Loop Id: 863 | Module: exec | Source: par_multi_interp.c:1747-1876 [...] | Coverage: 0.5% |
---|
Loop Id: 863 | Module: exec | Source: par_multi_interp.c:1747-1876 [...] | Coverage: 0.5% |
---|
0x448720 MOV -0xb0(%RBP),%RDX |
0x448727 INC %RDX |
0x44872a CMP -0x98(%RBP),%RDX |
0x448731 MOV -0x78(%RBP),%R8 |
0x448735 MOV -0x70(%RBP),%RDI |
0x448739 JGE 4492a0 |
0x44873f MOV -0x120(%RBP),%RAX |
0x448746 MOV %RDX,-0xb0(%RBP) |
0x44874d MOV (%RAX,%RDX,8),%R11 |
0x448751 MOV -0x128(%RBP),%RAX |
0x448758 MOV (%RAX,%R11,8),%RCX |
0x44875c MOV -0xb8(%RBP),%RAX |
0x448763 MOV (%RAX,%R11,8),%R12 |
0x448767 MOV 0x8(%RAX,%R11,8),%RBX |
0x44876c LEA (%RBX,%RCX,1),%RAX |
0x448770 SUB %R12,%RAX |
0x448773 MOV %RCX,-0x38(%RBP) |
0x448777 CMP %RAX,%RCX |
0x44877a MOV %R11,-0x30(%RBP) |
0x44877e JGE 44894f |
0x448784 MOV -0x58(%RBP),%RAX |
0x448788 MOV (%RAX),%RAX |
0x44878b MOV -0x100(%RBP),%RCX |
0x448792 MOV (%RCX,%RAX,8),%RCX |
0x448796 MOV %RBX,%RAX |
0x448799 SUB %R12,%RAX |
0x44879c CMP $0xd,%RAX |
0x4487a0 JB 448920 |
0x4487a6 MOV %RBX,-0xa8(%RBP) |
0x4487ad LEA (%R14,%R12,8),%RDI |
0x4487b1 LEA (,%RAX,8),%RDX |
0x4487b9 XOR %ESI,%ESI |
0x4487bb MOV %RCX,-0x60(%RBP) |
0x4487bf MOV %RAX,%RBX |
0x4487c2 VZEROUPPER |
0x4487c5 CALL 4fe630 <__intel_avx_rep_memset> |
0x4487ca MOV %RBX,%R9 |
0x4487cd MOV %RBX,%R8 |
0x4487d0 SHR $0x3,%R8 |
0x4487d4 MOV -0x38(%RBP),%RAX |
0x4487d8 MOV -0x60(%RBP),%RCX |
0x4487dc LEA (%RCX,%RAX,8),%RCX |
0x4487e0 ADD $0x38,%RCX |
0x4487e4 MOV -0xf8(%RBP),%RAX |
0x4487eb LEA (%RAX,%R12,8),%RDX |
0x4487ef XOR %ESI,%ESI |
0x4487f1 MOV -0x48(%RBP),%RAX |
0x4487f5 NOPW %CS:(%RAX,%RAX,1) |
(881) 0x448800 MOV -0x38(%RCX,%RSI,8),%RDI |
(881) 0x448805 LEA (%R12,%RSI,1),%RBX |
(881) 0x448809 MOV %RBX,(%RAX,%RDI,8) |
(881) 0x44880d MOV %RDI,-0x38(%RDX,%RSI,8) |
(881) 0x448812 MOV -0x30(%RCX,%RSI,8),%RDI |
(881) 0x448817 LEA 0x1(%R12,%RSI,1),%RBX |
(881) 0x44881c MOV %RBX,(%RAX,%RDI,8) |
(881) 0x448820 MOV %RDI,-0x30(%RDX,%RSI,8) |
(881) 0x448825 MOV -0x28(%RCX,%RSI,8),%RDI |
(881) 0x44882a LEA 0x2(%R12,%RSI,1),%RBX |
(881) 0x44882f MOV %RBX,(%RAX,%RDI,8) |
(881) 0x448833 MOV %RDI,-0x28(%RDX,%RSI,8) |
(881) 0x448838 MOV -0x20(%RCX,%RSI,8),%RDI |
(881) 0x44883d LEA 0x3(%R12,%RSI,1),%RBX |
(881) 0x448842 MOV %RBX,(%RAX,%RDI,8) |
(881) 0x448846 MOV %RDI,-0x20(%RDX,%RSI,8) |
(881) 0x44884b MOV -0x18(%RCX,%RSI,8),%RDI |
(881) 0x448850 LEA 0x4(%R12,%RSI,1),%RBX |
(881) 0x448855 MOV %RBX,(%RAX,%RDI,8) |
(881) 0x448859 MOV %RDI,-0x18(%RDX,%RSI,8) |
(881) 0x44885e MOV -0x10(%RCX,%RSI,8),%RDI |
(881) 0x448863 LEA 0x5(%R12,%RSI,1),%RBX |
(881) 0x448868 MOV %RBX,(%RAX,%RDI,8) |
(881) 0x44886c MOV %RDI,-0x10(%RDX,%RSI,8) |
(881) 0x448871 MOV -0x8(%RCX,%RSI,8),%RDI |
(881) 0x448876 LEA 0x6(%R12,%RSI,1),%RBX |
(881) 0x44887b MOV %RBX,(%RAX,%RDI,8) |
(881) 0x44887f MOV %RDI,-0x8(%RDX,%RSI,8) |
(881) 0x448884 MOV (%RCX,%RSI,8),%RDI |
(881) 0x448888 LEA (%R12,%RSI,1),%RBX |
(881) 0x44888c ADD $0x7,%RBX |
(881) 0x448890 MOV %RBX,(%RAX,%RDI,8) |
(881) 0x448894 MOV %RDI,(%RDX,%RSI,8) |
(881) 0x448898 ADD $0x8,%RSI |
(881) 0x44889c DEC %R8 |
(881) 0x44889f JNE 448800 |
0x4488a5 MOV %R9,%RDX |
0x4488a8 MOV %R9,%RCX |
0x4488ab AND $-0x8,%RCX |
0x4488af CMP %R9,%RCX |
0x4488b2 MOV -0x50(%RBP),%R10 |
0x4488b6 MOV -0x78(%RBP),%R8 |
0x4488ba MOV -0x70(%RBP),%RDI |
0x4488be MOV -0x80(%RBP),%RDX |
0x4488c2 MOV -0x68(%RBP),%R9 |
0x4488c6 MOV -0x30(%RBP),%R11 |
0x4488ca MOV -0xa8(%RBP),%RBX |
0x4488d1 JAE 44894f |
0x4488d3 MOV %RAX,%RSI |
0x4488d6 ADD %RCX,%R12 |
0x4488d9 MOV -0x38(%RBP),%RAX |
0x4488dd ADD %RCX,%RAX |
0x4488e0 MOV -0x60(%RBP),%RCX |
0x4488e4 LEA (%RCX,%RAX,8),%RAX |
0x4488e8 NOPL (%RAX,%RAX,1) |
(882) 0x4488f0 MOV (%RAX),%RCX |
(882) 0x4488f3 MOV %R12,(%RSI,%RCX,8) |
(882) 0x4488f7 MOV %RCX,(%RDX,%R12,8) |
(882) 0x4488fb INC %R12 |
(882) 0x4488fe ADD $0x8,%RAX |
(882) 0x448902 CMP %R12,%RBX |
(882) 0x448905 JNE 4488f0 |
0x448907 JMP 44894f |
0x448920 MOV -0x38(%RBP),%RAX |
0x448924 LEA (%RCX,%RAX,8),%RAX |
0x448928 MOV -0x80(%RBP),%RDX |
0x44892c MOV -0x48(%RBP),%RSI |
(880) 0x448930 MOV (%RAX),%RCX |
(880) 0x448933 MOV %R12,(%RSI,%RCX,8) |
(880) 0x448937 MOVQ $0,(%R14,%R12,8) |
(880) 0x44893f MOV %RCX,(%RDX,%R12,8) |
(880) 0x448943 INC %R12 |
(880) 0x448946 ADD $0x8,%RAX |
(880) 0x44894a CMP %R12,%RBX |
(880) 0x44894d JNE 448930 |
0x44894f MOV -0x130(%RBP),%RAX |
0x448956 MOV (%RAX,%R11,8),%RSI |
0x44895a MOV -0xc0(%RBP),%RAX |
0x448961 MOV %R11,%RCX |
0x448964 MOV (%RAX,%R11,8),%RBX |
0x448968 MOV 0x8(%RAX,%R11,8),%R12 |
0x44896d LEA (%R12,%RSI,1),%RAX |
0x448971 SUB %RBX,%RAX |
0x448974 CMP %RAX,%RSI |
0x448977 MOV -0x40(%RBP),%R11 |
0x44897b JGE 448b2f |
0x448981 MOV -0x58(%RBP),%RAX |
0x448985 MOV (%RAX),%RAX |
0x448988 MOV -0x108(%RBP),%RCX |
0x44898f MOV (%RCX,%RAX,8),%RAX |
0x448993 MOV %R12,%RCX |
0x448996 SUB %RBX,%RCX |
0x448999 CMP $0xd,%RCX |
0x44899d JB 448b00 |
0x4489a3 LEA (%R15,%RBX,8),%RDI |
0x4489a7 LEA (,%RCX,8),%RDX |
0x4489af MOV %RSI,-0x38(%RBP) |
0x4489b3 XOR %ESI,%ESI |
0x4489b5 MOV %RAX,-0x60(%RBP) |
0x4489b9 MOV %RCX,-0xa8(%RBP) |
0x4489c0 VZEROUPPER |
0x4489c3 CALL 4fe630 <__intel_avx_rep_memset> |
0x4489c8 MOV -0xa8(%RBP),%R8 |
0x4489cf MOV %R8,%R9 |
0x4489d2 SHR $0x3,%R8 |
0x4489d6 MOV -0x38(%RBP),%RAX |
0x4489da MOV -0x60(%RBP),%RCX |
0x4489de LEA (%RCX,%RAX,8),%RCX |
0x4489e2 ADD $0x38,%RCX |
0x4489e6 MOV -0xf0(%RBP),%RAX |
0x4489ed LEA (%RAX,%RBX,8),%RDX |
0x4489f1 XOR %ESI,%ESI |
0x4489f3 MOV -0x40(%RBP),%R11 |
0x4489f7 NOPW (%RAX,%RAX,1) |
(878) 0x448a00 MOV -0x38(%RCX,%RSI,8),%RDI |
(878) 0x448a05 LEA (%RBX,%RSI,1),%RAX |
(878) 0x448a09 MOV %RAX,(%R11,%RDI,8) |
(878) 0x448a0d MOV %RDI,-0x38(%RDX,%RSI,8) |
(878) 0x448a12 MOV -0x30(%RCX,%RSI,8),%RAX |
(878) 0x448a17 LEA 0x1(%RBX,%RSI,1),%RDI |
(878) 0x448a1c MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a20 MOV %RAX,-0x30(%RDX,%RSI,8) |
(878) 0x448a25 MOV -0x28(%RCX,%RSI,8),%RAX |
(878) 0x448a2a LEA 0x2(%RBX,%RSI,1),%RDI |
(878) 0x448a2f MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a33 MOV %RAX,-0x28(%RDX,%RSI,8) |
(878) 0x448a38 MOV -0x20(%RCX,%RSI,8),%RAX |
(878) 0x448a3d LEA 0x3(%RBX,%RSI,1),%RDI |
(878) 0x448a42 MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a46 MOV %RAX,-0x20(%RDX,%RSI,8) |
(878) 0x448a4b MOV -0x18(%RCX,%RSI,8),%RAX |
(878) 0x448a50 LEA 0x4(%RBX,%RSI,1),%RDI |
(878) 0x448a55 MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a59 MOV %RAX,-0x18(%RDX,%RSI,8) |
(878) 0x448a5e MOV -0x10(%RCX,%RSI,8),%RAX |
(878) 0x448a63 LEA 0x5(%RBX,%RSI,1),%RDI |
(878) 0x448a68 MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a6c MOV %RAX,-0x10(%RDX,%RSI,8) |
(878) 0x448a71 MOV -0x8(%RCX,%RSI,8),%RAX |
(878) 0x448a76 LEA 0x6(%RBX,%RSI,1),%RDI |
(878) 0x448a7b MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a7f MOV %RAX,-0x8(%RDX,%RSI,8) |
(878) 0x448a84 MOV (%RCX,%RSI,8),%RAX |
(878) 0x448a88 LEA (%RBX,%RSI,1),%RDI |
(878) 0x448a8c ADD $0x7,%RDI |
(878) 0x448a90 MOV %RDI,(%R11,%RAX,8) |
(878) 0x448a94 MOV %RAX,(%RDX,%RSI,8) |
(878) 0x448a98 ADD $0x8,%RSI |
(878) 0x448a9c DEC %R8 |
(878) 0x448a9f JNE 448a00 |
0x448aa5 MOV %R9,%RCX |
0x448aa8 MOV %R9,%RAX |
0x448aab AND $-0x8,%RAX |
0x448aaf CMP %R9,%RAX |
0x448ab2 MOV -0x50(%RBP),%R10 |
0x448ab6 MOV -0x78(%RBP),%R8 |
0x448aba MOV -0x70(%RBP),%RDI |
0x448abe MOV -0xa0(%RBP),%RDX |
0x448ac5 MOV -0x68(%RBP),%R9 |
0x448ac9 MOV -0x38(%RBP),%RCX |
0x448acd JAE 448b2f |
0x448acf ADD %RAX,%RBX |
0x448ad2 ADD %RAX,%RCX |
0x448ad5 MOV -0x60(%RBP),%RAX |
0x448ad9 LEA (%RAX,%RCX,8),%RAX |
0x448add NOPL (%RAX) |
(879) 0x448ae0 MOV (%RAX),%RCX |
(879) 0x448ae3 MOV %RBX,(%R11,%RCX,8) |
(879) 0x448ae7 MOV %RCX,(%RDX,%RBX,8) |
(879) 0x448aeb INC %RBX |
(879) 0x448aee ADD $0x8,%RAX |
(879) 0x448af2 CMP %RBX,%R12 |
(879) 0x448af5 JNE 448ae0 |
0x448af7 JMP 448b2f |
0x448b00 LEA (%RAX,%RSI,8),%RAX |
0x448b04 MOV -0xa0(%RBP),%RDX |
0x448b0b MOV -0x40(%RBP),%R11 |
0x448b0f NOP |
(877) 0x448b10 MOV (%RAX),%RCX |
(877) 0x448b13 MOV %RBX,(%R11,%RCX,8) |
(877) 0x448b17 MOVQ $0,(%R15,%RBX,8) |
(877) 0x448b1f MOV %RCX,(%RDX,%RBX,8) |
(877) 0x448b23 INC %RBX |
(877) 0x448b26 ADD $0x8,%RAX |
(877) 0x448b2a CMP %RBX,%R12 |
(877) 0x448b2d JNE 448b10 |
0x448b2f MOV -0xd8(%RBP),%RCX |
0x448b36 MOV -0x30(%RBP),%RBX |
0x448b3a MOV (%RCX,%RBX,8),%RAX |
0x448b3e MOV 0x8(%RCX,%RBX,8),%RCX |
0x448b43 CMP %RCX,%RAX |
0x448b46 MOV %R11,%R12 |
0x448b49 JGE 448ba0 |
0x448b4b MOV -0x58(%RBP),%RDX |
0x448b4f MOV (%RDX),%RDX |
0x448b52 DEC %RDX |
0x448b55 JMP 448b68 |
(876) 0x448b60 INC %RAX |
(876) 0x448b63 CMP %RCX,%RAX |
(876) 0x448b66 JGE 448ba0 |
(876) 0x448b68 MOV -0x180(%RBP),%RSI |
(876) 0x448b6f MOV (%RSI,%RAX,8),%RSI |
(876) 0x448b73 CMP %RDX,(%RDI,%RSI,8) |
(876) 0x448b77 JNE 448b60 |
(876) 0x448b79 MOV -0x90(%RBP),%RCX |
(876) 0x448b80 MOV %RBX,(%RCX,%RSI,8) |
(876) 0x448b84 MOV -0xd8(%RBP),%RCX |
(876) 0x448b8b MOV 0x8(%RCX,%RBX,8),%RCX |
(876) 0x448b90 JMP 448b60 |
0x448ba0 MOV -0xe0(%RBP),%RCX |
0x448ba7 MOV (%RCX,%RBX,8),%RAX |
0x448bab MOV 0x8(%RCX,%RBX,8),%RCX |
0x448bb0 CMP %RCX,%RAX |
0x448bb3 JGE 448c20 |
0x448bb5 MOV -0x58(%RBP),%RDX |
0x448bb9 MOV (%RDX),%RDX |
0x448bbc DEC %RDX |
0x448bbf JMP 448be8 |
(875) 0x448be0 INC %RAX |
(875) 0x448be3 CMP %RCX,%RAX |
(875) 0x448be6 JGE 448c20 |
(875) 0x448be8 MOV (%R9,%RAX,8),%RSI |
(875) 0x448bec CMP %RDX,(%R8,%RSI,8) |
(875) 0x448bf0 JNE 448be0 |
(875) 0x448bf2 MOV -0x88(%RBP),%RCX |
(875) 0x448bf9 MOV %RBX,(%RCX,%RSI,8) |
(875) 0x448bfd MOV -0xe0(%RBP),%RCX |
(875) 0x448c04 MOV 0x8(%RCX,%RBX,8),%RCX |
(875) 0x448c09 JMP 448be0 |
0x448c20 MOV -0x110(%RBP),%RAX |
0x448c27 MOV (%RAX,%RBX,8),%RCX |
0x448c2b MOV 0x8(%RAX,%RBX,8),%R9 |
0x448c30 MOV %RCX,%RAX |
0x448c33 MOV %RCX,-0x38(%RBP) |
0x448c37 LEA 0x1(%RCX),%RDX |
0x448c3b VXORPD %XMM1,%XMM1,%XMM1 |
0x448c3f VXORPD %XMM0,%XMM0,%XMM0 |
0x448c43 CMP %R9,%RDX |
0x448c46 JGE 448fc0 |
0x448c4c VXORPD %XMM1,%XMM1,%XMM1 |
0x448c50 MOV -0x80(%RBP),%R8 |
0x448c54 JMP 448c74 |
(870) 0x448c60 MOV -0x50(%RBP),%R10 |
(870) 0x448c64 MOV -0x30(%RBP),%RBX |
(870) 0x448c68 INC %RDX |
(870) 0x448c6b CMP %R9,%RDX |
(870) 0x448c6e JE 448fc0 |
(870) 0x448c74 MOV -0x170(%RBP),%RAX |
(870) 0x448c7b MOV (%RAX,%RDX,8),%R11 |
(870) 0x448c7f MOV -0x90(%RBP),%RAX |
(870) 0x448c86 CMP %RBX,(%RAX,%R11,8) |
(870) 0x448c8a JNE 448cc0 |
(870) 0x448c8c MOV -0xb8(%RBP),%RAX |
(870) 0x448c93 MOV (%RAX,%R11,8),%RDI |
(870) 0x448c97 MOV 0x8(%RAX,%R11,8),%RBX |
(870) 0x448c9c MOV %RBX,%R10 |
(870) 0x448c9f SUB %RDI,%R10 |
(870) 0x448ca2 JLE 448e44 |
(870) 0x448ca8 CMP $0x4,%R10 |
(870) 0x448cac JAE 448d00 |
(870) 0x448cae JMP 448de0 |
(870) 0x448cc0 MOV -0x158(%RBP),%RAX |
(870) 0x448cc7 CMPQ $-0x3,(%RAX,%R11,8) |
(870) 0x448ccc JE 448c68 |
(870) 0x448cce CMPQ $0x1,-0xe8(%RBP) |
(870) 0x448cd6 JE 448ced |
(870) 0x448cd8 MOV -0xc8(%RBP),%RCX |
(870) 0x448cdf MOV (%RCX,%RBX,8),%RAX |
(870) 0x448ce3 CMP (%RCX,%R11,8),%RAX |
(870) 0x448ce7 JNE 448c68 |
(870) 0x448ced VADDSD (%R13,%RDX,8),%XMM0,%XMM0 |
(870) 0x448cf4 JMP 448c68 |
(870) 0x448d00 MOV %R10,%RAX |
(870) 0x448d03 SHR $0x2,%RAX |
(870) 0x448d07 LEA 0x18(,%RDI,8),%RCX |
(870) 0x448d0f MOV -0x48(%RBP),%R12 |
(870) 0x448d13 NOPW %CS:(%RAX,%RAX,1) |
(873) 0x448d20 MOV -0x18(%R8,%RCX,1),%RSI |
(873) 0x448d25 VMOVSD -0x18(%R14,%RCX,1),%XMM8 |
(873) 0x448d2c VMOVSD (%R13,%RDX,8),%XMM3 |
(873) 0x448d33 MOV (%R12,%RSI,8),%RSI |
(873) 0x448d37 VMOVSD (%R14,%RSI,8),%XMM4 |
(873) 0x448d3d VFMADD231SD %XMM8,%XMM3,%XMM4 |
(873) 0x448d42 VMOVSD %XMM4,(%R14,%RSI,8) |
(873) 0x448d48 MOV -0x10(%R8,%RCX,1),%RSI |
(873) 0x448d4d VMOVSD -0x10(%R14,%RCX,1),%XMM4 |
(873) 0x448d54 VMOVSD (%R13,%RDX,8),%XMM5 |
(873) 0x448d5b MOV (%R12,%RSI,8),%RSI |
(873) 0x448d5f VMOVSD (%R14,%RSI,8),%XMM6 |
(873) 0x448d65 VFMADD231SD %XMM4,%XMM5,%XMM6 |
(873) 0x448d6a VMOVSD %XMM6,(%R14,%RSI,8) |
(873) 0x448d70 MOV -0x8(%R8,%RCX,1),%RSI |
(873) 0x448d75 VMOVSD -0x8(%R14,%RCX,1),%XMM6 |
(873) 0x448d7c VMOVSD (%R13,%RDX,8),%XMM7 |
(873) 0x448d83 MOV (%R12,%RSI,8),%RSI |
(873) 0x448d87 VMOVSD (%R14,%RSI,8),%XMM2 |
(873) 0x448d8d VFMADD231SD %XMM6,%XMM7,%XMM2 |
(873) 0x448d92 VMOVSD %XMM2,(%R14,%RSI,8) |
(873) 0x448d98 MOV (%R8,%RCX,1),%RSI |
(873) 0x448d9c VMOVSD (%R14,%RCX,1),%XMM2 |
(873) 0x448da2 VMULSD (%R13,%RDX,8),%XMM2,%XMM18 |
(873) 0x448daa MOV (%R12,%RSI,8),%RSI |
(873) 0x448dae VADDSD (%R14,%RSI,8),%XMM18,%XMM2 |
(873) 0x448db5 VMOVSD %XMM2,(%R14,%RSI,8) |
(873) 0x448dbb VFMADD213SD %XMM18,%XMM5,%XMM4 |
(873) 0x448dc1 VFMADD231SD %XMM8,%XMM3,%XMM4 |
(873) 0x448dc6 VFMADD231SD %XMM6,%XMM7,%XMM4 |
(873) 0x448dcb VADDSD %XMM1,%XMM4,%XMM1 |
(873) 0x448dcf VADDSD %XMM0,%XMM4,%XMM0 |
(873) 0x448dd3 ADD $0x20,%RCX |
(873) 0x448dd7 DEC %RAX |
(873) 0x448dda JNE 448d20 |
(870) 0x448de0 MOV %R10,%RAX |
(870) 0x448de3 AND $-0x4,%RAX |
(870) 0x448de7 CMP %R10,%RAX |
(870) 0x448dea JAE 448e40 |
(870) 0x448dec ADD %RAX,%RDI |
(870) 0x448def MOV -0x80(%RBP),%RCX |
(870) 0x448df3 MOV -0x48(%RBP),%RSI |
(870) 0x448df7 MOV -0x40(%RBP),%R12 |
(870) 0x448dfb NOPL (%RAX,%RAX,1) |
(874) 0x448e00 VMOVSD (%R14,%RDI,8),%XMM2 |
(874) 0x448e06 MOV (%RCX,%RDI,8),%RAX |
(874) 0x448e0a VMULSD (%R13,%RDX,8),%XMM2,%XMM18 |
(874) 0x448e12 MOV (%RSI,%RAX,8),%RAX |
(874) 0x448e16 VADDSD (%R14,%RAX,8),%XMM18,%XMM2 |
(874) 0x448e1d VMOVSD %XMM2,(%R14,%RAX,8) |
(874) 0x448e23 VADDSD %XMM1,%XMM18,%XMM1 |
(874) 0x448e29 VADDSD %XMM0,%XMM18,%XMM0 |
(874) 0x448e2f INC %RDI |
(874) 0x448e32 CMP %RDI,%RBX |
(874) 0x448e35 JNE 448e00 |
(870) 0x448e37 JMP 448e44 |
(870) 0x448e40 MOV -0x40(%RBP),%R12 |
(870) 0x448e44 MOV -0xc0(%RBP),%RAX |
(870) 0x448e4b MOV (%RAX,%R11,8),%RDI |
(870) 0x448e4f MOV 0x8(%RAX,%R11,8),%R11 |
(870) 0x448e54 MOV %R11,%R10 |
(870) 0x448e57 SUB %RDI,%R10 |
(870) 0x448e5a JLE 448c60 |
(870) 0x448e60 CMP $0x4,%R10 |
(870) 0x448e64 MOV -0xa0(%RBP),%RSI |
(870) 0x448e6b JAE 448e80 |
(870) 0x448e6d JMP 448f50 |
(870) 0x448e80 MOV %R10,%RCX |
(870) 0x448e83 SHR $0x2,%RCX |
(870) 0x448e87 LEA 0x18(,%RDI,8),%RBX |
(870) 0x448e8f NOP |
(871) 0x448e90 MOV -0x18(%RSI,%RBX,1),%RAX |
(871) 0x448e95 VMOVSD -0x18(%R15,%RBX,1),%XMM8 |
(871) 0x448e9c VMOVSD (%R13,%RDX,8),%XMM3 |
(871) 0x448ea3 MOV (%R12,%RAX,8),%RAX |
(871) 0x448ea7 VMOVSD (%R15,%RAX,8),%XMM4 |
(871) 0x448ead VFMADD231SD %XMM8,%XMM3,%XMM4 |
(871) 0x448eb2 VMOVSD %XMM4,(%R15,%RAX,8) |
(871) 0x448eb8 MOV -0x10(%RSI,%RBX,1),%RAX |
(871) 0x448ebd VMOVSD -0x10(%R15,%RBX,1),%XMM4 |
(871) 0x448ec4 VMOVSD (%R13,%RDX,8),%XMM5 |
(871) 0x448ecb MOV (%R12,%RAX,8),%RAX |
(871) 0x448ecf VMOVSD (%R15,%RAX,8),%XMM6 |
(871) 0x448ed5 VFMADD231SD %XMM4,%XMM5,%XMM6 |
(871) 0x448eda VMOVSD %XMM6,(%R15,%RAX,8) |
(871) 0x448ee0 MOV -0x8(%RSI,%RBX,1),%RAX |
(871) 0x448ee5 VMOVSD -0x8(%R15,%RBX,1),%XMM6 |
(871) 0x448eec VMOVSD (%R13,%RDX,8),%XMM7 |
(871) 0x448ef3 MOV (%R12,%RAX,8),%RAX |
(871) 0x448ef7 VMOVSD (%R15,%RAX,8),%XMM2 |
(871) 0x448efd VFMADD231SD %XMM6,%XMM7,%XMM2 |
(871) 0x448f02 VMOVSD %XMM2,(%R15,%RAX,8) |
(871) 0x448f08 MOV (%RSI,%RBX,1),%RAX |
(871) 0x448f0c VMOVSD (%R15,%RBX,1),%XMM2 |
(871) 0x448f12 VMULSD (%R13,%RDX,8),%XMM2,%XMM18 |
(871) 0x448f1a MOV (%R12,%RAX,8),%RAX |
(871) 0x448f1e VADDSD (%R15,%RAX,8),%XMM18,%XMM2 |
(871) 0x448f25 VMOVSD %XMM2,(%R15,%RAX,8) |
(871) 0x448f2b VFMADD213SD %XMM18,%XMM5,%XMM4 |
(871) 0x448f31 VFMADD231SD %XMM8,%XMM3,%XMM4 |
(871) 0x448f36 VFMADD231SD %XMM6,%XMM7,%XMM4 |
(871) 0x448f3b VADDSD %XMM1,%XMM4,%XMM1 |
(871) 0x448f3f VADDSD %XMM0,%XMM4,%XMM0 |
(871) 0x448f43 ADD $0x20,%RBX |
(871) 0x448f47 DEC %RCX |
(871) 0x448f4a JNE 448e90 |
(870) 0x448f50 MOV %R10,%RCX |
(870) 0x448f53 AND $-0x4,%RCX |
(870) 0x448f57 CMP %R10,%RCX |
(870) 0x448f5a JAE 448c60 |
(870) 0x448f60 ADD %RCX,%RDI |
(870) 0x448f63 MOV -0x50(%RBP),%R10 |
(870) 0x448f67 MOV -0x30(%RBP),%RBX |
(870) 0x448f6b NOPL (%RAX,%RAX,1) |
(872) 0x448f70 VMOVSD (%R15,%RDI,8),%XMM2 |
(872) 0x448f76 MOV (%RSI,%RDI,8),%RAX |
(872) 0x448f7a VMULSD (%R13,%RDX,8),%XMM2,%XMM18 |
(872) 0x448f82 MOV (%R12,%RAX,8),%RAX |
(872) 0x448f86 VADDSD (%R15,%RAX,8),%XMM18,%XMM2 |
(872) 0x448f8d VMOVSD %XMM2,(%R15,%RAX,8) |
(872) 0x448f93 VADDSD %XMM1,%XMM18,%XMM1 |
(872) 0x448f99 VADDSD %XMM0,%XMM18,%XMM0 |
(872) 0x448f9f INC %RDI |
(872) 0x448fa2 CMP %RDI,%R11 |
(872) 0x448fa5 JNE 448f70 |
(870) 0x448fa7 JMP 448c68 |
0x448fc0 MOV -0x118(%RBP),%RAX |
0x448fc7 MOV (%RAX,%RBX,8),%R12 |
0x448fcb MOV 0x8(%RAX,%RBX,8),%R9 |
0x448fd0 CMP %R9,%R12 |
0x448fd3 JGE 449160 |
0x448fd9 MOV -0xd0(%RBP),%R11 |
0x448fe0 MOV -0x40(%RBP),%R8 |
0x448fe4 JMP 449016 |
(868) 0x449000 VADDSD (%RDI,%R12,8),%XMM0,%XMM0 |
(868) 0x449006 INC %R12 |
(868) 0x449009 CMP %R9,%R12 |
(868) 0x44900c MOV -0x30(%RBP),%RBX |
(868) 0x449010 JE 449160 |
(868) 0x449016 MOV -0x178(%RBP),%RAX |
(868) 0x44901d LEA (%RAX,%R12,8),%RAX |
(868) 0x449021 CMPQ $0,-0x188(%RBP) |
(868) 0x449029 JE 449039 |
(868) 0x44902b MOV (%RAX),%RAX |
(868) 0x44902e MOV -0x160(%RBP),%RDX |
(868) 0x449035 LEA (%RDX,%RAX,8),%RAX |
(868) 0x449039 MOV (%RAX),%RSI |
(868) 0x44903c TEST %RSI,%RSI |
(868) 0x44903f JS 449100 |
(868) 0x449045 MOV -0x88(%RBP),%RAX |
(868) 0x44904c CMP %RBX,(%RAX,%RSI,8) |
(868) 0x449050 JNE 449100 |
(868) 0x449056 MOV -0x150(%RBP),%RAX |
(868) 0x44905d MOV 0x8(%RAX,%RSI,8),%RAX |
(868) 0x449062 TEST %RAX,%RAX |
(868) 0x449065 JLE 449006 |
(868) 0x449067 MOV -0x140(%RBP),%RDX |
(868) 0x44906e MOV (%RDX,%RSI,8),%RSI |
(868) 0x449072 ADD %RSI,%RAX |
(868) 0x449075 MOV -0x58(%RBP),%RCX |
(868) 0x449079 MOV (%RCX),%RDI |
(868) 0x44907c MOV -0x148(%RBP),%RDX |
(868) 0x449083 MOV (%RDX,%RDI,8),%RDI |
(868) 0x449087 MOV -0x48(%RBP),%RCX |
(868) 0x44908b NOPL (%RAX,%RAX,1) |
(869) 0x449090 VMOVSD (%R10,%RSI,8),%XMM2 |
(869) 0x449096 MOV (%RDI,%RSI,8),%RBX |
(869) 0x44909a VMULSD (%R11,%R12,8),%XMM2,%XMM18 |
(869) 0x4490a1 TEST %RBX,%RBX |
(869) 0x4490a4 LEA (%R8,%RBX,8),%RDX |
(869) 0x4490a8 NOT %RBX |
(869) 0x4490ab LEA (%RCX,%RBX,8),%RBX |
(869) 0x4490af CMOVNS %RDX,%RBX |
(869) 0x4490b3 MOV %R15,%RDX |
(869) 0x4490b6 CMOVS %R14,%RDX |
(869) 0x4490ba MOV (%RBX),%RBX |
(869) 0x4490bd VADDSD (%RDX,%RBX,8),%XMM18,%XMM2 |
(869) 0x4490c4 VMOVSD %XMM2,(%RDX,%RBX,8) |
(869) 0x4490c9 VADDSD %XMM1,%XMM18,%XMM1 |
(869) 0x4490cf VADDSD %XMM0,%XMM18,%XMM0 |
(869) 0x4490d5 INC %RSI |
(869) 0x4490d8 CMP %RAX,%RSI |
(869) 0x4490db JL 449090 |
(868) 0x4490dd JMP 449006 |
(868) 0x449100 MOV -0x168(%RBP),%RAX |
(868) 0x449107 CMPQ $-0x3,(%RAX,%RSI,8) |
(868) 0x44910c JE 449006 |
(868) 0x449112 CMPQ $0x1,-0xe8(%RBP) |
(868) 0x44911a MOV -0xd0(%RBP),%RDI |
(868) 0x449121 JE 449000 |
(868) 0x449127 MOV -0x138(%RBP),%RAX |
(868) 0x44912e MOV (%RAX,%RSI,8),%RAX |
(868) 0x449132 MOV -0xc8(%RBP),%RDX |
(868) 0x449139 CMP (%RDX,%RBX,8),%RAX |
(868) 0x44913d JE 449000 |
(868) 0x449143 JMP 449006 |
0x449160 MOV -0x38(%RBP),%RAX |
0x449164 VMULSD (%R13,%RAX,8),%XMM1,%XMM1 |
0x44916b VUCOMISD %XMM17,%XMM1 |
0x449171 JE 44917f |
0x449173 VXORPD %XMM16,%XMM0,%XMM0 |
0x449179 VDIVSD %XMM1,%XMM0,%XMM18 |
0x44917f MOV -0xb8(%RBP),%RAX |
0x449186 MOV (%RAX,%RBX,8),%R8 |
0x44918a MOV 0x8(%RAX,%RBX,8),%RAX |
0x44918f MOV %RAX,%RSI |
0x449192 SUB %R8,%RSI |
0x449195 MOV -0x68(%RBP),%R9 |
0x449199 MOV -0x40(%RBP),%R12 |
0x44919d JLE 449205 |
0x44919f MOV %RSI,%RCX |
0x4491a2 AND $-0x4,%RCX |
0x4491a6 JE 4491e0 |
0x4491a8 LEA -0x1(%RCX),%RDI |
0x4491ac VBROADCASTSD %XMM18,%YMM0 |
0x4491b2 LEA (%R14,%R8,8),%RBX |
0x4491b6 XOR %EDX,%EDX |
0x4491b8 NOPL (%RAX,%RAX,1) |
(867) 0x4491c0 VMULPD (%RBX,%RDX,8),%YMM0,%YMM1 |
(867) 0x4491c5 VMOVUPD %YMM1,(%RBX,%RDX,8) |
(867) 0x4491ca ADD $0x4,%RDX |
(867) 0x4491ce CMP %RDI,%RDX |
(867) 0x4491d1 JBE 4491c0 |
0x4491d3 CMP %RCX,%RSI |
0x4491d6 MOV -0x30(%RBP),%RBX |
0x4491da JNE 4491e2 |
0x4491dc JMP 449205 |
0x4491e0 XOR %ECX,%ECX |
0x4491e2 ADD %R8,%RCX |
0x4491e5 NOPW %CS:(%RAX,%RAX,1) |
(866) 0x4491f0 VMULSD (%R14,%RCX,8),%XMM18,%XMM0 |
(866) 0x4491f7 VMOVSD %XMM0,(%R14,%RCX,8) |
(866) 0x4491fd INC %RCX |
(866) 0x449200 CMP %RCX,%RAX |
(866) 0x449203 JNE 4491f0 |
0x449205 MOV -0xc0(%RBP),%RAX |
0x44920c MOV (%RAX,%RBX,8),%R8 |
0x449210 MOV 0x8(%RAX,%RBX,8),%RAX |
0x449215 MOV %RAX,%RSI |
0x449218 SUB %R8,%RSI |
0x44921b JLE 448720 |
0x449221 MOV %RSI,%RCX |
0x449224 AND $-0x4,%RCX |
0x449228 JE 449260 |
0x44922a LEA -0x1(%RCX),%RDI |
0x44922e VBROADCASTSD %XMM18,%YMM0 |
0x449234 LEA (%R15,%R8,8),%RBX |
0x449238 XOR %EDX,%EDX |
0x44923a NOPW (%RAX,%RAX,1) |
(865) 0x449240 VMULPD (%RBX,%RDX,8),%YMM0,%YMM1 |
(865) 0x449245 VMOVUPD %YMM1,(%RBX,%RDX,8) |
(865) 0x44924a ADD $0x4,%RDX |
(865) 0x44924e CMP %RDI,%RDX |
(865) 0x449251 JBE 449240 |
0x449253 CMP %RCX,%RSI |
0x449256 JE 448720 |
0x44925c JMP 449262 |
0x449260 XOR %ECX,%ECX |
0x449262 ADD %R8,%RCX |
0x449265 NOPW %CS:(%RAX,%RAX,1) |
(864) 0x449270 VMULSD (%R15,%RCX,8),%XMM18,%XMM0 |
(864) 0x449277 VMOVSD %XMM0,(%R15,%RCX,8) |
(864) 0x44927d INC %RCX |
(864) 0x449280 CMP %RCX,%RAX |
(864) 0x449283 JNE 449270 |
0x449285 JMP 448720 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 1747 - 1876 |
-------------------------------------------------------------------------------- |
1747: if (n_fine) |
[...] |
1774: for (i=thread_start; i < thread_stop; i++) |
1775: { |
1776: i1 = pass_array[i]; |
1777: sum_C = 0; |
1778: sum_N = 0; |
1779: j_start = P_diag_start[i1]; |
1780: j_end = j_start+P_diag_i[i1+1]-P_diag_i[i1]; |
1781: cnt = P_diag_i[i1]; |
1782: for (j=j_start; j < j_end; j++) |
1783: { |
1784: k1 = P_diag_pass[pass][j]; |
1785: tmp_array[k1] = cnt; |
1786: P_diag_data[cnt] = 0; |
1787: P_diag_j[cnt++] = k1; |
1788: } |
1789: j_start = P_offd_start[i1]; |
1790: j_end = j_start+P_offd_i[i1+1]-P_offd_i[i1]; |
1791: cnt_offd = P_offd_i[i1]; |
1792: for (j=j_start; j < j_end; j++) |
1793: { |
1794: k1 = P_offd_pass[pass][j]; |
1795: tmp_array_offd[k1] = cnt_offd; |
1796: P_offd_data[cnt_offd] = 0; |
1797: P_offd_j[cnt_offd++] = k1; |
1798: } |
1799: for (j=S_diag_i[i1]; j < S_diag_i[i1+1]; j++) |
1800: { |
1801: j1 = S_diag_j[j]; |
1802: if (assigned[j1] == pass-1) |
1803: tmp_marker[j1] = i1; |
1804: } |
1805: for (j=S_offd_i[i1]; j < S_offd_i[i1+1]; j++) |
1806: { |
1807: j1 = S_offd_j[j]; |
1808: if (assigned_offd[j1] == pass-1) |
1809: tmp_marker_offd[j1] = i1; |
1810: } |
1811: for (j=A_diag_i[i1]+1; j < A_diag_i[i1+1]; j++) |
1812: { |
1813: j1 = A_diag_j[j]; |
1814: if (tmp_marker[j1] == i1) |
1815: { |
1816: for (k=P_diag_i[j1]; k < P_diag_i[j1+1]; k++) |
1817: { |
1818: k1 = P_diag_j[k]; |
1819: alfa = A_diag_data[j]*P_diag_data[k]; |
1820: P_diag_data[tmp_array[k1]] += alfa; |
1821: sum_C += alfa; |
1822: sum_N += alfa; |
1823: } |
1824: for (k=P_offd_i[j1]; k < P_offd_i[j1+1]; k++) |
1825: { |
1826: k1 = P_offd_j[k]; |
1827: alfa = A_diag_data[j]*P_offd_data[k]; |
1828: P_offd_data[tmp_array_offd[k1]] += alfa; |
1829: sum_C += alfa; |
1830: sum_N += alfa; |
1831: } |
1832: } |
1833: else |
1834: { |
1835: if (CF_marker[j1] != -3 && |
1836: (num_functions == 1 || dof_func[i1] == dof_func[j1])) |
1837: sum_N += A_diag_data[j]; |
1838: } |
1839: } |
1840: for (j=A_offd_i[i1]; j < A_offd_i[i1+1]; j++) |
1841: { |
1842: if (col_offd_S_to_A) |
1843: j1 = map_A_to_S[A_offd_j[j]]; |
1844: else |
1845: j1 = A_offd_j[j]; |
1846: |
1847: if (j1 > -1 && tmp_marker_offd[j1] == i1) |
1848: { |
1849: j_start = Pext_start[j1]; |
1850: j_end = j_start+Pext_i[j1+1]; |
1851: for (k=j_start; k < j_end; k++) |
1852: { |
1853: k1 = Pext_pass[pass][k]; |
1854: alfa = A_offd_data[j]*Pext_data[k]; |
1855: if (k1 < 0) |
1856: P_diag_data[tmp_array[-k1-1]] += alfa; |
1857: else |
1858: P_offd_data[tmp_array_offd[k1]] += alfa; |
1859: sum_C += alfa; |
1860: sum_N += alfa; |
1861: } |
1862: } |
1863: else |
1864: { |
1865: if (CF_marker_offd[j1] != -3 && |
1866: (num_functions == 1 || dof_func_offd[j1] == dof_func[i1])) |
1867: sum_N += A_offd_data[j]; |
1868: } |
1869: } |
1870: diagonal = A_diag_data[A_diag_i[i1]]; |
1871: if (sum_C*diagonal) alfa = -sum_N/(sum_C*diagonal); |
1872: |
1873: for (j=P_diag_i[i1]; j < P_diag_i[i1+1]; j++) |
1874: P_diag_data[j] *= alfa; |
1875: for (j=P_offd_i[i1]; j < P_offd_i[i1+1]; j++) |
1876: P_offd_data[j] *= alfa; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGBuildMultipass | par_multi_interp.c:1737 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:737 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.01 |
CQA speedup if FP arith vectorized | 3.67 |
CQA speedup if fully vectorized | 7.93 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.35 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source | par_multi_interp.c:1747-1876 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 58.00 |
CQA cycles if no scalar integer | 19.25 |
CQA cycles if FP arith vectorized | 15.78 |
CQA cycles if fully vectorized | 7.32 |
Front-end cycles | 58.00 |
DIV/SQRT cycles | 22.50 |
P0 cycles | 22.42 |
P1 cycles | 43.00 |
P2 cycles | 43.00 |
P3 cycles | 11.00 |
P4 cycles | 22.58 |
P5 cycles | 22.50 |
P6 cycles | 11.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 56.30 - 56.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 223.00 |
Nb uops | 231.00 |
Nb loads | 86.00 |
Nb stores | 9.00 |
Nb stack references | 29.00 |
FLOP/cycle | 0.03 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
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 | 13.10 |
Bytes prefetched | 0.00 |
Bytes loaded | 688.00 |
Bytes stored | 72.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 13.33 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 25.00 |
Vector-efficiency ratio all | 14.17 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 15.63 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.01 |
CQA speedup if FP arith vectorized | 3.67 |
CQA speedup if fully vectorized | 7.93 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.35 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source | par_multi_interp.c:1747-1876 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 58.00 |
CQA cycles if no scalar integer | 19.25 |
CQA cycles if FP arith vectorized | 15.78 |
CQA cycles if fully vectorized | 7.32 |
Front-end cycles | 58.00 |
DIV/SQRT cycles | 22.50 |
P0 cycles | 22.42 |
P1 cycles | 43.00 |
P2 cycles | 43.00 |
P3 cycles | 11.00 |
P4 cycles | 22.58 |
P5 cycles | 22.50 |
P6 cycles | 11.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 56.30 - 56.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 223.00 |
Nb uops | 231.00 |
Nb loads | 86.00 |
Nb stores | 9.00 |
Nb stack references | 29.00 |
FLOP/cycle | 0.03 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
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 | 13.10 |
Bytes prefetched | 0.00 |
Bytes loaded | 688.00 |
Bytes stored | 72.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 13.33 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 25.00 |
Vector-efficiency ratio all | 14.17 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 12.50 |
Vector-efficiency ratio other | 15.63 |
Path / |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source file and lines | par_multi_interp.c:1747-1876 |
Module | exec |
nb instructions | 223 |
nb uops | 231 |
loop length | 950 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 29 |
micro-operation queue | 58.00 cycles |
front end | 58.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 22.50 | 22.42 | 43.00 | 43.00 | 11.00 | 22.58 | 22.50 | 11.00 |
cycles | 22.50 | 22.42 | 43.00 | 43.00 | 11.00 | 22.58 | 22.50 | 11.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 56.30-56.31 |
Stall cycles | 0.00 |
Front-end | 58.00 |
Dispatch | 43.00 |
DIV/SQRT | 4.00 |
Overall L1 | 58.00 |
all | 5% |
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 | 11% |
all | 44% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 57% |
all | 13% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 25% |
all | 13% |
load | 12% |
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 | 13% |
all | 18% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 19% |
all | 14% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0xb0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x98(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 4492a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x120(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RDX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%R11,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RBX,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R11,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JGE 44894f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x100(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0xd,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 448920 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R14,%R12,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RAX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4fe630 <__intel_avx_rep_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R12,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 44894f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 44894f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x130(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX,%R11,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R12,%RSI,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 448b2f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0xd,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 448b00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R15,%RBX,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RCX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4fe630 <__intel_avx_rep_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xa8(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 448b2f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 448b2f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA (%RAX,%RSI,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0xd8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R11,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 448ba0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 448b68 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0xe0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448c20 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 448be8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RCX),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448fc0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x80(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 448c74 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x118(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R9,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 449160 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 449016 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%R13,%RAX,8),%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM17,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 44917f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM16,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VDIVSD %XMM1,%XMM0,%XMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 449205 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4491e0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM18,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%R14,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4491e2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 449205 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0xc0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 448720 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449260 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM18,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%R15,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448720 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 449262 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 448720 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source file and lines | par_multi_interp.c:1747-1876 |
Module | exec |
nb instructions | 223 |
nb uops | 231 |
loop length | 950 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 29 |
micro-operation queue | 58.00 cycles |
front end | 58.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 22.50 | 22.42 | 43.00 | 43.00 | 11.00 | 22.58 | 22.50 | 11.00 |
cycles | 22.50 | 22.42 | 43.00 | 43.00 | 11.00 | 22.58 | 22.50 | 11.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 56.30-56.31 |
Stall cycles | 0.00 |
Front-end | 58.00 |
Dispatch | 43.00 |
DIV/SQRT | 4.00 |
Overall L1 | 58.00 |
all | 5% |
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 | 11% |
all | 44% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 57% |
all | 13% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 25% |
all | 13% |
load | 12% |
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 | 13% |
all | 18% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 19% |
all | 14% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0xb0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP -0x98(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 4492a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x120(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV (%RAX,%RDX,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%R11,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RBX,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R11,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JGE 44894f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x100(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0xd,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 448920 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R14,%R12,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RAX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4fe630 <__intel_avx_rep_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R12,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 44894f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 44894f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x130(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R11,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX,%R11,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%R11,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R12,%RSI,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SUB %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 448b2f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0xd,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 448b00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R15,%RBX,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RCX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RSI,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4fe630 <__intel_avx_rep_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xa8(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R9,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 448b2f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RCX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 448b2f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA (%RAX,%RSI,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0xd8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R11,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 448ba0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 448b68 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0xe0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448c20 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
DEC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 448be8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%RCX),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 448fc0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x80(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 448c74 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x118(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R9,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 449160 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 449016 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%R13,%RAX,8),%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VUCOMISD %XMM17,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 44917f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD %XMM16,%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 1 | 0.33 |
VDIVSD %XMM1,%XMM0,%XMM18 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
MOV -0xb8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x68(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 449205 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4491e0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM18,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%R14,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 4491e2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 449205 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0xc0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 448720 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 449260 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%RCX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM18,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
LEA (%R15,%R8,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %RCX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 448720 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 449262 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 448720 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |