Loop Id: 1199 | Module: libkripke.so | Source: forall.hpp:59-59 [...] | Coverage: 0.04% |
---|
Loop Id: 1199 | Module: libkripke.so | Source: forall.hpp:59-59 [...] | Coverage: 0.04% |
---|
0x83180 MOV -0x68(%RBP),%RCX |
0x83184 INC %RCX |
0x83187 ADD -0x1d8(%RBP),%RBX |
0x8318e MOV -0x60(%RBP),%RAX |
0x83192 ADD %RAX,%R10 |
0x83195 MOV -0x30(%RBP),%RSI |
0x83199 ADD %RAX,%RSI |
0x8319c ADD %RAX,%R11 |
0x8319f MOV %RCX,%RAX |
0x831a2 MOV %RCX,-0x68(%RBP) |
0x831a6 CMP -0x210(%RBP),%RCX |
0x831ad MOV -0x208(%RBP),%RDX |
0x831b4 MOV -0x200(%RBP),%RAX |
0x831bb MOV %R11,%RCX |
0x831be MOV %R10,%RDI |
0x831c1 JE 83070 |
0x831c7 MOV %RSI,-0x30(%RBP) |
0x831cb XOR %ESI,%ESI |
0x831cd TEST %RDX,%RDX |
0x831d0 SETNE %SIL |
0x831d4 ADD %RAX,%RSI |
0x831d7 MOV -0x1e0(%RBP),%RAX |
0x831de MOV -0x1f0(%RBP),%R12 |
0x831e5 MOV %RCX,%R11 |
0x831e8 MOV %RDI,%R10 |
0x831eb JLE 83180 |
0x831ed MOV -0x68(%RBP),%RCX |
0x831f1 IMUL -0x148(%RBP),%RCX |
0x831f9 ADD -0x150(%RBP),%RCX |
0x83200 MOV -0x1d0(%RBP),%RDX |
0x83207 MOV %RCX,-0x70(%RBP) |
0x8320b LEA (%RDX,%RCX,1),%RDI |
0x8320f XOR %ESI,%ESI |
0x83211 XOR %R13D,%R13D |
0x83214 MOV -0x1c8(%RBP),%RDX |
0x8321b NOPL (%RAX,%RAX,1) |
(1200) 0x83220 VMOVSD (%R12,%R8,8),%XMM0 |
(1200) 0x83226 VADDSD %XMM0,%XMM0,%XMM0 |
(1200) 0x8322a MOV -0x218(%RBP),%RCX |
(1200) 0x83231 VDIVSD (%RCX,%R13,1),%XMM0,%XMM0 |
(1200) 0x83237 MOV -0x240(%RBP),%RCX |
(1200) 0x8323e VMOVSD (%RCX,%R8,8),%XMM1 |
(1200) 0x83244 MOV -0x230(%RBP),%RCX |
(1200) 0x8324b VMOVHPD (%RCX,%R8,8),%XMM1,%XMM1 |
(1200) 0x83251 VADDPD %XMM1,%XMM1,%XMM1 |
(1200) 0x83255 MOV -0x238(%RBP),%RCX |
(1200) 0x8325c MOV -0x70(%RBP),%R14 |
(1200) 0x83260 VMOVSD (%RCX,%R14,8),%XMM2 |
(1200) 0x83266 MOV -0x228(%RBP),%RCX |
(1200) 0x8326d MOV -0x248(%RBP),%R14 |
(1200) 0x83274 VMOVHPD (%RCX,%R14,8),%XMM2,%XMM2 |
(1200) 0x8327a VDIVPD %XMM2,%XMM1,%XMM1 |
(1200) 0x8327e VMOVSD (%R15,%RDI,8),%XMM2 |
(1200) 0x83284 VFMADD213SD (%R11,%RSI,1),%XMM0,%XMM2 |
(1200) 0x8328a VFMADD231SD (%R9,%R13,1),%XMM1,%XMM2 |
(1200) 0x83290 VSHUFPD $0x1,%XMM1,%XMM1,%XMM3 |
(1200) 0x83295 VFMADD231SD (%RBX,%R13,1),%XMM3,%XMM2 |
(1200) 0x8329b VADDSD %XMM0,%XMM1,%XMM0 |
(1200) 0x8329f MOV %R12,%RCX |
(1200) 0x832a2 MOV %RAX,%R12 |
(1200) 0x832a5 MOV %R10,%RAX |
(1200) 0x832a8 MOV %R11,%R10 |
(1200) 0x832ab MOV -0x30(%RBP),%R11 |
(1200) 0x832af VADDSD (%R11,%RSI,1),%XMM3,%XMM1 |
(1200) 0x832b5 MOV %R10,%R11 |
(1200) 0x832b8 MOV %RAX,%R10 |
(1200) 0x832bb MOV %R12,%RAX |
(1200) 0x832be MOV %RCX,%R12 |
(1200) 0x832c1 VADDSD %XMM0,%XMM1,%XMM0 |
(1200) 0x832c5 VDIVSD %XMM0,%XMM2,%XMM0 |
(1200) 0x832c9 VMOVSD %XMM0,(%R10,%RSI,1) |
(1200) 0x832cf VADDSD %XMM0,%XMM0,%XMM0 |
(1200) 0x832d3 VSUBSD (%R15,%RDI,8),%XMM0,%XMM1 |
(1200) 0x832d9 VMOVSD %XMM1,(%R15,%RDI,8) |
(1200) 0x832df VSUBSD (%R9,%R13,1),%XMM0,%XMM1 |
(1200) 0x832e5 VMOVSD %XMM1,(%R9,%R13,1) |
(1200) 0x832eb VSUBSD (%RBX,%R13,1),%XMM0,%XMM0 |
(1200) 0x832f1 VMOVSD %XMM0,(%RBX,%R13,1) |
(1200) 0x832f7 ADD -0x220(%RBP),%R13 |
(1200) 0x832fe ADD %RAX,%RSI |
(1200) 0x83301 DEC %RDX |
(1200) 0x83304 JNE 83220 |
0x8330a JMP 83180 |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/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) { |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/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); |
[...] |
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); |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/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); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 9.83 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.24 |
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 | 5.58 |
CQA cycles if no scalar integer | 5.58 |
CQA cycles if FP arith vectorized | 5.58 |
CQA cycles if fully vectorized | 0.57 |
Front-end cycles | 5.25 |
DIV/SQRT cycles | 2.30 |
P0 cycles | 2.30 |
P1 cycles | 3.83 |
P2 cycles | 3.83 |
P3 cycles | 1.25 |
P4 cycles | 2.20 |
P5 cycles | 2.10 |
P6 cycles | 1.25 |
P7 cycles | 1.25 |
P8 cycles | 1.25 |
P9 cycles | 2.20 |
P10 cycles | 3.83 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 5 |
FE+BE cycles (UFS) | 5.37 |
Stall cycles (UFS) | 0.00 |
Nb insns | 31.50 |
Nb uops | 31.50 |
Nb loads | 11.50 |
Nb stores | 2.50 |
Nb stack references | 11.50 |
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 | 19.83 |
Bytes prefetched | 0.00 |
Bytes loaded | 92.00 |
Bytes stored | 20.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 3.00 |
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 | 11.98 |
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 | 11.33 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.08 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.32 |
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 | 6.17 |
CQA cycles if no scalar integer | 6.17 |
CQA cycles if FP arith vectorized | 6.17 |
CQA cycles if fully vectorized | 0.51 |
Front-end cycles | 6.17 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.60 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 1.50 |
P4 cycles | 2.40 |
P5 cycles | 2.30 |
P6 cycles | 1.50 |
P7 cycles | 1.50 |
P8 cycles | 1.50 |
P9 cycles | 2.40 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 5 |
FE+BE cycles (UFS) | 6.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 37.00 |
Nb uops | 37.00 |
Nb loads | 14.00 |
Nb stores | 3.00 |
Nb stack references | 14.00 |
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 | 22.05 |
Bytes prefetched | 0.00 |
Bytes loaded | 112.00 |
Bytes stored | 24.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 6.00 |
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 | 11.46 |
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 | 10.16 |
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 | 1.15 |
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 | 5.00 |
CQA cycles if no scalar integer | 5.00 |
CQA cycles if FP arith vectorized | 5.00 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 4.33 |
DIV/SQRT cycles | 2.10 |
P0 cycles | 2.00 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 1.00 |
P4 cycles | 2.00 |
P5 cycles | 1.90 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 2.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 5 |
FE+BE cycles (UFS) | 4.43 |
Stall cycles (UFS) | 0.00 |
Nb insns | 26.00 |
Nb uops | 26.00 |
Nb loads | 9.00 |
Nb stores | 2.00 |
Nb stack references | 9.00 |
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 | 17.60 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
Bytes stored | 16.00 |
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 | libkripke.so |
nb instructions | 31.50 |
nb uops | 31.50 |
loop length | 137 |
used x86 registers | 10.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 11.50 |
micro-operation queue | 5.25 cycles |
front end | 5.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.30 | 2.20 | 3.83 | 3.83 | 1.25 | 2.20 | 2.10 | 1.25 | 1.25 | 1.25 | 2.20 | 3.83 |
cycles | 2.30 | 2.30 | 3.83 | 3.83 | 1.25 | 2.20 | 2.10 | 1.25 | 1.25 | 1.25 | 2.20 | 3.83 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 5.00 |
FE+BE cycles | 5.37 |
Stall cycles | 0.00 |
Front-end | 5.25 |
Dispatch | 3.83 |
Data deps. | 5.00 |
Overall L1 | 5.58 |
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 | 11% |
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 | libkripke.so |
nb instructions | 37 |
nb uops | 37 |
loop length | 165 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 14 |
micro-operation queue | 6.17 cycles |
front end | 6.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.40 | 4.67 | 4.67 | 1.50 | 2.40 | 2.30 | 1.50 | 1.50 | 1.50 | 2.40 | 4.67 |
cycles | 2.50 | 2.60 | 4.67 | 4.67 | 1.50 | 2.40 | 2.30 | 1.50 | 1.50 | 1.50 | 2.40 | 4.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 5.00 |
FE+BE cycles | 6.31 |
Stall cycles | 0.00 |
Front-end | 6.17 |
Dispatch | 4.67 |
Data deps. | 5.00 |
Overall L1 | 6.17 |
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 | 11% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD -0x1d8(%RBP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %RAX,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RAX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RCX,-0x68(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0x210(%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 |
MOV -0x208(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x200(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R11,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 83070 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
TEST %RDX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
SETNE %SIL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x1e0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1f0(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RCX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JLE 83180 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL -0x148(%RBP),%RCX | 1 | 0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
ADD -0x150(%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 |
MOV -0x1d0(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RCX,-0x70(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDX,%RCX,1),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %R13D,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV -0x1c8(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 83180 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x6f0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | void Kripke::DispatchHelper |
Source file and lines | forall.hpp:59-59 |
Module | libkripke.so |
nb instructions | 26 |
nb uops | 26 |
loop length | 109 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 4.33 cycles |
front end | 4.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.10 | 2.00 | 3.00 | 3.00 | 1.00 | 2.00 | 1.90 | 1.00 | 1.00 | 1.00 | 2.00 | 3.00 |
cycles | 2.10 | 2.00 | 3.00 | 3.00 | 1.00 | 2.00 | 1.90 | 1.00 | 1.00 | 1.00 | 2.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 5.00 |
FE+BE cycles | 4.43 |
Stall cycles | 0.00 |
Front-end | 4.33 |
Dispatch | 3.00 |
Data deps. | 5.00 |
Overall L1 | 5.00 |
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 | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD -0x1d8(%RBP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
MOV -0x60(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %RAX,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
ADD %RAX,%R11 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RCX,-0x68(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0x210(%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 |
MOV -0x208(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x200(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R11,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JE 83070 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %RSI,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
TEST %RDX,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
SETNE %SIL | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV -0x1e0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1f0(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RCX,%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JLE 83180 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |