Loop Id: 1331 | Module: exec | Source: Scattering.cpp:82-97 [...] | Coverage: 55.98% |
---|
Loop Id: 1331 | Module: exec | Source: Scattering.cpp:82-97 [...] | Coverage: 55.98% |
---|
0x47cfa0 VXORPD %XMM1,%XMM1,%XMM1 |
0x47cfa4 MOV -0x138(%RBP),%RAX |
0x47cfab ADD %RCX,%RAX |
0x47cfae ADD -0x130(%RBP),%RAX |
0x47cfb5 MOV -0x118(%RBP),%RDI |
0x47cfbc VMOVSD (%RDI,%RAX,8),%XMM2 |
0x47cfc1 MOV -0x128(%RBP),%RAX |
0x47cfc8 ADD %RCX,%RAX |
0x47cfcb MOV -0x120(%RBP),%RDI |
0x47cfd2 VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 |
0x47cfd8 VMOVSD %XMM2,(%RDI,%RAX,8) |
0x47cfdd CMP -0x110(%RBP),%RCX |
0x47cfe4 LEA 0x1(%RCX),%RCX |
0x47cfe8 JE 47cf60 |
0x47cfee LEA (%R10,%RCX,1),%RAX |
0x47cff2 MOVSXD (%R11,%RAX,4),%RDI |
0x47cff6 TEST %RDI,%RDI |
0x47cff9 JLE 47cfa0 |
0x47cffb MOV -0xf0(%RBP),%RBX |
0x47d002 MOV (%RBX,%RAX,8),%RSI |
0x47d006 MOV -0xf8(%RBP),%RAX |
0x47d00d MOV -0x100(%RBP),%RBX |
0x47d014 MOV (%RAX,%RBX,8),%R8 |
0x47d018 ADD %RSI,%RDI |
0x47d01b LEA 0x1(%RSI),%RAX |
0x47d01f CMP %RAX,%RDI |
0x47d022 CMOVLE %RAX,%RDI |
0x47d026 MOV %RDI,%RBX |
0x47d029 SUB %RSI,%RBX |
0x47d02c MOV %RBX,%RAX |
0x47d02f AND $-0x4,%RAX |
0x47d033 MOV %RSI,-0x140(%RBP) |
0x47d03a JE 47d0e0 |
0x47d040 MOV %RBX,-0x108(%RBP) |
0x47d047 LEA -0x1(%RAX),%R11 |
0x47d04b MOV -0x80(%RBP),%RBX |
0x47d04f IMUL %R8,%RBX |
0x47d053 ADD -0x30(%RBP),%RBX |
0x47d057 ADD %R9,%RBX |
0x47d05a ADD %R13,%RBX |
0x47d05d ADD %RDX,%RBX |
0x47d060 VPBROADCASTQ %RBX,%YMM2 |
0x47d066 LEA (%R14,%RSI,8),%R10 |
0x47d06a MOV -0x78(%RBP),%RBX |
0x47d06e LEA (%RBX,%RSI,8),%R12 |
0x47d072 MOV %RBX,%RSI |
0x47d075 VXORPD %XMM1,%XMM1,%XMM1 |
0x47d079 XOR %EBX,%EBX |
0x47d07b NOPL (%RAX,%RAX,1) |
(1333) 0x47d080 VPMULLQ (%R12,%RBX,8),%YMM0,%YMM3 |
(1333) 0x47d087 VPADDQ %YMM3,%YMM2,%YMM3 |
(1333) 0x47d08b VXORPD %XMM4,%XMM4,%XMM4 |
(1333) 0x47d08f KXNORW %K0,%K0,%K1 |
(1333) 0x47d093 VGATHERQPD (%R15,%YMM3,8),%YMM4{%K1} |
(1333) 0x47d09a VFMADD231PD (%R10,%RBX,8),%YMM4,%YMM1 |
(1333) 0x47d0a0 ADD $0x4,%RBX |
(1333) 0x47d0a4 CMP %R11,%RBX |
(1333) 0x47d0a7 JBE 47d080 |
0x47d0a9 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
0x47d0af VADDPD %XMM2,%XMM1,%XMM1 |
0x47d0b3 VPERMILPD $0x1,%XMM1,%XMM2 |
0x47d0b9 VADDSD %XMM2,%XMM1,%XMM1 |
0x47d0bd CMP %RAX,-0x108(%RBP) |
0x47d0c4 MOV -0x70(%RBP),%R10 |
0x47d0c8 MOV -0xe8(%RBP),%R11 |
0x47d0cf MOV -0x48(%RBP),%R12 |
0x47d0d3 JE 47cfa4 |
0x47d0d9 JMP 47d0ee |
0x47d0e0 VXORPD %XMM1,%XMM1,%XMM1 |
0x47d0e4 XOR %EAX,%EAX |
0x47d0e6 MOV -0x48(%RBP),%R12 |
0x47d0ea MOV -0x78(%RBP),%RSI |
0x47d0ee IMUL -0x80(%RBP),%R8 |
0x47d0f3 ADD -0x30(%RBP),%R8 |
0x47d0f7 ADD -0x140(%RBP),%RAX |
0x47d0fe XCHG %AX,%AX |
(1332) 0x47d100 MOV (%RSI,%RAX,8),%RBX |
(1332) 0x47d104 IMUL %R12,%RBX |
(1332) 0x47d108 ADD %R8,%RBX |
(1332) 0x47d10b ADD %R9,%RBX |
(1332) 0x47d10e ADD %R13,%RBX |
(1332) 0x47d111 ADD %RDX,%RBX |
(1332) 0x47d114 VMOVSD (%R15,%RBX,8),%XMM2 |
(1332) 0x47d11a VFMADD231SD (%R14,%RAX,8),%XMM2,%XMM1 |
(1332) 0x47d120 INC %RAX |
(1332) 0x47d123 CMP %RAX,%RDI |
(1332) 0x47d126 JNE 47d100 |
0x47d128 JMP 47cfa4 |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/src/Kripke/Kernel/Scattering.cpp: 82 - 97 |
-------------------------------------------------------------------------------- |
82: Legendre n = moment_to_legendre(nm); |
83: |
84: GlobalGroup global_g{*g+glower_dst}; |
85: GlobalGroup global_gp{*gp+glower_src}; |
86: |
87: MixElem mix_start = zone_to_mixelem(z); |
88: MixElem mix_stop = mix_start + zone_to_num_mixelem(z); |
89: |
90: double sigs_z = 0.0; |
91: for(MixElem mix = mix_start;mix < mix_stop;++ mix){ |
92: Material mat = mixelem_to_material(mix); |
93: double fraction = mixelem_to_fraction(mix); |
94: |
95: sigs_z += sigs(mat, n, global_g, global_gp) * fraction; |
96: } |
97: phi_out(nm, g, z) += sigs_z * phi(nm, gp, z); |
/home/kcamus/qaas_runs/169-391-8990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/index/IndexValue.hpp: 217 - 217 |
-------------------------------------------------------------------------------- |
217: return (value < x.value); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | void Kripke::DispatchHelper<Kr[...] | internal.hpp:345 | exec |
○ | Kripke::Kernel::scattering(Kri[...] | ArchLayout.h:145 | exec |
○ | Kripke::SteadyStateSolver(Krip[...] | SteadyStateSolver.cpp:65 | exec |
○ | main | kripke.cpp:482 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.25 |
CQA speedup if FP arith vectorized | 2.80 |
CQA speedup if fully vectorized | 7.74 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,Scattering.cpp:82-97,IndexValue.hpp:217-217 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 11.38 |
CQA cycles if no scalar integer | 5.06 |
CQA cycles if FP arith vectorized | 4.06 |
CQA cycles if fully vectorized | 1.47 |
Front-end cycles | 11.38 |
DIV/SQRT cycles | 6.19 |
P0 cycles | 6.19 |
P1 cycles | 9.13 |
P2 cycles | 9.13 |
P3 cycles | 2.25 |
P4 cycles | 6.19 |
P5 cycles | 6.19 |
P6 cycles | 2.25 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 11.62 |
Stall cycles (UFS) | 0.00 |
Nb insns | 44.75 |
Nb uops | 44.50 |
Nb loads | 18.25 |
Nb stores | 2.25 |
Nb stack references | 13.50 |
FLOP/cycle | 0.31 |
Nb FLOP add-sub | 1.50 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 14.68 |
Bytes prefetched | 0.00 |
Bytes loaded | 142.00 |
Bytes stored | 18.00 |
Stride 0 | 1.50 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 18.60 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 27.78 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 38.84 |
Vector-efficiency ratio all | 14.82 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 15.97 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.35 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.80 |
CQA speedup if FP arith vectorized | 2.40 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.00 |
Bottlenecks | micro-operation queue, P2, P3, |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,Scattering.cpp:82-97,IndexValue.hpp:217-217 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.50 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 1.88 |
CQA cycles if fully vectorized | 0.56 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 2.25 |
P0 cycles | 2.25 |
P1 cycles | 4.50 |
P2 cycles | 4.50 |
P3 cycles | 1.00 |
P4 cycles | 2.25 |
P5 cycles | 2.25 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 4.74 |
Stall cycles (UFS) | 0.00 |
Nb insns | 18.00 |
Nb uops | 17.00 |
Nb loads | 9.00 |
Nb stores | 1.00 |
Nb stack references | 6.00 |
FLOP/cycle | 0.44 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 16.89 |
Bytes prefetched | 0.00 |
Bytes loaded | 68.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 20.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 50.00 |
Vector-efficiency ratio all | 15.00 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 18.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.10 |
CQA speedup if FP arith vectorized | 2.47 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | micro-operation queue, |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,Scattering.cpp:82-97,IndexValue.hpp:217-217 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 10.50 |
CQA cycles if no scalar integer | 5.00 |
CQA cycles if FP arith vectorized | 4.25 |
CQA cycles if fully vectorized | 1.31 |
Front-end cycles | 10.50 |
DIV/SQRT cycles | 5.25 |
P0 cycles | 5.25 |
P1 cycles | 9.50 |
P2 cycles | 9.50 |
P3 cycles | 2.00 |
P4 cycles | 5.25 |
P5 cycles | 5.25 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 10.76 |
Stall cycles (UFS) | 0.00 |
Nb insns | 41.00 |
Nb uops | 41.00 |
Nb loads | 19.00 |
Nb stores | 2.00 |
Nb stack references | 14.00 |
FLOP/cycle | 0.19 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 15.62 |
Bytes prefetched | 0.00 |
Bytes loaded | 148.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 7.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 8.33 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 25.00 |
Vector-efficiency ratio all | 13.54 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.63 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.46 |
CQA speedup if FP arith vectorized | 2.92 |
CQA speedup if fully vectorized | 7.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | micro-operation queue, |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,Scattering.cpp:82-97,IndexValue.hpp:217-217 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 16.00 |
CQA cycles if no scalar integer | 6.50 |
CQA cycles if FP arith vectorized | 5.48 |
CQA cycles if fully vectorized | 2.10 |
Front-end cycles | 16.00 |
DIV/SQRT cycles | 9.25 |
P0 cycles | 9.25 |
P1 cycles | 12.00 |
P2 cycles | 12.00 |
P3 cycles | 3.00 |
P4 cycles | 9.25 |
P5 cycles | 9.25 |
P6 cycles | 3.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 16.24 |
Stall cycles (UFS) | 0.00 |
Nb insns | 63.00 |
Nb uops | 63.00 |
Nb loads | 24.00 |
Nb stores | 3.00 |
Nb stack references | 17.00 |
FLOP/cycle | 0.31 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 13.25 |
Bytes prefetched | 0.00 |
Bytes loaded | 188.00 |
Bytes stored | 24.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 9.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 21.05 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 33.33 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 37.50 |
Vector-efficiency ratio all | 15.13 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 16.67 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.19 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.32 |
CQA speedup if FP arith vectorized | 3.13 |
CQA speedup if fully vectorized | 7.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.38 |
Bottlenecks | micro-operation queue, |
Function | void Kripke::DispatchHelper |
Source | forall.hpp:59-59,Scattering.cpp:82-97,IndexValue.hpp:217-217 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 14.50 |
CQA cycles if no scalar integer | 6.25 |
CQA cycles if FP arith vectorized | 4.63 |
CQA cycles if fully vectorized | 1.91 |
Front-end cycles | 14.50 |
DIV/SQRT cycles | 8.00 |
P0 cycles | 8.00 |
P1 cycles | 10.50 |
P2 cycles | 10.50 |
P3 cycles | 3.00 |
P4 cycles | 8.00 |
P5 cycles | 8.00 |
P6 cycles | 3.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 14.75 |
Stall cycles (UFS) | 0.00 |
Nb insns | 57.00 |
Nb uops | 57.00 |
Nb loads | 21.00 |
Nb stores | 3.00 |
Nb stack references | 17.00 |
FLOP/cycle | 0.34 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 1.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 12.97 |
Bytes prefetched | 0.00 |
Bytes loaded | 164.00 |
Bytes stored | 24.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 25.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 50.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 42.86 |
Vector-efficiency ratio all | 15.63 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 18.75 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.86 |
Path / |
nb instructions | 44.75 |
nb uops | 44.50 |
loop length | 211.25 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 13.50 |
micro-operation queue | 11.38 cycles |
front end | 11.38 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.19 | 6.19 | 9.13 | 9.13 | 2.25 | 6.19 | 6.19 | 2.25 |
cycles | 6.19 | 6.19 | 9.13 | 9.13 | 2.25 | 6.19 | 6.19 | 2.25 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 11.62 |
Stall cycles | 0.00 |
Front-end | 11.38 |
Dispatch | 9.13 |
Data deps. | 0.00 |
Overall L1 | 11.38 |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 37% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 18% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 27% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 38% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 17% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 14% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 15% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
nb instructions | 18 |
nb uops | 17 |
loop length | 91 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 6 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.25 | 2.25 | 4.50 | 4.50 | 1.00 | 2.25 | 2.25 | 1.00 |
cycles | 2.25 | 2.25 | 4.50 | 4.50 | 1.00 | 2.25 | 2.25 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 4.74 |
Stall cycles | 0.00 |
Front-end | 4.50 |
Dispatch | 4.50 |
Data deps. | 0.00 |
Overall L1 | 4.50 |
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) |
other | 0% |
all | 25% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 20% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 50% |
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) |
other | 12% |
all | 15% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 18% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x130(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RDI,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x110(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA 0x1(%RCX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 47cf60 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVSXD (%R11,%RAX,4),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 47cfa0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
nb instructions | 41 |
nb uops | 41 |
loop length | 193 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 14 |
micro-operation queue | 10.50 cycles |
front end | 10.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.25 | 5.25 | 9.50 | 9.50 | 2.00 | 5.25 | 5.25 | 2.00 |
cycles | 5.25 | 5.25 | 9.50 | 9.50 | 2.00 | 5.25 | 5.25 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 10.76 |
Stall cycles | 0.00 |
Front-end | 10.50 |
Dispatch | 9.50 |
Data deps. | 0.00 |
Overall L1 | 10.50 |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 25% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 8% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 15% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 13% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 15% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x130(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RDI,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x110(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA 0x1(%RCX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 47cf60 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVSXD (%R11,%RAX,4),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 47cfa0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xf0(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xf8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x100(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RSI,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x140(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 47d0e0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x480> | 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 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x78(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL -0x80(%RBP),%R8 | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%R8 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD -0x140(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 47cfa4 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x344> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
nb instructions | 63 |
nb uops | 63 |
loop length | 293 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 17 |
micro-operation queue | 16.00 cycles |
front end | 16.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 9.25 | 9.25 | 12.00 | 12.00 | 3.00 | 9.25 | 9.25 | 3.00 |
cycles | 9.25 | 9.25 | 12.00 | 12.00 | 3.00 | 9.25 | 9.25 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 16.24 |
Stall cycles | 0.00 |
Front-end | 16.00 |
Dispatch | 12.00 |
Data deps. | 0.00 |
Overall L1 | 16.00 |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 50% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 21% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 33% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 12% |
all | 18% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 12% |
store | 12% |
mul | 12% |
add-sub | 16% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x130(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RDI,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x110(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA 0x1(%RCX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 47cf60 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVSXD (%R11,%RAX,4),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 47cfa0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xf0(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xf8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x100(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RSI,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x140(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 47d0e0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x480> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0x108(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x1(%RAX),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R9,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R13,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %RBX,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R14,%RSI,8),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RBX,%RSI,8),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EBX,%EBX | 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 |
VEXTRACTF128 $0x1,%YMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
CMP %RAX,-0x108(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe8(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 47cfa4 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x344> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 47d0ee <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x48e> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
IMUL -0x80(%RBP),%R8 | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%R8 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD -0x140(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 47cfa4 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x344> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
nb instructions | 57 |
nb uops | 57 |
loop length | 268 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 17 |
micro-operation queue | 14.50 cycles |
front end | 14.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 8.00 | 8.00 | 10.50 | 10.50 | 3.00 | 8.00 | 8.00 | 3.00 |
cycles | 8.00 | 8.00 | 10.50 | 10.50 | 3.00 | 8.00 | 8.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 14.75 |
Stall cycles | 0.00 |
Front-end | 14.50 |
Dispatch | 10.50 |
Data deps. | 0.00 |
Overall L1 | 14.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 50% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 25% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 42% |
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 | 12% |
all | 18% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 15% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 17% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x138(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x130(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RDI,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x128(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x120(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RDI,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RDI,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP -0x110(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
LEA 0x1(%RCX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JE 47cf60 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%R10,%RCX,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOVSXD (%R11,%RAX,4),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RDI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 47cfa0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x340> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xf0(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RAX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xf8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x100(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RBX,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RSI,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RSI),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVLE %RAX,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RSI,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x140(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 47d0e0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x480> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RBX,-0x108(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x1(%RAX),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R9,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R13,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %RBX,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R14,%RSI,8),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RBX,%RSI,8),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EBX,%EBX | 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 |
VEXTRACTF128 $0x1,%YMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
VADDPD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VPERMILPD $0x1,%XMM1,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VADDSD %XMM2,%XMM1,%XMM1 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
CMP %RAX,-0x108(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xe8(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 47cfa4 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE14ScatteringSdomJRNS_6SdomIdES7_RNS_4Core3SetESA_SA_RNS8_5FieldIdJNS_6MomentENS_5GroupENS_4ZoneEEEESG_RNSB_IdJNS_8MaterialENS_8LegendreENS_11GlobalGroupESJ_EEERNSB_INS_7MixElemEJSE_EEERNSB_IiJSE_EEERNSB_ISH_JSM_EEERNSB_IdJSM_EEERNSB_ISI_JSC_EEEEEEvT_RKT0_DpOT1_.extracted+0x344> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |