Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcpl ... | Module: exec | Source: TwoBodyJastrowRef.h:148-304 [...] | Coverage: 1.57% |
---|
Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcpl ... | Module: exec | Source: TwoBodyJastrowRef.h:148-304 [...] | Coverage: 1.57% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 148 - 304 |
-------------------------------------------------------------------------------- |
148: for (int idim = 0; idim < OHMMS_DIM; ++idim) |
149: { |
150: const valT* restrict dX = displ.data(idim); |
151: valT s = valT(); |
152: |
153: for (int jat = 0; jat < N; ++jat) |
154: s += du[jat] * dX[jat]; |
155: grad[idim] = s; |
[...] |
295: TwoBodyJastrowRef<FT>::ratioGrad(ParticleSet& P, int iat, GradType& grad_iat) |
296: { |
297: UpdateMode = ORB_PBYP_PARTIAL; |
298: |
299: computeU3(P, iat, P.DistTables[0]->Temp_r.data(), cur_u.data(), cur_du.data(), cur_d2u.data()); |
300: cur_Uat = std::accumulate(cur_u.begin(), cur_u.begin() + N, valT()); |
301: DiffVal = Uat[iat] - cur_Uat; |
302: grad_iat += accumulateG(cur_du.data(), P.DistTables[0]->Temp_dr); |
303: return std::exp(DiffVal); |
304: } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 94 - 183 |
-------------------------------------------------------------------------------- |
94: (const_cast<T1&>(a) += b); |
[...] |
183: return (const_cast<T1&>(a) = b); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 221 - 221 |
-------------------------------------------------------------------------------- |
221: inline Type_t& operator[](size_t i) |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1258 - 1258 |
-------------------------------------------------------------------------------- |
1258: { return _M_data_ptr(this->_M_impl._M_start); } |
/usr/include/c++/13.1.1/bits/stl_iterator.h: 1148 - 1148 |
-------------------------------------------------------------------------------- |
1148: { return __normal_iterator(_M_current + __n); } |
/usr/include/c++/13.1.1/bits/stl_numeric.h: 140 - 141 |
-------------------------------------------------------------------------------- |
140: for (; __first != __last; ++__first) |
141: __init = _GLIBCXX_MOVE_IF_20(__init) + *__first; |
0x44a030 PUSH %RBP |
0x44a031 MOV %RSP,%RBP |
0x44a034 PUSH %R15 |
0x44a036 MOVSXD %EDX,%R15 |
0x44a039 MOV %R15D,%EDX |
0x44a03c PUSH %R14 |
0x44a03e PUSH %R13 |
0x44a040 MOV %RDI,%R13 |
0x44a043 PUSH %R12 |
0x44a045 MOV %RCX,%R12 |
0x44a048 PUSH %RBX |
0x44a049 SUB $0x38,%RSP |
0x44a04d MOV %FS:0x28,%RAX |
0x44a056 MOV %RAX,-0x38(%RBP) |
0x44a05a XOR %EAX,%EAX |
0x44a05c MOV 0xa10(%RSI),%RAX |
0x44a063 MOV 0x140(%RDI),%R8 |
0x44a06a MOVL $0x2,0xc(%RDI) |
0x44a071 MOV 0x158(%RDI),%RBX |
0x44a078 MOV (%RAX),%R14 |
0x44a07b MOV %RBX,%R9 |
0x44a07e MOV 0x68(%R14),%RCX |
0x44a082 PUSH $0 |
0x44a084 PUSHQ 0x170(%RDI) |
0x44a08a MOV %R8,-0x58(%RBP) |
0x44a08e CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> |
0x44a093 MOV 0x90(%R13),%R9 |
0x44a09a MOV -0x58(%RBP),%R8 |
0x44a09e VXORPD %XMM0,%XMM0,%XMM0 |
0x44a0a2 POP %RDX |
0x44a0a3 LEA (,%R9,8),%RSI |
0x44a0ab POP %RCX |
0x44a0ac LEA (%R8,%RSI,1),%RDI |
0x44a0b0 CMP %R8,%RDI |
0x44a0b3 JE 44a16a |
0x44a0b9 MOV %RDI,%RDX |
0x44a0bc SUB %R8,%RDX |
0x44a0bf SUB $0x8,%RDX |
0x44a0c3 SHR $0x3,%RDX |
0x44a0c7 INC %RDX |
0x44a0ca AND $0x7,%EDX |
0x44a0cd JE 44a132 |
0x44a0cf CMP $0x1,%RDX |
0x44a0d3 JE 44a124 |
0x44a0d5 CMP $0x2,%RDX |
0x44a0d9 JE 44a11b |
0x44a0db CMP $0x3,%RDX |
0x44a0df JE 44a112 |
0x44a0e1 CMP $0x4,%RDX |
0x44a0e5 JE 44a109 |
0x44a0e7 CMP $0x5,%RDX |
0x44a0eb JE 44a100 |
0x44a0ed CMP $0x6,%RDX |
0x44a0f1 JNE 44a362 |
0x44a0f7 VADDSD (%R8),%XMM0,%XMM0 |
0x44a0fc ADD $0x8,%R8 |
0x44a100 VADDSD (%R8),%XMM0,%XMM0 |
0x44a105 ADD $0x8,%R8 |
0x44a109 VADDSD (%R8),%XMM0,%XMM0 |
0x44a10e ADD $0x8,%R8 |
0x44a112 VADDSD (%R8),%XMM0,%XMM0 |
0x44a117 ADD $0x8,%R8 |
0x44a11b VADDSD (%R8),%XMM0,%XMM0 |
0x44a120 ADD $0x8,%R8 |
0x44a124 VADDSD (%R8),%XMM0,%XMM0 |
0x44a129 ADD $0x8,%R8 |
0x44a12d CMP %RDI,%R8 |
0x44a130 JE 44a16a |
(598) 0x44a132 VADDSD (%R8),%XMM0,%XMM1 |
(598) 0x44a137 ADD $0x40,%R8 |
(598) 0x44a13b VADDSD -0x38(%R8),%XMM1,%XMM2 |
(598) 0x44a141 VADDSD -0x30(%R8),%XMM2,%XMM3 |
(598) 0x44a147 VADDSD -0x28(%R8),%XMM3,%XMM4 |
(598) 0x44a14d VADDSD -0x20(%R8),%XMM4,%XMM5 |
(598) 0x44a153 VADDSD -0x18(%R8),%XMM5,%XMM6 |
(598) 0x44a159 VADDSD -0x10(%R8),%XMM6,%XMM7 |
(598) 0x44a15f VADDSD -0x8(%R8),%XMM7,%XMM0 |
(598) 0x44a165 CMP %RDI,%R8 |
(598) 0x44a168 JNE 44a132 |
0x44a16a MOV 0xd8(%R13),%RCX |
0x44a171 VMOVSD %XMM0,0x138(%R13) |
0x44a17a MOV 0x88(%R14),%R10 |
0x44a181 VXORPD %XMM10,%XMM10,%XMM10 |
0x44a186 MOVQ $0,-0x40(%RBP) |
0x44a18e MOV 0x98(%R14),%R14 |
0x44a195 LEA -0x50(%RBP),%R11 |
0x44a199 LEA -0x38(%RBP),%R8 |
0x44a19d VMOVSD (%RCX,%R15,8),%XMM8 |
0x44a1a3 VMOVAPD %XMM10,-0x50(%RBP) |
0x44a1a8 LEA (,%R10,8),%R15 |
0x44a1b0 VSUBSD %XMM0,%XMM8,%XMM9 |
0x44a1b4 VMOVSD %XMM9,0xb0(%R13) |
(596) 0x44a1bd TEST %R9,%R9 |
(596) 0x44a1c0 JE 44a358 |
(596) 0x44a1c6 LEA -0x8(%RSI),%RDI |
(596) 0x44a1ca XOR %EAX,%EAX |
(596) 0x44a1cc VXORPD %XMM11,%XMM11,%XMM11 |
(596) 0x44a1d1 SHR $0x3,%RDI |
(596) 0x44a1d5 INC %RDI |
(596) 0x44a1d8 AND $0x7,%EDI |
(596) 0x44a1db JE 44a268 |
(596) 0x44a1e1 CMP $0x1,%RDI |
(596) 0x44a1e5 JE 44a254 |
(596) 0x44a1e7 CMP $0x2,%RDI |
(596) 0x44a1eb JE 44a245 |
(596) 0x44a1ed CMP $0x3,%RDI |
(596) 0x44a1f1 JE 44a236 |
(596) 0x44a1f3 CMP $0x4,%RDI |
(596) 0x44a1f7 JE 44a227 |
(596) 0x44a1f9 CMP $0x5,%RDI |
(596) 0x44a1fd JE 44a218 |
(596) 0x44a1ff CMP $0x6,%RDI |
(596) 0x44a203 JNE 44a340 |
(596) 0x44a209 VMOVSD (%RBX,%RAX,1),%XMM13 |
(596) 0x44a20e VFMADD231SD (%R14,%RAX,1),%XMM13,%XMM11 |
(596) 0x44a214 ADD $0x8,%RAX |
(596) 0x44a218 VMOVSD (%RBX,%RAX,1),%XMM14 |
(596) 0x44a21d VFMADD231SD (%R14,%RAX,1),%XMM14,%XMM11 |
(596) 0x44a223 ADD $0x8,%RAX |
(596) 0x44a227 VMOVSD (%RBX,%RAX,1),%XMM15 |
(596) 0x44a22c VFMADD231SD (%R14,%RAX,1),%XMM15,%XMM11 |
(596) 0x44a232 ADD $0x8,%RAX |
(596) 0x44a236 VMOVSD (%RBX,%RAX,1),%XMM0 |
(596) 0x44a23b VFMADD231SD (%R14,%RAX,1),%XMM0,%XMM11 |
(596) 0x44a241 ADD $0x8,%RAX |
(596) 0x44a245 VMOVSD (%RBX,%RAX,1),%XMM1 |
(596) 0x44a24a VFMADD231SD (%R14,%RAX,1),%XMM1,%XMM11 |
(596) 0x44a250 ADD $0x8,%RAX |
(596) 0x44a254 VMOVSD (%RBX,%RAX,1),%XMM2 |
(596) 0x44a259 VFMADD231SD (%R14,%RAX,1),%XMM2,%XMM11 |
(596) 0x44a25f ADD $0x8,%RAX |
(596) 0x44a263 CMP %RAX,%RSI |
(596) 0x44a266 JE 44a2d7 |
(597) 0x44a268 VMOVSD (%RBX,%RAX,1),%XMM3 |
(597) 0x44a26d VMOVSD 0x8(%RBX,%RAX,1),%XMM4 |
(597) 0x44a273 VMOVSD 0x10(%RBX,%RAX,1),%XMM5 |
(597) 0x44a279 VMOVSD 0x18(%RBX,%RAX,1),%XMM6 |
(597) 0x44a27f VFMADD231SD (%R14,%RAX,1),%XMM3,%XMM11 |
(597) 0x44a285 VMOVSD 0x20(%RBX,%RAX,1),%XMM7 |
(597) 0x44a28b VMOVSD 0x28(%RBX,%RAX,1),%XMM8 |
(597) 0x44a291 VMOVSD 0x30(%RBX,%RAX,1),%XMM9 |
(597) 0x44a297 VMOVSD 0x38(%RBX,%RAX,1),%XMM10 |
(597) 0x44a29d ADD $0x40,%RAX |
(597) 0x44a2a1 VFMADD231SD -0x38(%RAX,%R14,1),%XMM4,%XMM11 |
(597) 0x44a2a8 VFMADD231SD -0x30(%RAX,%R14,1),%XMM5,%XMM11 |
(597) 0x44a2af VFMADD231SD -0x28(%RAX,%R14,1),%XMM6,%XMM11 |
(597) 0x44a2b6 VFMADD231SD -0x20(%RAX,%R14,1),%XMM7,%XMM11 |
(597) 0x44a2bd VFMADD231SD -0x18(%RAX,%R14,1),%XMM8,%XMM11 |
(597) 0x44a2c4 VFMADD231SD -0x10(%RAX,%R14,1),%XMM9,%XMM11 |
(597) 0x44a2cb VFMADD231SD -0x8(%RAX,%R14,1),%XMM10,%XMM11 |
(597) 0x44a2d2 CMP %RAX,%RSI |
(597) 0x44a2d5 JNE 44a268 |
(596) 0x44a2d7 VMOVSD %XMM11,(%R11) |
(596) 0x44a2dc ADD $0x8,%R11 |
(596) 0x44a2e0 ADD %R15,%R14 |
(596) 0x44a2e3 CMP %R8,%R11 |
(596) 0x44a2e6 JNE 44a1bd |
0x44a2ec VMOVUPD (%R12),%XMM11 |
0x44a2f2 VMOVSD 0x10(%R12),%XMM13 |
0x44a2f9 VADDPD -0x50(%RBP),%XMM11,%XMM12 |
0x44a2fe VADDSD -0x40(%RBP),%XMM13,%XMM14 |
0x44a303 VMOVUPD %XMM12,(%R12) |
0x44a309 VMOVSD %XMM14,0x10(%R12) |
0x44a310 MOV -0x38(%RBP),%RAX |
0x44a314 SUB %FS:0x28,%RAX |
0x44a31d JNE 44a370 |
0x44a31f VMOVSD 0xb0(%R13),%XMM0 |
0x44a328 LEA -0x28(%RBP),%RSP |
0x44a32c POP %RBX |
0x44a32d POP %R12 |
0x44a32f POP %R13 |
0x44a331 POP %R14 |
0x44a333 POP %R15 |
0x44a335 POP %RBP |
0x44a336 JMP 4040a0 |
0x44a33b NOPL (%RAX,%RAX,1) |
(596) 0x44a340 VMOVSD (%RBX),%XMM12 |
(596) 0x44a344 MOV $0x8,%EAX |
(596) 0x44a349 VFMADD231SD (%R14),%XMM12,%XMM11 |
(596) 0x44a34e JMP 44a209 |
0x44a353 NOPL (%RAX,%RAX,1) |
(596) 0x44a358 VXORPD %XMM11,%XMM11,%XMM11 |
(596) 0x44a35d JMP 44a2d7 |
0x44a362 VMOVSD (%R8),%XMM0 |
0x44a367 ADD $0x8,%R8 |
0x44a36b JMP 44a0f7 |
0x44a370 CALL 404140 <__stack_chk_fail@plt> |
0x44a375 NOPW %CS:(%RAX,%RAX,1) |
0x44a37f NOP |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | exec |
○ | main._omp_fn.1 | miniqmc.cpp:438 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | TwoBodyJastrowRef.h:148-304 |
Module | exec |
nb instructions | 107 |
nb uops | 110 |
loop length | 460 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 8 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 27.50 cycles |
front end | 27.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 13.00 | 13.00 | 18.17 | 17.83 | 19.00 | 13.00 | 13.00 | 18.00 |
cycles | 13.00 | 13.00 | 18.17 | 17.83 | 19.00 | 13.00 | 13.00 | 18.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 27.36 |
Stall cycles | 0.00 |
Front-end | 27.50 |
Dispatch | 19.00 |
Overall L1 | 27.50 |
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 | 28% |
load | 15% |
store | 40% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 11% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 14% |
load | 14% |
store | 22% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 7% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
all | 11% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 16% |
load | 14% |
store | 17% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 13% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 13% |
load | 14% |
store | 13% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 13% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 13% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EDX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R15D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x38,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0x2,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x158(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x68(%R14),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x170(%RDI) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x90(%R13),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
POP %RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
LEA (,%R9,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
LEA (%R8,%RSI,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a16a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x3,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x7,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a132 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a124 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a11b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a112 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a109 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a100 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44a362 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a16a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xd8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,0x138(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x88(%R14),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM10,%XMM10,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVQ $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x98(%R14),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x50(%RBP),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%RCX,%R15,8),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVAPD %XMM10,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%R10,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VSUBSD %XMM0,%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,0xb0(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD (%R12),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%R12),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDPD -0x50(%RBP),%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD -0x40(%RBP),%XMM13,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %XMM12,(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM14,0x10(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %FS:0x28,%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 44a370 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD 0xb0(%R13),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 4040a0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD (%R8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 44a0f7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CALL 404140 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | TwoBodyJastrowRef.h:148-304 |
Module | exec |
nb instructions | 107 |
nb uops | 110 |
loop length | 460 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 8 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 27.50 cycles |
front end | 27.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 13.00 | 13.00 | 18.17 | 17.83 | 19.00 | 13.00 | 13.00 | 18.00 |
cycles | 13.00 | 13.00 | 18.17 | 17.83 | 19.00 | 13.00 | 13.00 | 18.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 27.36 |
Stall cycles | 0.00 |
Front-end | 27.50 |
Dispatch | 19.00 |
Overall L1 | 27.50 |
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 | 28% |
load | 15% |
store | 40% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 11% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 14% |
load | 14% |
store | 22% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 7% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
all | 11% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 16% |
load | 14% |
store | 17% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 13% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 25% |
all | 13% |
load | 14% |
store | 13% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 13% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 13% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EDX,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R15D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RCX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x38,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa10(%RSI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x140(%RDI),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0x2,0xc(%RDI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x158(%RDI),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RBX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x68(%R14),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x170(%RDI) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 449690 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9computeU3ERKNS1_11ParticleSetEiPKdPdSA_SA_b> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x90(%R13),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
POP %RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
LEA (,%R9,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
LEA (%R8,%RSI,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a16a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %R8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x8,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x3,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
AND $0x7,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a132 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a124 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a11b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a112 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a109 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a100 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 44a362 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VADDSD (%R8),%XMM0,%XMM0 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RDI,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 44a16a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xd8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD %XMM0,0x138(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x88(%R14),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VXORPD %XMM10,%XMM10,%XMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVQ $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV 0x98(%R14),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x50(%RBP),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%RCX,%R15,8),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVAPD %XMM10,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (,%R10,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VSUBSD %XMM0,%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,0xb0(%R13) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVUPD (%R12),%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD 0x10(%R12),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VADDPD -0x50(%RBP),%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VADDSD -0x40(%RBP),%XMM13,%XMM14 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %XMM12,(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM14,0x10(%R12) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x38(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
SUB %FS:0x28,%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 44a370 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD 0xb0(%R13),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
JMP 4040a0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVSD (%R8),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 44a0f7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
CALL 404140 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::TwoBodyJastrowRef | 1.57 | 1.53 |
○Loop 598 - stl_numeric.h:140-141 - exec | 0.34 | 0.33 |
▼Loop 596 - TwoBodyJastrowRef.h:148-155 - exec– | 0 | 0 |
○Loop 597 - TwoBodyJastrowRef.h:153-154 - exec | 1.23 | 1.2 |