Loop Id: 1332 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.04% |
---|
Loop Id: 1332 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.04% |
---|
0x4736f0 MOV -0x70(%RBP),%RDX |
0x4736f4 INC %RDX |
0x4736f7 MOV -0x30(%RBP),%RCX |
0x4736fb ADD -0x1d8(%RBP),%RCX |
0x473702 MOV -0x68(%RBP),%RAX |
0x473706 MOV -0x38(%RBP),%RDI |
0x47370a ADD %RAX,%RDI |
0x47370d MOV -0x158(%RBP),%R8 |
0x473714 ADD %RAX,%R8 |
0x473717 MOV -0x40(%RBP),%RSI |
0x47371b ADD %RAX,%RSI |
0x47371e MOV -0x208(%RBP),%R9 |
0x473725 MOV %RDX,%RAX |
0x473728 MOV %RDX,-0x70(%RBP) |
0x47372c CMP %R9,%RDX |
0x47372f MOV -0x140(%RBP),%RAX |
0x473736 MOV %RSI,%RDX |
0x473739 MOV %R8,%RSI |
0x47373c JE 473610 |
0x473742 MOV %RCX,-0x30(%RBP) |
0x473746 MOV %RSI,-0x158(%RBP) |
0x47374d MOV %RDI,-0x38(%RBP) |
0x473751 MOV %RDX,-0x40(%RBP) |
0x473755 TEST %RAX,%RAX |
0x473758 MOV -0x1e0(%RBP),%R15 |
0x47375f MOV -0x1f8(%RBP),%R8 |
0x473766 MOV -0x1f0(%RBP),%RCX |
0x47376d MOV -0x1e8(%RBP),%RBX |
0x473774 MOV -0x1d0(%RBP),%RDI |
0x47377b MOV -0x150(%RBP),%R13 |
0x473782 JLE 4736f0 |
0x473788 MOV -0x70(%RBP),%RDX |
0x47378c IMUL -0x130(%RBP),%RDX |
0x473794 ADD -0x138(%RBP),%RDX |
0x47379b MOV -0x1c8(%RBP),%RAX |
0x4737a2 MOV %RDX,-0x238(%RBP) |
0x4737a9 ADD %RDX,%RAX |
0x4737ac MOV %RAX,-0x230(%RBP) |
0x4737b3 XOR %R11D,%R11D |
0x4737b6 XOR %R10D,%R10D |
0x4737b9 MOV -0x140(%RBP),%R14 |
(1333) 0x4737c0 MOV -0x228(%RBP),%RDX |
(1333) 0x4737c7 MOV -0x220(%RBP),%RAX |
(1333) 0x4737ce VMOVSD (%RAX,%RDX,8),%XMM0 |
(1333) 0x4737d3 VADDSD %XMM0,%XMM0,%XMM0 |
(1333) 0x4737d7 VDIVSD (%RDI,%R10,1),%XMM0,%XMM0 |
(1333) 0x4737dd MOV -0x218(%RBP),%RAX |
(1333) 0x4737e4 VMOVSD (%RAX,%RDX,8),%XMM1 |
(1333) 0x4737e9 VMOVHPD (%R8,%RDX,8),%XMM1,%XMM1 |
(1333) 0x4737ef VADDPD %XMM1,%XMM1,%XMM1 |
(1333) 0x4737f3 MOV -0x238(%RBP),%RDX |
(1333) 0x4737fa VMOVSD (%R12,%RDX,8),%XMM2 |
(1333) 0x473800 VMOVHPD (%RCX,%R13,8),%XMM2,%XMM2 |
(1333) 0x473806 VDIVPD %XMM2,%XMM1,%XMM1 |
(1333) 0x47380a MOV -0x230(%RBP),%RAX |
(1333) 0x473811 VMOVSD (%RBX,%RAX,8),%XMM2 |
(1333) 0x473816 MOV %RBX,%R13 |
(1333) 0x473819 MOV %RDI,%RSI |
(1333) 0x47381c MOV %RCX,%RDI |
(1333) 0x47381f MOV %R8,%RBX |
(1333) 0x473822 MOV %R12,%R8 |
(1333) 0x473825 MOV %R15,%R9 |
(1333) 0x473828 MOV -0x38(%RBP),%RDX |
(1333) 0x47382c VFMADD213SD (%RDX,%R11,1),%XMM0,%XMM2 |
(1333) 0x473832 MOV -0x148(%RBP),%R15 |
(1333) 0x473839 VFMADD231SD (%R15,%R10,1),%XMM1,%XMM2 |
(1333) 0x47383f VSHUFPD $0x1,%XMM1,%XMM1,%XMM3 |
(1333) 0x473844 MOV -0x30(%RBP),%RDX |
(1333) 0x473848 VFMADD231SD (%RDX,%R10,1),%XMM3,%XMM2 |
(1333) 0x47384e VADDSD %XMM0,%XMM1,%XMM0 |
(1333) 0x473852 MOV -0x158(%RBP),%RDX |
(1333) 0x473859 VADDSD (%RDX,%R11,1),%XMM3,%XMM1 |
(1333) 0x47385f VADDSD %XMM0,%XMM1,%XMM0 |
(1333) 0x473863 VDIVSD %XMM0,%XMM2,%XMM0 |
(1333) 0x473867 MOV -0x40(%RBP),%RDX |
(1333) 0x47386b VMOVSD %XMM0,(%RDX,%R11,1) |
(1333) 0x473871 MOV %RBX,%R8 |
(1333) 0x473874 MOV %RSI,%RDI |
(1333) 0x473877 MOV -0x210(%RBP),%RSI |
(1333) 0x47387e MOV %R13,%RBX |
(1333) 0x473881 MOV -0x150(%RBP),%R13 |
(1333) 0x473888 MOV -0x30(%RBP),%RDX |
(1333) 0x47388c VADDSD %XMM0,%XMM0,%XMM0 |
(1333) 0x473890 VSUBSD (%RBX,%RAX,8),%XMM0,%XMM1 |
(1333) 0x473895 VMOVSD %XMM1,(%RBX,%RAX,8) |
(1333) 0x47389a VSUBSD (%R15,%R10,1),%XMM0,%XMM1 |
(1333) 0x4738a0 VMOVSD %XMM1,(%R15,%R10,1) |
(1333) 0x4738a6 VSUBSD (%RDX,%R10,1),%XMM0,%XMM0 |
(1333) 0x4738ac VMOVSD %XMM0,(%RDX,%R10,1) |
(1333) 0x4738b2 ADD %RSI,%R10 |
(1333) 0x4738b5 MOV %R9,%R15 |
(1333) 0x4738b8 ADD %R9,%R11 |
(1333) 0x4738bb DEC %R14 |
(1333) 0x4738be JNE 4737c0 |
0x4738c4 JMP 4736f0 |
/home/eoseret/qaas_runs_CPU_9468/171-147-9160/intel/Kripke/build/Kripke/src/Kripke/Kernel/SweepSubdomain.cpp: 87 - 105 |
-------------------------------------------------------------------------------- |
87: double xcos_dxi = 2.0 * xcos(d) / dx(i); |
88: double ycos_dyj = 2.0 * ycos(d) / dy(j); |
89: double zcos_dzk = 2.0 * zcos(d) / dz(k); |
[...] |
95: + psi_lf(d, g, j, k) * xcos_dxi |
96: + psi_fr(d, g, i, k) * ycos_dyj |
97: + psi_bo(d, g, i, j) * zcos_dzk) |
98: / (xcos_dxi + ycos_dyj + zcos_dzk + sigt(g, z)); |
99: |
100: psi(d, g, z) = psi_d_g_z; |
101: |
102: /* Apply diamond-difference relationships */ |
103: psi_lf(d, g, j, k) = 2.0 * psi_d_g_z - psi_lf(d, g, j, k); |
104: psi_fr(d, g, i, k) = 2.0 * psi_d_g_z - psi_fr(d, g, i, k); |
105: psi_bo(d, g, i, j) = 2.0 * psi_d_g_z - psi_bo(d, g, i, j); |
/home/eoseret/qaas_runs_CPU_9468/171-147-9160/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/home/eoseret/qaas_runs_CPU_9468/171-147-9160/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/eoseret/qaas_runs_CPU_9468/171-147-9160/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 250 - 310 |
-------------------------------------------------------------------------------- |
250: return (diff % stride != difference_type{0}) |
[...] |
310: return value_type(val + rhs * stride); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.05 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.04 |
Bottlenecks | |
Function | void Kripke::DispatchHelper |
Source | Operators.hpp:307-307,forall.hpp:59-59,Iterators.hpp:250-250,Iterators.hpp:310-310 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.08 |
CQA cycles if no scalar integer | 6.08 |
CQA cycles if FP arith vectorized | 6.08 |
CQA cycles if fully vectorized | 0.67 |
Front-end cycles | 6.08 |
DIV/SQRT cycles | 1.90 |
P0 cycles | 2.10 |
P1 cycles | 5.83 |
P2 cycles | 5.83 |
P3 cycles | 3.00 |
P4 cycles | 1.90 |
P5 cycles | 1.90 |
P6 cycles | 3.00 |
P7 cycles | 3.00 |
P8 cycles | 3.00 |
P9 cycles | 1.90 |
P10 cycles | 5.83 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 36.50 |
Nb uops | 36.50 |
Nb loads | 17.50 |
Nb stores | 6.00 |
Nb stack references | 17.50 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 30.91 |
Bytes prefetched | 0.00 |
Bytes loaded | 140.00 |
Bytes stored | 48.00 |
Stride 0 | 1.00 |
Stride 1 | 0.50 |
Stride n | 0.00 |
Stride unknown | 3.50 |
Stride indirect | 0.50 |
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 | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.28 |
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 | NA |
Vector-efficiency ratio other | 11.25 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 10.03 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.05 |
Bottlenecks | micro-operation queue, |
Function | void Kripke::DispatchHelper |
Source | Operators.hpp:307-307,forall.hpp:59-59,Iterators.hpp:250-250,Iterators.hpp:310-310 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 7.00 |
CQA cycles if FP arith vectorized | 7.00 |
CQA cycles if fully vectorized | 0.70 |
Front-end cycles | 7.00 |
DIV/SQRT cycles | 2.20 |
P0 cycles | 2.60 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 3.50 |
P4 cycles | 2.20 |
P5 cycles | 2.20 |
P6 cycles | 3.50 |
P7 cycles | 3.50 |
P8 cycles | 3.50 |
P9 cycles | 2.20 |
P10 cycles | 6.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 42.00 |
Nb uops | 42.00 |
Nb loads | 20.00 |
Nb stores | 7.00 |
Nb stack references | 20.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 30.86 |
Bytes prefetched | 0.00 |
Bytes loaded | 160.00 |
Bytes stored | 56.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 7.00 |
Stride indirect | 1.00 |
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 | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.05 |
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 | NA |
Vector-efficiency ratio other | 10.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.03 |
Bottlenecks | micro-operation queue, |
Function | void Kripke::DispatchHelper |
Source | Operators.hpp:307-307,forall.hpp:59-59,Iterators.hpp:250-250,Iterators.hpp:310-310 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.17 |
CQA cycles if no scalar integer | 5.17 |
CQA cycles if FP arith vectorized | 5.17 |
CQA cycles if fully vectorized | 0.65 |
Front-end cycles | 5.17 |
DIV/SQRT cycles | 1.60 |
P0 cycles | 1.60 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 2.50 |
P4 cycles | 1.60 |
P5 cycles | 1.60 |
P6 cycles | 2.50 |
P7 cycles | 2.50 |
P8 cycles | 2.50 |
P9 cycles | 1.60 |
P10 cycles | 5.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 31.00 |
Nb uops | 31.00 |
Nb loads | 15.00 |
Nb stores | 5.00 |
Nb stack references | 15.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 30.97 |
Bytes prefetched | 0.00 |
Bytes loaded | 120.00 |
Bytes stored | 40.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
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 | NA |
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 | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 36.50 |
nb uops | 36.50 |
loop length | 182.50 |
used x86 registers | 12.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 17.50 |
micro-operation queue | 6.08 cycles |
front end | 6.08 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.90 | 1.90 | 5.83 | 5.83 | 3.00 | 1.90 | 1.90 | 3.00 | 3.00 | 3.00 | 1.90 | 5.83 |
cycles | 1.90 | 2.10 | 5.83 | 5.83 | 3.00 | 1.90 | 1.90 | 3.00 | 3.00 | 3.00 | 1.90 | 5.83 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 6.08 |
Dispatch | 5.83 |
Data deps. | 0.00 |
Overall L1 | 6.08 |
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 | NA (no div/sqrt vectorizable/vectorized instructions) |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 42 |
nb uops | 42 |
loop length | 213 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 20 |
micro-operation queue | 7.00 cycles |
front end | 7.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.20 | 2.20 | 6.67 | 6.67 | 3.50 | 2.20 | 2.20 | 3.50 | 3.50 | 3.50 | 2.20 | 6.67 |
cycles | 2.20 | 2.60 | 6.67 | 6.67 | 3.50 | 2.20 | 2.20 | 3.50 | 3.50 | 3.50 | 2.20 | 6.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 7.00 |
Dispatch | 6.67 |
Data deps. | 0.00 |
Overall L1 | 7.00 |
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 | NA (no div/sqrt vectorizable/vectorized instructions) |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x70(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD -0x1d8(%RBP),%RCX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x158(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x208(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
MOV %RDX,-0x70(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
CMP %R9,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x140(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (12.5%) |
JE 473610 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RSI,-0x158(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RDI,-0x38(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
TEST %RAX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (12.5%) |
MOV -0x1e0(%RBP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1f8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1f0(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1e8(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1d0(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x150(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
JLE 4736f0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x690> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
MOV -0x70(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
IMUL -0x130(%RBP),%RDX | 1 | 0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 | N/A |
ADD -0x138(%RBP),%RDX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | N/A |
MOV -0x1c8(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
MOV %RDX,-0x238(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
ADD %RDX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
MOV %RAX,-0x230(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (6.3%) |
XOR %R10D,%R10D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (6.3%) |
MOV -0x140(%RBP),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
JMP 4736f0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x690> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 | N/A |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | exec |
nb instructions | 31 |
nb uops | 31 |
loop length | 152 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 15 |
micro-operation queue | 5.17 cycles |
front end | 5.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.60 | 1.60 | 5.00 | 5.00 | 2.50 | 1.60 | 1.60 | 2.50 | 2.50 | 2.50 | 1.60 | 5.00 |
cycles | 1.60 | 1.60 | 5.00 | 5.00 | 2.50 | 1.60 | 1.60 | 2.50 | 2.50 | 2.50 | 1.60 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
Front-end | 5.17 |
Dispatch | 5.00 |
Data deps. | 0.00 |
Overall L1 | 5.17 |
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 | NA (no div/sqrt vectorizable/vectorized instructions) |
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) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x70(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (12.5%) |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD -0x1d8(%RBP),%RCX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x158(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%R8 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x208(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
MOV %RDX,-0x70(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
CMP %R9,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (12.5%) |
MOV -0x140(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
MOV %RSI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (12.5%) |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (12.5%) |
JE 473610 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RSI,-0x158(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RDI,-0x38(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
MOV %RDX,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 | scal (12.5%) |
TEST %RAX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | N/A |
MOV -0x1e0(%RBP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1f8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1f0(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1e8(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x1d0(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
MOV -0x150(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
JLE 4736f0 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x690> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |