 238cd9 <_Z11build_fieldR16global_variables.omp_outlined+0x629>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50-1	N/A
LEA 0x259a9(%RIP),%RDI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	1	0.25	N/A
MOV -0x44(%RBP),%ESI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	3	0.25	N/A
CALL 25cd00 <@plt_start@+0x540>	2	0	0	0	0.33	0.33	0.33	0.25	0.25	0.25	0.25	0	0.50	N/A
ADD $0x108,%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	0.33	N/A
POP %R12	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R13	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R14	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %R15	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
POP %RBP	1	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
RET	1	0	0	0	0.33	0.33	0.33	0	0	0	0	1	0.50	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A

Name	Coverage (%)	Time (s)
▼build_field(global_variables&) [clone .omp_outlined]–	0.09	0.03
○Loop 185 - build_field.cpp:101-113 - exec	0.09	0.03
○Loop 184 - build_field.cpp:101-113 - exec	0.00	0.00

Report Configuration

Vectorization

Details

Workaround

Execution units bottlenecks

Workaround

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

Workaround

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