| Loop Id: 1174 | Module: exec | Source: par_lr_interp.c:1221-1748 [...] | Coverage: 0.01% |
|---|
| Loop Id: 1174 | Module: exec | Source: par_lr_interp.c:1221-1748 [...] | Coverage: 0.01% |
|---|
0x452ce0 MOV -0x68(%RBP),%RAX |
0x452ce4 MOV (%RAX,%RDX,8),%RAX |
0x452ce8 MOV -0x128(%RBP),%RCX |
0x452cef MOV (%RCX),%RCX |
0x452cf2 MOV %RAX,(%RCX,%R13,8) |
0x452cf6 MOV -0xb8(%RBP),%RAX |
0x452cfd MOV (%RAX),%RAX |
0x452d00 MOV $0x3ff0000000000000,%RCX |
0x452d0a MOV %RCX,(%RAX,%R13,8) |
0x452d0e MOV -0x98(%RBP),%R13 |
0x452d15 DECQ -0x70(%RBP) |
0x452d19 INC %RDX |
0x452d1c CMP %R13,%RDX |
0x452d1f JE 453c0e |
0x452d25 MOV -0x80(%RBP),%RAX |
0x452d29 MOV (%RAX,%RDX,8),%R13 |
0x452d2d MOV (%R11,%RDX,8),%RAX |
0x452d31 TEST %RAX,%RAX |
0x452d34 JNS 452ce0 |
0x452d36 MOV %RDX,-0x30(%RBP) |
0x452d3a CMP $-0x3,%RAX |
0x452d3e JNE 452d46 |
0x452d40 MOV -0x30(%RBP),%RDX |
0x452d44 JMP 452d0e |
0x452d46 MOV -0xc0(%RBP),%RAX |
0x452d4d MOV -0x30(%RBP),%RCX |
0x452d51 MOV (%RAX,%RCX,8),%R10 |
0x452d55 DECQ -0x70(%RBP) |
0x452d59 MOV -0xd0(%RBP),%RAX |
0x452d60 MOV (%RAX,%RCX,8),%RDX |
0x452d64 MOV %R13,-0x50(%RBP) |
0x452d68 MOV %R10,-0x48(%RBP) |
0x452d6c CMP 0x8(%RAX,%RCX,8),%RDX |
0x452d71 JGE 452fa0 |
0x452d77 MOV %R10,-0x48(%RBP) |
0x452d7b MOV %R13,-0x50(%RBP) |
0x452d7f JMP 452da9 |
(1192) 0x452d81 MOV -0x40(%RBP),%R12 |
(1192) 0x452d85 MOV -0x38(%RBP),%R15 |
(1192) 0x452d89 NOPL (%RAX) |
(1192) 0x452d90 INC %RDX |
(1192) 0x452d93 MOV -0xd0(%RBP),%RAX |
(1192) 0x452d9a MOV -0x30(%RBP),%RCX |
(1192) 0x452d9e CMP 0x8(%RAX,%RCX,8),%RDX |
(1192) 0x452da3 JGE 452fa0 |
(1192) 0x452da9 MOV -0x150(%RBP),%RAX |
(1192) 0x452db0 MOV (%RAX,%RDX,8),%RAX |
(1192) 0x452db4 MOV (%R11,%RAX,8),%RCX |
(1192) 0x452db8 TEST %RCX,%RCX |
(1192) 0x452dbb JS 452e00 |
(1192) 0x452dbd CMP %R13,(%R15,%RAX,8) |
(1192) 0x452dc1 JGE 452d90 |
(1192) 0x452dc3 MOV -0x50(%RBP),%RSI |
(1192) 0x452dc7 MOV %RSI,(%R15,%RAX,8) |
(1192) 0x452dcb MOV -0x68(%RBP),%RCX |
(1192) 0x452dcf MOV (%RCX,%RAX,8),%RAX |
(1192) 0x452dd3 MOV -0x128(%RBP),%RCX |
(1192) 0x452dda MOV (%RCX),%RCX |
(1192) 0x452ddd MOV %RAX,(%RCX,%RSI,8) |
(1192) 0x452de1 MOV -0xb8(%RBP),%RAX |
(1192) 0x452de8 MOV (%RAX),%RAX |
(1192) 0x452deb MOVQ $0,(%RAX,%RSI,8) |
(1192) 0x452df3 INC %RSI |
(1192) 0x452df6 MOV %RSI,-0x50(%RBP) |
(1192) 0x452dfa JMP 452d90 |
(1192) 0x452e00 CMP $-0x3,%RCX |
(1192) 0x452e04 JE 452d90 |
(1192) 0x452e06 MOV -0x70(%RBP),%RCX |
(1192) 0x452e0a MOV %RCX,(%R15,%RAX,8) |
(1192) 0x452e0e MOV -0xd0(%RBP),%RCX |
(1192) 0x452e15 MOV (%RCX,%RAX,8),%RSI |
(1192) 0x452e19 MOV 0x8(%RCX,%RAX,8),%RDI |
(1192) 0x452e1e CMP %RDI,%RSI |
(1192) 0x452e21 JGE 452e89 |
(1192) 0x452e23 MOV -0x68(%RBP),%R12 |
(1192) 0x452e27 MOV -0x50(%RBP),%RBX |
(1192) 0x452e2b JMP 452e38 |
(1195) 0x452e30 INC %RSI |
(1195) 0x452e33 CMP %RDI,%RSI |
(1195) 0x452e36 JGE 452e8d |
(1195) 0x452e38 MOV -0x150(%RBP),%RCX |
(1195) 0x452e3f MOV (%RCX,%RSI,8),%RCX |
(1195) 0x452e43 CMPQ $0,(%R11,%RCX,8) |
(1195) 0x452e48 JS 452e30 |
(1195) 0x452e4a CMP %R13,(%R15,%RCX,8) |
(1195) 0x452e4e JGE 452e30 |
(1195) 0x452e50 MOV %RBX,(%R15,%RCX,8) |
(1195) 0x452e54 MOV (%R12,%RCX,8),%RCX |
(1195) 0x452e58 MOV -0x128(%RBP),%RDI |
(1195) 0x452e5f MOV (%RDI),%RDI |
(1195) 0x452e62 MOV %RCX,(%RDI,%RBX,8) |
(1195) 0x452e66 MOV -0xb8(%RBP),%RCX |
(1195) 0x452e6d MOV (%RCX),%RCX |
(1195) 0x452e70 MOVQ $0,(%RCX,%RBX,8) |
(1195) 0x452e78 INC %RBX |
(1195) 0x452e7b MOV -0xd0(%RBP),%RCX |
(1195) 0x452e82 MOV 0x8(%RCX,%RAX,8),%RDI |
(1195) 0x452e87 JMP 452e30 |
(1192) 0x452e89 MOV -0x50(%RBP),%RBX |
(1192) 0x452e8d MOV -0xc8(%RBP),%RCX |
(1192) 0x452e94 CMPQ $0x2,(%RCX) |
(1192) 0x452e98 MOV %RBX,-0x50(%RBP) |
(1192) 0x452e9c JL 452f97 |
(1192) 0x452ea2 MOV -0xa0(%RBP),%RCX |
(1192) 0x452ea9 MOV (%RCX,%RAX,8),%RBX |
(1192) 0x452ead MOV 0x8(%RCX,%RAX,8),%RSI |
(1192) 0x452eb2 CMP %RSI,%RBX |
(1192) 0x452eb5 JGE 452d81 |
(1192) 0x452ebb MOV -0x118(%RBP),%RCX |
(1192) 0x452ec2 MOV (%RCX),%R15 |
(1192) 0x452ec5 MOV -0x120(%RBP),%R12 |
(1192) 0x452ecc TEST %R12,%R12 |
(1192) 0x452ecf JNE 452eec |
(1192) 0x452ed1 JMP 452f4c |
(1193) 0x452ee0 INC %RBX |
(1193) 0x452ee3 CMP %RSI,%RBX |
(1193) 0x452ee6 JGE 452d81 |
(1193) 0x452eec MOV -0xf0(%RBP),%RCX |
(1193) 0x452ef3 MOV (%RCX,%RBX,8),%RCX |
(1193) 0x452ef7 MOV (%R12,%RCX,8),%RCX |
(1193) 0x452efb CMPQ $0,(%R15,%RCX,8) |
(1193) 0x452f00 JS 452ee0 |
(1193) 0x452f02 CMP %R10,(%R14,%RCX,8) |
(1193) 0x452f06 JGE 452ee0 |
(1193) 0x452f08 MOV -0x48(%RBP),%RDI |
(1193) 0x452f0c MOV %RDI,(%R14,%RCX,8) |
(1193) 0x452f10 MOV (%R8),%RSI |
(1193) 0x452f13 MOV %RCX,(%RSI,%RDI,8) |
(1193) 0x452f17 MOV -0x78(%RBP),%RCX |
(1193) 0x452f1b MOV (%RCX),%RCX |
(1193) 0x452f1e MOVQ $0,(%RCX,%RDI,8) |
(1193) 0x452f26 INC %RDI |
(1193) 0x452f29 MOV %RDI,-0x48(%RBP) |
(1193) 0x452f2d MOV -0xa0(%RBP),%RCX |
(1193) 0x452f34 MOV 0x8(%RCX,%RAX,8),%RSI |
(1193) 0x452f39 JMP 452ee0 |
(1194) 0x452f40 INC %RBX |
(1194) 0x452f43 CMP %RSI,%RBX |
(1194) 0x452f46 JGE 452d81 |
(1194) 0x452f4c MOV -0xf0(%RBP),%RCX |
(1194) 0x452f53 MOV (%RCX,%RBX,8),%RCX |
(1194) 0x452f57 CMPQ $0,(%R15,%RCX,8) |
(1194) 0x452f5c JS 452f40 |
(1194) 0x452f5e CMP %R10,(%R14,%RCX,8) |
(1194) 0x452f62 JGE 452f40 |
(1194) 0x452f64 MOV -0x48(%RBP),%RDI |
(1194) 0x452f68 MOV %RDI,(%R14,%RCX,8) |
(1194) 0x452f6c MOV (%R8),%RSI |
(1194) 0x452f6f MOV %RCX,(%RSI,%RDI,8) |
(1194) 0x452f73 MOV -0x78(%RBP),%RCX |
(1194) 0x452f77 MOV (%RCX),%RCX |
(1194) 0x452f7a MOVQ $0,(%RCX,%RDI,8) |
(1194) 0x452f82 INC %RDI |
(1194) 0x452f85 MOV %RDI,-0x48(%RBP) |
(1194) 0x452f89 MOV -0xa0(%RBP),%RCX |
(1194) 0x452f90 MOV 0x8(%RCX,%RAX,8),%RSI |
(1194) 0x452f95 JMP 452f40 |
(1192) 0x452f97 MOV -0x40(%RBP),%R12 |
(1192) 0x452f9b JMP 452d90 |
0x452fa0 MOV -0xc8(%RBP),%RAX |
0x452fa7 CMPQ $0x2,(%RAX) |
0x452fab MOV %R10,-0x58(%RBP) |
0x452faf JL 45313b |
0x452fb5 MOV -0xa0(%RBP),%RCX |
0x452fbc MOV -0x30(%RBP),%RDX |
0x452fc0 MOV (%RCX,%RDX,8),%RAX |
0x452fc4 CMP 0x8(%RCX,%RDX,8),%RAX |
0x452fc9 JGE 45313b |
0x452fcf MOV -0x118(%RBP),%RCX |
0x452fd6 MOV (%RCX),%R15 |
0x452fd9 MOV -0x120(%RBP),%R10 |
0x452fe0 JMP 453009 |
(1190) 0x452ff0 INC %RAX |
(1190) 0x452ff3 MOV -0xa0(%RBP),%RCX |
(1190) 0x452ffa MOV -0x30(%RBP),%RSI |
(1190) 0x452ffe CMP 0x8(%RCX,%RSI,8),%RAX |
(1190) 0x453003 JGE 45313b |
(1190) 0x453009 MOV -0xf0(%RBP),%RCX |
(1190) 0x453010 MOV (%RCX,%RAX,8),%RBX |
(1190) 0x453014 TEST %R10,%R10 |
(1190) 0x453017 JE 45301d |
(1190) 0x453019 MOV (%R10,%RBX,8),%RBX |
(1190) 0x45301d MOV (%R15,%RBX,8),%RCX |
(1190) 0x453021 TEST %RCX,%RCX |
(1190) 0x453024 JS 453060 |
(1190) 0x453026 MOV -0x58(%RBP),%RCX |
(1190) 0x45302a CMP %RCX,(%R14,%RBX,8) |
(1190) 0x45302e JGE 452ff0 |
(1190) 0x453030 MOV -0x48(%RBP),%RSI |
(1190) 0x453034 MOV %RSI,(%R14,%RBX,8) |
(1190) 0x453038 MOV (%R8),%RCX |
(1190) 0x45303b MOV %RBX,(%RCX,%RSI,8) |
(1190) 0x45303f MOV -0x78(%RBP),%RCX |
(1190) 0x453043 MOV (%RCX),%RCX |
(1190) 0x453046 MOVQ $0,(%RCX,%RSI,8) |
(1190) 0x45304e INC %RSI |
(1190) 0x453051 MOV %RSI,-0x48(%RBP) |
(1190) 0x453055 JMP 452ff0 |
(1190) 0x453060 CMP $-0x3,%RCX |
(1190) 0x453064 JE 452ff0 |
(1190) 0x453066 MOV -0x70(%RBP),%RCX |
(1190) 0x45306a MOV %RCX,(%R14,%RBX,8) |
(1190) 0x45306e MOV -0x148(%RBP),%RCX |
(1190) 0x453075 MOV (%RCX,%RBX,8),%RSI |
(1190) 0x453079 JMP 45308e |
(1191) 0x453080 MOV -0x40(%RBP),%R12 |
(1191) 0x453084 INC %RSI |
(1191) 0x453087 MOV -0x148(%RBP),%RCX |
(1191) 0x45308e CMP 0x8(%RCX,%RBX,8),%RSI |
(1191) 0x453093 JGE 452ff0 |
(1191) 0x453099 MOV -0x1e0(%RBP),%RCX |
(1191) 0x4530a0 MOV (%RCX,%RSI,8),%RCX |
(1191) 0x4530a4 MOV %RCX,%RDI |
(1191) 0x4530a7 SUB -0x100(%RBP),%RDI |
(1191) 0x4530ae JL 453100 |
(1191) 0x4530b0 CMP -0xf8(%RBP),%RCX |
(1191) 0x4530b7 JGE 453100 |
(1191) 0x4530b9 MOV -0x38(%RBP),%RCX |
(1191) 0x4530bd CMP %R13,(%RCX,%RDI,8) |
(1191) 0x4530c1 JGE 453080 |
(1191) 0x4530c3 MOV -0x50(%RBP),%RDX |
(1191) 0x4530c7 MOV %RDX,(%RCX,%RDI,8) |
(1191) 0x4530cb MOV -0x68(%RBP),%RCX |
(1191) 0x4530cf MOV (%RCX,%RDI,8),%RCX |
(1191) 0x4530d3 MOV -0x128(%RBP),%RDI |
(1191) 0x4530da MOV (%RDI),%RDI |
(1191) 0x4530dd MOV %RCX,(%RDI,%RDX,8) |
(1191) 0x4530e1 MOV -0xb8(%RBP),%RCX |
(1191) 0x4530e8 MOV (%RCX),%RCX |
(1191) 0x4530eb MOVQ $0,(%RCX,%RDX,8) |
(1191) 0x4530f3 INC %RDX |
(1191) 0x4530f6 MOV %RDX,-0x50(%RBP) |
(1191) 0x4530fa JMP 453080 |
(1191) 0x453100 NOT %RCX |
(1191) 0x453103 MOV -0x58(%RBP),%RDX |
(1191) 0x453107 CMP %RDX,(%R14,%RCX,8) |
(1191) 0x45310b JGE 453080 |
(1191) 0x453111 MOV -0x48(%RBP),%RDX |
(1191) 0x453115 MOV %RDX,(%R14,%RCX,8) |
(1191) 0x453119 MOV (%R8),%RDI |
(1191) 0x45311c MOV %RCX,(%RDI,%RDX,8) |
(1191) 0x453120 MOV -0x78(%RBP),%RCX |
(1191) 0x453124 MOV (%RCX),%RCX |
(1191) 0x453127 MOVQ $0,(%RCX,%RDX,8) |
(1191) 0x45312f INC %RDX |
(1191) 0x453132 MOV %RDX,-0x48(%RBP) |
(1191) 0x453136 JMP 453080 |
0x45313b MOV -0x198(%RBP),%RAX |
0x453142 MOV -0x30(%RBP),%RDI |
0x453146 MOV (%RAX,%RDI,8),%RDX |
0x45314a MOV 0x8(%RAX,%RDI,8),%R15 |
0x45314f MOV -0xe0(%RBP),%RBX |
0x453156 VMOVSD (%RBX,%RDX,8),%XMM6 |
0x45315b INC %RDX |
0x45315e CMP %R15,%RDX |
0x453161 JGE 4537e2 |
0x453167 VPBROADCASTQ %RDI,%YMM7 |
0x45316d VPBROADCASTQ %R13,%YMM8 |
0x453173 MOV -0x58(%RBP),%R10 |
0x453177 VPBROADCASTQ %R10,%YMM9 |
0x45317d MOV %R15,-0xb0(%RBP) |
0x453184 JMP 4531b9 |
(1182) 0x453190 MOV -0xb8(%RBP),%RCX |
(1182) 0x453197 MOV (%RCX),%RCX |
(1182) 0x45319a VMOVSD (%RCX,%RAX,8),%XMM3 |
(1182) 0x45319f VADDSD (%RBX,%RDX,8),%XMM3,%XMM3 |
(1182) 0x4531a4 VMOVSD %XMM3,(%RCX,%RAX,8) |
(1182) 0x4531a9 MOV -0x60(%RBP),%R14 |
(1182) 0x4531ad INC %RDX |
(1182) 0x4531b0 CMP %R15,%RDX |
(1182) 0x4531b3 JE 4537e6 |
(1182) 0x4531b9 MOV (%R12,%RDX,8),%R14 |
(1182) 0x4531bd MOV -0x38(%RBP),%RAX |
(1182) 0x4531c1 MOV (%RAX,%R14,8),%RAX |
(1182) 0x4531c5 CMP %R13,%RAX |
(1182) 0x4531c8 JGE 453190 |
(1182) 0x4531ca CMP -0x70(%RBP),%RAX |
(1182) 0x4531ce JNE 4533e0 |
(1182) 0x4531d4 MOV -0x198(%RBP),%RSI |
(1182) 0x4531db MOV (%RSI,%R14,8),%RAX |
(1182) 0x4531df VPXOR %XMM3,%XMM3,%XMM3 |
(1182) 0x4531e3 XOR %ECX,%ECX |
(1182) 0x4531e5 VUCOMISD (%RBX,%RAX,8),%XMM3 |
(1182) 0x4531ea MOV 0x8(%RSI,%R14,8),%R9 |
(1182) 0x4531ef SETBE %CL |
(1182) 0x4531f2 ADD %RCX,%RCX |
(1182) 0x4531f5 DEC %RCX |
(1182) 0x4531f8 MOV %RCX,-0x90(%RBP) |
(1182) 0x4531ff LEA 0x1(%RAX),%R10 |
(1182) 0x453203 CMP %R9,%R10 |
(1182) 0x453206 MOV -0x38(%RBP),%RBX |
(1182) 0x45320a JGE 4532e0 |
(1182) 0x453210 VCVTSI2SDQ -0x90(%RBP),%XMM16,%XMM5 |
(1182) 0x453217 MOV %RAX,%RDI |
(1182) 0x45321a NOT %RDI |
(1182) 0x45321d ADD %R9,%RDI |
(1182) 0x453220 MOV %RDI,%R8 |
(1182) 0x453223 AND $-0x4,%R8 |
(1182) 0x453227 JE 45359e |
(1182) 0x45322d LEA -0x1(%R8),%RSI |
(1182) 0x453231 VBROADCASTSD %XMM5,%YMM12 |
(1182) 0x453236 MOV -0x130(%RBP),%RCX |
(1182) 0x45323d LEA (%RCX,%RAX,8),%R11 |
(1182) 0x453241 MOV -0x170(%RBP),%RCX |
(1182) 0x453248 LEA (%RCX,%RAX,8),%R15 |
(1182) 0x45324c VXORPD %XMM3,%XMM3,%XMM3 |
(1182) 0x453250 XOR %R12D,%R12D |
(1182) 0x453253 NOPW %CS:(%RAX,%RAX,1) |
(1189) 0x453260 VMOVDQU (%R15,%R12,8),%YMM1 |
(1189) 0x453266 KXNORW %K0,%K0,%K1 |
(1189) 0x45326a VPXOR %XMM4,%XMM4,%XMM4 |
(1189) 0x45326e VPGATHERQQ (%RBX,%YMM1,8),%YMM4{%K1} |
(1189) 0x453275 VPCMPEQQ %YMM7,%YMM1,%K0 |
(1189) 0x45327b VPCMPNLTQ %YMM8,%YMM4,%K1 |
(1189) 0x453282 KORW %K0,%K1,%K1 |
(1189) 0x453286 VMOVUPD (%R11,%R12,8),%YMM1{%K1}{z} |
(1189) 0x45328d VMULPD %YMM1,%YMM12,%YMM4 |
(1189) 0x453291 VCMPPD $0x1,%YMM2,%YMM4,%K1{%K1} |
(1189) 0x453298 VADDPD %YMM1,%YMM3,%YMM3{%K1} |
(1189) 0x45329e ADD $0x4,%R12 |
(1189) 0x4532a2 CMP %RSI,%R12 |
(1189) 0x4532a5 JBE 453260 |
(1182) 0x4532a7 VEXTRACTF128 $0x1,%YMM3,%XMM1 |
(1182) 0x4532ad VADDPD %XMM1,%XMM3,%XMM1 |
(1182) 0x4532b1 VPERMILPD $0x1,%XMM1,%XMM3 |
(1182) 0x4532b7 VADDSD %XMM3,%XMM1,%XMM3 |
(1182) 0x4532bb CMP %R8,%RDI |
(1182) 0x4532be MOV -0x110(%RBP),%R11 |
(1182) 0x4532c5 MOV -0x40(%RBP),%RSI |
(1182) 0x4532c9 MOV -0xb0(%RBP),%R15 |
(1182) 0x4532d0 JNE 4535a9 |
(1182) 0x4532d6 NOPW %CS:(%RAX,%RAX,1) |
(1182) 0x4532e0 MOV -0xc8(%RBP),%RAX |
(1182) 0x4532e7 MOV (%RAX),%RAX |
(1182) 0x4532ea MOV %RAX,-0x140(%RBP) |
(1182) 0x4532f1 CMP $0x2,%RAX |
(1182) 0x4532f5 JL 45341b |
(1182) 0x4532fb MOV -0x178(%RBP),%RAX |
(1182) 0x453302 MOV (%RAX,%R14,8),%RBX |
(1182) 0x453306 MOV 0x8(%RAX,%R14,8),%R8 |
(1182) 0x45330b MOV %R8,%R15 |
(1182) 0x45330e SUB %RBX,%R15 |
(1182) 0x453311 JLE 453414 |
(1182) 0x453317 VCVTSI2SDQ -0x90(%RBP),%XMM16,%XMM5 |
(1182) 0x45331e MOV %R15,%RDI |
(1182) 0x453321 AND $-0x4,%RDI |
(1182) 0x453325 JE 453621 |
(1182) 0x45332b LEA -0x1(%RDI),%RSI |
(1182) 0x45332f VBROADCASTSD %XMM5,%YMM13 |
(1182) 0x453334 MOV -0x88(%RBP),%RAX |
(1182) 0x45333b LEA (%RAX,%RBX,8),%RAX |
(1182) 0x45333f MOV -0xd8(%RBP),%RCX |
(1182) 0x453346 MOV %RBX,-0x168(%RBP) |
(1182) 0x45334d LEA (%RCX,%RBX,8),%R11 |
(1182) 0x453351 VXORPD %XMM12,%XMM12,%XMM12 |
(1182) 0x453356 XOR %ECX,%ECX |
(1182) 0x453358 MOV -0x60(%RBP),%RBX |
(1182) 0x45335c NOPL (%RAX) |
(1187) 0x453360 VMOVDQU (%R11,%RCX,8),%YMM1 |
(1187) 0x453366 KXNORW %K0,%K0,%K1 |
(1187) 0x45336a VPXOR %XMM4,%XMM4,%XMM4 |
(1187) 0x45336e VPGATHERQQ (%RBX,%YMM1,8),%YMM4{%K1} |
(1187) 0x453375 VPCMPNLTQ %YMM9,%YMM4,%K1 |
(1187) 0x45337c VMOVUPD (%RAX,%RCX,8),%YMM1{%K1}{z} |
(1187) 0x453383 VMULPD %YMM1,%YMM13,%YMM4 |
(1187) 0x453387 VCMPPD $0x1,%YMM2,%YMM4,%K1{%K1} |
(1187) 0x45338e VADDPD %YMM1,%YMM12,%YMM12{%K1} |
(1187) 0x453394 ADD $0x4,%RCX |
(1187) 0x453398 CMP %RSI,%RCX |
(1187) 0x45339b JBE 453360 |
(1182) 0x45339d VEXTRACTF128 $0x1,%YMM12,%XMM1 |
(1182) 0x4533a3 VADDPD %XMM1,%XMM12,%XMM1 |
(1182) 0x4533a7 VPERMILPD $0x1,%XMM1,%XMM4 |
(1182) 0x4533ad VADDSD %XMM4,%XMM1,%XMM1 |
(1182) 0x4533b1 VADDSD %XMM1,%XMM3,%XMM3 |
(1182) 0x4533b5 CMP %RDI,%R15 |
(1182) 0x4533b8 MOV -0x110(%RBP),%R11 |
(1182) 0x4533bf MOV -0xb0(%RBP),%R15 |
(1182) 0x4533c6 MOV -0x168(%RBP),%RBX |
(1182) 0x4533cd JE 45341b |
(1182) 0x4533cf JMP 45362a |
(1182) 0x4533e0 CMPQ $-0x3,(%R11,%R14,8) |
(1182) 0x4533e5 JE 4531a9 |
(1182) 0x4533eb CMPQ $0x1,-0x190(%RBP) |
(1182) 0x4533f3 JE 45340a |
(1182) 0x4533f5 MOV -0x188(%RBP),%RCX |
(1182) 0x4533fc MOV (%RCX,%RDI,8),%RAX |
(1182) 0x453400 CMP (%RCX,%R14,8),%RAX |
(1182) 0x453404 JNE 4531a9 |
(1182) 0x45340a VADDSD (%RBX,%RDX,8),%XMM6,%XMM6 |
(1182) 0x45340f JMP 4531a9 |
(1182) 0x453414 MOV -0xb0(%RBP),%R15 |
(1182) 0x45341b VUCOMISD %XMM0,%XMM3 |
(1182) 0x45341f MOV -0xe0(%RBP),%RBX |
(1182) 0x453426 VMOVSD (%RBX,%RDX,8),%XMM4 |
(1182) 0x45342b JE 4534b8 |
(1182) 0x453431 VDIVSD %XMM3,%XMM4,%XMM3 |
(1182) 0x453435 CMP %R9,%R10 |
(1182) 0x453438 JGE 4534cc |
(1182) 0x45343e VCVTSI2SDQ -0x90(%RBP),%XMM16,%XMM5 |
(1182) 0x453445 MOV -0x40(%RBP),%R12 |
(1182) 0x453449 MOV -0x30(%RBP),%RDI |
(1182) 0x45344d JMP 453458 |
(1185) 0x453450 INC %R10 |
(1185) 0x453453 CMP %R10,%R9 |
(1185) 0x453456 JE 4534d4 |
(1185) 0x453458 MOV (%R12,%R10,8),%RAX |
(1185) 0x45345c MOV -0x38(%RBP),%RCX |
(1185) 0x453460 MOV (%RCX,%RAX,8),%RCX |
(1185) 0x453464 CMP %R13,%RCX |
(1185) 0x453467 JL 45348e |
(1185) 0x453469 VMOVSD (%RBX,%R10,8),%XMM4 |
(1185) 0x45346f VMULSD %XMM5,%XMM4,%XMM1 |
(1185) 0x453473 VUCOMISD %XMM0,%XMM1 |
(1185) 0x453477 JAE 45348e |
(1185) 0x453479 MOV -0xb8(%RBP),%RSI |
(1185) 0x453480 MOV (%RSI),%RSI |
(1185) 0x453483 VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1185) 0x453489 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1185) 0x45348e CMP %RDI,%RAX |
(1185) 0x453491 JNE 453450 |
(1185) 0x453493 VMOVSD (%RBX,%R10,8),%XMM1 |
(1185) 0x453499 VMULSD %XMM5,%XMM1,%XMM4 |
(1185) 0x45349d VMULSD %XMM3,%XMM1,%XMM1 |
(1185) 0x4534a1 VCMPSD $0x1,%XMM0,%XMM4,%K1 |
(1185) 0x4534a8 VMOVAPD %XMM15,%XMM4 |
(1185) 0x4534ac VMOVSD %XMM1,%XMM4,%XMM4{%K1} |
(1185) 0x4534b2 VADDSD %XMM6,%XMM4,%XMM6 |
(1185) 0x4534b6 JMP 453450 |
(1182) 0x4534b8 VADDSD %XMM6,%XMM4,%XMM6 |
(1182) 0x4534bc MOV -0xe8(%RBP),%R9 |
(1182) 0x4534c3 MOV -0x40(%RBP),%R12 |
(1182) 0x4534c7 JMP 453610 |
(1182) 0x4534cc MOV -0x40(%RBP),%R12 |
(1182) 0x4534d0 MOV -0x30(%RBP),%RDI |
(1182) 0x4534d4 CMPQ $0x2,-0x140(%RBP) |
(1182) 0x4534dc JL 45358a |
(1182) 0x4534e2 MOV -0x178(%RBP),%RCX |
(1182) 0x4534e9 MOV (%RCX,%R14,8),%RAX |
(1182) 0x4534ed MOV 0x8(%RCX,%R14,8),%R8 |
(1182) 0x4534f2 MOV %R8,%R9 |
(1182) 0x4534f5 SUB %RAX,%R9 |
(1182) 0x4534f8 JLE 453602 |
(1182) 0x4534fe VCVTSI2SDQ -0x90(%RBP),%XMM16,%XMM5 |
(1182) 0x453505 CMP $0x4,%R9 |
(1182) 0x453509 MOV -0x60(%RBP),%R14 |
(1182) 0x45350d MOV -0x58(%RBP),%R10 |
(1182) 0x453511 JAE 453684 |
(1182) 0x453517 MOV %R9,%RCX |
(1182) 0x45351a AND $-0x4,%RCX |
(1182) 0x45351e CMP %R9,%RCX |
(1182) 0x453521 JAE 4537b0 |
(1182) 0x453527 ADD %RCX,%RAX |
(1182) 0x45352a MOV -0xe8(%RBP),%R9 |
(1182) 0x453531 MOV -0x40(%RBP),%R12 |
(1182) 0x453535 MOV -0xb0(%RBP),%R15 |
(1182) 0x45353c JMP 45354c |
(1183) 0x453540 INC %RAX |
(1183) 0x453543 CMP %RAX,%R8 |
(1183) 0x453546 JE 4537d2 |
(1183) 0x45354c MOV -0xd8(%RBP),%RCX |
(1183) 0x453553 MOV (%RCX,%RAX,8),%RCX |
(1183) 0x453557 MOV (%R14,%RCX,8),%RCX |
(1183) 0x45355b CMP %R10,%RCX |
(1183) 0x45355e JL 453540 |
(1183) 0x453560 MOV -0x88(%RBP),%RSI |
(1183) 0x453567 VMOVSD (%RSI,%RAX,8),%XMM4 |
(1183) 0x45356c VMULSD %XMM5,%XMM4,%XMM1 |
(1183) 0x453570 VUCOMISD %XMM0,%XMM1 |
(1183) 0x453574 JAE 453540 |
(1183) 0x453576 MOV -0x78(%RBP),%RSI |
(1183) 0x45357a MOV (%RSI),%RSI |
(1183) 0x45357d VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1183) 0x453583 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1183) 0x453588 JMP 453540 |
(1182) 0x45358a MOV -0xe8(%RBP),%R9 |
(1182) 0x453591 MOV -0x60(%RBP),%R14 |
(1182) 0x453595 MOV -0x58(%RBP),%R10 |
(1182) 0x453599 JMP 4531ad |
(1182) 0x45359e VXORPD %XMM3,%XMM3,%XMM3 |
(1182) 0x4535a2 XOR %R8D,%R8D |
(1182) 0x4535a5 MOV -0x40(%RBP),%RSI |
(1182) 0x4535a9 ADD %R8,%RAX |
(1182) 0x4535ac INC %RAX |
(1182) 0x4535af MOV -0x30(%RBP),%RDI |
(1182) 0x4535b3 JMP 4535f1 |
(1188) 0x4535c0 MOV -0xe0(%RBP),%RCX |
(1188) 0x4535c7 VMOVSD (%RCX,%RAX,8),%XMM1 |
(1188) 0x4535cc VMULSD %XMM5,%XMM1,%XMM4 |
(1188) 0x4535d0 VCMPSD $0x1,%XMM0,%XMM4,%K1 |
(1188) 0x4535d7 VMOVAPD %XMM15,%XMM4 |
(1188) 0x4535db VMOVSD %XMM1,%XMM4,%XMM4{%K1} |
(1188) 0x4535e1 VADDSD %XMM3,%XMM4,%XMM3 |
(1188) 0x4535e5 INC %RAX |
(1188) 0x4535e8 CMP %RAX,%R9 |
(1188) 0x4535eb JE 4532e0 |
(1188) 0x4535f1 MOV (%RSI,%RAX,8),%RCX |
(1188) 0x4535f5 CMP %R13,(%RBX,%RCX,8) |
(1188) 0x4535f9 JGE 4535c0 |
(1188) 0x4535fb CMP %RDI,%RCX |
(1188) 0x4535fe JNE 4535e5 |
(1188) 0x453600 JMP 4535c0 |
(1182) 0x453602 MOV -0xe8(%RBP),%R9 |
(1182) 0x453609 MOV -0xe0(%RBP),%RBX |
(1182) 0x453610 MOV -0x60(%RBP),%R14 |
(1182) 0x453614 MOV -0x30(%RBP),%RDI |
(1182) 0x453618 MOV -0x58(%RBP),%R10 |
(1182) 0x45361c JMP 4531ad |
(1182) 0x453621 XOR %EDI,%EDI |
(1182) 0x453623 MOV -0xb0(%RBP),%R15 |
(1182) 0x45362a ADD %RBX,%RDI |
(1182) 0x45362d MOV -0x60(%RBP),%RCX |
(1182) 0x453631 MOV -0x58(%RBP),%RSI |
(1182) 0x453635 JMP 45364c |
(1186) 0x453640 INC %RDI |
(1186) 0x453643 CMP %RDI,%R8 |
(1186) 0x453646 JE 45341b |
(1186) 0x45364c MOV -0xd8(%RBP),%RAX |
(1186) 0x453653 MOV (%RAX,%RDI,8),%RAX |
(1186) 0x453657 CMP %RSI,(%RCX,%RAX,8) |
(1186) 0x45365b JL 453640 |
(1186) 0x45365d MOV -0x88(%RBP),%RAX |
(1186) 0x453664 VMOVSD (%RAX,%RDI,8),%XMM1 |
(1186) 0x453669 VMULSD %XMM5,%XMM1,%XMM4 |
(1186) 0x45366d VCMPSD $0x1,%XMM0,%XMM4,%K1 |
(1186) 0x453674 VMOVAPD %XMM15,%XMM4 |
(1186) 0x453678 VMOVSD %XMM1,%XMM4,%XMM4{%K1} |
(1186) 0x45367e VADDSD %XMM3,%XMM4,%XMM3 |
(1186) 0x453682 JMP 453640 |
(1182) 0x453684 MOV %R9,%RDI |
(1182) 0x453687 SHR $0x2,%RDI |
(1182) 0x45368b LEA 0x18(,%RAX,8),%RBX |
(1182) 0x453693 JMP 4536ad |
(1184) 0x4536a0 ADD $0x20,%RBX |
(1184) 0x4536a4 DEC %RDI |
(1184) 0x4536a7 JE 453517 |
(1184) 0x4536ad MOV -0xd8(%RBP),%RCX |
(1184) 0x4536b4 MOV -0x18(%RCX,%RBX,1),%RCX |
(1184) 0x4536b9 MOV (%R14,%RCX,8),%RCX |
(1184) 0x4536bd CMP %R10,%RCX |
(1184) 0x4536c0 JL 4536eb |
(1184) 0x4536c2 MOV -0x88(%RBP),%RSI |
(1184) 0x4536c9 VMOVSD -0x18(%RSI,%RBX,1),%XMM4 |
(1184) 0x4536cf VMULSD %XMM5,%XMM4,%XMM1 |
(1184) 0x4536d3 VUCOMISD %XMM0,%XMM1 |
(1184) 0x4536d7 JAE 4536eb |
(1184) 0x4536d9 MOV -0x78(%RBP),%RSI |
(1184) 0x4536dd MOV (%RSI),%RSI |
(1184) 0x4536e0 VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1184) 0x4536e6 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1184) 0x4536eb MOV -0xd8(%RBP),%RCX |
(1184) 0x4536f2 MOV -0x10(%RCX,%RBX,1),%RCX |
(1184) 0x4536f7 MOV (%R14,%RCX,8),%RCX |
(1184) 0x4536fb CMP %R10,%RCX |
(1184) 0x4536fe JL 453729 |
(1184) 0x453700 MOV -0x88(%RBP),%RSI |
(1184) 0x453707 VMOVSD -0x10(%RSI,%RBX,1),%XMM4 |
(1184) 0x45370d VMULSD %XMM5,%XMM4,%XMM1 |
(1184) 0x453711 VUCOMISD %XMM0,%XMM1 |
(1184) 0x453715 JAE 453729 |
(1184) 0x453717 MOV -0x78(%RBP),%RSI |
(1184) 0x45371b MOV (%RSI),%RSI |
(1184) 0x45371e VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1184) 0x453724 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1184) 0x453729 MOV -0xd8(%RBP),%RCX |
(1184) 0x453730 MOV -0x8(%RCX,%RBX,1),%RCX |
(1184) 0x453735 MOV (%R14,%RCX,8),%RCX |
(1184) 0x453739 CMP %R10,%RCX |
(1184) 0x45373c JL 453767 |
(1184) 0x45373e MOV -0x88(%RBP),%RSI |
(1184) 0x453745 VMOVSD -0x8(%RSI,%RBX,1),%XMM4 |
(1184) 0x45374b VMULSD %XMM5,%XMM4,%XMM1 |
(1184) 0x45374f VUCOMISD %XMM0,%XMM1 |
(1184) 0x453753 JAE 453767 |
(1184) 0x453755 MOV -0x78(%RBP),%RSI |
(1184) 0x453759 MOV (%RSI),%RSI |
(1184) 0x45375c VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1184) 0x453762 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1184) 0x453767 MOV -0xd8(%RBP),%RCX |
(1184) 0x45376e MOV (%RCX,%RBX,1),%RCX |
(1184) 0x453772 MOV (%R14,%RCX,8),%RCX |
(1184) 0x453776 CMP %R10,%RCX |
(1184) 0x453779 JL 4536a0 |
(1184) 0x45377f MOV -0x88(%RBP),%RSI |
(1184) 0x453786 VMOVSD (%RSI,%RBX,1),%XMM4 |
(1184) 0x45378b VMULSD %XMM5,%XMM4,%XMM1 |
(1184) 0x45378f VUCOMISD %XMM0,%XMM1 |
(1184) 0x453793 JAE 4536a0 |
(1184) 0x453799 MOV -0x78(%RBP),%RSI |
(1184) 0x45379d MOV (%RSI),%RSI |
(1184) 0x4537a0 VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM4 |
(1184) 0x4537a6 VMOVSD %XMM4,(%RSI,%RCX,8) |
(1184) 0x4537ab JMP 4536a0 |
(1182) 0x4537b0 MOV -0xe8(%RBP),%R9 |
(1182) 0x4537b7 MOV -0x40(%RBP),%R12 |
(1182) 0x4537bb MOV -0xe0(%RBP),%RBX |
(1182) 0x4537c2 MOV -0x30(%RBP),%RDI |
(1182) 0x4537c6 MOV -0xb0(%RBP),%R15 |
(1182) 0x4537cd JMP 4531ad |
(1182) 0x4537d2 MOV -0xe0(%RBP),%RBX |
(1182) 0x4537d9 MOV -0x30(%RBP),%RDI |
(1182) 0x4537dd JMP 4531ad |
0x4537e2 MOV -0x58(%RBP),%R10 |
0x4537e6 MOV -0xc8(%RBP),%RAX |
0x4537ed CMPQ $0x2,(%RAX) |
0x4537f1 JL 453abf |
0x4537f7 MOV -0x178(%RBP),%RAX |
0x4537fe MOV (%RAX,%RDI,8),%RDX |
0x453802 MOV 0x8(%RAX,%RDI,8),%R8 |
0x453807 CMP %R8,%RDX |
0x45380a JGE 453b2a |
0x453810 MOV -0x38(%RBP),%R15 |
0x453814 JMP 45384d |
(1179) 0x453820 MOV -0x78(%RBP),%RAX |
(1179) 0x453824 MOV (%RAX),%RAX |
(1179) 0x453827 VMOVSD (%RAX,%RCX,8),%XMM1 |
(1179) 0x45382c MOV -0x88(%RBP),%RSI |
(1179) 0x453833 VADDSD (%RSI,%RDX,8),%XMM1,%XMM1 |
(1179) 0x453838 VMOVSD %XMM1,(%RAX,%RCX,8) |
(1179) 0x45383d INC %RDX |
(1179) 0x453840 CMP %R8,%RDX |
(1179) 0x453843 MOV -0x40(%RBP),%R12 |
(1179) 0x453847 JE 453ac3 |
(1179) 0x45384d MOV -0xd8(%RBP),%RAX |
(1179) 0x453854 MOV (%RAX,%RDX,8),%RAX |
(1179) 0x453858 MOV (%R14,%RAX,8),%RCX |
(1179) 0x45385c CMP %R10,%RCX |
(1179) 0x45385f JGE 453820 |
(1179) 0x453861 CMP -0x70(%RBP),%RCX |
(1179) 0x453865 JNE 4538e0 |
(1179) 0x453867 MOV -0x1d8(%RBP),%RCX |
(1179) 0x45386e MOV (%RCX,%RAX,8),%RDI |
(1179) 0x453872 MOV 0x8(%RCX,%RAX,8),%RAX |
(1179) 0x453877 CMP %RDI,%RAX |
(1179) 0x45387a MOV -0x1d0(%RBP),%R12 |
(1179) 0x453881 JLE 453933 |
(1179) 0x453887 MOV %EAX,%ECX |
(1179) 0x453889 SUB %EDI,%ECX |
(1179) 0x45388b LEA 0x1(%RDI),%RSI |
(1179) 0x45388f VXORPD %XMM3,%XMM3,%XMM3 |
(1179) 0x453893 MOV %RDI,%RBX |
(1179) 0x453896 TEST $0x1,%CL |
(1179) 0x453899 JE 45395e |
(1179) 0x45389f MOV (%R9,%RDI,8),%RCX |
(1179) 0x4538a3 MOV %RCX,%RBX |
(1179) 0x4538a6 SUB -0x100(%RBP),%RBX |
(1179) 0x4538ad JL 453948 |
(1179) 0x4538b3 CMP -0xf8(%RBP),%RCX |
(1179) 0x4538ba JGE 453948 |
(1179) 0x4538c0 MOV -0x38(%RBP),%RCX |
(1179) 0x4538c4 CMP %R13,(%RCX,%RBX,8) |
(1179) 0x4538c8 JGE 453955 |
(1179) 0x4538ce VXORPD %XMM3,%XMM3,%XMM3 |
(1179) 0x4538d2 CMP -0x30(%RBP),%RBX |
(1179) 0x4538d6 JNE 45395b |
(1179) 0x4538dc JMP 453955 |
(1179) 0x4538e0 MOV -0x118(%RBP),%RCX |
(1179) 0x4538e7 MOV (%RCX),%RCX |
(1179) 0x4538ea CMPQ $-0x3,(%RCX,%RAX,8) |
(1179) 0x4538ef JE 45383d |
(1179) 0x4538f5 CMPQ $0x1,-0x190(%RBP) |
(1179) 0x4538fd JE 453922 |
(1179) 0x4538ff MOV -0x188(%RBP),%RCX |
(1179) 0x453906 MOV -0x30(%RBP),%RSI |
(1179) 0x45390a MOV (%RCX,%RSI,8),%RCX |
(1179) 0x45390e MOV -0x1c8(%RBP),%RSI |
(1179) 0x453915 MOV (%RSI),%RSI |
(1179) 0x453918 CMP (%RSI,%RAX,8),%RCX |
(1179) 0x45391c JNE 45383d |
(1179) 0x453922 MOV -0x88(%RBP),%RAX |
(1179) 0x453929 VADDSD (%RAX,%RDX,8),%XMM6,%XMM6 |
(1179) 0x45392e JMP 45383d |
(1179) 0x453933 MOV -0x88(%RBP),%RAX |
(1179) 0x45393a VMOVSD (%RAX,%RDX,8),%XMM5 |
(1179) 0x45393f VADDSD %XMM6,%XMM5,%XMM6 |
(1179) 0x453943 JMP 45383d |
(1179) 0x453948 NOT %RCX |
(1179) 0x45394b VXORPD %XMM3,%XMM3,%XMM3 |
(1179) 0x45394f CMP %R10,(%R14,%RCX,8) |
(1179) 0x453953 JL 45395b |
(1179) 0x453955 VMOVSD (%R12,%RDI,8),%XMM3 |
(1179) 0x45395b MOV %RSI,%RBX |
(1179) 0x45395e CMP %RSI,%RAX |
(1179) 0x453961 JNE 453a34 |
(1179) 0x453967 VUCOMISD %XMM0,%XMM3 |
(1179) 0x45396b MOV -0x88(%RBP),%RCX |
(1179) 0x453972 VMOVSD (%RCX,%RDX,8),%XMM5 |
(1179) 0x453977 JE 453ab2 |
(1179) 0x45397d VDIVSD %XMM3,%XMM5,%XMM3 |
(1179) 0x453981 MOV -0x38(%RBP),%R15 |
(1179) 0x453985 JMP 45399c |
(1180) 0x453990 INC %RDI |
(1180) 0x453993 CMP %RDI,%RAX |
(1180) 0x453996 JE 45383d |
(1180) 0x45399c MOV (%R9,%RDI,8),%RSI |
(1180) 0x4539a0 MOV %RSI,%RCX |
(1180) 0x4539a3 SUB -0x100(%RBP),%RCX |
(1180) 0x4539aa JL 4539f0 |
(1180) 0x4539ac CMP -0xf8(%RBP),%RSI |
(1180) 0x4539b3 JGE 4539f0 |
(1180) 0x4539b5 MOV (%R15,%RCX,8),%RSI |
(1180) 0x4539b9 CMP %R13,%RSI |
(1180) 0x4539bc JL 4539dd |
(1180) 0x4539be VMOVSD (%R12,%RDI,8),%XMM1 |
(1180) 0x4539c4 MOV -0xb8(%RBP),%RBX |
(1180) 0x4539cb MOV (%RBX),%RBX |
(1180) 0x4539ce VFMADD213SD (%RBX,%RSI,8),%XMM3,%XMM1 |
(1180) 0x4539d4 VMOVSD %XMM1,(%RBX,%RSI,8) |
(1180) 0x4539d9 MOV -0x38(%RBP),%R15 |
(1180) 0x4539dd CMP -0x30(%RBP),%RCX |
(1180) 0x4539e1 JNE 453990 |
(1180) 0x4539e3 VFMADD231SD (%R12,%RDI,8),%XMM3,%XMM6 |
(1180) 0x4539e9 JMP 453990 |
(1180) 0x4539f0 NOT %RSI |
(1180) 0x4539f3 MOV (%R14,%RSI,8),%RCX |
(1180) 0x4539f7 CMP %R10,%RCX |
(1180) 0x4539fa JL 453990 |
(1180) 0x4539fc VMOVSD (%R12,%RDI,8),%XMM1 |
(1180) 0x453a02 MOV -0x78(%RBP),%RSI |
(1180) 0x453a06 MOV (%RSI),%RSI |
(1180) 0x453a09 VFMADD213SD (%RSI,%RCX,8),%XMM3,%XMM1 |
(1180) 0x453a0f VMOVSD %XMM1,(%RSI,%RCX,8) |
(1180) 0x453a14 JMP 453990 |
(1181) 0x453a20 VADDSD 0x8(%R12,%RBX,8),%XMM3,%XMM3 |
(1181) 0x453a27 ADD $0x2,%RBX |
(1181) 0x453a2b CMP %RBX,%RAX |
(1181) 0x453a2e JE 453967 |
(1181) 0x453a34 MOV (%R9,%RBX,8),%RSI |
(1181) 0x453a38 MOV %RSI,%RCX |
(1181) 0x453a3b SUB -0x100(%RBP),%RCX |
(1181) 0x453a42 JL 453a60 |
(1181) 0x453a44 CMP -0xf8(%RBP),%RSI |
(1181) 0x453a4b JGE 453a60 |
(1181) 0x453a4d MOV -0x38(%RBP),%RSI |
(1181) 0x453a51 CMP %R13,(%RSI,%RCX,8) |
(1181) 0x453a55 JGE 453a69 |
(1181) 0x453a57 CMP -0x30(%RBP),%RCX |
(1181) 0x453a5b JNE 453a6f |
(1181) 0x453a5d JMP 453a69 |
(1181) 0x453a60 NOT %RSI |
(1181) 0x453a63 CMP %R10,(%R14,%RSI,8) |
(1181) 0x453a67 JL 453a6f |
(1181) 0x453a69 VADDSD (%R12,%RBX,8),%XMM3,%XMM3 |
(1181) 0x453a6f MOV 0x8(%R9,%RBX,8),%RSI |
(1181) 0x453a74 MOV %RSI,%RCX |
(1181) 0x453a77 SUB -0x100(%RBP),%RCX |
(1181) 0x453a7e JL 453aa0 |
(1181) 0x453a80 CMP -0xf8(%RBP),%RSI |
(1181) 0x453a87 JGE 453aa0 |
(1181) 0x453a89 MOV -0x38(%RBP),%RSI |
(1181) 0x453a8d CMP %R13,(%RSI,%RCX,8) |
(1181) 0x453a91 JGE 453a20 |
(1181) 0x453a93 CMP -0x30(%RBP),%RCX |
(1181) 0x453a97 JNE 453a27 |
(1181) 0x453a99 JMP 453a20 |
(1181) 0x453aa0 NOT %RSI |
(1181) 0x453aa3 CMP %R10,(%R14,%RSI,8) |
(1181) 0x453aa7 JL 453a27 |
(1181) 0x453aad JMP 453a20 |
(1179) 0x453ab2 MOV -0x38(%RBP),%R15 |
(1179) 0x453ab6 VADDSD %XMM6,%XMM5,%XMM6 |
(1179) 0x453aba JMP 45383d |
0x453abf MOV -0x38(%RBP),%R15 |
0x453ac3 VUCOMISD %XMM0,%XMM6 |
0x453ac7 JE 453b34 |
0x453ac9 MOV -0x50(%RBP),%RSI |
0x453acd SUB %R13,%RSI |
0x453ad0 JLE 453b6a |
0x453ad6 MOV -0xb8(%RBP),%RAX |
0x453add MOV (%RAX),%RAX |
0x453ae0 VDIVSD %XMM6,%XMM10,%XMM3 |
0x453ae4 MOV %RSI,%RDX |
0x453ae7 AND $-0x4,%RDX |
0x453aeb JE 453b44 |
0x453aed LEA -0x1(%RDX),%RCX |
0x453af1 VBROADCASTSD %XMM3,%YMM5 |
0x453af6 LEA (%RAX,%R13,8),%RDI |
0x453afa XOR %EBX,%EBX |
0x453afc NOPL (%RAX) |
(1178) 0x453b00 VXORPD (%RDI,%RBX,8),%YMM11,%YMM1 |
(1178) 0x453b05 VMULPD %YMM1,%YMM5,%YMM1 |
(1178) 0x453b09 VMOVUPD %YMM1,(%RDI,%RBX,8) |
(1178) 0x453b0e ADD $0x4,%RBX |
(1178) 0x453b12 CMP %RCX,%RBX |
(1178) 0x453b15 JBE 453b00 |
0x453b17 CMP %RDX,%RSI |
0x453b1a MOV -0x40(%RBP),%R12 |
0x453b1e MOV -0x38(%RBP),%R15 |
0x453b22 MOV -0x50(%RBP),%RCX |
0x453b26 JNE 453b4a |
0x453b28 JMP 453b6a |
0x453b2a MOV -0x38(%RBP),%R15 |
0x453b2e VUCOMISD %XMM0,%XMM6 |
0x453b32 JNE 453ac9 |
0x453b34 MOV -0x138(%RBP),%R8 |
0x453b3b MOV -0x30(%RBP),%RDX |
0x453b3f JMP 452d0e |
0x453b44 XOR %EDX,%EDX |
0x453b46 MOV -0x50(%RBP),%RCX |
0x453b4a ADD %R13,%RDX |
0x453b4d NOPL (%RAX) |
(1177) 0x453b50 VMOVSD (%RAX,%RDX,8),%XMM1 |
(1177) 0x453b55 VXORPD %XMM1,%XMM14,%XMM1 |
(1177) 0x453b59 VMULSD %XMM1,%XMM3,%XMM1 |
(1177) 0x453b5d VMOVSD %XMM1,(%RAX,%RDX,8) |
(1177) 0x453b62 INC %RDX |
(1177) 0x453b65 CMP %RDX,%RCX |
(1177) 0x453b68 JNE 453b50 |
0x453b6a MOV -0x48(%RBP),%RDX |
0x453b6e SUB %R10,%RDX |
0x453b71 MOV -0x138(%RBP),%R8 |
0x453b78 MOV -0x98(%RBP),%R13 |
0x453b7f JLE 453bfa |
0x453b81 MOV -0x78(%RBP),%RAX |
0x453b85 MOV (%RAX),%RAX |
0x453b88 VDIVSD %XMM6,%XMM10,%XMM3 |
0x453b8c MOV %RDX,%RCX |
0x453b8f AND $-0x4,%RCX |
0x453b93 JE 453bd6 |
0x453b95 LEA -0x1(%RCX),%RSI |
0x453b99 VBROADCASTSD %XMM3,%YMM5 |
0x453b9e LEA (%RAX,%R10,8),%RDI |
0x453ba2 XOR %EBX,%EBX |
0x453ba4 NOPW %CS:(%RAX,%RAX,1) |
(1176) 0x453bb0 VXORPD (%RDI,%RBX,8),%YMM11,%YMM1 |
(1176) 0x453bb5 VMULPD %YMM1,%YMM5,%YMM1 |
(1176) 0x453bb9 VMOVUPD %YMM1,(%RDI,%RBX,8) |
(1176) 0x453bbe ADD $0x4,%RBX |
(1176) 0x453bc2 CMP %RSI,%RBX |
(1176) 0x453bc5 JBE 453bb0 |
0x453bc7 CMP %RCX,%RDX |
0x453bca MOV -0x40(%RBP),%R12 |
0x453bce MOV -0x38(%RBP),%R15 |
0x453bd2 JNE 453bd8 |
0x453bd4 JMP 453bfa |
0x453bd6 XOR %ECX,%ECX |
0x453bd8 ADD %R10,%RCX |
0x453bdb MOV -0x48(%RBP),%RDX |
0x453bdf NOP |
(1175) 0x453be0 VMOVSD (%RAX,%RCX,8),%XMM1 |
(1175) 0x453be5 VXORPD %XMM1,%XMM14,%XMM1 |
(1175) 0x453be9 VMULSD %XMM1,%XMM3,%XMM1 |
(1175) 0x453bed VMOVSD %XMM1,(%RAX,%RCX,8) |
(1175) 0x453bf2 INC %RCX |
(1175) 0x453bf5 CMP %RCX,%RDX |
(1175) 0x453bf8 JNE 453be0 |
0x453bfa MOV -0x30(%RBP),%RDX |
0x453bfe DECQ -0x70(%RBP) |
0x453c02 INC %RDX |
0x453c05 CMP %R13,%RDX |
0x453c08 JNE 452d25 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_lr_interp.c: 1221 - 1748 |
-------------------------------------------------------------------------------- |
1221: if (n_fine) |
[...] |
1469: for (i = start; i < stop; i++) |
1470: { |
1471: jj_begin_row = P_diag_i[i]; |
1472: jj_begin_row_offd = P_offd_i[i]; |
[...] |
1480: if (CF_marker[i] >= 0) |
1481: { |
1482: P_diag_j[jj_counter] = fine_to_coarse[i]; |
1483: P_diag_data[jj_counter] = one; |
[...] |
1491: else if (CF_marker[i] != -3) |
1492: { |
1493: strong_f_marker--; |
1494: for (jj = S_diag_i[i]; jj < S_diag_i[i+1]; jj++) |
1495: { |
1496: i1 = S_diag_j[jj]; |
[...] |
1503: if (CF_marker[i1] >= 0) |
1504: { |
1505: if (P_marker[i1] < jj_begin_row) |
1506: { |
1507: P_marker[i1] = jj_counter; |
1508: P_diag_j[jj_counter] = fine_to_coarse[i1]; |
1509: P_diag_data[jj_counter] = zero; |
1510: jj_counter++; |
1511: } |
1512: } |
1513: else if (CF_marker[i1] != -3) |
1514: { |
1515: P_marker[i1] = strong_f_marker; |
1516: for (kk = S_diag_i[i1]; kk < S_diag_i[i1+1]; kk++) |
1517: { |
1518: k1 = S_diag_j[kk]; |
1519: if (CF_marker[k1] >= 0) |
1520: { |
1521: if(P_marker[k1] < jj_begin_row) |
1522: { |
1523: P_marker[k1] = jj_counter; |
1524: P_diag_j[jj_counter] = fine_to_coarse[k1]; |
1525: P_diag_data[jj_counter] = zero; |
1526: jj_counter++; |
1527: } |
1528: } |
1529: } |
1530: if(num_procs > 1) |
1531: { |
1532: for (kk = S_offd_i[i1]; kk < S_offd_i[i1+1]; kk++) |
1533: { |
1534: if(col_offd_S_to_A) |
1535: k1 = col_offd_S_to_A[S_offd_j[kk]]; |
1536: else |
1537: k1 = S_offd_j[kk]; |
1538: if(CF_marker_offd[k1] >= 0) |
1539: { |
1540: if(P_marker_offd[k1] < jj_begin_row_offd) |
1541: { |
1542: P_marker_offd[k1] = jj_counter_offd; |
1543: P_offd_j[jj_counter_offd] = k1; |
1544: P_offd_data[jj_counter_offd] = zero; |
1545: jj_counter_offd++; |
[...] |
1553: if ( num_procs > 1) |
1554: { |
1555: for (jj=S_offd_i[i]; jj < S_offd_i[i+1]; jj++) |
1556: { |
1557: i1 = S_offd_j[jj]; |
1558: if(col_offd_S_to_A) |
1559: i1 = col_offd_S_to_A[i1]; |
1560: if ( CF_marker_offd[i1] >= 0) |
1561: { |
1562: if(P_marker_offd[i1] < jj_begin_row_offd) |
1563: { |
1564: P_marker_offd[i1] = jj_counter_offd; |
1565: P_offd_j[jj_counter_offd] = i1; |
1566: P_offd_data[jj_counter_offd] = zero; |
1567: jj_counter_offd++; |
1568: } |
1569: } |
1570: else if (CF_marker_offd[i1] != -3) |
1571: { |
1572: P_marker_offd[i1] = strong_f_marker; |
1573: for(kk = Sop_i[i1]; kk < Sop_i[i1+1]; kk++) |
1574: { |
1575: k1 = Sop_j[kk]; |
1576: /* Find local col number */ |
1577: if(k1 >= col_1 && k1 < col_n) |
1578: { |
1579: loc_col = k1-col_1; |
1580: if(P_marker[loc_col] < jj_begin_row) |
1581: { |
1582: P_marker[loc_col] = jj_counter; |
1583: P_diag_j[jj_counter] = fine_to_coarse[loc_col]; |
1584: P_diag_data[jj_counter] = zero; |
1585: jj_counter++; |
1586: } |
1587: } |
1588: else |
1589: { |
1590: loc_col = -k1 - 1; |
1591: if(P_marker_offd[loc_col] < jj_begin_row_offd) |
1592: { |
1593: P_marker_offd[loc_col] = jj_counter_offd; |
1594: P_offd_j[jj_counter_offd]=loc_col; |
1595: P_offd_data[jj_counter_offd] = zero; |
1596: jj_counter_offd++; |
[...] |
1607: diagonal = A_diag_data[A_diag_i[i]]; |
1608: |
1609: for (jj = A_diag_i[i]+1; jj < A_diag_i[i+1]; jj++) |
1610: { /* i1 is a c-point and strongly influences i, accumulate |
1611: * a_(i,i1) into interpolation weight */ |
1612: i1 = A_diag_j[jj]; |
1613: if (P_marker[i1] >= jj_begin_row) |
1614: { |
1615: P_diag_data[P_marker[i1]] += A_diag_data[jj]; |
1616: } |
1617: else if(P_marker[i1] == strong_f_marker) |
1618: { |
1619: sum = zero; |
1620: sgn = 1; |
1621: if(A_diag_data[A_diag_i[i1]] < 0) sgn = -1; |
1622: /* Loop over row of A for point i1 and calculate the sum |
1623: * of the connections to c-points that strongly influence i. */ |
1624: for(jj1 = A_diag_i[i1]+1; jj1 < A_diag_i[i1+1]; jj1++) |
1625: { |
1626: i2 = A_diag_j[jj1]; |
1627: if((P_marker[i2] >= jj_begin_row || i2 == i) && (sgn*A_diag_data[jj1]) < 0) |
1628: sum += A_diag_data[jj1]; |
1629: } |
1630: if(num_procs > 1) |
1631: { |
1632: for(jj1 = A_offd_i[i1]; jj1< A_offd_i[i1+1]; jj1++) |
1633: { |
1634: i2 = A_offd_j[jj1]; |
1635: if(P_marker_offd[i2] >= jj_begin_row_offd && |
1636: (sgn*A_offd_data[jj1]) < 0) |
1637: sum += A_offd_data[jj1]; |
1638: } |
1639: } |
1640: if(sum != 0) |
1641: { |
1642: distribute = A_diag_data[jj]/sum; |
1643: /* Loop over row of A for point i1 and do the distribution */ |
1644: for(jj1 = A_diag_i[i1]+1; jj1 < A_diag_i[i1+1]; jj1++) |
1645: { |
1646: i2 = A_diag_j[jj1]; |
1647: if(P_marker[i2] >= jj_begin_row && (sgn*A_diag_data[jj1]) < 0) |
1648: P_diag_data[P_marker[i2]] += |
1649: distribute*A_diag_data[jj1]; |
1650: if(i2 == i && (sgn*A_diag_data[jj1]) < 0) |
1651: diagonal += distribute*A_diag_data[jj1]; |
1652: } |
1653: if(num_procs > 1) |
1654: { |
1655: for(jj1 = A_offd_i[i1]; jj1 < A_offd_i[i1+1]; jj1++) |
1656: { |
1657: i2 = A_offd_j[jj1]; |
1658: if(P_marker_offd[i2] >= jj_begin_row_offd && |
1659: (sgn*A_offd_data[jj1]) < 0) |
1660: P_offd_data[P_marker_offd[i2]] += |
[...] |
1667: diagonal += A_diag_data[jj]; |
1668: } |
1669: } |
1670: /* neighbor i1 weakly influences i, accumulate a_(i,i1) into |
1671: * diagonal */ |
1672: else if (CF_marker[i1] != -3) |
1673: { |
1674: if(num_functions == 1 || dof_func[i] == dof_func[i1]) |
1675: diagonal += A_diag_data[jj]; |
1676: } |
1677: } |
1678: if(num_procs > 1) |
1679: { |
1680: for(jj = A_offd_i[i]; jj < A_offd_i[i+1]; jj++) |
1681: { |
1682: i1 = A_offd_j[jj]; |
1683: if(P_marker_offd[i1] >= jj_begin_row_offd) |
1684: P_offd_data[P_marker_offd[i1]] += A_offd_data[jj]; |
1685: else if(P_marker_offd[i1] == strong_f_marker) |
1686: { |
1687: sum = zero; |
1688: for(jj1 = A_ext_i[i1]; jj1 < A_ext_i[i1+1]; jj1++) |
1689: { |
1690: k1 = A_ext_j[jj1]; |
1691: if(k1 >= col_1 && k1 < col_n) |
1692: { /* diag */ |
1693: loc_col = k1 - col_1; |
1694: if(P_marker[loc_col] >= jj_begin_row || loc_col == i) |
1695: sum += A_ext_data[jj1]; |
1696: } |
1697: else |
1698: { |
1699: loc_col = -k1 - 1; |
1700: if(P_marker_offd[loc_col] >= jj_begin_row_offd) |
1701: sum += A_ext_data[jj1]; |
1702: } |
1703: } |
1704: if(sum != 0) |
1705: { |
1706: distribute = A_offd_data[jj] / sum; |
1707: for(jj1 = A_ext_i[i1]; jj1 < A_ext_i[i1+1]; jj1++) |
1708: { |
1709: k1 = A_ext_j[jj1]; |
1710: if(k1 >= col_1 && k1 < col_n) |
1711: { /* diag */ |
1712: loc_col = k1 - col_1; |
1713: if(P_marker[loc_col] >= jj_begin_row) |
1714: P_diag_data[P_marker[loc_col]] += distribute* |
1715: A_ext_data[jj1]; |
1716: if(loc_col == i) |
1717: diagonal += distribute*A_ext_data[jj1]; |
1718: } |
1719: else |
1720: { |
1721: loc_col = -k1 - 1; |
1722: if(P_marker_offd[loc_col] >= jj_begin_row_offd) |
1723: P_offd_data[P_marker_offd[loc_col]] += distribute* |
1724: A_ext_data[jj1]; |
[...] |
1730: diagonal += A_offd_data[jj]; |
1731: } |
1732: } |
1733: else if (CF_marker_offd[i1] != -3) |
1734: { |
1735: if(num_functions == 1 || dof_func[i] == dof_func_offd[i1]) |
1736: diagonal += A_offd_data[jj]; |
1737: } |
1738: } |
1739: } |
1740: if (diagonal) |
1741: { |
1742: for(jj = jj_begin_row; jj < jj_end_row; jj++) |
1743: P_diag_data[jj] /= -diagonal; |
1744: for(jj = jj_begin_row_offd; jj < jj_end_row_offd; jj++) |
1745: P_offd_data[jj] /= -diagonal; |
1746: } |
1747: } |
1748: strong_f_marker--; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_fork_call | libiomp5.so | |
| ○ | __kmpc_fork_call | libiomp5.so | |
| ○ | hypre_BoomerAMGBuildExtPIInter[...] | par_lr_interp.c:1196 | exec |
| ○ | hypre_BoomerAMGSetup | par_amg_setup.c:847 | exec |
| ○ | hypre_PCGSetup | pcg.c:234 | exec |
| ○ | main | amg.c:398 | exec |
| ○ | __libc_init_first | libc.so.6 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.11 |
| CQA speedup if FP arith vectorized | 2.45 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.16 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_BoomerAMGBuildExtPIInterp.extracted |
| Source | par_lr_interp.c:1221-1748 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 36.50 |
| CQA cycles if no scalar integer | 11.75 |
| CQA cycles if FP arith vectorized | 14.90 |
| CQA cycles if fully vectorized | 4.56 |
| Front-end cycles | 36.50 |
| DIV/SQRT cycles | 15.75 |
| P0 cycles | 15.75 |
| P1 cycles | 31.50 |
| P2 cycles | 31.50 |
| P3 cycles | 12.00 |
| P4 cycles | 15.75 |
| P5 cycles | 15.75 |
| P6 cycles | 12.00 |
| P7 cycles | 8.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 36.04 - 36.05 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 139.00 |
| Nb uops | 144.00 |
| Nb loads | 63.00 |
| Nb stores | 12.00 |
| Nb stack references | 24.00 |
| FLOP/cycle | 0.05 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 2.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 16.44 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 504.00 |
| Bytes stored | 96.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | 0.00 |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | 12.50 |
| Vector-efficiency ratio other | 12.50 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.11 |
| CQA speedup if FP arith vectorized | 2.45 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.16 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_BoomerAMGBuildExtPIInterp.extracted |
| Source | par_lr_interp.c:1221-1748 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 36.50 |
| CQA cycles if no scalar integer | 11.75 |
| CQA cycles if FP arith vectorized | 14.90 |
| CQA cycles if fully vectorized | 4.56 |
| Front-end cycles | 36.50 |
| DIV/SQRT cycles | 15.75 |
| P0 cycles | 15.75 |
| P1 cycles | 31.50 |
| P2 cycles | 31.50 |
| P3 cycles | 12.00 |
| P4 cycles | 15.75 |
| P5 cycles | 15.75 |
| P6 cycles | 12.00 |
| P7 cycles | 8.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 36.04 - 36.05 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 139.00 |
| Nb uops | 144.00 |
| Nb loads | 63.00 |
| Nb stores | 12.00 |
| Nb stack references | 24.00 |
| FLOP/cycle | 0.05 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 2.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 16.44 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 504.00 |
| Bytes stored | 96.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | 0.00 |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | 12.50 |
| Vector-efficiency ratio other | 12.50 |
| Path / |
| Function | hypre_BoomerAMGBuildExtPIInterp.extracted |
| Source file and lines | par_lr_interp.c:1221-1748 |
| Module | exec |
| nb instructions | 139 |
| nb uops | 144 |
| loop length | 591 |
| used x86 registers | 13 |
| used mmx registers | 0 |
| used xmm registers | 4 |
| used ymm registers | 4 |
| used zmm registers | 0 |
| nb stack references | 24 |
| micro-operation queue | 36.50 cycles |
| front end | 36.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 15.75 | 15.75 | 31.50 | 31.50 | 12.00 | 15.75 | 15.75 | 12.00 |
| cycles | 15.75 | 15.75 | 31.50 | 31.50 | 12.00 | 15.75 | 15.75 | 12.00 |
| Cycles executing div or sqrt instructions | 8.00 |
| FE+BE cycles | 36.04-36.05 |
| Stall cycles | 0.00 |
| Front-end | 36.50 |
| Dispatch | 31.50 |
| DIV/SQRT | 8.00 |
| Overall L1 | 36.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 0% |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 0% |
| other | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 12% |
| load | 12% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 12% |
| other | 12% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 12% |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RCX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,(%RCX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0xb8(%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 $0x3ff0000000000000,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV %RCX,(%RAX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x98(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 453c0e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x80(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R11,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNS 452ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RDX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| CMP $-0x3,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 452d46 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 452d0e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| 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),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| MOV -0xd0(%RBP),%RAX | 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 %R13,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| CMP 0x8(%RAX,%RCX,8),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 452fa0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R13,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 452da9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMPQ $0x2,(%RAX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %R10,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JL 45313b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0xa0(%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 |
| CMP 0x8(%RCX,%RDX,8),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 45313b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RCX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x120(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 453009 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x198(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0xe0(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVSD (%RBX,%RDX,8),%XMM6 | 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 %R15,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4537e2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| VPBROADCASTQ %RDI,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| VPBROADCASTQ %R13,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VPBROADCASTQ %R10,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| MOV %R15,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 4531b9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x58(%RBP),%R10 | 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 |
| CMPQ $0x2,(%RAX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JL 453abf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x178(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 453b2a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 45384d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VUCOMISD %XMM0,%XMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| JE 453b34 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x50(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| SUB %R13,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JLE 453b6a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0xb8(%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 |
| VDIVSD %XMM6,%XMM10,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
| MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| AND $-0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 453b44 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%RDX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VBROADCASTSD %XMM3,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| LEA (%RAX,%R13,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| XOR %EBX,%EBX | 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 %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JNE 453b4a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 453b6a | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VUCOMISD %XMM0,%XMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| JNE 453ac9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x138(%RBP),%R8 | 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 |
| JMP 452d0e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| ADD %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x48(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| SUB %R10,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x138(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x98(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JLE 453bfa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x78(%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 |
| VDIVSD %XMM6,%XMM10,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
| MOV %RDX,%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 453bd6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%RCX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VBROADCASTSD %XMM3,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| LEA (%RAX,%R10,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JNE 453bd8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 453bfa | 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 %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x48(%RBP),%RDX | 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 -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 452d25 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| Function | hypre_BoomerAMGBuildExtPIInterp.extracted |
| Source file and lines | par_lr_interp.c:1221-1748 |
| Module | exec |
| nb instructions | 139 |
| nb uops | 144 |
| loop length | 591 |
| used x86 registers | 13 |
| used mmx registers | 0 |
| used xmm registers | 4 |
| used ymm registers | 4 |
| used zmm registers | 0 |
| nb stack references | 24 |
| micro-operation queue | 36.50 cycles |
| front end | 36.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 15.75 | 15.75 | 31.50 | 31.50 | 12.00 | 15.75 | 15.75 | 12.00 |
| cycles | 15.75 | 15.75 | 31.50 | 31.50 | 12.00 | 15.75 | 15.75 | 12.00 |
| Cycles executing div or sqrt instructions | 8.00 |
| FE+BE cycles | 36.04-36.05 |
| Stall cycles | 0.00 |
| Front-end | 36.50 |
| Dispatch | 31.50 |
| DIV/SQRT | 8.00 |
| Overall L1 | 36.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 0% |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 0% |
| other | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 12% |
| load | 12% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 12% |
| other | 12% |
| all | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | 12% |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RCX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,(%RCX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0xb8(%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 $0x3ff0000000000000,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV %RCX,(%RAX,%R13,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV -0x98(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 453c0e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x80(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDX,8),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%R11,%RDX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNS 452ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %RDX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| CMP $-0x3,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 452d46 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 452d0e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| 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),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| MOV -0xd0(%RBP),%RAX | 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 %R13,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| CMP 0x8(%RAX,%RCX,8),%RDX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 452fa0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R10,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV %R13,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 452da9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0xc8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMPQ $0x2,(%RAX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %R10,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JL 45313b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0xa0(%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 |
| CMP 0x8(%RCX,%RDX,8),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 45313b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RCX),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x120(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 453009 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x198(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0xe0(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VMOVSD (%RBX,%RDX,8),%XMM6 | 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 %R15,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 4537e2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| VPBROADCASTQ %RDI,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| VPBROADCASTQ %R13,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| MOV -0x58(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VPBROADCASTQ %R10,%YMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| MOV %R15,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| JMP 4531b9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x58(%RBP),%R10 | 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 |
| CMPQ $0x2,(%RAX) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JL 453abf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x178(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JGE 453b2a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 45384d | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VUCOMISD %XMM0,%XMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| JE 453b34 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x50(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| SUB %R13,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JLE 453b6a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0xb8(%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 |
| VDIVSD %XMM6,%XMM10,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
| MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| AND $-0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 453b44 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%RDX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VBROADCASTSD %XMM3,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| LEA (%RAX,%R13,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| XOR %EBX,%EBX | 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 %RDX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JNE 453b4a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 453b6a | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| VUCOMISD %XMM0,%XMM6 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
| JNE 453ac9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x138(%RBP),%R8 | 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 |
| JMP 452d0e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x50(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| ADD %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x48(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| SUB %R10,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x138(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x98(%RBP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JLE 453bfa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x78(%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 |
| VDIVSD %XMM6,%XMM10,%XMM3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 13-14 | 4 |
| MOV %RDX,%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 453bd6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%RCX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VBROADCASTSD %XMM3,%YMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| LEA (%RAX,%R10,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x40(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x38(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JNE 453bd8 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 453bfa | 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 %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x48(%RBP),%RDX | 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 -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| DECQ -0x70(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| CMP %R13,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JNE 452d25 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
