OV - exec - Loop 194

	Loop Id: 194	Module: exec	Source: generate_chunk.cpp:85-128 [...]	Coverage: 0.01%

0x42e8c0 MOV	-0x50(%RBP),%RSI

0x42e8c4 LEA	(%RSI,%RAX,8),%RDX

0x42e8c8 VMOVSD	(%R15,%R8,8),%XMM2

0x42e8ce VMOVSD	%XMM2,(%RDX)

0x42e8d2 MOV	-0x30(%RBP),%RCX

0x42e8d6 VMOVSD	(%RCX),%XMM2

0x42e8da VMOVSD	%XMM2,0x8(%R12,%R14,8)

0x42e8e1 VMOVSD	(%R15,%R8,8),%XMM2

0x42e8e7 VMOVSD	%XMM2,0x8(%RSI,%RAX,8)

0x42e8ed NOPL	(%RAX)

0x42e8f0 INC	%R10

0x42e8f3 CMP	%R11,%R10

0x42e8f6 JE	42e7ec

0x42e8fc LEA	(%R9,%R10,1),%RAX

0x42e900 MOV	%RAX,%RCX

0x42e903 OR	%R13,%RCX

0x42e906 SHR	$0x20,%RCX

0x42e90a JE	42ebc0

0x42e910 CQTO

0x42e912 IDIV	%R13

0x42e915 MOV	%RDX,%R14

0x42e918 MOV	%RAX,%RSI

0x42e91b CMP	$0x3,%EBX

0x42e91e JE	42ebd3

0x42e924 CMP	$0x2,%EBX

0x42e927 JE	42edc0

0x42e92d CMP	$0x1,%EBX

0x42e930 JNE	42e8f0

0x42e932 MOV	0x258(%RDI),%RAX

0x42e939 MOVSXD	%R14D,%RCX

0x42e93c VMOVSD	0x8(%RAX,%RCX,8),%XMM2

0x42e942 VUCOMISD	%XMM0,%XMM2

0x42e946 JB	42e8f0

0x42e948 MOV	-0xc8(%RBP),%RCX

0x42e94f VMOVSD	(%RCX,%R8,8),%XMM2

0x42e955 VUCOMISD	(%RAX,%R14,8),%XMM2

0x42e95b JBE	42e8f0

0x42e95d MOV	0x278(%RDI),%RAX

0x42e964 SAL	$0x20,%RSI

0x42e968 MOV	$0x100000000,%RCX

0x42e972 LEA	(%RSI,%RCX,1),%R15

0x42e976 MOV	%R15,%RCX

0x42e979 SAR	$0x1d,%RCX

0x42e97d VMOVSD	(%RAX,%RCX,1),%XMM2

0x42e982 VUCOMISD	%XMM1,%XMM2

0x42e986 JB	42e8f0

0x42e98c MOV	%RSI,%RCX

0x42e98f SAR	$0x1d,%RCX

0x42e993 MOV	-0xc0(%RBP),%RDX

0x42e99a VMOVSD	(%RDX,%R8,8),%XMM2

0x42e9a0 VUCOMISD	(%RAX,%RCX,1),%XMM2

0x42e9a5 JBE	42e8f0

0x42e9ab SAR	$0x20,%RSI

0x42e9af MOV	-0x90(%RBP),%RAX

0x42e9b6 MOV	0x8(%RAX),%RAX

0x42e9ba MOV	0x40(%RDI),%RCX

0x42e9be MOV	0x30(%RDI),%RDX

0x42e9c2 IMUL	%RSI,%RDX

0x42e9c6 ADD	%R14,%RDX

0x42e9c9 VMOVSD	(%RAX,%R8,8),%XMM2

0x42e9cf VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42e9d4 MOV	-0x88(%RBP),%RAX

0x42e9db MOV	0x8(%RAX),%RAX

0x42e9df MOV	0x10(%RDI),%RCX

0x42e9e3 MOV	(%RDI),%RDX

0x42e9e6 IMUL	%RSI,%RDX

0x42e9ea MOV	%R14,-0x40(%RBP)

0x42e9ee ADD	%R14,%RDX

0x42e9f1 VMOVSD	(%RAX,%R8,8),%XMM2

0x42e9f7 VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42e9fc SAR	$0x20,%R15

0x42ea00 MOV	-0x98(%RBP),%RAX

0x42ea07 MOV	0x8(%RAX),%R12

0x42ea0b MOV	0xa8(%RDI),%RAX

0x42ea12 MOV	%RAX,-0x30(%RBP)

0x42ea16 MOV	0xb8(%RDI),%RAX

0x42ea1d MOV	%RAX,-0x58(%RBP)

0x42ea21 MOV	-0xa0(%RBP),%RAX

0x42ea28 MOV	%R15,%RCX

0x42ea2b MOV	0x8(%RAX),%R15

0x42ea2f MOV	0xe8(%RDI),%RAX

0x42ea36 MOV	%RAX,-0x50(%RBP)

0x42ea3a MOV	0xd8(%RDI),%RAX

0x42ea41 MOV	%RAX,-0x48(%RBP)

0x42ea45 INC	%RCX

0x42ea48 LEA	0x1(%RSI),%RAX

0x42ea4c CMP	%RAX,%RCX

0x42ea4f CMOVLE	%RAX,%RCX

0x42ea53 SUB	%RSI,%RCX

0x42ea56 MOV	%RCX,-0x38(%RBP)

0x42ea5a CMP	$0x2,%RCX

0x42ea5e JB	42eb3d

0x42ea64 MOV	-0x38(%RBP),%RCX

0x42ea68 SHR	$0x1,%RCX

0x42ea6b NEG	%RCX

0x42ea6e MOV	-0x48(%RBP),%R9

0x42ea72 LEA	(,%R9,8),%RDI

0x42ea7a MOV	%RDI,%R14

0x42ea7d IMUL	%RAX,%R14

0x42ea81 MOV	-0x50(%RBP),%R11

0x42ea85 ADD	%R11,%R14

0x42ea88 MOV	-0x40(%RBP),%RDX

0x42ea8c LEA	0x8(,%RDX,8),%R13

0x42ea94 SAL	$0x4,%R9

0x42ea98 IMUL	%RSI,%RDI

0x42ea9c ADD	%R11,%RDI

0x42ea9f MOV	-0x30(%RBP),%RBX

0x42eaa3 LEA	(,%RBX,8),%R11

0x42eaab IMUL	%R11,%RAX

0x42eaaf MOV	-0x58(%RBP),%RDX

0x42eab3 ADD	%RDX,%RAX

0x42eab6 SAL	$0x4,%RBX

0x42eaba IMUL	%RSI,%R11

0x42eabe ADD	%RDX,%R11

0x42eac1 MOV	%R13,%RDX

0x42eac4 NOPW	%CS:(%RAX,%RAX,1)

  (196) 0x42ead0 VMOVSD	(%R12,%R8,8),%XMM2

  (196) 0x42ead6 VMOVSD	%XMM2,-0x8(%R11,%R13,1)

  (196) 0x42eadd VMOVSD	(%R15,%R8,8),%XMM2

  (196) 0x42eae3 VMOVSD	%XMM2,-0x8(%RDI,%RDX,1)

  (196) 0x42eae9 VMOVSD	(%R12,%R8,8),%XMM2

  (196) 0x42eaef VMOVSD	%XMM2,(%R11,%R13,1)

  (196) 0x42eaf5 VMOVSD	(%R15,%R8,8),%XMM2

  (196) 0x42eafb VMOVSD	%XMM2,(%RDI,%RDX,1)

  (196) 0x42eb00 VMOVSD	(%R12,%R8,8),%XMM2

  (196) 0x42eb06 VMOVSD	%XMM2,-0x8(%RAX,%R13,1)

  (196) 0x42eb0d VMOVSD	(%R15,%R8,8),%XMM2

  (196) 0x42eb13 VMOVSD	%XMM2,-0x8(%R14,%RDX,1)

  (196) 0x42eb1a VMOVSD	(%R12,%R8,8),%XMM2

  (196) 0x42eb20 VMOVSD	%XMM2,(%RAX,%R13,1)

  (196) 0x42eb26 VMOVSD	(%R15,%R8,8),%XMM2

  (196) 0x42eb2c VMOVSD	%XMM2,(%R14,%RDX,1)

  (196) 0x42eb32 ADD	%R9,%RDX

  (196) 0x42eb35 ADD	%RBX,%R13

  (196) 0x42eb38 INC	%RCX

  (196) 0x42eb3b JNE	42ead0

0x42eb3d MOV	-0x38(%RBP),%RCX

0x42eb41 MOV	%RCX,%RAX

0x42eb44 AND	$-0x2,%RAX

0x42eb48 CMP	%RCX,%RAX

0x42eb4b MOV	-0x80(%RBP),%R13

0x42eb4f MOV	-0x68(%RBP),%RDI

0x42eb53 MOV	-0x78(%RBP),%R9

0x42eb57 MOV	-0x70(%RBP),%R11

0x42eb5b MOV	-0x5c(%RBP),%EBX

0x42eb5e MOV	-0x40(%RBP),%RDX

0x42eb62 JE	42e8f0

0x42eb68 MOV	%RAX,%RCX

0x42eb6b MOV	-0x30(%RBP),%R14

0x42eb6f IMUL	%R14,%RCX

0x42eb73 IMUL	%RSI,%R14

0x42eb77 ADD	%RDX,%R14

0x42eb7a ADD	%RCX,%R14

0x42eb7d VMOVSD	(%R12,%R8,8),%XMM2

0x42eb83 MOV	-0x58(%RBP),%RDX

0x42eb87 VMOVSD	%XMM2,(%RDX,%R14,8)

0x42eb8d LEA	(%R12,%R8,8),%RCX

0x42eb91 MOV	%RCX,-0x30(%RBP)

0x42eb95 MOV	%RDX,%R12

0x42eb98 MOV	-0x48(%RBP),%RCX

0x42eb9c IMUL	%RCX,%RSI

0x42eba0 ADD	-0x40(%RBP),%RSI

0x42eba4 IMUL	%RCX,%RAX

0x42eba8 ADD	%RSI,%RAX

0x42ebab JMP	42e8c0

0x42ebc0 XOR	%EDX,%EDX

0x42ebc2 DIV	%R13D

0x42ebc5 MOV	%EDX,%R14D

0x42ebc8 MOV	%EAX,%ESI

0x42ebca CMP	$0x3,%EBX

0x42ebcd JNE	42e924

0x42ebd3 MOV	0x258(%RDI),%RAX

0x42ebda VMOVSD	(%RAX,%R14,8),%XMM2

0x42ebe0 VUCOMISD	%XMM0,%XMM2

0x42ebe4 JNE	42e8f0

0x42ebea JP	42e8f0

0x42ebf0 MOV	0x278(%RDI),%RAX

0x42ebf7 MOVSXD	%ESI,%R12

0x42ebfa VMOVSD	(%RAX,%R12,8),%XMM2

0x42ec00 VUCOMISD	%XMM1,%XMM2

0x42ec04 JNE	42e8f0

0x42ec0a JP	42e8f0

0x42ec10 SAL	$0x20,%RSI

0x42ec14 MOV	-0x90(%RBP),%RAX

0x42ec1b MOV	0x8(%RAX),%RAX

0x42ec1f MOV	0x40(%RDI),%RCX

0x42ec23 MOV	0x30(%RDI),%RDX

0x42ec27 IMUL	%R12,%RDX

0x42ec2b ADD	%R14,%RDX

0x42ec2e VMOVSD	(%RAX,%R8,8),%XMM2

0x42ec34 VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42ec39 MOV	-0x88(%RBP),%RAX

0x42ec40 MOV	0x8(%RAX),%RAX

0x42ec44 MOV	0x10(%RDI),%RCX

0x42ec48 MOV	(%RDI),%RDX

0x42ec4b IMUL	%R12,%RDX

0x42ec4f MOV	%R14,-0x40(%RBP)

0x42ec53 ADD	%R14,%RDX

0x42ec56 VMOVSD	(%RAX,%R8,8),%XMM2

0x42ec5c VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42ec61 MOV	-0x98(%RBP),%RAX

0x42ec68 MOV	0x8(%RAX),%RCX

0x42ec6c MOV	0xa8(%RDI),%RAX

0x42ec73 MOV	%RAX,-0x30(%RBP)

0x42ec77 MOV	0xb8(%RDI),%RAX

0x42ec7e MOV	%RAX,-0x58(%RBP)

0x42ec82 MOV	-0xa0(%RBP),%RAX

0x42ec89 MOV	0x8(%RAX),%R15

0x42ec8d MOV	0xe8(%RDI),%RAX

0x42ec94 MOV	%RAX,-0x50(%RBP)

0x42ec98 MOV	0xd8(%RDI),%RAX

0x42ec9f MOV	%RAX,-0x48(%RBP)

0x42eca3 MOV	$0x100000000,%RAX

0x42ecad ADD	%RAX,%RSI

0x42ecb0 SAR	$0x20,%RSI

0x42ecb4 INC	%RSI

0x42ecb7 LEA	0x1(%R12),%RAX

0x42ecbc CMP	%RAX,%RSI

0x42ecbf CMOVLE	%RAX,%RSI

0x42ecc3 MOV	%R12,-0x38(%RBP)

0x42ecc7 SUB	%R12,%RSI

0x42ecca CMP	$0x2,%RSI

0x42ecce JB	42ef9c

0x42ecd4 MOV	%RSI,%RDI

0x42ecd7 SHR	$0x1,%RDI

0x42ecda NEG	%RDI

0x42ecdd MOV	-0x48(%RBP),%R11

0x42ece1 LEA	(,%R11,8),%R12

0x42ece9 MOV	%R12,%R13

0x42ecec IMUL	%RAX,%R13

0x42ecf0 MOV	-0x50(%RBP),%R9

0x42ecf4 ADD	%R9,%R13

0x42ecf7 MOV	-0x40(%RBP),%RDX

0x42ecfb LEA	0x8(,%RDX,8),%R14

0x42ed03 SAL	$0x4,%R11

0x42ed07 IMUL	-0x38(%RBP),%R12

0x42ed0c ADD	%R9,%R12

0x42ed0f MOV	-0x30(%RBP),%RDX

0x42ed13 LEA	(,%RDX,8),%RBX

0x42ed1b IMUL	%RBX,%RAX

0x42ed1f MOV	-0x58(%RBP),%R9

0x42ed23 ADD	%R9,%RAX

0x42ed26 SAL	$0x4,%RDX

0x42ed2a IMUL	-0x38(%RBP),%RBX

0x42ed2f ADD	%R9,%RBX

0x42ed32 MOV	%R14,%R9

0x42ed35 NOPW	%CS:(%RAX,%RAX,1)

  (197) 0x42ed40 VMOVSD	(%RCX,%R8,8),%XMM2

  (197) 0x42ed46 VMOVSD	%XMM2,-0x8(%RBX,%R14,1)

  (197) 0x42ed4d VMOVSD	(%R15,%R8,8),%XMM2

  (197) 0x42ed53 VMOVSD	%XMM2,-0x8(%R12,%R9,1)

  (197) 0x42ed5a VMOVSD	(%RCX,%R8,8),%XMM2

  (197) 0x42ed60 VMOVSD	%XMM2,(%RBX,%R14,1)

  (197) 0x42ed66 VMOVSD	(%R15,%R8,8),%XMM2

  (197) 0x42ed6c VMOVSD	%XMM2,(%R12,%R9,1)

  (197) 0x42ed72 VMOVSD	(%RCX,%R8,8),%XMM2

  (197) 0x42ed78 VMOVSD	%XMM2,-0x8(%RAX,%R14,1)

  (197) 0x42ed7f VMOVSD	(%R15,%R8,8),%XMM2

  (197) 0x42ed85 VMOVSD	%XMM2,-0x8(%R13,%R9,1)

  (197) 0x42ed8c VMOVSD	(%RCX,%R8,8),%XMM2

  (197) 0x42ed92 VMOVSD	%XMM2,(%RAX,%R14,1)

  (197) 0x42ed98 VMOVSD	(%R15,%R8,8),%XMM2

  (197) 0x42ed9e VMOVSD	%XMM2,(%R13,%R9,1)

  (197) 0x42eda5 ADD	%R11,%R9

  (197) 0x42eda8 ADD	%RDX,%R14

  (197) 0x42edab INC	%RDI

  (197) 0x42edae JNE	42ed40

0x42edb0 JMP	42ef9c

0x42edc0 MOV	0x218(%RDI),%RAX

0x42edc7 MOV	0x238(%RDI),%RCX

0x42edce VMOVSD	(%RAX,%R14,8),%XMM2

0x42edd4 VSUBSD	%XMM0,%XMM2,%XMM2

0x42edd8 VMULSD	%XMM2,%XMM2,%XMM2

0x42eddc MOVSXD	%ESI,%R12

0x42eddf VMOVSD	(%RCX,%R12,8),%XMM3

0x42ede5 VSUBSD	%XMM1,%XMM3,%XMM3

0x42ede9 VFMADD213SD	%XMM2,%XMM3,%XMM3

0x42edee VSQRTSD	%XMM3,%XMM3,%XMM2

0x42edf2 MOV	-0xd0(%RBP),%RAX

0x42edf9 VMOVSD	(%RAX,%R8,8),%XMM3

0x42edff VUCOMISD	%XMM2,%XMM3

0x42ee03 JB	42e8f0

0x42ee09 SAL	$0x20,%RSI

0x42ee0d MOV	-0x90(%RBP),%RAX

0x42ee14 MOV	0x8(%RAX),%RAX

0x42ee18 MOV	0x40(%RDI),%RCX

0x42ee1c MOV	0x30(%RDI),%RDX

0x42ee20 IMUL	%R12,%RDX

0x42ee24 ADD	%R14,%RDX

0x42ee27 VMOVSD	(%RAX,%R8,8),%XMM2

0x42ee2d VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42ee32 MOV	-0x88(%RBP),%RAX

0x42ee39 MOV	0x8(%RAX),%RAX

0x42ee3d MOV	0x10(%RDI),%RCX

0x42ee41 MOV	(%RDI),%RDX

0x42ee44 IMUL	%R12,%RDX

0x42ee48 MOV	%R14,-0x40(%RBP)

0x42ee4c ADD	%R14,%RDX

0x42ee4f VMOVSD	(%RAX,%R8,8),%XMM2

0x42ee55 VMOVSD	%XMM2,(%RCX,%RDX,8)

0x42ee5a MOV	-0x98(%RBP),%RAX

0x42ee61 MOV	0x8(%RAX),%RCX

0x42ee65 MOV	0xa8(%RDI),%RAX

0x42ee6c MOV	%RAX,-0x30(%RBP)

0x42ee70 MOV	0xb8(%RDI),%RAX

0x42ee77 MOV	%RAX,-0x58(%RBP)

0x42ee7b MOV	-0xa0(%RBP),%RAX

0x42ee82 MOV	0x8(%RAX),%R15

0x42ee86 MOV	0xe8(%RDI),%RAX

0x42ee8d MOV	%RAX,-0x50(%RBP)

0x42ee91 MOV	0xd8(%RDI),%RAX

0x42ee98 MOV	%RAX,-0x48(%RBP)

0x42ee9c MOV	$0x100000000,%RAX

0x42eea6 ADD	%RAX,%RSI

0x42eea9 SAR	$0x20,%RSI

0x42eead INC	%RSI

0x42eeb0 LEA	0x1(%R12),%RAX

0x42eeb5 CMP	%RAX,%RSI

0x42eeb8 CMOVLE	%RAX,%RSI

0x42eebc MOV	%R12,-0x38(%RBP)

0x42eec0 SUB	%R12,%RSI

0x42eec3 CMP	$0x2,%RSI

0x42eec7 JB	42ef9c

0x42eecd MOV	%RSI,%RDI

0x42eed0 SHR	$0x1,%RDI

0x42eed3 NEG	%RDI

0x42eed6 MOV	-0x48(%RBP),%R11

0x42eeda LEA	(,%R11,8),%R12

0x42eee2 MOV	%R12,%R13

0x42eee5 IMUL	%RAX,%R13

0x42eee9 MOV	-0x50(%RBP),%R9

0x42eeed ADD	%R9,%R13

0x42eef0 MOV	-0x40(%RBP),%RDX

0x42eef4 LEA	0x8(,%RDX,8),%RDX

0x42eefc SAL	$0x4,%R11

0x42ef00 IMUL	-0x38(%RBP),%R12

0x42ef05 ADD	%R9,%R12

0x42ef08 MOV	-0x30(%RBP),%R14

0x42ef0c LEA	(,%R14,8),%RBX

0x42ef14 IMUL	%RBX,%RAX

0x42ef18 MOV	-0x58(%RBP),%R9

0x42ef1c ADD	%R9,%RAX

0x42ef1f SAL	$0x4,%R14

0x42ef23 IMUL	-0x38(%RBP),%RBX

0x42ef28 ADD	%R9,%RBX

0x42ef2b MOV	%RDX,%R9

0x42ef2e XCHG	%AX,%AX

  (195) 0x42ef30 VMOVSD	(%RCX,%R8,8),%XMM2

  (195) 0x42ef36 VMOVSD	%XMM2,-0x8(%RBX,%RDX,1)

  (195) 0x42ef3c VMOVSD	(%R15,%R8,8),%XMM2

  (195) 0x42ef42 VMOVSD	%XMM2,-0x8(%R12,%R9,1)

  (195) 0x42ef49 VMOVSD	(%RCX,%R8,8),%XMM2

  (195) 0x42ef4f VMOVSD	%XMM2,(%RBX,%RDX,1)

  (195) 0x42ef54 VMOVSD	(%R15,%R8,8),%XMM2

  (195) 0x42ef5a VMOVSD	%XMM2,(%R12,%R9,1)

  (195) 0x42ef60 VMOVSD	(%RCX,%R8,8),%XMM2

  (195) 0x42ef66 VMOVSD	%XMM2,-0x8(%RAX,%RDX,1)

  (195) 0x42ef6c VMOVSD	(%R15,%R8,8),%XMM2

  (195) 0x42ef72 VMOVSD	%XMM2,-0x8(%R13,%R9,1)

  (195) 0x42ef79 VMOVSD	(%RCX,%R8,8),%XMM2

  (195) 0x42ef7f VMOVSD	%XMM2,(%RAX,%RDX,1)

  (195) 0x42ef84 VMOVSD	(%R15,%R8,8),%XMM2

  (195) 0x42ef8a VMOVSD	%XMM2,(%R13,%R9,1)

  (195) 0x42ef91 ADD	%R11,%R9

  (195) 0x42ef94 ADD	%R14,%RDX

  (195) 0x42ef97 INC	%RDI

  (195) 0x42ef9a JNE	42ef30

0x42ef9c MOV	%RSI,%RAX

0x42ef9f AND	$-0x2,%RAX

0x42efa3 CMP	%RSI,%RAX

0x42efa6 MOV	-0x80(%RBP),%R13

0x42efaa MOV	-0x68(%RBP),%RDI

0x42efae MOV	-0x78(%RBP),%R9

0x42efb2 MOV	-0x70(%RBP),%R11

0x42efb6 MOV	-0x5c(%RBP),%EBX

0x42efb9 MOV	-0x40(%RBP),%RSI

0x42efbd MOV	-0x38(%RBP),%R12

0x42efc1 JE	42e8f0

0x42efc7 MOV	%RAX,%RDX

0x42efca MOV	-0x30(%RBP),%R14

0x42efce IMUL	%R14,%RDX

0x42efd2 IMUL	%R12,%R14

0x42efd6 ADD	%RSI,%R14

0x42efd9 ADD	%RDX,%R14

0x42efdc VMOVSD	(%RCX,%R8,8),%XMM2

0x42efe2 MOV	%R12,%RDX

0x42efe5 MOV	-0x58(%RBP),%R12

0x42efe9 VMOVSD	%XMM2,(%R12,%R14,8)

0x42efef LEA	(%RCX,%R8,8),%RCX

0x42eff3 MOV	%RCX,-0x30(%RBP)

0x42eff7 MOV	-0x48(%RBP),%RCX

0x42effb IMUL	%RCX,%RDX

0x42efff ADD	%RSI,%RDX

0x42f002 IMUL	%RCX,%RAX

0x42f006 ADD	%RDX,%RAX

0x42f009 JMP	42e8c0

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp: 85 - 128

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

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

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

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

88:         double x_cent = state_xmin[state];

89:         double y_cent = state_ymin[state];

90:         if (state_geometry[state] == g_rect) {

91:           if (field.vertexx[i + 1] >= state_xmin[state] && field.vertexx[i] < state_xmax[state]) {

92:             if (field.vertexy[j + 1] >= state_ymin[state] && field.vertexy[j] < state_ymax[state]) {

93:               field.energy0(i, j) = state_energy[state];

94:               field.density0(i, j) = state_density[state];

95:               for (int kt = j; kt <= j + 1; ++kt) {

96:                 for (int jt = i; jt <= i + 1; ++jt) {

97:                   field.xvel0(jt, kt) = state_xvel[state];

98:                   field.yvel0(jt, kt) = state_yvel[state];

[...]

105:               std::sqrt((field.cellx[i] - x_cent) * (field.cellx[i] - x_cent) + (field.celly[j] - y_cent) * (field.celly[j] - y_cent));

106:           if (radius <= state_radius[state]) {

107:             field.energy0(i, j) = state_energy[state];

108:             field.density0(i, j) = state_density[state];

109:             for (int kt = j; kt <= j + 1; ++kt) {

110:               for (int jt = i; jt <= i + 1; ++jt) {

111:                 field.xvel0(jt, kt) = state_xvel[state];

112:                 field.yvel0(jt, kt) = state_yvel[state];

113:               }

114:             }

115:           }

116:         } else if (state_geometry[state] == g_point) {

117:           if (field.vertexx[i] == x_cent && field.vertexy[j] == y_cent) {

118:             field.energy0(i, j) = state_energy[state];

119:             field.density0(i, j) = state_density[state];

120:             for (int kt = j; kt <= j + 1; ++kt) {

121:               for (int jt = i; jt <= i + 1; ++jt) {

122:                 field.xvel0(jt, kt) = state_xvel[state];

123:                 field.yvel0(jt, kt) = state_yvel[state];

124:               }

125:             }

126:           }

127:         }

128:       }

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 46 - 69

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

46:   T &operator[](size_t i) const { return data[i]; }

[...]

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

Coverage (%)	Name	Source Location	Module
►100.00+	__kmp_invoke_microtask		libiomp5.so
○	__kmp_invoke_task_func		libiomp5.so

Path /

Metric	Value
CQA speedup if no scalar integer	2.16
CQA speedup if FP arith vectorized	3.00
CQA speedup if fully vectorized	6.55
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.32
Bottlenecks	micro-operation queue,
Function	generate_chunk(int, global_variables&) [clone .extracted]
Source	generate_chunk.cpp:85-86,generate_chunk.cpp:89-98,generate_chunk.cpp:105-109,generate_chunk.cpp:117-120,generate_chunk.cpp:128-128,context.h:46-46,context.h:69-69
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	57.33
CQA cycles if no scalar integer	26.50
CQA cycles if FP arith vectorized	19.11
CQA cycles if fully vectorized	8.75
Front-end cycles	57.33
P0 cycles	27.50
P1 cycles	43.40
P2 cycles	40.67
P3 cycles	40.67
P4 cycles	15.50
P5 cycles	27.53
P6 cycles	27.50
P7 cycles	15.50
P8 cycles	15.50
P9 cycles	15.50
P10 cycles	27.47
P11 cycles	40.67
DIV/SQRT cycles	20.50
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	336.00
Nb uops	344.00
Nb loads	122.00
Nb stores	31.00
Nb stack references	18.00
FLOP/cycle	0.10
Nb FLOP add-sub	2.00
Nb FLOP mul	1.00
Nb FLOP fma	1.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	1.00
Nb FLOP rsqrt	0.00
Bytes/cycle	21.21
Bytes prefetched	0.00
Bytes loaded	968.00
Bytes stored	248.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	0.00
Vectorization ratio other	0.00
Vector-efficiency ratio all	12.14
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	12.50
Vector-efficiency ratio div_sqrt	10.42
Vector-efficiency ratio other	11.41

Metric	Value
CQA speedup if no scalar integer	2.16
CQA speedup if FP arith vectorized	3.00
CQA speedup if fully vectorized	6.55
CQA speedup if no inter-iteration dependency	NA
CQA speedup if next bottleneck killed	1.32
Bottlenecks	micro-operation queue,
Function	generate_chunk(int, global_variables&) [clone .extracted]
Source	generate_chunk.cpp:85-86,generate_chunk.cpp:89-98,generate_chunk.cpp:105-109,generate_chunk.cpp:117-120,generate_chunk.cpp:128-128,context.h:46-46,context.h:69-69
Source loop unroll info	NA
Source loop unroll confidence level	NA
Unroll/vectorization loop type	NA
Unroll factor	NA
CQA cycles	57.33
CQA cycles if no scalar integer	26.50
CQA cycles if FP arith vectorized	19.11
CQA cycles if fully vectorized	8.75
Front-end cycles	57.33
P0 cycles	27.50
P1 cycles	43.40
P2 cycles	40.67
P3 cycles	40.67
P4 cycles	15.50
P5 cycles	27.53
P6 cycles	27.50
P7 cycles	15.50
P8 cycles	15.50
P9 cycles	15.50
P10 cycles	27.47
P11 cycles	40.67
DIV/SQRT cycles	20.50
Inter-iter dependencies cycles	NA
FE+BE cycles (UFS)	NA
Stall cycles (UFS)	NA
Nb insns	336.00
Nb uops	344.00
Nb loads	122.00
Nb stores	31.00
Nb stack references	18.00
FLOP/cycle	0.10
Nb FLOP add-sub	2.00
Nb FLOP mul	1.00
Nb FLOP fma	1.00
Nb FLOP div	0.00
Nb FLOP rcp	0.00
Nb FLOP sqrt	1.00
Nb FLOP rsqrt	0.00
Bytes/cycle	21.21
Bytes prefetched	0.00
Bytes loaded	968.00
Bytes stored	248.00
Stride 0	NA
Stride 1	NA
Stride n	NA
Stride unknown	NA
Stride indirect	NA
Vectorization ratio all	0.00
Vectorization ratio load	0.00
Vectorization ratio store	0.00
Vectorization ratio mul	0.00
Vectorization ratio add_sub	0.00
Vectorization ratio fma	0.00
Vectorization ratio div_sqrt	0.00
Vectorization ratio other	0.00
Vector-efficiency ratio all	12.14
Vector-efficiency ratio load	12.50
Vector-efficiency ratio store	12.50
Vector-efficiency ratio mul	12.50
Vector-efficiency ratio add_sub	12.50
Vector-efficiency ratio fma	12.50
Vector-efficiency ratio div_sqrt	10.42
Vector-efficiency ratio other	11.41

Path /

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

Function	generate_chunk(int, global_variables&) [clone .extracted]
Source file and lines	generate_chunk.cpp:85-128
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:85-98,105-128
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 44 paths individually, rerun with max-paths=44
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

Try to simplify control and/or increase the maximum number of paths per function/loop through the 'max-paths-nb' option.

This loop has 44 execution paths.

The presence of multiple execution paths is typically the main/first bottleneck.
Try to simplify control inside loop: ideally, try to remove all conditional expressions, for example by (if applicable):

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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 57.33 to 26.50 cycles (2.16x speedup).

Workaround

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

Vectorization

Your loop is not vectorized. Only 12% 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 57.33 to 8.75 cycles (6.55x 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 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

Detected 1 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

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.

DIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86
IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86
VUCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:91
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:92

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86

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

12 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 6 FP arithmetical operations:

3: addition or subtraction (1 inside FMA instructions)
2: multiply (1 inside FMA instructions)
1: square root

The binary loop is loading 968 bytes (121 double precision FP elements). The binary loop is storing 248 bytes (31 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	336
nb uops	344
loop length	1514
used x86 registers	15
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	18
ADD-SUB / MUL ratio	2.00

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	57.33 cycles
front end	57.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	27.50	32.00	40.67	40.67	15.50	27.53	27.50	15.50	15.50	15.50	27.47	40.67
cycles	27.50	43.40	40.67	40.67	15.50	27.53	27.50	15.50	15.50	15.50	27.47	40.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

20.50

Cycles summary

Front-end	57.33
Dispatch	43.40
DIV/SQRT	20.50
Overall L1	57.33

Vectorization ratios

INT

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

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

Vector efficiency ratios

INT

all	11%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	12%
other	12%

INT+FP

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	10%
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 57.33 cycles. At this rate:

8% of peak load performance is reached (16.88 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.33 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 57.33 to 43.40 cycles (1.32x speedup).

ASM code

In the binary file, the address of the loop is: 42e8fc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RSI,%RAX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%R15,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RDX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,0x8(%R12,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R15,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,0x8(%RSI,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R11,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 42e7ec <_Z14generate_chunkiR16global_variables.extracted+0xfc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R9,%R10,1),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
OR %R13,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
SHR $0x20,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
JE 42ebc0 <_Z14generate_chunkiR16global_variables.extracted+0x4d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %R13	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x3,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 42ebd3 <_Z14generate_chunkiR16global_variables.extracted+0x4e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 42edc0 <_Z14generate_chunkiR16global_variables.extracted+0x6d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x258(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R14D,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD 0x8(%RAX,%RCX,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM0,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD (%RAX,%R14,8),%XMM2	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JBE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x278(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $0x100000000,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
LEA (%RSI,%RCX,1),%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x1d,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VMOVSD (%RAX,%RCX,1),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM1,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x1d,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0xc0(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD (%RAX,%RCX,1),%XMM2	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JBE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RSI,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RSI,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAR $0x20,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R15,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%RSI),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
SUB %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x2,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42eb3d <_Z14generate_chunkiR16global_variables.extracted+0x44d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x38(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x1,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R9,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %RAX,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x50(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R11,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %RSI,%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%RBX,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %R11,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %RSI,%R11	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x80(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x68(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x5c(%RBP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R14,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %RSI,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RCX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%R12,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM2,(%RDX,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%R12,%R8,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RCX,%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD -0x40(%RBP),%RSI	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 42e8c0 <_Z14generate_chunkiR16global_variables.extracted+0x1d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIV %R13D	4	0	3	0	0	0	0	0	0	0	0	0	0	11-16	6	scal (6.3%)
MOV %EDX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x3,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 42e924 <_Z14generate_chunkiR16global_variables.extracted+0x234>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x258(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R14,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM0,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JP 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x278(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %ESI,%R12	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%RAX,%R12,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM1,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JP 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x100000000,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%R12),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %R12,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x1,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R11,8),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
IMUL %RAX,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
MOV -0x50(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%R12	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%RDX,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%RBX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R14,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV 0x218(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x238(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R14,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM0,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM2,%XMM2,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVSXD %ESI,%R12	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%RCX,%R12,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM1,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VFMADD213SD %XMM2,%XMM3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSQRTSD %XMM3,%XMM3,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	13-19	4.50	scal (12.5%)
MOV -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R8,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM2,%XMM3	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x100000000,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%R12),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %R12,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x1,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R11,8),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
IMUL %RAX,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
MOV -0x50(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%R12	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R14,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%R14	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%RBX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RDX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x80(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x68(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x5c(%RBP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R14,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R12,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RCX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R12,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x58(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM2,(%R12,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%RCX,%R8,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RCX,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 42e8c0 <_Z14generate_chunkiR16global_variables.extracted+0x1d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A

Function	generate_chunk(int, global_variables&) [clone .extracted]
Source file and lines	generate_chunk.cpp:85-128
Module	exec

The loop is defined in:

/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:85-98,105-128
/home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h:46,69

Warnings:

Non-innermost loop: analyzing only self part (ignoring child loops).
Ignoring paths for analysis
Too many paths. If you really need to analyze all of the 44 paths individually, rerun with max-paths=44
RecMII not computed since number of paths is unknown or > max_paths
Streams not analyzed since number of paths is unknown or > max_paths

hoisting them (moving them outside the loop)
turning them into conditional moves, MIN or MAX

Ex: if (x<0) x=0 => x = (x<0 ? 0 : x) (or MAX(0,x) after defining the corresponding macro)

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

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 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

Detected 1 FMA (fused multiply-add) operations. Presence of both ADD/SUB and MUL operations.

Workaround

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.

DIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86
IDIV: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86
VUCOMISD: 2 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:91
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:92

Conversion instructions

Detected expensive conversion instructions.

Details

CQTO: 1 occurrences►
- /home/eoseret/qaas_runs_GNR/173-814-2343/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/generate_chunk.cpp:86

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

12 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 6 FP arithmetical operations:

3: addition or subtraction (1 inside FMA instructions)
2: multiply (1 inside FMA instructions)
1: square root

The binary loop is loading 968 bytes (121 double precision FP elements). The binary loop is storing 248 bytes (31 double precision FP elements).

Arithmetic intensity

Arithmetic intensity is 0.00 FP operations per loaded or stored byte.

General properties

nb instructions	336
nb uops	344
loop length	1514
used x86 registers	15
used mmx registers	0
used xmm registers	4
used ymm registers	0
used zmm registers	0
nb stack references	18
ADD-SUB / MUL ratio	2.00

Front-end

ASSUMED MACRO FUSION FIT IN UOP CACHE

micro-operation queue	57.33 cycles
front end	57.33 cycles

Back-end

	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11
uops	27.50	32.00	40.67	40.67	15.50	27.53	27.50	15.50	15.50	15.50	27.47	40.67
cycles	27.50	43.40	40.67	40.67	15.50	27.53	27.50	15.50	15.50	15.50	27.47	40.67

Execution ports to units layout:

P0 (256 bits): VPU, BRU, ALU, DIV/SQRT
P1 (256 bits): ALU, VPU
P2 (512 bits): load
P3 (512 bits): load
P4 (512 bits): store data
P5 (512 bits): ALU, VPU
P6: ALU, BRU
P7: store address
P8: store address
P9 (512 bits): store data
P10: ALU
P11 (512 bits): load

Cycles executing div or sqrt instructions

20.50

Cycles summary

Front-end	57.33
Dispatch	43.40
DIV/SQRT	20.50
Overall L1	57.33

Vectorization ratios

INT

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

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

INT+FP

all	0%
load	0%
store	0%
mul	0%
add-sub	0%
fma	0%
div/sqrt	0%
other	0%

Vector efficiency ratios

INT

all	11%
load	12%
store	12%
mul	12%
add-sub	12%
fma	NA (no fma vectorizable/vectorized instructions)
other	10%

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	12%
other	12%

INT+FP

all	12%
load	12%
store	12%
mul	12%
add-sub	12%
fma	12%
div/sqrt	10%
other	11%

Cycles and memory resources usage

Assuming all data fit into the L1 cache, each iteration of the binary loop takes 57.33 cycles. At this rate:

8% of peak load performance is reached (16.88 out of 192.00 bytes loaded per cycle (GB/s @ 1GHz))
3% of peak store performance is reached (4.33 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: 42e8fc

Instruction	Nb FU	P0	P1	P2	P3	P4	P5	P6	P7	P8	P9	P10	P11	Latency	Recip. throughput	Vectorization
MOV -0x50(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (%RSI,%RAX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
VMOVSD (%R15,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RDX)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x30(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,0x8(%R12,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
VMOVSD (%R15,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,0x8(%RSI,%RAX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
NOPL (%RAX)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
INC %R10	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP %R11,%R10	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JE 42e7ec <_Z14generate_chunkiR16global_variables.extracted+0xfc>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
LEA (%R9,%R10,1),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
OR %R13,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
SHR $0x20,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
JE 42ebc0 <_Z14generate_chunkiR16global_variables.extracted+0x4d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CQTO	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	scal (12.5%)
IDIV %R13	5	0	3	0	0	0	0	0	0	0	0	0	0	11-16	10	scal (12.5%)
MOV %RDX,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %RAX,%RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x3,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 42ebd3 <_Z14generate_chunkiR16global_variables.extracted+0x4e3>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x2,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JE 42edc0 <_Z14generate_chunkiR16global_variables.extracted+0x6d0>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
CMP $0x1,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x258(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %R14D,%RCX	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD 0x8(%RAX,%RCX,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM0,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0xc8(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RCX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD (%RAX,%R14,8),%XMM2	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JBE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x278(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV $0x100000000,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
LEA (%RSI,%RCX,1),%R15	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R15,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x1d,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
VMOVSD (%RAX,%RCX,1),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM1,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SAR $0x1d,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0xc0(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RDX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD (%RAX,%RCX,1),%XMM2	2	1	0	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	scal (12.5%)
JBE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RSI,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RSI,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SAR $0x20,%R15	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %R15,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
INC %RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%RSI),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
SUB %RSI,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RCX,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
CMP $0x2,%RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42eb3d <_Z14generate_chunkiR16global_variables.extracted+0x44d>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV -0x38(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
SHR $0x1,%RCX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RCX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R9,8),%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RDI,%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
IMUL %RAX,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x50(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R11,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R9	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %RSI,%RDI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R11,%RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%RBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%RBX,8),%R11	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %R11,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%RBX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL %RSI,%R11	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%R11	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R13,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV -0x38(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RCX,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RCX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x80(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x68(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x5c(%RBP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R14,%RCX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %RSI,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RCX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%R12,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x58(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM2,(%RDX,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%R12,%R8,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV %RDX,%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x48(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RCX,%RSI	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD -0x40(%RBP),%RSI	1	0.20	0.20	0.33	0.33	0	0.20	0.20	0	0	0	0.20	0.33	1	0.33	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 42e8c0 <_Z14generate_chunkiR16global_variables.extracted+0x1d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
XOR %EDX,%EDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
DIV %R13D	4	0	3	0	0	0	0	0	0	0	0	0	0	11-16	6	scal (6.3%)
MOV %EDX,%R14D	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV %EAX,%ESI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
CMP $0x3,%EBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (6.3%)
JNE 42e924 <_Z14generate_chunkiR16global_variables.extracted+0x234>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x258(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R14,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM0,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JP 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV 0x278(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOVSXD %ESI,%R12	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%RAX,%R12,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM1,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JNE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
JP 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x100000000,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%R12),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %R12,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x1,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R11,8),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
IMUL %RAX,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
MOV -0x50(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%R14	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%R12	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%RDX,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%RDX	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%RBX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %R14,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
NOPW %CS:(%RAX,%RAX,1)	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
JMP 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	N/A
MOV 0x218(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x238(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R14,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM0,%XMM2,%XMM2	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VMULSD %XMM2,%XMM2,%XMM2	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
MOVSXD %ESI,%R12	1	0	0.33	0	0	0	0.33	0	0	0	0	0.33	0	1	0.33	N/A
VMOVSD (%RCX,%R12,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VSUBSD %XMM1,%XMM3,%XMM3	1	0	0.50	0	0	0	0.50	0	0	0	0	0	0	3	0.50	scal (12.5%)
VFMADD213SD %XMM2,%XMM3,%XMM3	1	0.50	0.50	0	0	0	0	0	0	0	0	0	0	4	0.50	scal (12.5%)
VSQRTSD %XMM3,%XMM3,%XMM2	1	1	0	0	0	0	0	0	0	0	0	0	0	13-19	4.50	scal (12.5%)
MOV -0xd0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD (%RAX,%R8,8),%XMM3	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VUCOMISD %XMM2,%XMM3	1	1	0	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
JB 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
SAL $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
MOV -0x90(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x40(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x30(%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x88(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x10(%RDI),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV (%RDI),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R12,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV %R14,-0x40(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
ADD %R14,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RAX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
VMOVSD %XMM2,(%RCX,%RDX,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x98(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xa8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xb8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x58(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0xa0(%RBP),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0x8(%RAX),%R15	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV 0xe8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x50(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV 0xd8(%RDI),%RAX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV %RAX,-0x48(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV $0x100000000,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.28	N/A
ADD %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAR $0x20,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
INC %RSI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
LEA 0x1(%R12),%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
CMP %RAX,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
CMOVLE %RAX,%RSI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	1	0.50	N/A
MOV %R12,-0x38(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
SUB %R12,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
CMP $0x2,%RSI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
JB 42ef9c <_Z14generate_chunkiR16global_variables.extracted+0x8ac>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RSI,%RDI	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
SHR $0x1,%RDI	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
NEG %RDI	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x48(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R11,8),%R12	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %R12,%R13	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	scal (12.5%)
IMUL %RAX,%R13	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	scal (12.5%)
MOV -0x50(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%R13	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x40(%RBP),%RDX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA 0x8(,%RDX,8),%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
SAL $0x4,%R11	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%R12	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%R12	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
LEA (,%R14,8),%RBX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
IMUL %RBX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
MOV -0x58(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
ADD %R9,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
SAL $0x4,%R14	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0-2	0.50	N/A
IMUL -0x38(%RBP),%RBX	1	0	1	0.33	0.33	0	0	0	0	0	0	0	0.33	3	1	N/A
ADD %R9,%RBX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
MOV %RDX,%R9	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
XCHG %AX,%AX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RSI,%RAX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
AND $-0x2,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1-2	0.20	N/A
CMP %RSI,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	scal (12.5%)
MOV -0x80(%RBP),%R13	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV -0x68(%RBP),%RDI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x78(%RBP),%R9	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x70(%RBP),%R11	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x5c(%RBP),%EBX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x40(%RBP),%RSI	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
MOV -0x38(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
JE 42e8f0 <_Z14generate_chunkiR16global_variables.extracted+0x200>	1	0.50	0	0	0	0	0	0.50	0	0	0	0	0	0	0.50	N/A
MOV %RAX,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x30(%RBP),%R14	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %R14,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
IMUL %R12,%R14	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
ADD %RDX,%R14	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
VMOVSD (%RCX,%R8,8),%XMM2	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	scal (12.5%)
MOV %R12,%RDX	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0.17	N/A
MOV -0x58(%RBP),%R12	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
VMOVSD %XMM2,(%R12,%R14,8)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
LEA (%RCX,%R8,8),%RCX	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0.17	N/A
MOV %RCX,-0x30(%RBP)	1	0	0	0	0	0.50	0	0	0.50	0.50	0.50	0	0	1	0.50	scal (12.5%)
MOV -0x48(%RBP),%RCX	1	0	0	0.33	0.33	0	0	0	0	0	0	0	0.33	1	0.33	N/A
IMUL %RCX,%RDX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RSI,%RDX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
IMUL %RCX,%RAX	1	0	1	0	0	0	0	0	0	0	0	0	0	3	1	N/A
ADD %RDX,%RAX	1	0.20	0.20	0	0	0	0.20	0.20	0	0	0	0.20	0	1	0.20	N/A
JMP 42e8c0 <_Z14generate_chunkiR16global_variables.extracted+0x1d0>	1	0	0	0	0	0	0	0	0	0	0	0	0	0	2.08	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