Loop Id: 1247 | Module: exec | Source: Scattering.cpp:82-97 [...] | Coverage: 51.92% |
---|
Loop Id: 1247 | Module: exec | Source: Scattering.cpp:82-97 [...] | Coverage: 51.92% |
---|
0x460ae0 VXORPD %XMM1,%XMM1,%XMM1 |
0x460ae4 MOV -0x100(%RBP),%RAX |
0x460aeb IMUL %RDX,%RAX |
0x460aef ADD %RBX,%RAX |
0x460af2 ADD -0xe8(%RBP),%RAX |
0x460af9 MOV -0x128(%RBP),%RCX |
0x460b00 ADD %R11,%RCX |
0x460b03 ADD %RCX,%RAX |
0x460b06 MOV -0xf8(%RBP),%RCX |
0x460b0d VMOVSD (%RCX,%RAX,8),%XMM2 |
0x460b12 MOV -0x110(%RBP),%RAX |
0x460b19 IMUL %RDX,%RAX |
0x460b1d ADD %RBX,%RAX |
0x460b20 ADD -0x120(%RBP),%RAX |
0x460b27 ADD %R11,%RAX |
0x460b2a MOV -0x108(%RBP),%RCX |
0x460b31 VFMADD213SD (%RCX,%RAX,8),%XMM1,%XMM2 |
0x460b37 VMOVSD %XMM2,(%RCX,%RAX,8) |
0x460b3c LEA 0x1(%R11),%RAX |
0x460b40 CMP -0xf0(%RBP),%R11 |
0x460b47 MOV %RAX,%R11 |
0x460b4a JE 460ab0 |
0x460b50 LEA (%RBX,%R11,1),%RAX |
0x460b54 MOV -0x118(%RBP),%RCX |
0x460b5b MOVSXD (%RCX,%RAX,4),%RDI |
0x460b5f TEST %RDI,%RDI |
0x460b62 JLE 460ae0 |
0x460b68 MOV -0xd0(%RBP),%RCX |
0x460b6f MOV (%RCX,%RAX,8),%RBX |
0x460b73 MOV -0xd8(%RBP),%RAX |
0x460b7a MOV (%RAX,%RDX,8),%RCX |
0x460b7e ADD %RBX,%RDI |
0x460b81 LEA 0x1(%RBX),%RAX |
0x460b85 CMP %RAX,%RDI |
0x460b88 CMOVLE %RAX,%RDI |
0x460b8c MOV %RDI,%RAX |
0x460b8f SUB %RBX,%RAX |
0x460b92 MOV %RAX,%R10 |
0x460b95 AND $-0x4,%R10 |
0x460b99 MOV %RBX,-0x130(%RBP) |
0x460ba0 JE 460c50 |
0x460ba6 MOV %RAX,-0xe0(%RBP) |
0x460bad LEA -0x1(%R10),%RDX |
0x460bb1 MOV -0x78(%RBP),%RAX |
0x460bb5 IMUL %RCX,%RAX |
0x460bb9 ADD -0x30(%RBP),%RAX |
0x460bbd ADD %R9,%RAX |
0x460bc0 ADD %RSI,%RAX |
0x460bc3 ADD %R8,%RAX |
0x460bc6 VPBROADCASTQ %RAX,%YMM2 |
0x460bcc LEA (%R14,%RBX,8),%RAX |
0x460bd0 LEA (,%RBX,8),%R15 |
0x460bd8 ADD %R13,%R15 |
0x460bdb VXORPD %XMM1,%XMM1,%XMM1 |
0x460bdf XOR %EBX,%EBX |
0x460be1 NOPW %CS:(%RAX,%RAX,1) |
(1249) 0x460bf0 VPMULLQ (%R15,%RBX,8),%YMM0,%YMM3 |
(1249) 0x460bf7 VPADDQ %YMM3,%YMM2,%YMM3 |
(1249) 0x460bfb VXORPD %XMM4,%XMM4,%XMM4 |
(1249) 0x460bff KXNORW %K0,%K0,%K1 |
(1249) 0x460c03 VGATHERQPD (%R12,%YMM3,8),%YMM4{%K1} |
(1249) 0x460c0a VFMADD231PD (%RAX,%RBX,8),%YMM4,%YMM1 |
(1249) 0x460c10 ADD $0x4,%RBX |
(1249) 0x460c14 CMP %RDX,%RBX |
(1249) 0x460c17 JBE 460bf0 |
0x460c19 VEXTRACTF128 $0x1,%YMM1,%XMM2 |
0x460c1f VADDPD %XMM2,%XMM1,%XMM1 |
0x460c23 VPERMILPD $0x1,%XMM1,%XMM2 |
0x460c29 VADDSD %XMM2,%XMM1,%XMM1 |
0x460c2d CMP %R10,-0xe0(%RBP) |
0x460c34 MOV -0x70(%RBP),%RBX |
0x460c38 MOV -0x48(%RBP),%R15 |
0x460c3c MOV -0xc8(%RBP),%RDX |
0x460c43 JE 460ae4 |
0x460c49 JMP 460c5f |
0x460c50 VXORPD %XMM1,%XMM1,%XMM1 |
0x460c54 XOR %R10D,%R10D |
0x460c57 MOV -0x48(%RBP),%R15 |
0x460c5b MOV -0x70(%RBP),%RBX |
0x460c5f IMUL -0x78(%RBP),%RCX |
0x460c64 ADD -0x30(%RBP),%RCX |
0x460c68 ADD -0x130(%RBP),%R10 |
0x460c6f NOP |
(1248) 0x460c70 MOV (%R13,%R10,8),%RAX |
(1248) 0x460c75 IMUL %R15,%RAX |
(1248) 0x460c79 ADD %RCX,%RAX |
(1248) 0x460c7c ADD %R9,%RAX |
(1248) 0x460c7f ADD %RSI,%RAX |
(1248) 0x460c82 ADD %R8,%RAX |
(1248) 0x460c85 VMOVSD (%R12,%RAX,8),%XMM2 |
(1248) 0x460c8b VFMADD231SD (%R14,%R10,8),%XMM2,%XMM1 |
(1248) 0x460c91 INC %R10 |
(1248) 0x460c94 CMP %R10,%RDI |
(1248) 0x460c97 JNE 460c70 |
0x460c99 JMP 460ae4 |
/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 | 3.87 |
CQA speedup if FP arith vectorized | 3.18 |
CQA speedup if fully vectorized | 7.78 |
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 | 13.31 |
CQA cycles if no scalar integer | 3.44 |
CQA cycles if FP arith vectorized | 4.18 |
CQA cycles if fully vectorized | 1.71 |
Front-end cycles | 13.31 |
DIV/SQRT cycles | 7.81 |
P0 cycles | 9.06 |
P1 cycles | 10.00 |
P2 cycles | 10.00 |
P3 cycles | 2.25 |
P4 cycles | 7.81 |
P5 cycles | 7.81 |
P6 cycles | 2.25 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 13.60 |
Stall cycles (UFS) | 0.00 |
Nb insns | 52.50 |
Nb uops | 52.25 |
Nb loads | 20.00 |
Nb stores | 2.25 |
Nb stack references | 15.25 |
FLOP/cycle | 0.26 |
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 | 13.42 |
Bytes prefetched | 0.00 |
Bytes loaded | 156.00 |
Bytes stored | 18.00 |
Stride 0 | 1.50 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.25 |
Stride indirect | 0.00 |
Vectorization ratio all | 17.35 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 16.67 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 35.21 |
Vector-efficiency ratio all | 14.67 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 12.50 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 14.58 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.90 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.38 |
CQA speedup if FP arith vectorized | 3.27 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.13 |
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 | 6.75 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.06 |
CQA cycles if fully vectorized | 0.84 |
Front-end cycles | 6.75 |
DIV/SQRT cycles | 3.75 |
P0 cycles | 5.00 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 1.00 |
P4 cycles | 3.75 |
P5 cycles | 3.75 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 7.05 |
Stall cycles (UFS) | 0.00 |
Nb insns | 27.00 |
Nb uops | 26.00 |
Nb loads | 12.00 |
Nb stores | 1.00 |
Nb stack references | 9.00 |
FLOP/cycle | 0.30 |
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 | 14.81 |
Bytes prefetched | 0.00 |
Bytes loaded | 92.00 |
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 | 4.17 |
CQA speedup if FP arith vectorized | 3.39 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
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 | 12.50 |
CQA cycles if no scalar integer | 3.00 |
CQA cycles if FP arith vectorized | 3.68 |
CQA cycles if fully vectorized | 1.56 |
Front-end cycles | 12.50 |
DIV/SQRT cycles | 6.75 |
P0 cycles | 8.25 |
P1 cycles | 10.50 |
P2 cycles | 10.50 |
P3 cycles | 2.00 |
P4 cycles | 6.75 |
P5 cycles | 6.75 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 12.80 |
Stall cycles (UFS) | 0.00 |
Nb insns | 49.00 |
Nb uops | 49.00 |
Nb loads | 21.00 |
Nb stores | 2.00 |
Nb stack references | 16.00 |
FLOP/cycle | 0.16 |
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 | 14.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 164.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 6.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 8.33 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 20.00 |
Vector-efficiency ratio all | 13.54 |
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 | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 15.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.94 |
CQA speedup if FP arith vectorized | 3.12 |
CQA speedup if fully vectorized | 7.67 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.42 |
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 | 17.75 |
CQA cycles if no scalar integer | 4.50 |
CQA cycles if FP arith vectorized | 5.69 |
CQA cycles if fully vectorized | 2.31 |
Front-end cycles | 17.75 |
DIV/SQRT cycles | 11.00 |
P0 cycles | 12.25 |
P1 cycles | 12.50 |
P2 cycles | 12.50 |
P3 cycles | 3.00 |
P4 cycles | 11.00 |
P5 cycles | 11.00 |
P6 cycles | 3.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 18.02 |
Stall cycles (UFS) | 0.00 |
Nb insns | 70.00 |
Nb uops | 70.00 |
Nb loads | 25.00 |
Nb stores | 3.00 |
Nb stack references | 18.00 |
FLOP/cycle | 0.28 |
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 | 12.39 |
Bytes prefetched | 0.00 |
Bytes loaded | 196.00 |
Bytes stored | 24.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 8.00 |
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 | 25.00 |
Vectorization ratio fma | 0.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 33.33 |
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 | 15.63 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.67 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 3.82 |
CQA speedup if FP arith vectorized | 3.08 |
CQA speedup if fully vectorized | 7.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.48 |
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 | 16.25 |
CQA cycles if no scalar integer | 4.25 |
CQA cycles if FP arith vectorized | 5.28 |
CQA cycles if fully vectorized | 2.13 |
Front-end cycles | 16.25 |
DIV/SQRT cycles | 9.75 |
P0 cycles | 10.75 |
P1 cycles | 11.00 |
P2 cycles | 11.00 |
P3 cycles | 3.00 |
P4 cycles | 9.75 |
P5 cycles | 9.75 |
P6 cycles | 3.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 16.53 |
Stall cycles (UFS) | 0.00 |
Nb insns | 64.00 |
Nb uops | 64.00 |
Nb loads | 22.00 |
Nb stores | 3.00 |
Nb stack references | 18.00 |
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 | 12.06 |
Bytes prefetched | 0.00 |
Bytes loaded | 172.00 |
Bytes stored | 24.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 5.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 21.05 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 25.00 |
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 | NA |
Vector-efficiency ratio add_sub | 15.63 |
Vector-efficiency ratio fma | 12.50 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 17.19 |
Path / |
nb instructions | 52.50 |
nb uops | 52.25 |
loop length | 255.75 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 1 |
used zmm registers | 0 |
nb stack references | 15.25 |
micro-operation queue | 13.31 cycles |
front end | 13.31 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.81 | 7.81 | 10.00 | 10.00 | 2.25 | 7.81 | 7.81 | 2.25 |
cycles | 7.81 | 9.06 | 10.00 | 10.00 | 2.25 | 7.81 | 7.81 | 2.25 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 13.60 |
Stall cycles | 0.00 |
Front-end | 13.31 |
Dispatch | 10.00 |
Data deps. | 0.00 |
Overall L1 | 13.31 |
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 | 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 | 17% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 16% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 35% |
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 | 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 | NA (no mul vectorizable/vectorized instructions) |
add-sub | 14% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
nb instructions | 27 |
nb uops | 26 |
loop length | 136 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 6.75 cycles |
front end | 6.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 3.75 | 3.75 | 6.00 | 6.00 | 1.00 | 3.75 | 3.75 | 1.00 |
cycles | 3.75 | 5.00 | 6.00 | 6.00 | 1.00 | 3.75 | 3.75 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 7.05 |
Stall cycles | 0.00 |
Front-end | 6.75 |
Dispatch | 6.00 |
Data deps. | 0.00 |
Overall L1 | 6.75 |
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 -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0xe8(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x120(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RCX,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R11),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0xf0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 460ab0 <_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+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%R11,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD (%RCX,%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 460ae0 <_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+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
nb instructions | 49 |
nb uops | 49 |
loop length | 231 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 16 |
micro-operation queue | 12.50 cycles |
front end | 12.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 6.75 | 6.75 | 10.50 | 10.50 | 2.00 | 6.75 | 6.75 | 2.00 |
cycles | 6.75 | 8.25 | 10.50 | 10.50 | 2.00 | 6.75 | 6.75 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 12.80 |
Stall cycles | 0.00 |
Front-end | 12.50 |
Dispatch | 10.50 |
Data deps. | 0.00 |
Overall L1 | 12.50 |
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 | 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 | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 20% |
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 | 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 | NA (no mul vectorizable/vectorized instructions) |
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 -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0xe8(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x120(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RCX,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R11),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0xf0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 460ab0 <_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+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%R11,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD (%RCX,%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 460ae0 <_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+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xd8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RBX),%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,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 460c50 <_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+0x440> | 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 %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL -0x78(%RBP),%RCX | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD -0x130(%RBP),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 460ae4 <_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+0x2d4> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
nb instructions | 70 |
nb uops | 70 |
loop length | 340 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 18 |
micro-operation queue | 17.75 cycles |
front end | 17.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 11.00 | 11.00 | 12.50 | 12.50 | 3.00 | 11.00 | 11.00 | 3.00 |
cycles | 11.00 | 12.25 | 12.50 | 12.50 | 3.00 | 11.00 | 11.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 18.02 |
Stall cycles | 0.00 |
Front-end | 17.75 |
Dispatch | 12.50 |
Data deps. | 0.00 |
Overall L1 | 17.75 |
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 | 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 | 20% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
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 | 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 | 15% |
fma | 12% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0xe8(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x120(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RCX,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R11),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0xf0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 460ab0 <_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+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%R11,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD (%RCX,%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 460ae0 <_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+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xd8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RBX),%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,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 460c50 <_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+0x440> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,-0xe0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x1(%R10),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RCX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R9,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %RAX,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R14,%RBX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RBX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R13,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 |
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 %R10,-0xe0(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc8(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 460ae4 <_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+0x2d4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 460c5f <_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+0x44f> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
IMUL -0x78(%RBP),%RCX | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD -0x130(%RBP),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 460ae4 <_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+0x2d4> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
nb instructions | 64 |
nb uops | 64 |
loop length | 316 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 2 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 18 |
micro-operation queue | 16.25 cycles |
front end | 16.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 9.75 | 9.75 | 11.00 | 11.00 | 3.00 | 9.75 | 9.75 | 3.00 |
cycles | 9.75 | 10.75 | 11.00 | 11.00 | 3.00 | 9.75 | 9.75 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 16.53 |
Stall cycles | 0.00 |
Front-end | 16.25 |
Dispatch | 11.00 |
Data deps. | 0.00 |
Overall L1 | 16.25 |
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 | 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 | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 0% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 37% |
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 | 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 | 15% |
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 -0x100(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0xe8(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x128(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xf8(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RCX,%RAX,8),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x110(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD -0x120(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x108(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMADD213SD (%RCX,%RAX,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM2,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R11),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0xf0(%RBP),%R11 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 460ab0 <_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+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%R11,1),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x118(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD (%RCX,%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 460ae0 <_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+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0xd0(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RAX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xd8(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RDX,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RBX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA 0x1(%RBX),%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,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RBX,-0x130(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JE 460c50 <_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+0x440> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RAX,-0xe0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x1(%R10),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RCX,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD -0x30(%RBP),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
ADD %R9,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VPBROADCASTQ %RAX,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R14,%RBX,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (,%RBX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD %R13,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VXORPD %XMM1,%XMM1,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 |
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 %R10,-0xe0(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x70(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x48(%RBP),%R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0xc8(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JE 460ae4 <_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+0x2d4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |