Loop Id: 847 | Module: exec | Source: par_multi_interp.c:1747-1876 [...] | Coverage: 0.46% |
---|
Loop Id: 847 | Module: exec | Source: par_multi_interp.c:1747-1876 [...] | Coverage: 0.46% |
---|
0x442d00 MOV -0xb0(%RBP),%RDX |
0x442d07 INC %RDX |
0x442d0a CMP -0x70(%RBP),%RDX |
0x442d0e JGE 4437d9 |
0x442d14 MOV -0x130(%RBP),%RAX |
0x442d1b MOV %RDX,-0xb0(%RBP) |
0x442d22 MOV (%RAX,%RDX,8),%RCX |
0x442d26 MOV -0x138(%RBP),%RAX |
0x442d2d MOV (%RAX,%RCX,8),%RBX |
0x442d31 MOV -0xb8(%RBP),%RAX |
0x442d38 MOV (%RAX,%RCX,8),%R12 |
0x442d3c MOV %RCX,-0x30(%RBP) |
0x442d40 MOV 0x8(%RAX,%RCX,8),%RSI |
0x442d45 LEA (%RSI,%RBX,1),%RAX |
0x442d49 SUB %R12,%RAX |
0x442d4c CMP %RAX,%RBX |
0x442d4f JGE 442f1f |
0x442d55 MOV -0x50(%RBP),%RAX |
0x442d59 MOV (%RAX),%RCX |
0x442d5c MOV %RSI,%RAX |
0x442d5f SUB %R12,%RAX |
0x442d62 CMP $0xd,%RAX |
0x442d66 JB 442ee0 |
0x442d6c MOV %RSI,-0xa8(%RBP) |
0x442d73 VMOVUPD %XMM10,-0x90(%RBP) |
0x442d7b LEA (%R14,%R12,8),%RDI |
0x442d7f LEA (,%RAX,8),%RDX |
0x442d87 XOR %ESI,%ESI |
0x442d89 MOV %RBX,-0xa0(%RBP) |
0x442d90 MOV %RAX,%RBX |
0x442d93 MOV %RCX,-0x98(%RBP) |
0x442d9a VZEROUPPER |
0x442d9d CALL 4e6020 <_intel_fast_memset> |
0x442da2 MOV -0xa0(%RBP),%R11 |
0x442da9 MOV -0xc8(%RBP),%RAX |
0x442db0 MOV -0x98(%RBP),%RCX |
0x442db7 MOV (%RAX,%RCX,8),%R8 |
0x442dbb MOV %RBX,%R10 |
0x442dbe MOV %RBX,%R9 |
0x442dc1 SHR $0x3,%R9 |
0x442dc5 LEA (%R8,%R11,8),%RDX |
0x442dc9 ADD $0x38,%RDX |
0x442dcd MOV -0x108(%RBP),%RAX |
0x442dd4 LEA (%RAX,%R12,8),%RSI |
0x442dd8 XOR %EDI,%EDI |
0x442dda MOV -0x40(%RBP),%RCX |
0x442dde XCHG %AX,%AX |
(865) 0x442de0 MOV -0x38(%RDX,%RDI,8),%RAX |
(865) 0x442de5 LEA (%R12,%RDI,1),%RBX |
(865) 0x442de9 MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442ded MOV %RAX,-0x38(%RSI,%RDI,8) |
(865) 0x442df2 MOV -0x30(%RDX,%RDI,8),%RAX |
(865) 0x442df7 LEA 0x1(%R12,%RDI,1),%RBX |
(865) 0x442dfc MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e00 MOV %RAX,-0x30(%RSI,%RDI,8) |
(865) 0x442e05 MOV -0x28(%RDX,%RDI,8),%RAX |
(865) 0x442e0a LEA 0x2(%R12,%RDI,1),%RBX |
(865) 0x442e0f MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e13 MOV %RAX,-0x28(%RSI,%RDI,8) |
(865) 0x442e18 MOV -0x20(%RDX,%RDI,8),%RAX |
(865) 0x442e1d LEA 0x3(%R12,%RDI,1),%RBX |
(865) 0x442e22 MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e26 MOV %RAX,-0x20(%RSI,%RDI,8) |
(865) 0x442e2b MOV -0x18(%RDX,%RDI,8),%RAX |
(865) 0x442e30 LEA 0x4(%R12,%RDI,1),%RBX |
(865) 0x442e35 MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e39 MOV %RAX,-0x18(%RSI,%RDI,8) |
(865) 0x442e3e MOV -0x10(%RDX,%RDI,8),%RAX |
(865) 0x442e43 LEA 0x5(%R12,%RDI,1),%RBX |
(865) 0x442e48 MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e4c MOV %RAX,-0x10(%RSI,%RDI,8) |
(865) 0x442e51 MOV -0x8(%RDX,%RDI,8),%RAX |
(865) 0x442e56 LEA 0x6(%R12,%RDI,1),%RBX |
(865) 0x442e5b MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e5f MOV %RAX,-0x8(%RSI,%RDI,8) |
(865) 0x442e64 MOV (%RDX,%RDI,8),%RAX |
(865) 0x442e68 LEA (%R12,%RDI,1),%RBX |
(865) 0x442e6c ADD $0x7,%RBX |
(865) 0x442e70 MOV %RBX,(%RCX,%RAX,8) |
(865) 0x442e74 MOV %RAX,(%RSI,%RDI,8) |
(865) 0x442e78 ADD $0x8,%RDI |
(865) 0x442e7c DEC %R9 |
(865) 0x442e7f JNE 442de0 |
0x442e85 MOV %R10,%RDX |
0x442e88 MOV %R10,%RAX |
0x442e8b AND $-0x8,%RAX |
0x442e8f CMP %R10,%RAX |
0x442e92 MOV -0x48(%RBP),%R10 |
0x442e96 MOV -0x58(%RBP),%RDX |
0x442e9a VXORPD %XMM9,%XMM9,%XMM9 |
0x442e9f VMOVUPD -0x90(%RBP),%XMM10 |
0x442ea7 MOV -0xa8(%RBP),%RDI |
0x442eae JAE 442f1f |
0x442eb0 MOV %RCX,%RSI |
0x442eb3 ADD %RAX,%R12 |
0x442eb6 ADD %RAX,%R11 |
0x442eb9 LEA (%R8,%R11,8),%RAX |
0x442ebd NOPL (%RAX) |
(866) 0x442ec0 MOV (%RAX),%RCX |
(866) 0x442ec3 MOV %R12,(%RSI,%RCX,8) |
(866) 0x442ec7 MOV %RCX,(%RDX,%R12,8) |
(866) 0x442ecb INC %R12 |
(866) 0x442ece ADD $0x8,%RAX |
(866) 0x442ed2 CMP %R12,%RDI |
(866) 0x442ed5 JNE 442ec0 |
0x442ed7 JMP 442f1f |
0x442ee0 SAL $0x3,%RBX |
0x442ee4 MOV -0xc8(%RBP),%RAX |
0x442eeb ADD (%RAX,%RCX,8),%RBX |
0x442eef MOV -0x58(%RBP),%RCX |
0x442ef3 MOV -0x40(%RBP),%RDX |
0x442ef7 NOPW (%RAX,%RAX,1) |
(864) 0x442f00 MOV (%RBX),%RAX |
(864) 0x442f03 MOV %R12,(%RDX,%RAX,8) |
(864) 0x442f07 MOVQ $0,(%R14,%R12,8) |
(864) 0x442f0f MOV %RAX,(%RCX,%R12,8) |
(864) 0x442f13 INC %R12 |
(864) 0x442f16 ADD $0x8,%RBX |
(864) 0x442f1a CMP %R12,%RSI |
(864) 0x442f1d JNE 442f00 |
0x442f1f MOV -0x140(%RBP),%RAX |
0x442f26 MOV -0x30(%RBP),%RCX |
0x442f2a MOV (%RAX,%RCX,8),%R12 |
0x442f2e MOV -0xc0(%RBP),%RAX |
0x442f35 MOV (%RAX,%RCX,8),%RBX |
0x442f39 MOV 0x8(%RAX,%RCX,8),%RDX |
0x442f3e LEA (%RDX,%R12,1),%RAX |
0x442f42 SUB %RBX,%RAX |
0x442f45 CMP %RAX,%R12 |
0x442f48 MOV -0x38(%RBP),%R11 |
0x442f4c JGE 443120 |
0x442f52 MOV -0x50(%RBP),%RAX |
0x442f56 MOV (%RAX),%RCX |
0x442f59 MOV %RDX,%RAX |
0x442f5c SUB %RBX,%RAX |
0x442f5f CMP $0xd,%RAX |
0x442f63 JB 4430e0 |
0x442f69 MOV %RDX,-0xa8(%RBP) |
0x442f70 VMOVUPD %XMM10,-0x90(%RBP) |
0x442f78 LEA (%R15,%RBX,8),%RDI |
0x442f7c LEA (,%RAX,8),%RDX |
0x442f84 XOR %ESI,%ESI |
0x442f86 MOV %RAX,-0xa0(%RBP) |
0x442f8d MOV %RCX,-0x98(%RBP) |
0x442f94 VZEROUPPER |
0x442f97 CALL 4e6020 <_intel_fast_memset> |
0x442f9c MOV -0xd0(%RBP),%RAX |
0x442fa3 MOV -0x98(%RBP),%RCX |
0x442faa MOV (%RAX,%RCX,8),%R8 |
0x442fae MOV -0xa0(%RBP),%R9 |
0x442fb5 MOV %R9,%R10 |
0x442fb8 SHR $0x3,%R9 |
0x442fbc LEA (%R8,%R12,8),%RDX |
0x442fc0 ADD $0x38,%RDX |
0x442fc4 MOV -0x100(%RBP),%RAX |
0x442fcb LEA (%RAX,%RBX,8),%RSI |
0x442fcf XOR %EDI,%EDI |
0x442fd1 MOV -0x38(%RBP),%R11 |
0x442fd5 NOPW %CS:(%RAX,%RAX,1) |
(862) 0x442fe0 MOV -0x38(%RDX,%RDI,8),%RAX |
(862) 0x442fe5 LEA (%RBX,%RDI,1),%RCX |
(862) 0x442fe9 MOV %RCX,(%R11,%RAX,8) |
(862) 0x442fed MOV %RAX,-0x38(%RSI,%RDI,8) |
(862) 0x442ff2 MOV -0x30(%RDX,%RDI,8),%RAX |
(862) 0x442ff7 LEA 0x1(%RBX,%RDI,1),%RCX |
(862) 0x442ffc MOV %RCX,(%R11,%RAX,8) |
(862) 0x443000 MOV %RAX,-0x30(%RSI,%RDI,8) |
(862) 0x443005 MOV -0x28(%RDX,%RDI,8),%RAX |
(862) 0x44300a LEA 0x2(%RBX,%RDI,1),%RCX |
(862) 0x44300f MOV %RCX,(%R11,%RAX,8) |
(862) 0x443013 MOV %RAX,-0x28(%RSI,%RDI,8) |
(862) 0x443018 MOV -0x20(%RDX,%RDI,8),%RAX |
(862) 0x44301d LEA 0x3(%RBX,%RDI,1),%RCX |
(862) 0x443022 MOV %RCX,(%R11,%RAX,8) |
(862) 0x443026 MOV %RAX,-0x20(%RSI,%RDI,8) |
(862) 0x44302b MOV -0x18(%RDX,%RDI,8),%RAX |
(862) 0x443030 LEA 0x4(%RBX,%RDI,1),%RCX |
(862) 0x443035 MOV %RCX,(%R11,%RAX,8) |
(862) 0x443039 MOV %RAX,-0x18(%RSI,%RDI,8) |
(862) 0x44303e MOV -0x10(%RDX,%RDI,8),%RAX |
(862) 0x443043 LEA 0x5(%RBX,%RDI,1),%RCX |
(862) 0x443048 MOV %RCX,(%R11,%RAX,8) |
(862) 0x44304c MOV %RAX,-0x10(%RSI,%RDI,8) |
(862) 0x443051 MOV -0x8(%RDX,%RDI,8),%RAX |
(862) 0x443056 LEA 0x6(%RBX,%RDI,1),%RCX |
(862) 0x44305b MOV %RCX,(%R11,%RAX,8) |
(862) 0x44305f MOV %RAX,-0x8(%RSI,%RDI,8) |
(862) 0x443064 MOV (%RDX,%RDI,8),%RAX |
(862) 0x443068 LEA (%RBX,%RDI,1),%RCX |
(862) 0x44306c ADD $0x7,%RCX |
(862) 0x443070 MOV %RCX,(%R11,%RAX,8) |
(862) 0x443074 MOV %RAX,(%RSI,%RDI,8) |
(862) 0x443078 ADD $0x8,%RDI |
(862) 0x44307c DEC %R9 |
(862) 0x44307f JNE 442fe0 |
0x443085 MOV %R10,%RAX |
0x443088 MOV %R10,%RCX |
0x44308b AND $-0x8,%RCX |
0x44308f CMP %R10,%RCX |
0x443092 MOV -0x48(%RBP),%R10 |
0x443096 MOV -0x78(%RBP),%RDX |
0x44309a VXORPD %XMM9,%XMM9,%XMM9 |
0x44309f VMOVUPD -0x90(%RBP),%XMM10 |
0x4430a7 MOV -0xa8(%RBP),%RSI |
0x4430ae JAE 443120 |
0x4430b0 ADD %RCX,%RBX |
0x4430b3 ADD %RCX,%R12 |
0x4430b6 LEA (%R8,%R12,8),%RAX |
0x4430ba NOPW (%RAX,%RAX,1) |
(863) 0x4430c0 MOV (%RAX),%RCX |
(863) 0x4430c3 MOV %RBX,(%R11,%RCX,8) |
(863) 0x4430c7 MOV %RCX,(%RDX,%RBX,8) |
(863) 0x4430cb INC %RBX |
(863) 0x4430ce ADD $0x8,%RAX |
(863) 0x4430d2 CMP %RBX,%RSI |
(863) 0x4430d5 JNE 4430c0 |
0x4430d7 JMP 443120 |
0x4430e0 SAL $0x3,%R12 |
0x4430e4 MOV -0xd0(%RBP),%RAX |
0x4430eb ADD (%RAX,%RCX,8),%R12 |
0x4430ef MOV -0x78(%RBP),%RCX |
0x4430f3 MOV -0x38(%RBP),%R11 |
0x4430f7 NOPW (%RAX,%RAX,1) |
(861) 0x443100 MOV (%R12),%RAX |
(861) 0x443104 MOV %RBX,(%R11,%RAX,8) |
(861) 0x443108 MOVQ $0,(%R15,%RBX,8) |
(861) 0x443110 MOV %RAX,(%RCX,%RBX,8) |
(861) 0x443114 INC %RBX |
(861) 0x443117 ADD $0x8,%R12 |
(861) 0x44311b CMP %RBX,%RDX |
(861) 0x44311e JNE 443100 |
0x443120 MOV -0xe8(%RBP),%RCX |
0x443127 MOV -0x30(%RBP),%RDX |
0x44312b MOV (%RCX,%RDX,8),%RAX |
0x44312f MOV 0x8(%RCX,%RDX,8),%RCX |
0x443134 CMP %RCX,%RAX |
0x443137 MOV -0x150(%RBP),%R8 |
0x44313e MOV -0x148(%RBP),%R9 |
0x443145 MOV -0x120(%RBP),%RDI |
0x44314c MOV %R11,%R12 |
0x44314f JGE 4431a0 |
0x443151 MOV -0x50(%RBP),%RDX |
0x443155 MOV (%RDX),%RDX |
0x443158 DEC %RDX |
0x44315b MOV -0x30(%RBP),%RBX |
0x44315f JMP 443178 |
(860) 0x443170 INC %RAX |
(860) 0x443173 CMP %RCX,%RAX |
(860) 0x443176 JGE 4431a0 |
(860) 0x443178 MOV (%RDI,%RAX,8),%RSI |
(860) 0x44317c CMP %RDX,(%R9,%RSI,8) |
(860) 0x443180 JNE 443170 |
(860) 0x443182 MOV -0x68(%RBP),%RCX |
(860) 0x443186 MOV %RBX,(%RCX,%RSI,8) |
(860) 0x44318a MOV -0xe8(%RBP),%RCX |
(860) 0x443191 MOV 0x8(%RCX,%RBX,8),%RCX |
(860) 0x443196 JMP 443170 |
0x4431a0 MOV -0xf0(%RBP),%RCX |
0x4431a7 MOV -0x30(%RBP),%RDX |
0x4431ab MOV (%RCX,%RDX,8),%RAX |
0x4431af MOV 0x8(%RCX,%RDX,8),%RCX |
0x4431b4 CMP %RCX,%RAX |
0x4431b7 MOV -0x128(%RBP),%RBX |
0x4431be JGE 443200 |
0x4431c0 MOV -0x50(%RBP),%RDX |
0x4431c4 MOV (%RDX),%RDX |
0x4431c7 DEC %RDX |
0x4431ca MOV -0x30(%RBP),%RDI |
0x4431ce JMP 4431d8 |
(859) 0x4431d0 INC %RAX |
(859) 0x4431d3 CMP %RCX,%RAX |
(859) 0x4431d6 JGE 443200 |
(859) 0x4431d8 MOV (%RBX,%RAX,8),%RSI |
(859) 0x4431dc CMP %RDX,(%R8,%RSI,8) |
(859) 0x4431e0 JNE 4431d0 |
(859) 0x4431e2 MOV -0x60(%RBP),%RCX |
(859) 0x4431e6 MOV %RDI,(%RCX,%RSI,8) |
(859) 0x4431ea MOV -0xf0(%RBP),%RCX |
(859) 0x4431f1 MOV 0x8(%RCX,%RDI,8),%RCX |
(859) 0x4431f6 JMP 4431d0 |
0x443200 MOV -0x110(%RBP),%RAX |
0x443207 MOV -0x30(%RBP),%RCX |
0x44320b MOV (%RAX,%RCX,8),%RDX |
0x44320f MOV 0x8(%RAX,%RCX,8),%R9 |
0x443214 MOV %RDX,%RAX |
0x443217 MOV %RDX,-0x90(%RBP) |
0x44321e INC %RDX |
0x443221 VXORPD %XMM1,%XMM1,%XMM1 |
0x443225 VXORPD %XMM0,%XMM0,%XMM0 |
0x443229 CMP %R9,%RDX |
0x44322c JGE 443560 |
0x443232 VXORPD %XMM1,%XMM1,%XMM1 |
0x443236 MOV -0x58(%RBP),%R8 |
0x44323a JMP 443250 |
(854) 0x443240 MOV -0x48(%RBP),%R10 |
(854) 0x443244 INC %RDX |
(854) 0x443247 CMP %R9,%RDX |
(854) 0x44324a JE 443560 |
(854) 0x443250 MOV -0x190(%RBP),%RAX |
(854) 0x443257 MOV (%RAX,%RDX,8),%R11 |
(854) 0x44325b MOV -0x68(%RBP),%RAX |
(854) 0x44325f MOV -0x30(%RBP),%RCX |
(854) 0x443263 CMP %RCX,(%RAX,%R11,8) |
(854) 0x443267 JNE 443290 |
(854) 0x443269 MOV -0xb8(%RBP),%RAX |
(854) 0x443270 MOV (%RAX,%R11,8),%RDI |
(854) 0x443274 MOV 0x8(%RAX,%R11,8),%RBX |
(854) 0x443279 MOV %RBX,%R10 |
(854) 0x44327c SUB %RDI,%R10 |
(854) 0x44327f JLE 4433f7 |
(854) 0x443285 CMP $0x4,%R10 |
(854) 0x443289 JAE 4432c9 |
(854) 0x44328b JMP 44339d |
(854) 0x443290 MOV -0x178(%RBP),%RAX |
(854) 0x443297 CMPQ $-0x3,(%RAX,%R11,8) |
(854) 0x44329c JE 443244 |
(854) 0x44329e CMPQ $0x1,-0xf8(%RBP) |
(854) 0x4432a6 JE 4432bd |
(854) 0x4432a8 MOV -0xd8(%RBP),%RCX |
(854) 0x4432af MOV -0x30(%RBP),%RAX |
(854) 0x4432b3 MOV (%RCX,%RAX,8),%RAX |
(854) 0x4432b7 CMP (%RCX,%R11,8),%RAX |
(854) 0x4432bb JNE 443244 |
(854) 0x4432bd VADDSD (%R13,%RDX,8),%XMM0,%XMM0 |
(854) 0x4432c4 JMP 443244 |
(854) 0x4432c9 MOV %R10,%RAX |
(854) 0x4432cc SHR $0x2,%RAX |
(854) 0x4432d0 LEA 0x18(,%RDI,8),%RCX |
(854) 0x4432d8 MOV -0x40(%RBP),%R12 |
(854) 0x4432dc NOPL (%RAX) |
(857) 0x4432e0 MOV -0x18(%R8,%RCX,1),%RSI |
(857) 0x4432e5 VMOVSD -0x18(%R14,%RCX,1),%XMM8 |
(857) 0x4432ec VMOVSD (%R13,%RDX,8),%XMM3 |
(857) 0x4432f3 MOV (%R12,%RSI,8),%RSI |
(857) 0x4432f7 VMOVSD (%R14,%RSI,8),%XMM4 |
(857) 0x4432fd VFMADD231SD %XMM8,%XMM3,%XMM4 |
(857) 0x443302 VMOVSD %XMM4,(%R14,%RSI,8) |
(857) 0x443308 MOV -0x10(%R8,%RCX,1),%RSI |
(857) 0x44330d VMOVSD -0x10(%R14,%RCX,1),%XMM4 |
(857) 0x443314 VMOVSD (%R13,%RDX,8),%XMM5 |
(857) 0x44331b MOV (%R12,%RSI,8),%RSI |
(857) 0x44331f VMOVSD (%R14,%RSI,8),%XMM6 |
(857) 0x443325 VFMADD231SD %XMM4,%XMM5,%XMM6 |
(857) 0x44332a VMOVSD %XMM6,(%R14,%RSI,8) |
(857) 0x443330 MOV -0x8(%R8,%RCX,1),%RSI |
(857) 0x443335 VMOVSD -0x8(%R14,%RCX,1),%XMM6 |
(857) 0x44333c VMOVSD (%R13,%RDX,8),%XMM7 |
(857) 0x443343 MOV (%R12,%RSI,8),%RSI |
(857) 0x443347 VMOVSD (%R14,%RSI,8),%XMM2 |
(857) 0x44334d VFMADD231SD %XMM6,%XMM7,%XMM2 |
(857) 0x443352 VMOVSD %XMM2,(%R14,%RSI,8) |
(857) 0x443358 MOV (%R8,%RCX,1),%RSI |
(857) 0x44335c VMOVSD (%R14,%RCX,1),%XMM2 |
(857) 0x443362 VMULSD (%R13,%RDX,8),%XMM2,%XMM10 |
(857) 0x443369 MOV (%R12,%RSI,8),%RSI |
(857) 0x44336d VADDSD (%R14,%RSI,8),%XMM10,%XMM2 |
(857) 0x443373 VMOVSD %XMM2,(%R14,%RSI,8) |
(857) 0x443379 VFMADD213SD %XMM10,%XMM5,%XMM4 |
(857) 0x44337e VFMADD231SD %XMM8,%XMM3,%XMM4 |
(857) 0x443383 VFMADD231SD %XMM6,%XMM7,%XMM4 |
(857) 0x443388 VADDSD %XMM1,%XMM4,%XMM1 |
(857) 0x44338c VADDSD %XMM0,%XMM4,%XMM0 |
(857) 0x443390 ADD $0x20,%RCX |
(857) 0x443394 DEC %RAX |
(857) 0x443397 JNE 4432e0 |
(854) 0x44339d MOV %R10,%RAX |
(854) 0x4433a0 AND $-0x4,%RAX |
(854) 0x4433a4 CMP %R10,%RAX |
(854) 0x4433a7 JAE 4433f3 |
(854) 0x4433a9 ADD %RAX,%RDI |
(854) 0x4433ac MOV -0x58(%RBP),%RCX |
(854) 0x4433b0 MOV -0x40(%RBP),%RSI |
(854) 0x4433b4 MOV -0x38(%RBP),%R12 |
(854) 0x4433b8 NOPL (%RAX,%RAX,1) |
(858) 0x4433c0 VMOVSD (%R14,%RDI,8),%XMM2 |
(858) 0x4433c6 MOV (%RCX,%RDI,8),%RAX |
(858) 0x4433ca VMULSD (%R13,%RDX,8),%XMM2,%XMM10 |
(858) 0x4433d1 MOV (%RSI,%RAX,8),%RAX |
(858) 0x4433d5 VADDSD (%R14,%RAX,8),%XMM10,%XMM2 |
(858) 0x4433db VMOVSD %XMM2,(%R14,%RAX,8) |
(858) 0x4433e1 VADDSD %XMM1,%XMM10,%XMM1 |
(858) 0x4433e5 VADDSD %XMM0,%XMM10,%XMM0 |
(858) 0x4433e9 INC %RDI |
(858) 0x4433ec CMP %RDI,%RBX |
(858) 0x4433ef JNE 4433c0 |
(854) 0x4433f1 JMP 4433f7 |
(854) 0x4433f3 MOV -0x38(%RBP),%R12 |
(854) 0x4433f7 MOV -0xc0(%RBP),%RAX |
(854) 0x4433fe MOV (%RAX,%R11,8),%RDI |
(854) 0x443402 MOV 0x8(%RAX,%R11,8),%R11 |
(854) 0x443407 MOV %R11,%R10 |
(854) 0x44340a SUB %RDI,%R10 |
(854) 0x44340d JLE 443240 |
(854) 0x443413 CMP $0x4,%R10 |
(854) 0x443417 MOV -0x78(%RBP),%RSI |
(854) 0x44341b JAE 443422 |
(854) 0x44341d JMP 4434fd |
(854) 0x443422 MOV %R10,%RCX |
(854) 0x443425 SHR $0x2,%RCX |
(854) 0x443429 LEA 0x18(,%RDI,8),%RBX |
(854) 0x443431 NOPW %CS:(%RAX,%RAX,1) |
(855) 0x443440 MOV -0x18(%RSI,%RBX,1),%RAX |
(855) 0x443445 VMOVSD -0x18(%R15,%RBX,1),%XMM8 |
(855) 0x44344c VMOVSD (%R13,%RDX,8),%XMM3 |
(855) 0x443453 MOV (%R12,%RAX,8),%RAX |
(855) 0x443457 VMOVSD (%R15,%RAX,8),%XMM4 |
(855) 0x44345d VFMADD231SD %XMM8,%XMM3,%XMM4 |
(855) 0x443462 VMOVSD %XMM4,(%R15,%RAX,8) |
(855) 0x443468 MOV -0x10(%RSI,%RBX,1),%RAX |
(855) 0x44346d VMOVSD -0x10(%R15,%RBX,1),%XMM4 |
(855) 0x443474 VMOVSD (%R13,%RDX,8),%XMM5 |
(855) 0x44347b MOV (%R12,%RAX,8),%RAX |
(855) 0x44347f VMOVSD (%R15,%RAX,8),%XMM6 |
(855) 0x443485 VFMADD231SD %XMM4,%XMM5,%XMM6 |
(855) 0x44348a VMOVSD %XMM6,(%R15,%RAX,8) |
(855) 0x443490 MOV -0x8(%RSI,%RBX,1),%RAX |
(855) 0x443495 VMOVSD -0x8(%R15,%RBX,1),%XMM6 |
(855) 0x44349c VMOVSD (%R13,%RDX,8),%XMM7 |
(855) 0x4434a3 MOV (%R12,%RAX,8),%RAX |
(855) 0x4434a7 VMOVSD (%R15,%RAX,8),%XMM2 |
(855) 0x4434ad VFMADD231SD %XMM6,%XMM7,%XMM2 |
(855) 0x4434b2 VMOVSD %XMM2,(%R15,%RAX,8) |
(855) 0x4434b8 MOV (%RSI,%RBX,1),%RAX |
(855) 0x4434bc VMOVSD (%R15,%RBX,1),%XMM2 |
(855) 0x4434c2 VMULSD (%R13,%RDX,8),%XMM2,%XMM10 |
(855) 0x4434c9 MOV (%R12,%RAX,8),%RAX |
(855) 0x4434cd VADDSD (%R15,%RAX,8),%XMM10,%XMM2 |
(855) 0x4434d3 VMOVSD %XMM2,(%R15,%RAX,8) |
(855) 0x4434d9 VFMADD213SD %XMM10,%XMM5,%XMM4 |
(855) 0x4434de VFMADD231SD %XMM8,%XMM3,%XMM4 |
(855) 0x4434e3 VFMADD231SD %XMM6,%XMM7,%XMM4 |
(855) 0x4434e8 VADDSD %XMM1,%XMM4,%XMM1 |
(855) 0x4434ec VADDSD %XMM0,%XMM4,%XMM0 |
(855) 0x4434f0 ADD $0x20,%RBX |
(855) 0x4434f4 DEC %RCX |
(855) 0x4434f7 JNE 443440 |
(854) 0x4434fd MOV %R10,%RCX |
(854) 0x443500 AND $-0x4,%RCX |
(854) 0x443504 CMP %R10,%RCX |
(854) 0x443507 JAE 443240 |
(854) 0x44350d ADD %RCX,%RDI |
(854) 0x443510 MOV -0x48(%RBP),%R10 |
(854) 0x443514 NOPW %CS:(%RAX,%RAX,1) |
(856) 0x443520 VMOVSD (%R15,%RDI,8),%XMM2 |
(856) 0x443526 MOV (%RSI,%RDI,8),%RAX |
(856) 0x44352a VMULSD (%R13,%RDX,8),%XMM2,%XMM10 |
(856) 0x443531 MOV (%R12,%RAX,8),%RAX |
(856) 0x443535 VADDSD (%R15,%RAX,8),%XMM10,%XMM2 |
(856) 0x44353b VMOVSD %XMM2,(%R15,%RAX,8) |
(856) 0x443541 VADDSD %XMM1,%XMM10,%XMM1 |
(856) 0x443545 VADDSD %XMM0,%XMM10,%XMM0 |
(856) 0x443549 INC %RDI |
(856) 0x44354c CMP %RDI,%R11 |
(856) 0x44354f JNE 443520 |
(854) 0x443551 JMP 443244 |
0x443560 MOV -0x118(%RBP),%RAX |
0x443567 MOV -0x30(%RBP),%RCX |
0x44356b MOV (%RAX,%RCX,8),%R12 |
0x44356f MOV 0x8(%RAX,%RCX,8),%R9 |
0x443574 CMP %R9,%R12 |
0x443577 JGE 4436c0 |
0x44357d MOV -0xe0(%RBP),%R11 |
0x443584 MOV -0x38(%RBP),%R8 |
0x443588 JMP 4435a2 |
(852) 0x443590 VADDSD (%RDI,%R12,8),%XMM0,%XMM0 |
(852) 0x443596 INC %R12 |
(852) 0x443599 CMP %R9,%R12 |
(852) 0x44359c JE 4436c0 |
(852) 0x4435a2 MOV -0x198(%RBP),%RAX |
(852) 0x4435a9 LEA (%RAX,%R12,8),%RAX |
(852) 0x4435ad CMPQ $0,-0x1a0(%RBP) |
(852) 0x4435b5 JE 4435c5 |
(852) 0x4435b7 MOV (%RAX),%RAX |
(852) 0x4435ba MOV -0x180(%RBP),%RDX |
(852) 0x4435c1 LEA (%RDX,%RAX,8),%RAX |
(852) 0x4435c5 MOV (%RAX),%RSI |
(852) 0x4435c8 TEST %RSI,%RSI |
(852) 0x4435cb JS 443670 |
(852) 0x4435d1 MOV -0x60(%RBP),%RAX |
(852) 0x4435d5 MOV -0x30(%RBP),%RCX |
(852) 0x4435d9 CMP %RCX,(%RAX,%RSI,8) |
(852) 0x4435dd JNE 443670 |
(852) 0x4435e3 MOV -0x170(%RBP),%RAX |
(852) 0x4435ea MOV 0x8(%RAX,%RSI,8),%RAX |
(852) 0x4435ef TEST %RAX,%RAX |
(852) 0x4435f2 JLE 443596 |
(852) 0x4435f4 MOV -0x160(%RBP),%RDX |
(852) 0x4435fb MOV (%RDX,%RSI,8),%RSI |
(852) 0x4435ff ADD %RSI,%RAX |
(852) 0x443602 MOV -0x50(%RBP),%RCX |
(852) 0x443606 MOV (%RCX),%RDI |
(852) 0x443609 MOV -0x168(%RBP),%RDX |
(852) 0x443610 MOV (%RDX,%RDI,8),%RDI |
(852) 0x443614 MOV -0x40(%RBP),%RCX |
(852) 0x443618 NOPL (%RAX,%RAX,1) |
(853) 0x443620 VMOVSD (%R10,%RSI,8),%XMM2 |
(853) 0x443626 MOV (%RDI,%RSI,8),%RBX |
(853) 0x44362a VMULSD (%R11,%R12,8),%XMM2,%XMM10 |
(853) 0x443630 TEST %RBX,%RBX |
(853) 0x443633 LEA (%R8,%RBX,8),%RDX |
(853) 0x443637 NOT %RBX |
(853) 0x44363a LEA (%RCX,%RBX,8),%RBX |
(853) 0x44363e CMOVNS %RDX,%RBX |
(853) 0x443642 MOV %R15,%RDX |
(853) 0x443645 CMOVS %R14,%RDX |
(853) 0x443649 MOV (%RBX),%RBX |
(853) 0x44364c VADDSD (%RDX,%RBX,8),%XMM10,%XMM2 |
(853) 0x443651 VMOVSD %XMM2,(%RDX,%RBX,8) |
(853) 0x443656 VADDSD %XMM1,%XMM10,%XMM1 |
(853) 0x44365a VADDSD %XMM0,%XMM10,%XMM0 |
(853) 0x44365e INC %RSI |
(853) 0x443661 CMP %RAX,%RSI |
(853) 0x443664 JL 443620 |
(852) 0x443666 JMP 443596 |
(852) 0x443670 MOV -0x188(%RBP),%RAX |
(852) 0x443677 CMPQ $-0x3,(%RAX,%RSI,8) |
(852) 0x44367c JE 443596 |
(852) 0x443682 CMPQ $0x1,-0xf8(%RBP) |
(852) 0x44368a MOV -0xe0(%RBP),%RDI |
(852) 0x443691 JE 443590 |
(852) 0x443697 MOV -0x158(%RBP),%RAX |
(852) 0x44369e MOV (%RAX,%RSI,8),%RAX |
(852) 0x4436a2 MOV -0xd8(%RBP),%RDX |
(852) 0x4436a9 MOV -0x30(%RBP),%RCX |
(852) 0x4436ad CMP (%RDX,%RCX,8),%RAX |
(852) 0x4436b1 JE 443590 |
(852) 0x4436b7 JMP 443596 |
0x4436c0 MOV -0x90(%RBP),%RAX |
0x4436c7 VMULSD (%R13,%RAX,8),%XMM1,%XMM1 |
0x4436ce VUCOMISD %XMM9,%XMM1 |
0x4436d3 JE 4436e3 |
0x4436d5 VXORPD 0xb23e1(%RIP){1to2},%XMM0,%XMM0 |
0x4436df VDIVSD %XMM1,%XMM0,%XMM10 |
0x4436e3 MOV -0xb8(%RBP),%RAX |
0x4436ea MOV -0x30(%RBP),%RCX |
0x4436ee MOV (%RAX,%RCX,8),%R8 |
0x4436f2 MOV 0x8(%RAX,%RCX,8),%RAX |
0x4436f7 MOV %RAX,%RSI |
0x4436fa SUB %R8,%RSI |
0x4436fd MOV -0x38(%RBP),%R12 |
0x443701 JLE 443754 |
0x443703 MOV %RSI,%RCX |
0x443706 AND $-0x4,%RCX |
0x44370a JE 44373a |
0x44370c LEA -0x1(%RCX),%RDI |
0x443710 VBROADCASTSD %XMM10,%YMM0 |
0x443715 LEA (%R14,%R8,8),%RBX |
0x443719 XOR %EDX,%EDX |
0x44371b NOPL (%RAX,%RAX,1) |
(851) 0x443720 VMULPD (%RBX,%RDX,8),%YMM0,%YMM1 |
(851) 0x443725 VMOVUPD %YMM1,(%RBX,%RDX,8) |
(851) 0x44372a ADD $0x4,%RDX |
(851) 0x44372e CMP %RDI,%RDX |
(851) 0x443731 JBE 443720 |
0x443733 CMP %RCX,%RSI |
0x443736 JNE 44373c |
0x443738 JMP 443754 |
0x44373a XOR %ECX,%ECX |
0x44373c ADD %R8,%RCX |
0x44373f NOP |
(850) 0x443740 VMULSD (%R14,%RCX,8),%XMM10,%XMM0 |
(850) 0x443746 VMOVSD %XMM0,(%R14,%RCX,8) |
(850) 0x44374c INC %RCX |
(850) 0x44374f CMP %RCX,%RAX |
(850) 0x443752 JNE 443740 |
0x443754 MOV -0xc0(%RBP),%RAX |
0x44375b MOV -0x30(%RBP),%RCX |
0x44375f MOV (%RAX,%RCX,8),%R8 |
0x443763 MOV 0x8(%RAX,%RCX,8),%RAX |
0x443768 MOV %RAX,%RSI |
0x44376b SUB %R8,%RSI |
0x44376e JLE 442d00 |
0x443774 MOV %RSI,%RCX |
0x443777 AND $-0x4,%RCX |
0x44377b JE 4437ae |
0x44377d LEA -0x1(%RCX),%RDI |
0x443781 VBROADCASTSD %XMM10,%YMM0 |
0x443786 LEA (%R15,%R8,8),%RBX |
0x44378a XOR %EDX,%EDX |
0x44378c NOPL (%RAX) |
(849) 0x443790 VMULPD (%RBX,%RDX,8),%YMM0,%YMM1 |
(849) 0x443795 VMOVUPD %YMM1,(%RBX,%RDX,8) |
(849) 0x44379a ADD $0x4,%RDX |
(849) 0x44379e CMP %RDI,%RDX |
(849) 0x4437a1 JBE 443790 |
0x4437a3 CMP %RCX,%RSI |
0x4437a6 JE 442d00 |
0x4437ac JMP 4437b0 |
0x4437ae XOR %ECX,%ECX |
0x4437b0 ADD %R8,%RCX |
0x4437b3 NOPW %CS:(%RAX,%RAX,1) |
(848) 0x4437c0 VMULSD (%R15,%RCX,8),%XMM10,%XMM0 |
(848) 0x4437c6 VMOVSD %XMM0,(%R15,%RCX,8) |
(848) 0x4437cc INC %RCX |
(848) 0x4437cf CMP %RCX,%RAX |
(848) 0x4437d2 JNE 4437c0 |
0x4437d4 JMP 442d00 |
/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 | 3.24 |
CQA speedup if FP arith vectorized | 3.43 |
CQA speedup if fully vectorized | 12.72 |
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 | 60.00 |
CQA cycles if no scalar integer | 18.50 |
CQA cycles if FP arith vectorized | 17.47 |
CQA cycles if fully vectorized | 4.72 |
Front-end cycles | 60.00 |
DIV/SQRT cycles | 23.00 |
P0 cycles | 22.92 |
P1 cycles | 44.50 |
P2 cycles | 44.50 |
P3 cycles | 13.00 |
P4 cycles | 23.08 |
P5 cycles | 23.00 |
P6 cycles | 13.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 58.32 - 58.33 |
Stall cycles (UFS) | 0.00 |
Nb insns | 229.00 |
Nb uops | 237.00 |
Nb loads | 89.00 |
Nb stores | 11.00 |
Nb stack references | 31.00 |
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 | 13.87 |
Bytes prefetched | 0.00 |
Bytes loaded | 728.00 |
Bytes stored | 104.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 21.82 |
Vectorization ratio load | 21.43 |
Vectorization ratio store | 18.18 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 25.81 |
Vector-efficiency ratio all | 15.00 |
Vector-efficiency ratio load | 15.18 |
Vector-efficiency ratio store | 14.77 |
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 | 15.32 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.24 |
CQA speedup if FP arith vectorized | 3.43 |
CQA speedup if fully vectorized | 12.72 |
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 | 60.00 |
CQA cycles if no scalar integer | 18.50 |
CQA cycles if FP arith vectorized | 17.47 |
CQA cycles if fully vectorized | 4.72 |
Front-end cycles | 60.00 |
DIV/SQRT cycles | 23.00 |
P0 cycles | 22.92 |
P1 cycles | 44.50 |
P2 cycles | 44.50 |
P3 cycles | 13.00 |
P4 cycles | 23.08 |
P5 cycles | 23.00 |
P6 cycles | 13.00 |
P7 cycles | 4.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 58.32 - 58.33 |
Stall cycles (UFS) | 0.00 |
Nb insns | 229.00 |
Nb uops | 237.00 |
Nb loads | 89.00 |
Nb stores | 11.00 |
Nb stack references | 31.00 |
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 | 13.87 |
Bytes prefetched | 0.00 |
Bytes loaded | 728.00 |
Bytes stored | 104.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 21.82 |
Vectorization ratio load | 21.43 |
Vectorization ratio store | 18.18 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 25.81 |
Vector-efficiency ratio all | 15.00 |
Vector-efficiency ratio load | 15.18 |
Vector-efficiency ratio store | 14.77 |
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 | 15.32 |
Path / |
Function | hypre_BoomerAMGBuildMultipass.extracted.28 |
Source file and lines | par_multi_interp.c:1747-1876 |
Module | exec |
nb instructions | 229 |
nb uops | 237 |
loop length | 1021 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 31 |
micro-operation queue | 60.00 cycles |
front end | 60.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 23.00 | 22.92 | 44.50 | 44.50 | 13.00 | 23.08 | 23.00 | 13.00 |
cycles | 23.00 | 22.92 | 44.50 | 44.50 | 13.00 | 23.08 | 23.00 | 13.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 58.32-58.33 |
Stall cycles | 0.00 |
Front-end | 60.00 |
Dispatch | 44.50 |
DIV/SQRT | 4.00 |
Overall L1 | 60.00 |
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 | 9% |
all | 66% |
load | 75% |
store | 100% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 66% |
all | 21% |
load | 21% |
store | 18% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 25% |
all | 12% |
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 | 20% |
load | 21% |
store | 25% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 20% |
all | 15% |
load | 15% |
store | 14% |
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 -0x70(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4437d9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%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),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RBX | 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,%RCX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%RAX,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RBX,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 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 442f1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%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 442ee0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM10,-0x90(%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 %RBX,-0xa0(%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 |
MOV %RCX,-0x98(%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 4e6020 <_intel_fast_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xa0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R8,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R12,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%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 %R10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM9,%XMM9,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD -0x90(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 442f1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R11,8),%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 442f1f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%RAX,%RCX,8),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RDX | 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 -0x140(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R12 | 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 (%RAX,%RCX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%R12,1),%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,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 443120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%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 4430e0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM10,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R15,%RBX,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 %RAX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x98(%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 4e6020 <_intel_fast_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xd0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa0(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R8,%R12,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x38(%RBP),%R11 | 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 %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%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 %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM9,%XMM9,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD -0x90(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 443120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R12,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 443120 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
SAL $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0xd0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%RAX,%RCX,8),%R12 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%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 -0xe8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RDX,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 -0x150(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 4431a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%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 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 443178 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0xf0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RDX,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 -0x128(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 443200 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%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 |
MOV -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4431d8 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 443560 | 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 -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 443250 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 4436c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xe0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4435a2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x90(%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 %XMM9,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 4436e3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD 0xb23e1(%RIP){1to2},%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VDIVSD %XMM1,%XMM0,%XMM10 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 443754 | 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 44373a | 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 %XMM10,%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 |
JNE 44373c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 443754 | 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 |
NOP | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 442d00 | 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 4437ae | 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 %XMM10,%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 |
NOPL (%RAX) | 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 442d00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4437b0 | 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 442d00 | 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 | 229 |
nb uops | 237 |
loop length | 1021 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 4 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 31 |
micro-operation queue | 60.00 cycles |
front end | 60.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 23.00 | 22.92 | 44.50 | 44.50 | 13.00 | 23.08 | 23.00 | 13.00 |
cycles | 23.00 | 22.92 | 44.50 | 44.50 | 13.00 | 23.08 | 23.00 | 13.00 |
Cycles executing div or sqrt instructions | 4.00 |
FE+BE cycles | 58.32-58.33 |
Stall cycles | 0.00 |
Front-end | 60.00 |
Dispatch | 44.50 |
DIV/SQRT | 4.00 |
Overall L1 | 60.00 |
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 | 9% |
all | 66% |
load | 75% |
store | 100% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 66% |
all | 21% |
load | 21% |
store | 18% |
mul | 0% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 25% |
all | 12% |
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 | 20% |
load | 21% |
store | 25% |
mul | 12% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 12% |
other | 20% |
all | 15% |
load | 15% |
store | 14% |
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 -0x70(%RBP),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 4437d9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%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),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RBX | 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,%RCX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%RAX,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RBX,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 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 442f1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RSI,%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 442ee0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RSI,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM10,-0x90(%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 %RBX,-0xa0(%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 |
MOV %RCX,-0x98(%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 4e6020 <_intel_fast_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xa0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R8,%R11,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%R12,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%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 %R10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM9,%XMM9,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD -0x90(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 442f1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD %RAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R11,8),%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 442f1f | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
SAL $0x3,%RBX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%RAX,%RCX,8),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RDX | 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 -0x140(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R12 | 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 (%RAX,%RCX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%R12,1),%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,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x38(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 443120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%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 4430e0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD %XMM10,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R15,%RBX,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 %RAX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,-0x98(%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 4e6020 <_intel_fast_memset> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0xd0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x98(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa0(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%R9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%R8,%R12,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x38,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDI,%EDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x38(%RBP),%R11 | 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 %R10,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%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 %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM9,%XMM9,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPD -0x90(%RBP),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xa8(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JAE 443120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RCX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R8,%R12,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 443120 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
SAL $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV -0xd0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%RAX,%RCX,8),%R12 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%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 -0xe8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RDX,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 -0x150(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R11,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JGE 4431a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%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 |
MOV -0x30(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 443178 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0xf0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RDX,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 -0x128(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JGE 443200 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%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 |
MOV -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4431d8 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 443560 | 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 -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 443250 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 4436c0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xe0(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4435a2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x90(%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 %XMM9,%XMM1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
JE 4436e3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VXORPD 0xb23e1(%RIP){1to2},%XMM0,%XMM0 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VDIVSD %XMM1,%XMM0,%XMM10 | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 -0x38(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JLE 443754 | 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 44373a | 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 %XMM10,%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 |
JNE 44373c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 443754 | 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 |
NOP | 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 -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,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 442d00 | 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 4437ae | 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 %XMM10,%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 |
NOPL (%RAX) | 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 442d00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4437b0 | 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 442d00 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |