Loop Id: 883 | Module: exec | Source: einspline_spo_ref.hpp:183-187 [...] | Coverage: 0.01% |
---|
Loop Id: 883 | Module: exec | Source: einspline_spo_ref.hpp:183-187 [...] | Coverage: 0.01% |
---|
0x43c470 MOVSXD %EAX,%RCX |
0x43c473 ADD $0x18,%RBX |
0x43c477 CMP %RCX,%R14 |
0x43c47a JGE 43c4c5 |
0x43c47c MOV %R14D,%EDX |
0x43c47f IMUL %EAX,%EDX |
0x43c482 INC %R14 |
0x43c485 MOV 0x40(%R12),%ECX [2] |
0x43c48a IMUL %R14D,%ECX |
0x43c48e MOV 0x8(%R12),%ESI [2] |
0x43c493 CMP %ECX,%ESI |
0x43c495 CMOVL %ESI,%ECX |
0x43c498 SUB %EDX,%ECX |
0x43c49a JLE 43c470 |
0x43c49c MOV 0x310(%R12),%RAX [2] |
0x43c4a4 MOVSXD %EDX,%RDI |
0x43c4a7 SAL $0x3,%RDI |
0x43c4ab ADD 0x18(%R15),%RDI [1] |
0x43c4af MOV (%RAX,%RBX,1),%RSI [3] |
0x43c4b3 MOV %ECX,%EDX |
0x43c4b5 SAL $0x3,%RDX |
0x43c4b9 CALL 4040a0 <memmove@plt> |
0x43c4be MOV 0x30(%R12),%EAX [2] |
0x43c4c3 JMP 43c470 |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1046 - 1169 |
-------------------------------------------------------------------------------- |
1046: return *(this->_M_impl._M_start + __n); |
[...] |
1169: { return _M_data_ptr(this->_M_impl._M_start); } |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algobase.h: 235 - 431 |
-------------------------------------------------------------------------------- |
235: if (__b < __a) |
[...] |
429: const ptrdiff_t _Num = __last - __first; |
430: if (_Num) |
431: __builtin_memmove(__result, __first, sizeof(_Tp) * _Num); |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp: 183 - 187 |
-------------------------------------------------------------------------------- |
183: for (int i = 0; i < nBlocks; ++i) |
184: { |
185: // in real simulation, phase needs to be applied. Here just fake computation |
186: const int first = i * nBlocks; |
187: std::copy_n(psi[i].data(), std::min((i + 1) * nSplinesPerBlock, OrbitalSetSize) - first, psi_v.data() + first); |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_algo.h: 725 - 751 |
-------------------------------------------------------------------------------- |
725: { return std::copy(__first, __first + __n, __result); } |
[...] |
751: if (__n2 <= 0) |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.16 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.22 |
Bottlenecks | |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source | stl_vector.h:1046-1046,stl_vector.h:1169-1169,stl_algobase.h:235-235,stl_algobase.h:429-431,einspline_spo_ref.hpp:183-187,stl_algo.h:725-725,stl_algo.h:751-751 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.45 |
CQA cycles if no scalar integer | 3.45 |
CQA cycles if FP arith vectorized | 3.45 |
CQA cycles if fully vectorized | 0.24 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 2.10 |
P0 cycles | 3.10 |
P1 cycles | 1.33 |
P2 cycles | 1.33 |
P3 cycles | 0.25 |
P4 cycles | 2.03 |
P5 cycles | 2.00 |
P6 cycles | 0.25 |
P7 cycles | 0.25 |
P8 cycles | 0.25 |
P9 cycles | 2.07 |
P10 cycles | 1.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 3.21 - 3.22 |
Stall cycles (UFS) | 0.00 |
Nb insns | 19.00 |
Nb uops | 19.00 |
Nb loads | 4.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
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 | 5.78 |
Bytes prefetched | 0.00 |
Bytes loaded | 22.00 |
Bytes stored | 0.00 |
Stride 0 | 1.50 |
Stride 1 | 0.00 |
Stride n | 0.50 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 9.24 |
Vector-efficiency ratio load | 7.29 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 6.25 |
Vector-efficiency ratio add_sub | 10.94 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.15 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 13.71 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.20 |
Bottlenecks | micro-operation queue, |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source | stl_vector.h:1046-1046,stl_vector.h:1169-1169,stl_algobase.h:235-235,stl_algobase.h:429-431,einspline_spo_ref.hpp:183-187,stl_algo.h:725-725,stl_algo.h:751-751 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.17 |
CQA cycles if no scalar integer | 4.17 |
CQA cycles if FP arith vectorized | 4.17 |
CQA cycles if fully vectorized | 0.30 |
Front-end cycles | 4.17 |
DIV/SQRT cycles | 2.70 |
P0 cycles | 3.47 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 0.50 |
P4 cycles | 2.60 |
P5 cycles | 2.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 2.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 4.14 - 4.15 |
Stall cycles (UFS) | 0.00 |
Nb insns | 24.00 |
Nb uops | 25.00 |
Nb loads | 6.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
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 | 8.64 |
Bytes prefetched | 0.00 |
Bytes loaded | 36.00 |
Bytes stored | 0.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 8.48 |
Vector-efficiency ratio load | 8.33 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 6.25 |
Vector-efficiency ratio add_sub | 9.38 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 8.93 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.91 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.26 |
Bottlenecks | P1, |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source | stl_vector.h:1046-1046,stl_vector.h:1169-1169,stl_algobase.h:235-235,stl_algobase.h:429-431,einspline_spo_ref.hpp:183-187,stl_algo.h:725-725,stl_algo.h:751-751 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.73 |
CQA cycles if no scalar integer | 2.73 |
CQA cycles if FP arith vectorized | 2.73 |
CQA cycles if fully vectorized | 0.18 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 2.73 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.00 |
P4 cycles | 1.47 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.53 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.29 |
Stall cycles (UFS) | 0.00 |
Nb insns | 14.00 |
Nb uops | 13.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
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 | 2.93 |
Bytes prefetched | 0.00 |
Bytes loaded | 8.00 |
Bytes stored | 0.00 |
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 | NA |
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 | 10.00 |
Vector-efficiency ratio load | 6.25 |
Vector-efficiency ratio store | NA |
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 | 9.38 |
Path / |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source file and lines | einspline_spo_ref.hpp:183-187 |
Module | exec |
nb instructions | 19 |
nb uops | 19 |
loop length | 64.50 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.10 | 2.30 | 1.33 | 1.33 | 0.25 | 2.03 | 2.00 | 0.25 | 0.25 | 0.25 | 2.07 | 1.33 |
cycles | 2.10 | 3.10 | 1.33 | 1.33 | 0.25 | 2.03 | 2.00 | 0.25 | 0.25 | 0.25 | 2.07 | 1.33 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 3.21-3.22 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 3.10 |
Data deps. | 1.00 |
Overall L1 | 3.45 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 9% |
load | 7% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 6% |
add-sub | 10% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 9% |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source file and lines | einspline_spo_ref.hpp:183-187 |
Module | exec |
nb instructions | 24 |
nb uops | 25 |
loop length | 85 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 4.17 cycles |
front end | 4.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.70 | 2.60 | 2.00 | 2.00 | 0.50 | 2.60 | 2.50 | 0.50 | 0.50 | 0.50 | 2.60 | 2.00 |
cycles | 2.70 | 3.47 | 2.00 | 2.00 | 0.50 | 2.60 | 2.50 | 0.50 | 0.50 | 0.50 | 2.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 4.14-4.15 |
Stall cycles | 0.00 |
Front-end | 4.17 |
Dispatch | 3.47 |
Data deps. | 1.00 |
Overall L1 | 4.17 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 8% |
load | 8% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 6% |
add-sub | 9% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %EAX,%RCX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD $0x18,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RCX,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 43c4c5 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x755> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %EAX,%EDX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
INC %R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x40(%R12),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL %R14D,%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x8(%R12),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %ECX,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMOVL %ESI,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
SUB %EDX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 43c470 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x700> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x310(%R12),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD %EDX,%RDI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
SAL $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
ADD 0x18(%R15),%RDI | 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 (%RAX,%RBX,1),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %ECX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SAL $0x3,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
CALL 4040a0 <memmove@plt> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%R12),%EAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 43c470 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x700> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source file and lines | einspline_spo_ref.hpp:183-187 |
Module | exec |
nb instructions | 14 |
nb uops | 13 |
loop length | 44 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 2.00 | 0.67 | 0.67 | 0.00 | 1.47 | 1.50 | 0.00 | 0.00 | 0.00 | 1.53 | 0.67 |
cycles | 1.50 | 2.73 | 0.67 | 0.67 | 0.00 | 1.47 | 1.50 | 0.00 | 0.00 | 0.00 | 1.53 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.29 |
Stall cycles | 0.00 |
Front-end | 2.17 |
Dispatch | 2.73 |
Data deps. | 1.00 |
Overall L1 | 2.73 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 10% |
load | 6% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 9% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD %EAX,%RCX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD $0x18,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RCX,%R14 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JGE 43c4c5 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x755> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R14D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
IMUL %EAX,%EDX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
INC %R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x40(%R12),%ECX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
IMUL %R14D,%ECX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV 0x8(%R12),%ESI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %ECX,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CMOVL %ESI,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
SUB %EDX,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 43c470 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x700> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |