OV - exec - Loop 1497

	Loop Id: 1497	Module: exec	Source: par_lr_interp.c:1221-1743 [...]	Coverage: 0.04%

0x484570 MOV	-0xa0(%RBP),%RCX

0x484577 MOV	(%RCX),%RCX

0x48457a MOVSD	(%RCX,%RAX,8),%XMM6

0x48457f MOV	-0x60(%RBP),%RSI

0x484583 ADDSD	(%RSI,%R9,8),%XMM6

0x484589 MOVSD	%XMM6,(%RCX,%RAX,8)

0x48458e INC	%R9

0x484591 CMP	-0x90(%RBP),%R9

0x484598 JE	484417

0x48459e MOV	-0xa8(%RBP),%RAX

0x4845a5 MOV	(%RAX,%R9,8),%R10

0x4845a9 MOV	(%RBX,%R10,8),%RAX

0x4845ad CMP	%RDI,%RAX

0x4845b0 JGE	484570

0x4845b2 CMP	-0x48(%RBP),%RAX

0x4845b6 JNE	484680

0x4845bc MOV	-0x188(%RBP),%RCX

0x4845c3 MOV	(%RCX,%R10,8),%R11

0x4845c7 XORPD	%XMM6,%XMM6

0x4845cb XOR	%EAX,%EAX

0x4845cd MOV	-0x60(%RBP),%RSI

0x4845d1 UCOMISD	(%RSI,%R11,8),%XMM6

0x4845d7 SETBE	%AL

0x4845da MOV	%R10,-0xb8(%RBP)

0x4845e1 MOV	0x8(%RCX,%R10,8),%RCX

0x4845e6 LEA	-0x1(,%RAX,2),%RAX

0x4845ee MOV	%RAX,-0x80(%RBP)

0x4845f2 LEA	0x1(%R11),%R10

0x4845f6 CMP	%RCX,%R10

0x4845f9 JGE	4849a0

0x4845ff XORPS	%XMM7,%XMM7

0x484602 CVTSI2SDL	-0x80(%RBP),%XMM7

0x484607 MOV	%RCX,%RAX

0x48460a MOV	%R11,-0xb0(%RBP)

0x484611 SUB	%R11,%RAX

0x484614 MOV	%RAX,-0x108(%RBP)

0x48461b DEC	%RAX

0x48461e MOV	%RAX,-0x88(%RBP)

0x484625 CMP	$0x4,%RAX

0x484629 JAE	4846c0

0x48462f MOV	-0x88(%RBP),%R15

0x484636 AND	$-0x4,%R15

0x48463a MOV	-0x108(%RBP),%RAX

0x484641 SUB	%R15,%RAX

0x484644 CMP	$0x2,%RAX

0x484648 JE	484938

0x48464e CMP	$0x4,%RAX

0x484652 JE	484876

0x484658 CMP	$0x3,%RAX

0x48465c MOV	-0x58(%RBP),%R12

0x484660 JNE	4849a0

0x484666 MOV	-0xb0(%RBP),%R12

0x48466d ADD	%R15,%R12

0x484670 JMP	4848dc

0x484680 MOV	-0xe0(%RBP),%RAX

0x484687 CMPQ	$-0x3,(%RAX,%R10,8)

0x48468c JE	48458e

0x484692 CMPQ	$0x1,-0x180(%RBP)

0x48469a JE	4846b1

0x48469c MOV	-0x178(%RBP),%RCX

0x4846a3 MOV	(%RCX,%R13,8),%RAX

0x4846a7 CMP	(%RCX,%R10,8),%RAX

0x4846ab JNE	48458e

0x4846b1 MOV	-0x60(%RBP),%RAX

0x4846b5 ADDSD	(%RAX,%R9,8),%XMM5

0x4846bb JMP	48458e

0x4846c0 MOV	-0x88(%RBP),%R15

0x4846c7 SHR	$0x2,%R15

0x4846cb MOV	-0xb0(%RBP),%RAX

0x4846d2 LEA	0x20(,%RAX,8),%RSI

0x4846da XORPD	%XMM8,%XMM8

0x4846df JMP	4846fd

  (1502) 0x4846f0 ADD	$0x20,%RSI

  (1502) 0x4846f4 DEC	%R15

  (1502) 0x4846f7 JE	48462f

  (1502) 0x4846fd MOV	-0xa8(%RBP),%RAX

  (1502) 0x484704 MOV	-0x18(%RAX,%RSI,1),%R12

  (1502) 0x484709 XOR	%R11D,%R11D

  (1502) 0x48470c CMP	%RDI,(%RBX,%R12,8)

  (1502) 0x484710 SETGE	%R11B

  (1502) 0x484714 XOR	%EAX,%EAX

  (1502) 0x484716 CMP	%R13,%R12

  (1502) 0x484719 SETE	%AL

  (1502) 0x48471c CMP	%R11B,%AL

  (1502) 0x48471f CMOVA	%EAX,%R11D

  (1502) 0x484723 CMP	$0x1,%R11B

  (1502) 0x484727 JNE	484758

  (1502) 0x484729 MOV	-0x60(%RBP),%RAX

  (1502) 0x48472d MOVSD	-0x18(%RAX,%RSI,1),%XMM9

  (1502) 0x484734 MOVAPD	%XMM9,%XMM10

  (1502) 0x484739 MULSD	%XMM7,%XMM10

  (1502) 0x48473e CMPSD	$0x1,%XMM8,%XMM10

  (1502) 0x484744 ANDPD	%XMM10,%XMM9

  (1502) 0x484749 ANDNPD	%XMM1,%XMM10

  (1502) 0x48474e ORPD	%XMM9,%XMM10

  (1502) 0x484753 ADDSD	%XMM10,%XMM6

  (1502) 0x484758 MOV	-0xa8(%RBP),%RAX

  (1502) 0x48475f MOV	-0x10(%RAX,%RSI,1),%RAX

  (1502) 0x484764 XOR	%R11D,%R11D

  (1502) 0x484767 CMP	%RDI,(%RBX,%RAX,8)

  (1502) 0x48476b SETGE	%R11B

  (1502) 0x48476f XOR	%R12D,%R12D

  (1502) 0x484772 CMP	%R13,%RAX

  (1502) 0x484775 SETE	%R12B

  (1502) 0x484779 CMP	%R11B,%R12B

  (1502) 0x48477c CMOVA	%R12D,%R11D

  (1502) 0x484780 CMP	$0x1,%R11B

  (1502) 0x484784 JNE	4847b5

  (1502) 0x484786 MOV	-0x60(%RBP),%RAX

  (1502) 0x48478a MOVSD	-0x10(%RAX,%RSI,1),%XMM9

  (1502) 0x484791 MOVAPD	%XMM9,%XMM10

  (1502) 0x484796 MULSD	%XMM7,%XMM10

  (1502) 0x48479b CMPSD	$0x1,%XMM8,%XMM10

  (1502) 0x4847a1 ANDPD	%XMM10,%XMM9

  (1502) 0x4847a6 ANDNPD	%XMM1,%XMM10

  (1502) 0x4847ab ORPD	%XMM9,%XMM10

  (1502) 0x4847b0 ADDSD	%XMM10,%XMM6

  (1502) 0x4847b5 MOV	-0xa8(%RBP),%RAX

  (1502) 0x4847bc MOV	-0x8(%RAX,%RSI,1),%RAX

  (1502) 0x4847c1 XOR	%R11D,%R11D

  (1502) 0x4847c4 CMP	%RDI,(%RBX,%RAX,8)

  (1502) 0x4847c8 SETGE	%R11B

  (1502) 0x4847cc XOR	%R12D,%R12D

  (1502) 0x4847cf CMP	%R13,%RAX

  (1502) 0x4847d2 SETE	%R12B

  (1502) 0x4847d6 CMP	%R11B,%R12B

  (1502) 0x4847d9 CMOVA	%R12D,%R11D

  (1502) 0x4847dd CMP	$0x1,%R11B

  (1502) 0x4847e1 JNE	484812

  (1502) 0x4847e3 MOV	-0x60(%RBP),%RAX

  (1502) 0x4847e7 MOVSD	-0x8(%RAX,%RSI,1),%XMM9

  (1502) 0x4847ee MOVAPD	%XMM9,%XMM10

  (1502) 0x4847f3 MULSD	%XMM7,%XMM10

  (1502) 0x4847f8 CMPSD	$0x1,%XMM8,%XMM10

  (1502) 0x4847fe ANDPD	%XMM10,%XMM9

  (1502) 0x484803 ANDNPD	%XMM1,%XMM10

  (1502) 0x484808 ORPD	%XMM9,%XMM10

  (1502) 0x48480d ADDSD	%XMM10,%XMM6

  (1502) 0x484812 MOV	-0xa8(%RBP),%RAX

  (1502) 0x484819 MOV	(%RAX,%RSI,1),%RAX

  (1502) 0x48481d XOR	%R11D,%R11D

  (1502) 0x484820 CMP	%RDI,(%RBX,%RAX,8)

  (1502) 0x484824 SETGE	%R11B

  (1502) 0x484828 XOR	%R12D,%R12D

  (1502) 0x48482b CMP	%R13,%RAX

  (1502) 0x48482e SETE	%R12B

  (1502) 0x484832 CMP	%R11B,%R12B

  (1502) 0x484835 CMOVA	%R12D,%R11D

  (1502) 0x484839 CMP	$0x1,%R11B

  (1502) 0x48483d JNE	4846f0

  (1502) 0x484843 MOV	-0x60(%RBP),%RAX

  (1502) 0x484847 MOVSD	(%RAX,%RSI,1),%XMM9

  (1502) 0x48484d MOVAPD	%XMM9,%XMM10

  (1502) 0x484852 MULSD	%XMM7,%XMM10

  (1502) 0x484857 CMPSD	$0x1,%XMM8,%XMM10

  (1502) 0x48485d ANDPD	%XMM10,%XMM9

  (1502) 0x484862 ANDNPD	%XMM1,%XMM10

  (1502) 0x484867 ORPD	%XMM9,%XMM10

  (1502) 0x48486c ADDSD	%XMM10,%XMM6

  (1502) 0x484871 JMP	4846f0

0x484876 MOV	-0xb0(%RBP),%R12

0x48487d ADD	%R15,%R12

0x484880 MOV	-0xa8(%RBP),%RAX

0x484887 MOV	0x18(%RAX,%R12,8),%RAX

0x48488c XOR	%ESI,%ESI

0x48488e CMP	%RDI,(%RBX,%RAX,8)

0x484892 SETGE	%SIL

0x484896 XOR	%R11D,%R11D

0x484899 CMP	%R13,%RAX

0x48489c SETE	%R11B

0x4848a0 CMP	%SIL,%R11B

0x4848a3 CMOVA	%R11D,%ESI

0x4848a7 CMP	$0x1,%SIL

0x4848ab JNE	4848dc

0x4848ad MOV	-0x60(%RBP),%RAX

0x4848b1 MOVSD	0x18(%RAX,%R12,8),%XMM8

0x4848b8 MOVAPD	%XMM8,%XMM9

0x4848bd MULSD	%XMM7,%XMM9

0x4848c2 CMPSD	$0x1,%XMM0,%XMM9

0x4848c8 ANDPD	%XMM9,%XMM8

0x4848cd ANDNPD	%XMM1,%XMM9

0x4848d2 ORPD	%XMM8,%XMM9

0x4848d7 ADDSD	%XMM9,%XMM6

0x4848dc MOV	-0xa8(%RBP),%RAX

0x4848e3 MOV	0x10(%RAX,%R12,8),%RAX

0x4848e8 XOR	%ESI,%ESI

0x4848ea CMP	%RDI,(%RBX,%RAX,8)

0x4848ee SETGE	%SIL

0x4848f2 XOR	%R11D,%R11D

0x4848f5 CMP	%R13,%RAX

0x4848f8 SETE	%R11B

0x4848fc CMP	%SIL,%R11B

0x4848ff CMOVA	%R11D,%ESI

0x484903 CMP	$0x1,%SIL

0x484907 JNE	484938

0x484909 MOV	-0x60(%RBP),%RAX

0x48490d MOVSD	0x10(%RAX,%R12,8),%XMM8

0x484914 MOVAPD	%XMM8,%XMM9

0x484919 MULSD	%XMM7,%XMM9

0x48491e CMPSD	$0x1,%XMM0,%XMM9

0x484924 ANDPD	%XMM9,%XMM8

0x484929 ANDNPD	%XMM1,%XMM9

0x48492e ORPD	%XMM8,%XMM9

0x484933 ADDSD	%XMM9,%XMM6

0x484938 MOV	-0x58(%RBP),%R12

0x48493c ADD	%R10,%R15

0x48493f MOV	-0xa8(%RBP),%RAX

0x484946 MOV	(%RAX,%R15,8),%RAX

0x48494a XOR	%ESI,%ESI

0x48494c CMP	%RDI,(%RBX,%RAX,8)

0x484950 SETGE	%SIL

0x484954 XOR	%R11D,%R11D

0x484957 CMP	%R13,%RAX

0x48495a SETE	%R11B

0x48495e CMP	%SIL,%R11B

0x484961 CMOVA	%R11D,%ESI

0x484965 CMP	$0x1,%SIL

0x484969 JNE	4849a0

0x48496b MOV	-0x60(%RBP),%RAX

0x48496f MOVSD	(%RAX,%R15,8),%XMM8

0x484975 MULSD	%XMM8,%XMM7

0x48497a CMPSD	$0x1,%XMM0,%XMM7

0x48497f ANDPD	%XMM7,%XMM8

0x484984 ANDNPD	%XMM1,%XMM7

0x484988 ORPD	%XMM8,%XMM7

0x48498d ADDSD	%XMM7,%XMM6

0x484991 NOPW	%CS:(%RAX,%RAX,1)

0x4849a0 MOV	-0xc0(%RBP),%RAX

0x4849a7 MOV	(%RAX),%RAX

0x4849aa MOV	%RAX,-0x88(%RBP)

0x4849b1 CMP	$0x2,%RAX

0x4849b5 JL	484c48

0x4849bb MOV	-0x150(%RBP),%RAX

0x4849c2 MOV	-0xb8(%RBP),%RSI

0x4849c9 MOV	(%RAX,%RSI,8),%R12

0x4849cd MOV	0x8(%RAX,%RSI,8),%RAX

0x4849d2 SUB	%R12,%RAX

0x4849d5 JLE	484c44

0x4849db XORPS	%XMM7,%XMM7

0x4849de CVTSI2SDL	-0x80(%RBP),%XMM7

0x4849e3 CMP	$0x4,%RAX

0x4849e7 JAE	484a6f

0x4849ed MOV	%RAX,%RSI

0x4849f0 AND	$-0x4,%RSI

0x4849f4 AND	$0x3,%EAX

0x4849f7 CMP	$0x1,%RAX

0x4849fb JE	484bd4

0x484a01 CMP	$0x3,%EAX

0x484a04 JE	484be7

0x484a0a CMP	$0x2,%EAX

0x484a0d JNE	484c44

0x484a13 ADD	%RSI,%R12

0x484a16 MOV	-0x78(%RBP),%RAX

0x484a1a MOV	0x8(%RAX,%R12,8),%RAX

0x484a1f CMP	%RDX,(%R14,%RAX,8)

0x484a23 JL	484c10

0x484a29 MOV	-0x50(%RBP),%RAX

0x484a2d MOVSD	0x8(%RAX,%R12,8),%XMM8

0x484a34 MOVAPD	%XMM8,%XMM9

0x484a39 MULSD	%XMM7,%XMM9

0x484a3e CMPSD	$0x1,%XMM0,%XMM9

0x484a44 ANDPD	%XMM9,%XMM8

0x484a49 ANDNPD	%XMM1,%XMM9

0x484a4e ORPD	%XMM8,%XMM9

0x484a53 ADDSD	%XMM9,%XMM6

0x484a58 MOV	-0x78(%RBP),%RAX

0x484a5c MOV	(%RAX,%R12,8),%RAX

0x484a60 CMP	%RDX,(%R14,%RAX,8)

0x484a64 JGE	484c1e

0x484a6a JMP	484c44

0x484a6f MOV	%RAX,%RSI

0x484a72 SHR	$0x2,%RSI

0x484a76 LEA	0x18(,%R12,8),%R15

0x484a7e JMP	484a8d

  (1501) 0x484a80 ADD	$0x20,%R15

  (1501) 0x484a84 DEC	%RSI

  (1501) 0x484a87 JE	4849ed

  (1501) 0x484a8d MOV	-0x78(%RBP),%R11

  (1501) 0x484a91 MOV	-0x18(%R11,%R15,1),%R11

  (1501) 0x484a96 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484a9a JGE	484ae0

  (1501) 0x484a9c MOV	-0x78(%RBP),%R11

  (1501) 0x484aa0 MOV	-0x10(%R11,%R15,1),%R11

  (1501) 0x484aa5 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484aa9 JGE	484b1e

  (1501) 0x484aab MOV	-0x78(%RBP),%R11

  (1501) 0x484aaf MOV	-0x8(%R11,%R15,1),%R11

  (1501) 0x484ab4 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484ab8 JGE	484b60

  (1501) 0x484abe MOV	-0x78(%RBP),%R11

  (1501) 0x484ac2 MOV	(%R11,%R15,1),%R11

  (1501) 0x484ac6 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484aca JL	484a80

  (1501) 0x484acc JMP	484ba1

  (1501) 0x484ae0 MOV	-0x50(%RBP),%R11

  (1501) 0x484ae4 MOVSD	-0x18(%R11,%R15,1),%XMM8

  (1501) 0x484aeb MOVAPD	%XMM8,%XMM9

  (1501) 0x484af0 MULSD	%XMM7,%XMM9

  (1501) 0x484af5 CMPSD	$0x1,%XMM0,%XMM9

  (1501) 0x484afb ANDPD	%XMM9,%XMM8

  (1501) 0x484b00 ANDNPD	%XMM1,%XMM9

  (1501) 0x484b05 ORPD	%XMM8,%XMM9

  (1501) 0x484b0a ADDSD	%XMM9,%XMM6

  (1501) 0x484b0f MOV	-0x78(%RBP),%R11

  (1501) 0x484b13 MOV	-0x10(%R11,%R15,1),%R11

  (1501) 0x484b18 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484b1c JL	484aab

  (1501) 0x484b1e MOV	-0x50(%RBP),%R11

  (1501) 0x484b22 MOVSD	-0x10(%R11,%R15,1),%XMM8

  (1501) 0x484b29 MOVAPD	%XMM8,%XMM9

  (1501) 0x484b2e MULSD	%XMM7,%XMM9

  (1501) 0x484b33 CMPSD	$0x1,%XMM0,%XMM9

  (1501) 0x484b39 ANDPD	%XMM9,%XMM8

  (1501) 0x484b3e ANDNPD	%XMM1,%XMM9

  (1501) 0x484b43 ORPD	%XMM8,%XMM9

  (1501) 0x484b48 ADDSD	%XMM9,%XMM6

  (1501) 0x484b4d MOV	-0x78(%RBP),%R11

  (1501) 0x484b51 MOV	-0x8(%R11,%R15,1),%R11

  (1501) 0x484b56 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484b5a JL	484abe

  (1501) 0x484b60 MOV	-0x50(%RBP),%R11

  (1501) 0x484b64 MOVSD	-0x8(%R11,%R15,1),%XMM8

  (1501) 0x484b6b MOVAPD	%XMM8,%XMM9

  (1501) 0x484b70 MULSD	%XMM7,%XMM9

  (1501) 0x484b75 CMPSD	$0x1,%XMM0,%XMM9

  (1501) 0x484b7b ANDPD	%XMM9,%XMM8

  (1501) 0x484b80 ANDNPD	%XMM1,%XMM9

  (1501) 0x484b85 ORPD	%XMM8,%XMM9

  (1501) 0x484b8a ADDSD	%XMM9,%XMM6

  (1501) 0x484b8f MOV	-0x78(%RBP),%R11

  (1501) 0x484b93 MOV	(%R11,%R15,1),%R11

  (1501) 0x484b97 CMP	%RDX,(%R14,%R11,8)

  (1501) 0x484b9b JL	484a80

  (1501) 0x484ba1 MOV	-0x50(%RBP),%R11

  (1501) 0x484ba5 MOVSD	(%R11,%R15,1),%XMM8

  (1501) 0x484bab MOVAPD	%XMM8,%XMM9

  (1501) 0x484bb0 MULSD	%XMM7,%XMM9

  (1501) 0x484bb5 CMPSD	$0x1,%XMM0,%XMM9

  (1501) 0x484bbb ANDPD	%XMM9,%XMM8

  (1501) 0x484bc0 ANDNPD	%XMM1,%XMM9

  (1501) 0x484bc5 ORPD	%XMM8,%XMM9

  (1501) 0x484bca ADDSD	%XMM9,%XMM6

  (1501) 0x484bcf JMP	484a80

0x484bd4 ADD	%RSI,%R12

0x484bd7 MOV	-0x78(%RBP),%RAX

0x484bdb MOV	(%RAX,%R12,8),%RAX

0x484bdf CMP	%RDX,(%R14,%RAX,8)

0x484be3 JGE	484c1e

0x484be5 JMP	484c44

0x484be7 ADD	%RSI,%R12

0x484bea MOV	-0x78(%RBP),%RAX

0x484bee MOV	0x10(%RAX,%R12,8),%RAX

0x484bf3 CMP	%RDX,(%R14,%RAX,8)

0x484bf7 JGE	484f1d

0x484bfd MOV	-0x78(%RBP),%RAX

0x484c01 MOV	0x8(%RAX,%R12,8),%RAX

0x484c06 CMP	%RDX,(%R14,%RAX,8)

0x484c0a JGE	484a29

0x484c10 MOV	-0x78(%RBP),%RAX

0x484c14 MOV	(%RAX,%R12,8),%RAX

0x484c18 CMP	%RDX,(%R14,%RAX,8)

0x484c1c JL	484c44

0x484c1e MOV	-0x50(%RBP),%RAX

0x484c22 MOVSD	(%RAX,%R12,8),%XMM8

0x484c28 MULSD	%XMM8,%XMM7

0x484c2d CMPSD	$0x1,%XMM0,%XMM7

0x484c32 ANDPD	%XMM7,%XMM8

0x484c37 ANDNPD	%XMM1,%XMM7

0x484c3b ORPD	%XMM8,%XMM7

0x484c40 ADDSD	%XMM7,%XMM6

0x484c44 MOV	-0x58(%RBP),%R12

0x484c48 UCOMISD	%XMM0,%XMM6

0x484c4c MOV	-0x60(%RBP),%RAX

0x484c50 MOVSD	(%RAX,%R9,8),%XMM7

0x484c56 JE	484dc2

0x484c5c DIVSD	%XMM6,%XMM7

0x484c60 CMP	%RCX,%R10

0x484c63 JGE	484d13

0x484c69 XORPS	%XMM6,%XMM6

0x484c6c CVTSI2SDL	-0x80(%RBP),%XMM6

0x484c71 JMP	484c8c

  (1500) 0x484c80 INC	%R10

  (1500) 0x484c83 CMP	%R10,%RCX

  (1500) 0x484c86 JE	484d13

  (1500) 0x484c8c MOV	-0xa8(%RBP),%RAX

  (1500) 0x484c93 MOV	(%RAX,%R10,8),%RAX

  (1500) 0x484c97 MOV	(%RBX,%RAX,8),%RSI

  (1500) 0x484c9b CMP	%RDI,%RSI

  (1500) 0x484c9e JL	484cd6

  (1500) 0x484ca0 MOV	-0x60(%RBP),%R11

  (1500) 0x484ca4 MOVSD	(%R11,%R10,8),%XMM8

  (1500) 0x484caa MOVAPD	%XMM8,%XMM9

  (1500) 0x484caf MULSD	%XMM6,%XMM9

  (1500) 0x484cb4 UCOMISD	%XMM0,%XMM9

  (1500) 0x484cb9 JAE	484cd6

  (1500) 0x484cbb MULSD	%XMM7,%XMM8

  (1500) 0x484cc0 MOV	-0xa0(%RBP),%R11

  (1500) 0x484cc7 MOV	(%R11),%R15

  (1500) 0x484cca ADDSD	(%R15,%RSI,8),%XMM8

  (1500) 0x484cd0 MOVSD	%XMM8,(%R15,%RSI,8)

  (1500) 0x484cd6 CMP	%R13,%RAX

  (1500) 0x484cd9 JNE	484c80

  (1500) 0x484cdb MOV	-0x60(%RBP),%RAX

  (1500) 0x484cdf MOVSD	(%RAX,%R10,8),%XMM8

  (1500) 0x484ce5 MOVAPD	%XMM8,%XMM9

  (1500) 0x484cea MULSD	%XMM6,%XMM9

  (1500) 0x484cef MULSD	%XMM7,%XMM8

  (1500) 0x484cf4 CMPSD	$0x1,%XMM0,%XMM9

  (1500) 0x484cfa ANDPD	%XMM9,%XMM8

  (1500) 0x484cff ANDNPD	%XMM1,%XMM9

  (1500) 0x484d04 ORPD	%XMM8,%XMM9

  (1500) 0x484d09 ADDSD	%XMM9,%XMM5

  (1500) 0x484d0e JMP	484c80

0x484d13 CMPQ	$0x2,-0x88(%RBP)

0x484d1b JL	48458e

0x484d21 MOV	-0x150(%RBP),%RCX

0x484d28 MOV	-0xb8(%RBP),%RSI

0x484d2f MOV	(%RCX,%RSI,8),%RAX

0x484d33 MOV	0x8(%RCX,%RSI,8),%RCX

0x484d38 MOV	%RCX,%RSI

0x484d3b SUB	%RAX,%RSI

0x484d3e JLE	48458e

0x484d44 XORPS	%XMM6,%XMM6

0x484d47 CVTSI2SDL	-0x80(%RBP),%XMM6

0x484d4c CMP	$0x4,%RSI

0x484d50 JAE	484dcb

0x484d52 MOV	%RSI,%R10

0x484d55 AND	$-0x4,%R10

0x484d59 CMP	%RSI,%R10

0x484d5c JAE	484f14

0x484d62 ADD	%R10,%RAX

0x484d65 MOV	-0x58(%RBP),%R12

0x484d69 JMP	484d7c

  (1498) 0x484d70 INC	%RAX

  (1498) 0x484d73 CMP	%RAX,%RCX

  (1498) 0x484d76 JE	48458e

  (1498) 0x484d7c MOV	-0x78(%RBP),%RSI

  (1498) 0x484d80 MOV	(%RSI,%RAX,8),%RSI

  (1498) 0x484d84 MOV	(%R14,%RSI,8),%RSI

  (1498) 0x484d88 CMP	%RDX,%RSI

  (1498) 0x484d8b JL	484d70

  (1498) 0x484d8d MOV	-0x50(%RBP),%R10

  (1498) 0x484d91 MOVSD	(%R10,%RAX,8),%XMM8

  (1498) 0x484d97 MOVAPD	%XMM8,%XMM9

  (1498) 0x484d9c MULSD	%XMM6,%XMM9

  (1498) 0x484da1 UCOMISD	%XMM0,%XMM9

  (1498) 0x484da6 JAE	484d70

  (1498) 0x484da8 MULSD	%XMM7,%XMM8

  (1498) 0x484dad MOV	-0x70(%RBP),%R10

  (1498) 0x484db1 MOV	(%R10),%R10

  (1498) 0x484db4 ADDSD	(%R10,%RSI,8),%XMM8

  (1498) 0x484dba MOVSD	%XMM8,(%R10,%RSI,8)

  (1498) 0x484dc0 JMP	484d70

0x484dc2 ADDSD	%XMM7,%XMM5

0x484dc6 JMP	48458e

0x484dcb MOV	%RSI,%R10

0x484dce SHR	$0x2,%R10

0x484dd2 LEA	0x18(,%RAX,8),%R11

0x484dda JMP	484ded

  (1499) 0x484de0 ADD	$0x20,%R11

  (1499) 0x484de4 DEC	%R10

  (1499) 0x484de7 JE	484d52

  (1499) 0x484ded MOV	-0x78(%RBP),%R15

  (1499) 0x484df1 MOV	-0x18(%R15,%R11,1),%R15

  (1499) 0x484df6 MOV	(%R14,%R15,8),%R15

  (1499) 0x484dfa CMP	%RDX,%R15

  (1499) 0x484dfd JL	484e34

  (1499) 0x484dff MOV	-0x50(%RBP),%R12

  (1499) 0x484e03 MOVSD	-0x18(%R12,%R11,1),%XMM8

  (1499) 0x484e0a MOVAPD	%XMM8,%XMM9

  (1499) 0x484e0f MULSD	%XMM6,%XMM9

  (1499) 0x484e14 UCOMISD	%XMM0,%XMM9

  (1499) 0x484e19 JAE	484e34

  (1499) 0x484e1b MULSD	%XMM7,%XMM8

  (1499) 0x484e20 MOV	-0x70(%RBP),%R12

  (1499) 0x484e24 MOV	(%R12),%R12

  (1499) 0x484e28 ADDSD	(%R12,%R15,8),%XMM8

  (1499) 0x484e2e MOVSD	%XMM8,(%R12,%R15,8)

  (1499) 0x484e34 MOV	-0x78(%RBP),%R15

  (1499) 0x484e38 MOV	-0x10(%R15,%R11,1),%R15

  (1499) 0x484e3d MOV	(%R14,%R15,8),%R15

  (1499) 0x484e41 CMP	%RDX,%R15

  (1499) 0x484e44 JL	484e7b

  (1499) 0x484e46 MOV	-0x50(%RBP),%R12

  (1499) 0x484e4a MOVSD	-0x10(%R12,%R11,1),%XMM8

  (1499) 0x484e51 MOVAPD	%XMM8,%XMM9

  (1499) 0x484e56 MULSD	%XMM6,%XMM9

  (1499) 0x484e5b UCOMISD	%XMM0,%XMM9

  (1499) 0x484e60 JAE	484e7b

  (1499) 0x484e62 MULSD	%XMM7,%XMM8

  (1499) 0x484e67 MOV	-0x70(%RBP),%R12

  (1499) 0x484e6b MOV	(%R12),%R12

  (1499) 0x484e6f ADDSD	(%R12,%R15,8),%XMM8

  (1499) 0x484e75 MOVSD	%XMM8,(%R12,%R15,8)

  (1499) 0x484e7b MOV	-0x78(%RBP),%R15

  (1499) 0x484e7f MOV	-0x8(%R15,%R11,1),%R15

  (1499) 0x484e84 MOV	(%R14,%R15,8),%R15

  (1499) 0x484e88 CMP	%RDX,%R15

  (1499) 0x484e8b JL	484ec2

  (1499) 0x484e8d MOV	-0x50(%RBP),%R12

  (1499) 0x484e91 MOVSD	-0x8(%R12,%R11,1),%XMM8

  (1499) 0x484e98 MOVAPD	%XMM8,%XMM9

  (1499) 0x484e9d MULSD	%XMM6,%XMM9

  (1499) 0x484ea2 UCOMISD	%XMM0,%XMM9

  (1499) 0x484ea7 JAE	484ec2

  (1499) 0x484ea9 MULSD	%XMM7,%XMM8

  (1499) 0x484eae MOV	-0x70(%RBP),%R12

  (1499) 0x484eb2 MOV	(%R12),%R12

  (1499) 0x484eb6 ADDSD	(%R12,%R15,8),%XMM8

  (1499) 0x484ebc MOVSD	%XMM8,(%R12,%R15,8)

  (1499) 0x484ec2 MOV	-0x78(%RBP),%R15

  (1499) 0x484ec6 MOV	(%R15,%R11,1),%R15

  (1499) 0x484eca MOV	(%R14,%R15,8),%R15

  (1499) 0x484ece CMP	%RDX,%R15

  (1499) 0x484ed1 JL	484de0

  (1499) 0x484ed7 MOV	-0x50(%RBP),%R12

  (1499) 0x484edb MOVSD	(%R12,%R11,1),%XMM8

  (1499) 0x484ee1 MOVAPD	%XMM8,%XMM9

  (1499) 0x484ee6 MULSD	%XMM6,%XMM9

  (1499) 0x484eeb UCOMISD	%XMM0,%XMM9

  (1499) 0x484ef0 JAE	484de0

  (1499) 0x484ef6 MULSD	%XMM7,%XMM8

  (1499) 0x484efb MOV	-0x70(%RBP),%R12

  (1499) 0x484eff MOV	(%R12),%R12

  (1499) 0x484f03 ADDSD	(%R12,%R15,8),%XMM8

  (1499) 0x484f09 MOVSD	%XMM8,(%R12,%R15,8)

  (1499) 0x484f0f JMP	484de0

0x484f14 MOV	-0x58(%RBP),%R12

0x484f18 JMP	48458e

0x484f1d MOV	-0x50(%RBP),%RAX

0x484f21 MOVSD	0x10(%RAX,%R12,8),%XMM8

0x484f28 MOVAPD	%XMM8,%XMM9

0x484f2d MULSD	%XMM7,%XMM9

0x484f32 CMPSD	$0x1,%XMM0,%XMM9

0x484f38 ANDPD	%XMM9,%XMM8

0x484f3d ANDNPD	%XMM1,%XMM9

0x484f42 ORPD	%XMM8,%XMM9

0x484f47 ADDSD	%XMM9,%XMM6

0x484f4c MOV	-0x78(%RBP),%RAX

0x484f50 MOV	0x8(%RAX,%R12,8),%RAX

0x484f55 CMP	%RDX,(%R14,%RAX,8)

0x484f59 JL	484c10

0x484f5f JMP	484a29

/home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c: 1221 - 1743

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

1221:        if (n_fine)

[...]

1609:            for (jj = A_diag_i[i]+1; jj < A_diag_i[i+1]; jj++)

1610:            { /* i1 is a c-point and strongly influences i, accumulate

1611:               * a_(i,i1) into interpolation weight */

1612:              i1 = A_diag_j[jj];

1613:              if (P_marker[i1] >= jj_begin_row)

1614:              {

1615:                P_diag_data[P_marker[i1]] += A_diag_data[jj];

1616:              }

1617:              else if(P_marker[i1] == strong_f_marker)

1618:              {

1619:                sum = zero;

1620:                sgn = 1;

1621:                if(A_diag_data[A_diag_i[i1]] < 0) sgn = -1;

1622:                /* Loop over row of A for point i1 and calculate the sum

1623:                 * of the connections to c-points that strongly influence i. */

1624:                for(jj1 = A_diag_i[i1]+1; jj1 < A_diag_i[i1+1]; jj1++)

1625:                {

1626:                  i2 = A_diag_j[jj1];

1627:                  if((P_marker[i2] >= jj_begin_row || i2 == i) && (sgn*A_diag_data[jj1]) < 0)

1628:                    sum += A_diag_data[jj1];

1629:                }

1630:                if(num_procs > 1)

1631:                {

1632:                  for(jj1 = A_offd_i[i1]; jj1< A_offd_i[i1+1]; jj1++)

1633:                  {

1634:                    i2 = A_offd_j[jj1];

1635:                    if(P_marker_offd[i2] >= jj_begin_row_offd &&

1636:                       (sgn*A_offd_data[jj1]) < 0)

1637:                       sum += A_offd_data[jj1];

1638:                  }

1639:                }

1640:                if(sum != 0)

1641:                {

1642:                  distribute = A_diag_data[jj]/sum;

1643:                  /* Loop over row of A for point i1 and do the distribution */

1644:                  for(jj1 = A_diag_i[i1]+1; jj1 < A_diag_i[i1+1]; jj1++)

1645:                  {

1646:                    i2 = A_diag_j[jj1];

1647:                    if(P_marker[i2] >= jj_begin_row && (sgn*A_diag_data[jj1]) < 0)

1648:                       P_diag_data[P_marker[i2]] +=

1649:                       distribute*A_diag_data[jj1];

1650:                        if(i2 == i && (sgn*A_diag_data[jj1]) < 0)

1651:                          diagonal += distribute*A_diag_data[jj1];

1652:                  }

1653:                  if(num_procs > 1)

1654:                  {

1655:                    for(jj1 = A_offd_i[i1]; jj1 < A_offd_i[i1+1]; jj1++)

1656:                    {

1657:                      i2 = A_offd_j[jj1];

1658:                      if(P_marker_offd[i2] >= jj_begin_row_offd &&

1659:                                 (sgn*A_offd_data[jj1]) < 0)

1660:                        P_offd_data[P_marker_offd[i2]] +=

1661:                          distribute*A_offd_data[jj1];

[...]

1667:                  diagonal += A_diag_data[jj];

1668:                }

1669:              }

1670:              /* neighbor i1 weakly influences i, accumulate a_(i,i1) into

1671:               * diagonal */

1672:              else if (CF_marker[i1] != -3)

1673:              {

1674:                if(num_functions == 1 || dof_func[i] == dof_func[i1])

1675:                  diagonal += A_diag_data[jj];

[...]

1743:                 P_diag_data[jj] /= -diagonal;

Coverage (%)	Name	Source Location	Module
►95.57+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_launch_thread		libiomp5.so
○	_INTERNALea951ae6::__kmp_launc[...]		libiomp5.so
○	start_thread		libc.so.6
○	__GI___clone3		libc.so.6
►2.32+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so
○	__kmp_fork_call		libiomp5.so
○	__kmpc_fork_call		libiomp5.so
○	hypre_BoomerAMGBuildExtPIInter[...]	par_lr_interp.c:1196	exec
○	hypre_BoomerAMGSetup	par_amg_setup.c:847	exec
○	hypre_PCGSetup	pcg.c:234	exec
○	main	amg.c:398	exec
○	__libc_start_call_main		libc.so.6
○	__libc_start_main		libc.so.6
○	_start		exec

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 /

Metric	Value
CQA speedup if no scalar integer	2.70
CQA speedup if FP arith vectorized	2.76
CQA speedup if fully vectorized	11.47
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.35
Bottlenecks	micro-operation queue,
Function	hypre_BoomerAMGBuildExtPIInterp.extracted
Source	par_lr_interp.c:1221-1221,par_lr_interp.c:1609-1609,par_lr_interp.c:1612-1617,par_lr_interp.c:1621-1621,par_lr_interp.c:1624-1627,par_lr_interp.c:1630-1636,par_lr_interp.c:1640-1644,par_lr_interp.c:1647-1647,par_lr_interp.c:1653-1655,par_lr_interp.c:1659-1660,par_lr_interp.c:1667-1667,par_lr_interp.c:1672-1675,par_lr_interp.c:1743-1743
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	33.75
CQA cycles if no scalar integer	12.50
CQA cycles if FP arith vectorized	12.21
CQA cycles if fully vectorized	2.94
Front-end cycles	33.75
P0 cycles	20.33
P1 cycles	20.33
P2 cycles	20.33
P3 cycles	20.33
P4 cycles	20.33
P5 cycles	20.33
P6 cycles	25.00
P7 cycles	25.00
P8 cycles	25.00
P9 cycles	25.00
P10 cycles	11.50
P11 cycles	11.50
P12 cycles	11.50
P13 cycles	11.50
P14 cycles	1.50
P15 cycles	1.50
DIV/SQRT cycles	4.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	266.00
Nb uops	270.00
Nb loads	93.00
Nb stores	7.00
Nb stack references	19.00
FLOP/cycle	0.47
Nb FLOP add-sub	9.00
Nb FLOP mul	6.00
Nb FLOP fma	0.00
Nb FLOP div	1.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	23.23
Bytes prefetched	0.00
Bytes loaded	728.00
Bytes stored	56.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	27.18
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	0.00
Vectorization ratio other	38.89
Vector-efficiency ratio all	15.53
Vector-efficiency ratio load	11.67
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	12.50
Vector-efficiency ratio other	16.84

Metric	Value
CQA speedup if no scalar integer	2.70
CQA speedup if FP arith vectorized	2.76
CQA speedup if fully vectorized	11.47
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.35
Bottlenecks	micro-operation queue,
Function	hypre_BoomerAMGBuildExtPIInterp.extracted
Source	par_lr_interp.c:1221-1221,par_lr_interp.c:1609-1609,par_lr_interp.c:1612-1617,par_lr_interp.c:1621-1621,par_lr_interp.c:1624-1627,par_lr_interp.c:1630-1636,par_lr_interp.c:1640-1644,par_lr_interp.c:1647-1647,par_lr_interp.c:1653-1655,par_lr_interp.c:1659-1660,par_lr_interp.c:1667-1667,par_lr_interp.c:1672-1675,par_lr_interp.c:1743-1743
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	33.75
CQA cycles if no scalar integer	12.50
CQA cycles if FP arith vectorized	12.21
CQA cycles if fully vectorized	2.94
Front-end cycles	33.75
P0 cycles	20.33
P1 cycles	20.33
P2 cycles	20.33
P3 cycles	20.33
P4 cycles	20.33
P5 cycles	20.33
P6 cycles	25.00
P7 cycles	25.00
P8 cycles	25.00
P9 cycles	25.00
P10 cycles	11.50
P11 cycles	11.50
P12 cycles	11.50
P13 cycles	11.50
P14 cycles	1.50
P15 cycles	1.50
DIV/SQRT cycles	4.00
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	266.00
Nb uops	270.00
Nb loads	93.00
Nb stores	7.00
Nb stack references	19.00
FLOP/cycle	0.47
Nb FLOP add-sub	9.00
Nb FLOP mul	6.00
Nb FLOP fma	0.00
Nb FLOP div	1.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	0.00
Nb FLOP rsqrt	0.00
Bytes/cycle	23.23
Bytes prefetched	0.00
Bytes loaded	728.00
Bytes stored	56.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	27.18
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	NA
Vectorization ratio div_sqrt	0.00
Vectorization ratio other	38.89
Vector-efficiency ratio all	15.53
Vector-efficiency ratio load	11.67
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	NA
Vector-efficiency ratio div_sqrt	12.50
Vector-efficiency ratio other	16.84

Path /

Average path: Display a virtual path defined by average values of all real paths

Function	hypre_BoomerAMGBuildExtPIInterp.extracted
Source file and lines	par_lr_interp.c:1221-1743
Module	exec

The loop is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1221,1609-1661,1667-1675,1743.

Analyzed code is defined in /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1221,1609,1612-1617,1621,1624-1627,1630-1636,1640-1644,1647,1653-1655,1659-1660,1667,1672-1675,1743.

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

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 33.75 to 12.50 cycles (2.70x speedup).

Workaround

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

Vectorization

Your loop is probably not vectorized. Only 15% of vector register length is used (average across all SSE/AVX instructions). By vectorizing your loop, you can lower the cost of an iteration from 33.75 to 2.94 cycles (11.47x 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 loop can use their full power.

Workaround

Try another compiler or update/tune your current one:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

CMOVA: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
UCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1621
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1640

Conversion instructions

Detected expensive conversion instructions.

Details

CVTSI2SD (INT32/64 to FP64, scalar): 4 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1636
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1647
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1659

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

24 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

Matching between your loop (in the source code) and the binary loop

The binary loop is composed of 16 FP arithmetical operations:

9: addition or subtraction
6: multiply
1: divide

The binary loop is loading 728 bytes (91 double precision FP elements). The binary loop is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	266
nb uops	270
loop length	1233
used x86 registers	14
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	19
ADD-SUB / MUL ratio	1.50

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	33.75 cycles
front end	33.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	20.33	20.33	20.33	20.33	20.33	20.33	25.00	25.00	25.00	25.00	11.50	11.50	11.50	11.50	1.50	1.50
cycles	20.33	20.33	20.33	20.33	20.33	20.33	25.00	25.00	25.00	25.00	11.50	11.50	11.50	11.50	1.50	1.50

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

4.00

Cycles summary

Front-end	33.75
Dispatch	25.00
DIV/SQRT	4.00
Overall L1	33.75

Vectorization ratios

INT

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)
other	0%

all	45%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	77%

INT+FP

all	27%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	38%

Vector efficiency ratios

INT

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

all	18%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	22%

INT+FP

all	15%
load	11%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 33.75 cycles. At this rate:

8% of peak load performance is reached (21.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.66 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 33.75 to 25.00 cycles (1.35x speedup).

ASM code

In the binary file, the address of the loop is: 48459e

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
MOV -0xa0(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RCX,%RAX,8),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADDSD (%RSI,%R9,8),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM6,(%RCX,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
INC %R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP -0x90(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 484417 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1487>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R9,8),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RBX,%R10,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 484570 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15e0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP -0x48(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JNE 484680 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x16f0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x188(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%R10,8),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XORPD %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
UCOMISD (%RSI,%R11,8),%XMM6	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
SETBE %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x8(%RCX,%R10,8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA -0x1(,%RAX,2),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA 0x1(%R11),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RCX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %R11,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
DEC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 4846c0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1730>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x88(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
AND $-0x4,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x108(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484938 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x19a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484876 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x18e6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JNE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xb0(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 4848dc <hypre_BoomerAMGBuildExtPIInterp.extracted+0x194c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xe0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMPQ $-0x3,(%RAX,%R10,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMPQ $0x1,-0x180(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 4846b1 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1721>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x178(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%R13,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP (%RCX,%R10,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JNE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADDSD (%RAX,%R9,8),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x88(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SHR $0x2,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV -0xb0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA 0x20(,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XORPD %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 4846fd <hypre_BoomerAMGBuildExtPIInterp.extracted+0x176d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xb0(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 4848dc <hypre_BoomerAMGBuildExtPIInterp.extracted+0x194c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x18(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 484938 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x19a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x10(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R10,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R15,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R15,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM7,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM7,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JL 484c48 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x150(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%RSI,8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%RSI,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484a6f <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1adf>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x1,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484bd4 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c44>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 484be7 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c57>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 484c10 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x8(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484c1e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c8e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%RSI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x18(,%R12,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 484a8d <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1afd>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484c1e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c8e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484f1d <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1f8d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484a29 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM7,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM7,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
UCOMISD %XMM0,%XMM6	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R9,8),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
JE 484dc2 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e32>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
DIVSD %XMM6,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	13	4	scal (12.5%)
CMP %RCX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 484d13 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1d83>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
JMP 484c8c <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cfc>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
CMPQ $0x2,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x150(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%RSI,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RCX,%RSI,8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484dcb <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e3b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484f14 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1f84>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %R10,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 484d7c <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1dec>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADDSD %XMM7,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RSI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%R10	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x18(,%RAX,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 484ded <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e5d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x10(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
JL 484c10 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484a29 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A

Function	hypre_BoomerAMGBuildExtPIInterp.extracted
Source file and lines	par_lr_interp.c:1221-1743
Module	exec

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Failed to get the number of paths (too many, greater than internal limit = 100000)
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is very high. Force analysis with --force-loop-streams-analysis: expect potentially high RAM/CPU footprint

Try to simplify control.

gain
potential
hint
expert

Code clean check

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:
- recompile with ffast-math (included in Ofast) to extend loop vectorization to FP reductions.
Remove inter-iterations dependences from your loop and make it unit-stride:
- If your arrays have 2 or more dimensions, check whether elements are accessed contiguously and, otherwise, try to permute loops accordingly: C storage order is row-major: for(i) for(j) a[j][i] = b[j][i]; (slow, non stride 1) => for(i) for(j) a[i][j] = b[i][j]; (fast, stride 1)
- If your loop 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.

FMA

Presence of both ADD/SUB and MUL operations.

Workaround

Pass to your compiler a micro-architecture specialization option:
- use march=native
Try to change order in which elements are evaluated (using parentheses) in arithmetic expressions containing both ADD/SUB and MUL operations to enable your compiler to generate FMA instructions wherever possible. For instance a + b*c is a valid FMA (MUL then ADD). However (a+b)* c cannot be translated into an FMA (ADD then MUL).

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.

CMOVA: 3 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
UCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1621
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1640

Conversion instructions

Detected expensive conversion instructions.

Details

CVTSI2SD (INT32/64 to FP64, scalar): 4 occurrences►
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1627
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1636
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1647
- /home/eoseret/qaas_runs_ZEN5/173-989-6379/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c:1659

Workaround

Avoid mixing data with different types. In particular, check if the type of constants is the same as array elements.

Type of elements and instruction set

24 SSE or AVX instructions are processing arithmetic or math operations on double precision FP elements in scalar mode (one at a time).

Matching between your loop (in the source code) and the binary loop

The binary loop is composed of 16 FP arithmetical operations:

9: addition or subtraction
6: multiply
1: divide

The binary loop is loading 728 bytes (91 double precision FP elements). The binary loop is storing 56 bytes (7 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.02 FP operations per loaded or stored byte.

General properties

nb instructions	266
nb uops	270
loop length	1233
used x86 registers	14
used mmx registers	0
used xmm registers	7
used ymm registers	0
used zmm registers	0
nb stack references	19
ADD-SUB / MUL ratio	1.50

Front-end

MACRO FUSION NOT POSSIBLE FIT IN UOP CACHE

micro-operation queue	33.75 cycles
front end	33.75 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15
uops	20.33	20.33	20.33	20.33	20.33	20.33	25.00	25.00	25.00	25.00	11.50	11.50	11.50	11.50	1.50	1.50
cycles	20.33	20.33	20.33	20.33	20.33	20.33	25.00	25.00	25.00	25.00	11.50	11.50	11.50	11.50	1.50	1.50

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

4.00

Cycles summary

Front-end	33.75
Dispatch	25.00
DIV/SQRT	4.00
Overall L1	33.75

Vectorization ratios

INT

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)
other	0%

all	45%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	77%

INT+FP

all	27%
load	0%
store	0%
mul	0%
add-sub	0%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	0%
other	38%

Vector efficiency ratios

INT

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

all	18%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	22%

INT+FP

all	15%
load	11%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
div/sqrt	12%
other	16%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 33.75 cycles. At this rate:

8% of peak load performance is reached (21.57 out of 256.00 bytes loaded per cycle (GB/s @ 1GHz))
1% of peak store performance is reached (1.66 out of 128.00 bytes stored per cycle (GB/s @ 1GHz))

Front-end bottlenecks

ASM code

In the binary file, the address of the loop is: 48459e

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	P12	P13	P14	P15	Latency	Recip. throughput	Vectorization
MOV -0xa0(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RCX,%RAX,8),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADDSD (%RSI,%R9,8),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOVSD %XMM6,(%RCX,%RAX,8)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0.50	0.50	1	0.50	scal (12.5%)
INC %R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP -0x90(%RBP),%R9	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 484417 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1487>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R9,8),%R10	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RBX,%R10,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDI,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 484570 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15e0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP -0x48(%RBP),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JNE 484680 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x16f0>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x188(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%R10,8),%R11	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XORPD %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
XOR %EAX,%EAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
MOV -0x60(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
UCOMISD (%RSI,%R11,8),%XMM6	2	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
SETBE %AL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %R10,-0xb8(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOV 0x8(%RCX,%R10,8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA -0x1(,%RAX,2),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
MOV %RAX,-0x80(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
LEA 0x1(%R11),%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
CMP %RCX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R11,-0xb0(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
SUB %R11,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x108(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
DEC %RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 4846c0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1730>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x88(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
AND $-0x4,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x108(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB %R15,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	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	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484938 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x19a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484876 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x18e6>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JNE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0xb0(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JMP 4848dc <hypre_BoomerAMGBuildExtPIInterp.extracted+0x194c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xe0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMPQ $-0x3,(%RAX,%R10,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMPQ $0x1,-0x180(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JE 4846b1 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1721>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x178(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%R13,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP (%RCX,%R10,8),%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JNE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADDSD (%RAX,%R9,8),%XMM5	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x88(%RBP),%R15	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SHR $0x2,%R15	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
MOV -0xb0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
LEA 0x20(,%RAX,8),%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
XORPD %XMM8,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
JMP 4846fd <hypre_BoomerAMGBuildExtPIInterp.extracted+0x176d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0xb0(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R15,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x18(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 4848dc <hypre_BoomerAMGBuildExtPIInterp.extracted+0x194c>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x18(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 484938 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x19a8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x10(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
ADD %R10,%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0xa8(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R15,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
XOR %ESI,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %RDI,(%RBX,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
SETGE %SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XOR %R11D,%R11D	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.25	N/A
CMP %R13,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
SETE %R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %SIL,%R11B	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMOVA %R11D,%ESI	2	0.33	0.33	0.33	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
CMP $0x1,%SIL	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JNE 4849a0 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a10>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R15,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM7,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM7,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
NOPW %CS:(%RAX,%RAX,1)	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.09	N/A
MOV -0xc0(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RAX,-0x88(%RBP)	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	4	0.50	scal (12.5%)
CMP $0x2,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JL 484c48 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb8>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x150(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%RSI,8),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%RSI,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
SUB %R12,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM7,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
CMP $0x4,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484a6f <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1adf>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x1,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JE 484bd4 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c44>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x3,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JE 484be7 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c57>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
CMP $0x2,%EAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (6.3%)
JNE 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 484c10 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x8(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484c1e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c8e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%RSI	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x18(,%R12,8),%R15	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 484a8d <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1afd>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484c1e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c8e>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADD %RSI,%R12	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x10(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484f1d <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1f8d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JGE 484a29 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 484c44 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cb4>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MULSD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM7,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM7,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
UCOMISD %XMM0,%XMM6	2	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0.50	0.50	7	1	scal (12.5%)
MOV -0x60(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD (%RAX,%R9,8),%XMM7	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
JE 484dc2 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e32>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
DIVSD %XMM6,%XMM7	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	13	4	scal (12.5%)
CMP %RCX,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JGE 484d13 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1d83>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
JMP 484c8c <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1cfc>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
CMPQ $0x2,-0x88(%RBP)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	scal (12.5%)
JL 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV -0x150(%RBP),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV -0xb8(%RBP),%RSI	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV (%RCX,%RSI,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RCX,%RSI,8),%RCX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV %RCX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SUB %RAX,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
JLE 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
XORPS %XMM6,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
CVTSI2SDL -0x80(%RBP),%XMM6	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0.50	0.50	0	0	3	0.50	scal (6.3%)
CMP $0x4,%RSI	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484dcb <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e3b>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
MOV %RSI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
AND $-0x4,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %RSI,%R10	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
JAE 484f14 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1f84>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
ADD %R10,%RAX	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 484d7c <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1dec>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
ADDSD %XMM7,%XMM5	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV %RSI,%R10	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SHR $0x2,%R10	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.33	N/A
LEA 0x18(,%RAX,8),%R11	1	0.17	0.17	0.17	0.17	0.17	0.17	0	0	0	0	0	0	0	0	0	0	1	0.25	N/A
JMP 484ded <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1e5d>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x58(%RBP),%R12	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
JMP 48458e <hypre_BoomerAMGBuildExtPIInterp.extracted+0x15fe>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A
MOV -0x50(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOVSD 0x10(%RAX,%R12,8),%XMM8	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.50	scal (12.5%)
MOVAPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	vect (25.0%)
MULSD %XMM7,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	0	0	3	0.50	scal (12.5%)
CMPSD $0x1,%XMM0,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
ANDPD %XMM9,%XMM8	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ANDNPD %XMM1,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ORPD %XMM8,%XMM9	1	0	0	0	0	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	1	0.25	vect (25.0%)
ADDSD %XMM9,%XMM6	1	0	0	0	0	0	0	0	0	0	0	0	0	0.50	0.50	0	0	2	0.50	scal (12.5%)
MOV -0x78(%RBP),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
MOV 0x8(%RAX,%R12,8),%RAX	1	0	0	0	0	0	0	0.25	0.25	0.25	0.25	0	0	0	0	0	0	3	0.25	N/A
CMP %RDX,(%R14,%RAX,8)	1	0.17	0.17	0.17	0.17	0.17	0.17	0.25	0.25	0.25	0.25	0	0	0	0	0	0	1	0.25	N/A
JL 484c10 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1c80>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	1	0.50-1	N/A
JMP 484a29 <hypre_BoomerAMGBuildExtPIInterp.extracted+0x1a99>	1	0	0	0	0.33	0.33	0.33	0	0	0	0	0	0	0	0	0	0	0	1	N/A

Report Configuration

Code clean check

Workaround

Vectorization

Details

Workaround

Execution units bottlenecks

FMA

Workaround

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

Matching between your loop (in the source code) and the binary loop

Arithmetic intensity

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

FMA

Workaround

Complex instructions

Details

Conversion instructions

Details

Workaround

Type of elements and instruction set

Matching between your loop (in the source code) and the binary loop

Arithmetic intensity

General properties

Front-end

Back-end

Cycles summary

Vectorization ratios

Vector efficiency ratios

Cycles and memory resources usage

Front-end bottlenecks

ASM code