Loop Id: 75 | Module: exec | Source: NonLocalPP.hpp:122-135 [...] | Coverage: 0.01% |
---|
Loop Id: 75 | Module: exec | Source: NonLocalPP.hpp:122-135 [...] | Coverage: 0.01% |
---|
0x40d6b0 MOV 0x260(%RSI),%RCX |
0x40d6b7 MOV -0x48(%RBP),%R12 |
0x40d6bb MOV -0x30(%RBP),%RDI |
0x40d6bf INC %RDI |
0x40d6c2 MOV %RDI,%RDX |
0x40d6c5 MOV %RDI,-0x30(%RBP) |
0x40d6c9 CMP %RDI,%RCX |
0x40d6cc JBE 40d85f |
0x40d6d2 CMPQ $0,0x260(%RAX) |
0x40d6da JE 40d6bb |
0x40d6dc MOV -0x38(%RBP),%RDX |
0x40d6e0 MOV 0x48(%RDX),%RCX |
0x40d6e4 MOV 0x60(%RDX),%RDX |
0x40d6e8 MOV -0x30(%RBP),%R8 |
0x40d6ec LEA (,%R8,8),%RDI |
0x40d6f4 LEA (%RDI,%RDI,4),%RDI |
0x40d6f8 LEA 0x18(%RCX,%RDI,1),%R15 |
0x40d6fd LEA 0x18(%RDX,%RDI,1),%RBX |
0x40d702 LEA (%R8,%R8,2),%R12 |
0x40d706 XOR %R14D,%R14D |
0x40d709 JMP 40d71c |
(76) 0x40d710 INC %R14 |
(76) 0x40d713 CMP %R14,0x260(%RAX) |
(76) 0x40d71a JBE 40d6b0 |
(76) 0x40d71c MOV (%R15),%RCX |
(76) 0x40d71f VMOVSD (%RCX,%R14,8),%XMM0 |
(76) 0x40d725 VUCOMISD (%R13),%XMM0 |
(76) 0x40d72b JAE 40d710 |
(76) 0x40d72d MOV 0x13f0(%R13),%RCX |
(76) 0x40d734 SUB 0x13e8(%R13),%RCX |
(76) 0x40d73b SHR $0x3,%RCX |
(76) 0x40d73f IMUL $-0x55555555,%ECX,%ECX |
(76) 0x40d745 TEST %ECX,%ECX |
(76) 0x40d747 JLE 40d809 |
(76) 0x40d74d VPBROADCASTQ %R14,%XMM0 |
(76) 0x40d753 MOV $0x10,%EAX |
(76) 0x40d758 XOR %ECX,%ECX |
(76) 0x40d75a MOV -0x48(%RBP),%R8 |
(76) 0x40d75e XCHG %AX,%AX |
(77) 0x40d760 MOV (%R15),%RDX |
(77) 0x40d763 VMOVDDUP (%RDX,%R14,8),%XMM1 |
(77) 0x40d769 MOV (%RBX),%RDX |
(77) 0x40d76c MOVSXD -0x10(%RBX),%R9 |
(77) 0x40d770 VMOVSD (%R8,%RAX,1),%XMM2 |
(77) 0x40d776 LEA (%R14,%R9,2),%RDI |
(77) 0x40d77a VFMADD213SD (%RDX,%RDI,8),%XMM1,%XMM2 |
(77) 0x40d780 VPBROADCASTQ %RDX,%XMM3 |
(77) 0x40d786 VMOVQ %R9,%XMM4 |
(77) 0x40d78b VPSLLDQ $0x8,%XMM4,%XMM4 |
(77) 0x40d790 VPADDQ %XMM4,%XMM0,%XMM4 |
(77) 0x40d794 VPSLLQ $0x3,%XMM4,%XMM4 |
(77) 0x40d799 VPADDQ %XMM4,%XMM3,%XMM3 |
(77) 0x40d79d VMOVQ %XMM3,%RDX |
(77) 0x40d7a2 VMOVSD (%RDX),%XMM4 |
(77) 0x40d7a6 VPEXTRQ $0x1,%XMM3,%RDX |
(77) 0x40d7ac VMOVHPD (%RDX),%XMM4,%XMM3 |
(77) 0x40d7b0 MOV 0x40(%RSI),%RDX |
(77) 0x40d7b4 VADDSD 0x10(%RDX,%R12,8),%XMM2,%XMM2 |
(77) 0x40d7bb VFMADD231PD -0x10(%R8,%RAX,1),%XMM1,%XMM3 |
(77) 0x40d7c2 VADDPD (%RDX,%R12,8),%XMM3,%XMM1 |
(77) 0x40d7c8 MOV -0x60(%RBP),%RDX |
(77) 0x40d7cc VMOVUPD %XMM1,-0x10(%RDX,%RAX,1) |
(77) 0x40d7d2 VMOVSD %XMM2,(%RDX,%RAX,1) |
(77) 0x40d7d7 MOV 0x13f0(%R13),%RDX |
(77) 0x40d7de SUB 0x13e8(%R13),%RDX |
(77) 0x40d7e5 INC %RCX |
(77) 0x40d7e8 SHR $0x3,%RDX |
(77) 0x40d7ec IMUL $-0x55555555,%EDX,%EDX |
(77) 0x40d7f2 MOVSXD %EDX,%RDX |
(77) 0x40d7f5 ADD $0x18,%RAX |
(77) 0x40d7f9 CMP %RDX,%RCX |
(77) 0x40d7fc JL 40d760 |
(76) 0x40d802 MOV 0x1418(%R13),%RAX |
(76) 0x40d809 MOV 0x18(%RAX),%RAX |
(76) 0x40d80d MOVSXD (%RAX,%R14,4),%RAX |
(76) 0x40d811 MOV 0x1400(%R13),%RCX |
(76) 0x40d818 MOV (%RCX,%RAX,8),%R13 |
(76) 0x40d81c MOV %R13,%RDI |
(76) 0x40d81f MOV -0x30(%RBP),%RDX |
(76) 0x40d823 LEA -0x60(%RBP),%RCX |
(76) 0x40d827 MOV $0x1,%R8D |
(76) 0x40d82d MOV %R14D,%R9D |
(76) 0x40d830 CALL 464170 <_ZN11qmcplusplus18VirtualParticleSet9makeMovesERKNS_11ParticleSetEiRKSt6vectorINS_10TinyVectorIdLj3EEESaIS6_EEbi> |
(76) 0x40d835 MOV -0x90(%RBP),%RDI |
(76) 0x40d83c MOV %R13,%RSI |
(76) 0x40d83f LEA -0x80(%RBP),%RDX |
(76) 0x40d843 CALL 40fc10 <_ZN11qmcplusplus12WaveFunction14evaluateRatiosERNS_18VirtualParticleSetERSt6vectorIdSaIdEE> |
(76) 0x40d848 MOV -0x68(%RBP),%R13 |
(76) 0x40d84c MOV 0x1418(%R13),%RAX |
(76) 0x40d853 MOV -0x88(%RBP),%RSI |
(76) 0x40d85a JMP 40d710 |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 231 - 231 |
-------------------------------------------------------------------------------- |
231: inline const AoSElement_t operator[](size_t i) const { return AoSElement_t(myData + i, nGhosts); } |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 277 - 277 |
-------------------------------------------------------------------------------- |
277: inline size_t getTotalNum() const { return TotalNum; } |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 145 - 170 |
-------------------------------------------------------------------------------- |
145: X[i] = base[i * offset]; |
[...] |
170: inline const Type_t& operator[](unsigned int i) const { return X[i]; } |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 43 - 63 |
-------------------------------------------------------------------------------- |
43: return (a + b); |
[...] |
63: return (a * b); |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/stl_vector.h: 806 - 951 |
-------------------------------------------------------------------------------- |
806: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
[...] |
933: return *(this->_M_impl._M_start + __n); |
[...] |
951: return *(this->_M_impl._M_start + __n); |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp: 122 - 135 |
-------------------------------------------------------------------------------- |
122: for (int jel = 0; jel < els.getTotalNum(); ++jel) |
123: { |
124: const auto& dist = d_ie.getDistRow(jel); |
125: const auto& displ = d_ie.getDisplRow(jel); |
126: for (int iat = 0; iat < ions_ref.getTotalNum(); ++iat) |
127: { |
128: //due to < Rmax condition, the actually iteration iat is [0,2] in a real simulation |
129: if (dist[iat] < Rmax) |
130: { |
131: for (int k = 0; k < size(); k++) |
132: virtualPos[k] = dist[iat] * rOnSphere[k] + displ[iat] + els.R[jel]; |
133: auto& VP = *VPs[ions_ref.GroupID[iat]]; |
134: VP.makeMoves(els, jel, virtualPos, true, iat); |
135: wf.evaluateRatios(VP, ratios); |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/unique_ptr.h: 150 - 150 |
-------------------------------------------------------------------------------- |
150: pointer _M_ptr() const { return std::get<0>(_M_t); } |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | main.extracted.110 | NewTimer.h:249 | exec |
○ | __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 | 12.91 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.31 |
Bottlenecks | |
Function | qmcplusplus::NonLocalPP |
Source | VectorSoAContainer.h:231-231,ParticleSet.h:277-277,TinyVector.h:170-170,OhmmsVector.h:229-229,stl_vector.h:951-951,NonLocalPP.hpp:122-122,NonLocalPP.hpp:126-126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.96 |
CQA cycles if no scalar integer | 2.96 |
CQA cycles if FP arith vectorized | 2.96 |
CQA cycles if fully vectorized | 0.23 |
Front-end cycles | 2.96 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 2.00 |
P1 cycles | 2.17 |
P2 cycles | 2.17 |
P3 cycles | 0.50 |
P4 cycles | 0.90 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.90 |
P10 cycles | 2.17 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.10 |
Stall cycles (UFS) | 0.00 |
Nb insns | 17.75 |
Nb uops | 17.75 |
Nb loads | 6.50 |
Nb stores | 1.00 |
Nb stack references | 2.50 |
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 | 19.93 |
Bytes prefetched | 0.00 |
Bytes loaded | 52.00 |
Bytes stored | 8.00 |
Stride 0 | 2.50 |
Stride 1 | 0.75 |
Stride n | 1.00 |
Stride unknown | 1.50 |
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 | 11.33 |
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 | 1.33 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::NonLocalPP |
Source | VectorSoAContainer.h:231-231,ParticleSet.h:277-277,TinyVector.h:170-170,OhmmsVector.h:229-229,stl_vector.h:951-951,NonLocalPP.hpp:122-122,NonLocalPP.hpp:126-126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.33 |
CQA cycles if no scalar integer | 1.33 |
CQA cycles if FP arith vectorized | 1.33 |
CQA cycles if fully vectorized | 0.17 |
Front-end cycles | 1.33 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.50 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.60 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 1.44 |
Stall cycles (UFS) | 0.00 |
Nb insns | 8.00 |
Nb uops | 8.00 |
Nb loads | 2.00 |
Nb stores | 1.00 |
Nb stack references | 1.00 |
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 | 18.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 16.00 |
Bytes stored | 8.00 |
Stride 0 | 1.00 |
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 | 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 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 14.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.31 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::NonLocalPP |
Source | VectorSoAContainer.h:231-231,ParticleSet.h:277-277,TinyVector.h:170-170,OhmmsVector.h:229-229,stl_vector.h:951-951,NonLocalPP.hpp:122-122,NonLocalPP.hpp:126-126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 3.50 |
CQA cycles if fully vectorized | 0.25 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 2.40 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 0.50 |
P4 cycles | 1.00 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 0 |
FE+BE cycles (UFS) | 3.66 |
Stall cycles (UFS) | 0.00 |
Nb insns | 21.00 |
Nb uops | 21.00 |
Nb loads | 8.00 |
Nb stores | 1.00 |
Nb stack references | 3.00 |
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 | 20.57 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 8.00 |
Stride 0 | 3.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 2.00 |
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 | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 10.94 |
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 | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.38 |
Path / |
Function | qmcplusplus::NonLocalPP |
Source file and lines | NonLocalPP.hpp:122-135 |
Module | exec |
nb instructions | 17.75 |
nb uops | 17.75 |
loop length | 76.50 |
used x86 registers | 9.50 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2.50 |
micro-operation queue | 2.96 cycles |
front end | 2.96 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 1.70 | 2.17 | 2.17 | 0.50 | 0.90 | 1.00 | 0.50 | 0.50 | 0.50 | 0.90 | 2.17 |
cycles | 1.00 | 2.00 | 2.17 | 2.17 | 0.50 | 0.90 | 1.00 | 0.50 | 0.50 | 0.50 | 0.90 | 2.17 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.10 |
Stall cycles | 0.00 |
Front-end | 2.96 |
Dispatch | 2.25 |
Data deps. | 0.00 |
Overall L1 | 2.96 |
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% |
Function | qmcplusplus::NonLocalPP |
Source file and lines | NonLocalPP.hpp:122-135 |
Module | exec |
nb instructions | 8 |
nb uops | 8 |
loop length | 33 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 1.33 cycles |
front end | 1.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 0.67 | 0.67 | 0.50 | 0.60 | 1.00 | 0.50 | 0.50 | 0.50 | 0.60 | 0.67 |
cycles | 1.00 | 0.80 | 0.67 | 0.67 | 0.50 | 0.60 | 1.00 | 0.50 | 0.50 | 0.50 | 0.60 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 1.44 |
Stall cycles | 0.00 |
Front-end | 1.33 |
Dispatch | 1.00 |
Data deps. | 0.00 |
Overall L1 | 1.33 |
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 -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 40d85f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x77f> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPQ $0,0x260(%RAX) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 40d6bb <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x5db> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | qmcplusplus::NonLocalPP |
Source file and lines | NonLocalPP.hpp:122-135 |
Module | exec |
nb instructions | 21 |
nb uops | 21 |
loop length | 91 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 2.00 | 2.67 | 2.67 | 0.50 | 1.00 | 1.00 | 0.50 | 0.50 | 0.50 | 1.00 | 2.67 |
cycles | 1.00 | 2.40 | 2.67 | 2.67 | 0.50 | 1.00 | 1.00 | 0.50 | 0.50 | 0.50 | 1.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 0.00 |
FE+BE cycles | 3.66 |
Stall cycles | 0.00 |
Front-end | 3.50 |
Dispatch | 2.67 |
Data deps. | 0.00 |
Overall L1 | 3.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 10% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV 0x260(%RSI),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RDI,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 40d85f <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x77f> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
CMPQ $0,0x260(%RAX) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 40d6bb <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x5db> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x48(%RDX),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x60(%RDX),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (,%R8,8),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA (%RDI,%RDI,4),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
LEA 0x18(%RCX,%RDI,1),%R15 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA 0x18(%RDX,%RDI,1),%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%R8,%R8,2),%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
JMP 40d71c <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x63c> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |