Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ... | Module: libqmcwfs.so | Source: einspline_spo_ref.hpp:172-189 [...] | Coverage: 14.65% |
---|
Function: miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int ... | Module: libqmcwfs.so | Source: einspline_spo_ref.hpp:172-189 [...] | Coverage: 14.65% |
---|
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineEvalHelper.hpp: 55 - 65 |
-------------------------------------------------------------------------------- |
55: if (x < 0) |
[...] |
62: ind = static_cast<int>(x); |
63: dx = x - ind; |
64: // upper bound |
65: if (ind > nmax) |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 217 - 217 |
-------------------------------------------------------------------------------- |
217: inline const PosType& activeR(int iat) const { return (activePtcl == iat) ? activePos : R[iat]; } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineData.hpp: 54 - 57 |
-------------------------------------------------------------------------------- |
54: a[0] = ((A00 * tx + A01) * tx + A02) * tx + A03; |
55: a[1] = ((A10 * tx + A11) * tx + A12) * tx + A13; |
56: a[2] = ((A20 * tx + A21) * tx + A22) * tx + A23; |
57: a[3] = ((A30 * tx + A31) * tx + A32) * tx + A33; |
/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_algo.h: 731 - 757 |
-------------------------------------------------------------------------------- |
731: { return std::copy(__first, __first + __n, __result); } |
[...] |
757: if (__n2 <= 0) |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 42 - 74 |
-------------------------------------------------------------------------------- |
42: x -= spline_m->x_grid.start; |
43: y -= spline_m->y_grid.start; |
44: z -= spline_m->z_grid.start; |
45: T tx, ty, tz; |
46: int ix, iy, iz; |
47: spline2::getSplineBound(x * spline_m->x_grid.delta_inv, tx, ix, spline_m->x_grid.num - 1); |
48: spline2::getSplineBound(y * spline_m->y_grid.delta_inv, ty, iy, spline_m->y_grid.num - 1); |
49: spline2::getSplineBound(z * spline_m->z_grid.delta_inv, tz, iz, spline_m->z_grid.num - 1); |
[...] |
56: const intptr_t xs = spline_m->x_stride; |
57: const intptr_t ys = spline_m->y_stride; |
58: const intptr_t zs = spline_m->z_stride; |
59: |
60: constexpr int simdlen_ = QMC_SIMD_ALIGNMENT/sizeof(T); |
61: constexpr T zero(0); |
62: |
63: std::fill(vals, vals + num_splines, zero); |
64: |
65: for (size_t i = 0; i < 4; i++) |
66: for (size_t j = 0; j < 4; j++) |
67: { |
68: const T pre00 = a[i] * b[j]; |
69: const T* restrict coefs = spline_m->coefs + (ix + i) * xs + (iy + j) * ys + iz * zs; |
70: #pragma omp simd aligned(coefs: QMC_SIMD_ALIGNMENT) simdlen(simdlen_) |
71: for (size_t n = 0; n < num_splines; n++) |
72: vals[n] += pre00 * |
73: (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] + |
74: c[3] * coefs[n + 3 * zs]); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
/usr/include/c++/13.1.1/bits/stl_algobase.h: 238 - 931 |
-------------------------------------------------------------------------------- |
238: if (__b < __a) |
[...] |
398: { *__to = *__from; } |
[...] |
436: if (__builtin_expect(_Num > 1, true)) |
437: __builtin_memmove(__result, __first, sizeof(_Tp) * _Num); |
[...] |
930: for (; __first != __last; ++__first) |
931: *__first = __tmp; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/einspline_spo_ref.hpp: 172 - 189 |
-------------------------------------------------------------------------------- |
172: ScopedTimer local_timer(timer); |
173: |
174: auto u = Lattice.toUnit_floor(P.activeR(iat)); |
175: for (int i = 0; i < nBlocks; ++i) |
176: MultiBsplineEvalRef::evaluate_v(einsplines[i], u[0], u[1], u[2], psi[i].data(), nSplinesPerBlock); |
177: } |
178: |
179: inline void evaluate(const ParticleSet& P, int iat, ValueVector_t& psi_v) |
180: { |
181: evaluate_v(P, iat); |
182: |
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); |
188: } |
189: } |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249 |
-------------------------------------------------------------------------------- |
242: ScopeGuard(TIMER& t) : timer(t) { timer.start(); } |
[...] |
249: ~ScopeGuard() { timer.stop(); } |
0x4f9f0 PUSH %RBP |
0x4f9f1 MOV %RSP,%RBP |
0x4f9f4 PUSH %R15 |
0x4f9f6 MOVSXD %EDX,%R15 |
0x4f9f9 PUSH %R14 |
0x4f9fb PUSH %R13 |
0x4f9fd PUSH %R12 |
0x4f9ff MOV %RSI,%R12 |
0x4fa02 PUSH %RBX |
0x4fa03 MOV %RDI,%RBX |
0x4fa06 AND $-0x40,%RSP |
0x4fa0a SUB $0x140,%RSP |
0x4fa11 MOV %RCX,0x10(%RSP) |
0x4fa16 MOV %FS:0x28,%RAX |
0x4fa1f MOV %RAX,0x138(%RSP) |
0x4fa27 MOV 0x348(%RDI),%RAX |
0x4fa2e MOV %RAX,%RDI |
0x4fa31 MOV %RAX,0x18(%RSP) |
0x4fa36 CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> |
0x4fa3b LEA 0x48(%RBX),%RSI |
0x4fa3f LEA 0x988(%R12),%RDX |
0x4fa47 CMP 0x984(%R12),%R15D |
0x4fa4f JE 4fa61 |
0x4fa51 MOV 0x5e8(%R12),%RCX |
0x4fa59 LEA (%R15,%R15,2),%RDX |
0x4fa5d LEA (%RCX,%RDX,8),%RDX |
0x4fa61 LEA 0xc0(%RSP),%RDI |
0x4fa69 CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> |
0x4fa6e MOVSXD 0x30(%RBX),%RSI |
0x4fa72 TEST %ESI,%ESI |
0x4fa74 JLE 50204 |
0x4fa7a MOVSXD 0x40(%RBX),%R14 |
0x4fa7e MOV 0x2e8(%RBX),%R10 |
0x4fa85 LEA 0xe0(%RSP),%R15 |
0x4fa8d LEA 0x100(%RSP),%RDX |
0x4fa95 MOV 0x300(%RBX),%R9 |
0x4fa9c LEA 0x120(%RSP),%RAX |
0x4faa4 VMOVSD 0xd0(%RSP),%XMM7 |
0x4faad MOV %R15,0x20(%RSP) |
0x4fab2 MOV %R14,%R12 |
0x4fab5 LEA (,%R14,8),%R8 |
0x4fabd LEA (%R10,%RSI,8),%R11 |
0x4fac1 VMOVSD 0xc8(%RSP),%XMM0 |
0x4faca AND $-0x8,%R12 |
0x4face VMOVSD 0xc0(%RSP),%XMM1 |
0x4fad7 MOV %R14,%R13 |
0x4fada MOV %R14D,0x74(%RSP) |
0x4fadf MOV %R8,0x60(%RSP) |
0x4fae4 SHR $0x3,%R13 |
0x4fae8 MOV %R9,0x58(%RSP) |
0x4faed SAL $0x6,%R13 |
0x4faf1 MOV %R10,0x68(%RSP) |
0x4faf6 MOV %R11,0x28(%RSP) |
0x4fafb MOV %R12,0xa0(%RSP) |
0x4fb03 MOV %RAX,0xb0(%RSP) |
0x4fb0b MOV %RBX,0x8(%RSP) |
0x4fb10 MOV %RDX,0x98(%RSP) |
0x4fb18 VMOVSD %XMM7,0x40(%RSP) |
0x4fb1e VMOVSD %XMM0,0x38(%RSP) |
0x4fb24 VMOVSD %XMM1,0x30(%RSP) |
(556) 0x4fb2a MOV 0x68(%RSP),%RSI |
(556) 0x4fb2f VMOVSD 0x30(%RSP),%XMM6 |
(556) 0x4fb35 VXORPD %XMM8,%XMM8,%XMM8 |
(556) 0x4fb3a MOV 0x58(%RSP),%RBX |
(556) 0x4fb3f VMOVSD 0x38(%RSP),%XMM2 |
(556) 0x4fb45 MOV (%RSI),%R15 |
(556) 0x4fb48 VMOVSD 0x40(%RSP),%XMM3 |
(556) 0x4fb4e MOV (%RBX),%RCX |
(556) 0x4fb51 VSUBSD 0x28(%R15),%XMM6,%XMM4 |
(556) 0x4fb57 VSUBSD 0x50(%R15),%XMM2,%XMM10 |
(556) 0x4fb5d VSUBSD 0x78(%R15),%XMM3,%XMM11 |
(556) 0x4fb63 MOV 0x38(%R15),%EDI |
(556) 0x4fb67 VMULSD 0x48(%R15),%XMM4,%XMM5 |
(556) 0x4fb6d VCOMISD %XMM5,%XMM8 |
(556) 0x4fb71 JA 502f6 |
(556) 0x4fb77 VCVTTSD2SI %XMM5,%R8D |
(556) 0x4fb7b DEC %EDI |
(556) 0x4fb7d CMP %R8D,%EDI |
(556) 0x4fb80 JL 50306 |
(556) 0x4fb86 VRNDSCALESD $0xb,%XMM5,%XMM5,%XMM9 |
(556) 0x4fb8d VSUBSD %XMM9,%XMM5,%XMM12 |
(556) 0x4fb92 VMOVSD 0x178ae(%RIP),%XMM15 |
(556) 0x4fb9a VMOVSD 0x16ede(%RIP),%XMM0 |
(556) 0x4fba2 MOVSXD %R8D,%R12 |
(556) 0x4fba5 VMULSD 0x16e13(%RIP),%XMM12,%XMM14 |
(556) 0x4fbad VMOVSD %XMM12,%XMM12,%XMM1 |
(556) 0x4fbb1 VMOVSD %XMM12,%XMM12,%XMM2 |
(556) 0x4fbb5 VFNMADD132SD %XMM15,%XMM15,%XMM1 |
(556) 0x4fbba VFMADD213SD 0x16e05(%RIP),%XMM15,%XMM2 |
(556) 0x4fbc3 VMULSD %XMM12,%XMM12,%XMM13 |
(556) 0x4fbc8 VADDSD %XMM15,%XMM14,%XMM7 |
(556) 0x4fbcd VXORPD 0x16e7b(%RIP),%XMM14,%XMM3 |
(556) 0x4fbd5 VFMADD231SD %XMM1,%XMM12,%XMM15 |
(556) 0x4fbda VMULSD %XMM13,%XMM3,%XMM6 |
(556) 0x4fbdf VFMADD213SD 0x16ea0(%RIP),%XMM13,%XMM2 |
(556) 0x4fbe8 VFMADD213SD 0x1785f(%RIP),%XMM12,%XMM7 |
(556) 0x4fbf1 VFMADD132SD %XMM12,%XMM0,%XMM7 |
(556) 0x4fbf6 VFMADD231SD %XMM15,%XMM12,%XMM0 |
(556) 0x4fbfb VUNPCKLPD %XMM2,%XMM7,%XMM5 |
(556) 0x4fbff VUNPCKLPD %XMM6,%XMM0,%XMM4 |
(556) 0x4fc03 VINSERTF128 $0x1,%XMM4,%YMM5,%YMM12 |
(556) 0x4fc09 VMULSD 0x70(%R15),%XMM10,%XMM10 |
(556) 0x4fc0f VXORPD %XMM8,%XMM8,%XMM8 |
(556) 0x4fc14 MOV 0x60(%R15),%EAX |
(556) 0x4fc18 VCOMISD %XMM10,%XMM8 |
(556) 0x4fc1d JA 502dd |
(556) 0x4fc23 VCVTTSD2SI %XMM10,%R9D |
(556) 0x4fc28 DEC %EAX |
(556) 0x4fc2a CMP %R9D,%EAX |
(556) 0x4fc2d JL 50346 |
(556) 0x4fc33 VRNDSCALESD $0xb,%XMM10,%XMM10,%XMM9 |
(556) 0x4fc3a VSUBSD %XMM9,%XMM10,%XMM13 |
(556) 0x4fc3f VMOVSD 0x16e39(%RIP),%XMM15 |
(556) 0x4fc47 VMOVSD 0x177f9(%RIP),%XMM0 |
(556) 0x4fc4f MOVSXD %R9D,%R10 |
(556) 0x4fc52 MOV %R10,0xa8(%RSP) |
(556) 0x4fc5a VMULSD %XMM15,%XMM13,%XMM7 |
(556) 0x4fc5f VMOVSD %XMM13,%XMM13,%XMM3 |
(556) 0x4fc63 VMOVSD %XMM13,%XMM13,%XMM1 |
(556) 0x4fc67 VFNMADD132SD %XMM0,%XMM0,%XMM3 |
(556) 0x4fc6c VFMADD213SD 0x16d53(%RIP),%XMM0,%XMM1 |
(556) 0x4fc75 VMULSD %XMM13,%XMM13,%XMM14 |
(556) 0x4fc7a VSUBSD %XMM7,%XMM0,%XMM2 |
(556) 0x4fc7e VFMADD231SD %XMM3,%XMM13,%XMM0 |
(556) 0x4fc83 VMULSD %XMM14,%XMM7,%XMM6 |
(556) 0x4fc88 VFMADD213SD 0x16df7(%RIP),%XMM14,%XMM1 |
(556) 0x4fc91 VFMADD213SD 0x177b6(%RIP),%XMM13,%XMM2 |
(556) 0x4fc9a VFMADD132SD %XMM13,%XMM15,%XMM2 |
(556) 0x4fc9f VFMADD231SD %XMM0,%XMM13,%XMM15 |
(556) 0x4fca4 VUNPCKLPD %XMM1,%XMM2,%XMM5 |
(556) 0x4fca8 VUNPCKLPD %XMM6,%XMM15,%XMM4 |
(556) 0x4fcac VINSERTF128 $0x1,%XMM4,%YMM5,%YMM13 |
(556) 0x4fcb2 VMULSD 0x98(%R15),%XMM11,%XMM11 |
(556) 0x4fcbb VXORPD %XMM10,%XMM10,%XMM10 |
(556) 0x4fcc0 MOV 0x88(%R15),%EAX |
(556) 0x4fcc7 VCOMISD %XMM11,%XMM10 |
(556) 0x4fccc JA 502af |
(556) 0x4fcd2 VCVTTSD2SI %XMM11,%R11D |
(556) 0x4fcd7 DEC %EAX |
(556) 0x4fcd9 CMP %R11D,%EAX |
(556) 0x4fcdc JL 50316 |
(556) 0x4fce2 VRNDSCALESD $0xb,%XMM11,%XMM11,%XMM8 |
(556) 0x4fce9 VSUBSD %XMM8,%XMM11,%XMM7 |
(556) 0x4fcee VMOVSD 0x17752(%RIP),%XMM15 |
(556) 0x4fcf6 VMOVSD 0x16d82(%RIP),%XMM0 |
(556) 0x4fcfe MOVSXD %R11D,%RDX |
(556) 0x4fd01 MOV %RDX,0x90(%RSP) |
(556) 0x4fd09 VMULSD 0x16caf(%RIP),%XMM7,%XMM14 |
(556) 0x4fd11 VMOVSD %XMM7,%XMM7,%XMM1 |
(556) 0x4fd15 VMOVSD %XMM7,%XMM7,%XMM10 |
(556) 0x4fd19 VFNMADD132SD %XMM15,%XMM15,%XMM1 |
(556) 0x4fd1e VFMADD213SD 0x16ca1(%RIP),%XMM15,%XMM10 |
(556) 0x4fd27 VMULSD %XMM7,%XMM7,%XMM2 |
(556) 0x4fd2b VADDSD %XMM15,%XMM14,%XMM9 |
(556) 0x4fd30 VXORPD 0x16d18(%RIP),%XMM14,%XMM3 |
(556) 0x4fd38 VFMADD231SD %XMM1,%XMM7,%XMM15 |
(556) 0x4fd3d VMULSD %XMM2,%XMM3,%XMM8 |
(556) 0x4fd41 VFMADD213SD 0x16d3e(%RIP),%XMM2,%XMM10 |
(556) 0x4fd4a VFMADD213SD 0x176fd(%RIP),%XMM7,%XMM9 |
(556) 0x4fd53 VFMADD132SD %XMM7,%XMM0,%XMM9 |
(556) 0x4fd58 VFMADD132SD %XMM15,%XMM0,%XMM7 |
(556) 0x4fd5d MOV 0x10(%R15),%RDI |
(556) 0x4fd61 MOV 0x18(%R15),%R8 |
(556) 0x4fd65 VMOVAPD %YMM12,0xe0(%RSP) |
(556) 0x4fd6e CMPQ $0,0x60(%RSP) |
(556) 0x4fd74 MOV 0x20(%R15),%RBX |
(556) 0x4fd78 VMOVAPD %YMM13,0x100(%RSP) |
(556) 0x4fd81 MOV %RDI,0x80(%RSP) |
(556) 0x4fd89 MOV %R8,0xb8(%RSP) |
(556) 0x4fd91 JE 4fdde |
(556) 0x4fd93 MOV 0x60(%RSP),%RDX |
(556) 0x4fd98 VMOVSD %XMM8,0x48(%RSP) |
(556) 0x4fd9e XOR %ESI,%ESI |
(556) 0x4fda0 MOV %RCX,%RDI |
(556) 0x4fda3 VMOVSD %XMM7,0x50(%RSP) |
(556) 0x4fda9 VMOVSD %XMM10,0x78(%RSP) |
(556) 0x4fdaf VMOVSD %XMM9,0x88(%RSP) |
(556) 0x4fdb8 VZEROUPPER |
(556) 0x4fdbb CALL 80e0 <memset@plt> |
(556) 0x4fdc0 VMOVSD 0x88(%RSP),%XMM9 |
(556) 0x4fdc9 VMOVSD 0x78(%RSP),%XMM10 |
(556) 0x4fdcf VMOVSD 0x50(%RSP),%XMM7 |
(556) 0x4fdd5 VMOVSD 0x48(%RSP),%XMM8 |
(556) 0x4fddb MOV %RAX,%RCX |
(556) 0x4fdde MOV 0xb8(%RSP),%R10 |
(556) 0x4fde6 MOV 0xa8(%RSP),%RDX |
(556) 0x4fdee VBROADCASTSD %XMM9,%YMM14 |
(556) 0x4fdf3 VBROADCASTSD %XMM8,%YMM13 |
(556) 0x4fdf8 MOV 0x80(%RSP),%R9 |
(556) 0x4fe00 MOV 0x20(%RSP),%R8 |
(556) 0x4fe05 VBROADCASTSD %XMM10,%YMM12 |
(556) 0x4fe0a VBROADCASTSD %XMM7,%YMM11 |
(556) 0x4fe0f SAL $0x3,%R10 |
(556) 0x4fe13 IMUL %R10,%RDX |
(556) 0x4fe17 MOV %R10,0xb8(%RSP) |
(556) 0x4fe1f IMUL %R12,%R9 |
(556) 0x4fe23 MOV 0x90(%RSP),%R12 |
(556) 0x4fe2b ADD 0x8(%R15),%RDX |
(556) 0x4fe2f IMUL %RBX,%R12 |
(556) 0x4fe33 LEA -0x1(%R14),%R15 |
(556) 0x4fe37 MOV %R15,0xa8(%RSP) |
(556) 0x4fe3f MOV %RDX,0x78(%RSP) |
(556) 0x4fe44 LEA (%R9,%R12,1),%R11 |
(556) 0x4fe48 LEA (,%RBX,8),%R12 |
(555) 0x4fe50 MOV 0x78(%RSP),%RAX |
(555) 0x4fe55 MOV 0x74(%RSP),%R10D |
(555) 0x4fe5a MOV %R8,0x90(%RSP) |
(555) 0x4fe62 VBROADCASTSD %XMM9,%ZMM5 |
(555) 0x4fe68 MOV %R11,0x88(%RSP) |
(555) 0x4fe70 VMOVSD (%R8),%XMM15 |
(555) 0x4fe75 VBROADCASTSD %XMM10,%ZMM4 |
(555) 0x4fe7b VBROADCASTSD %XMM7,%ZMM3 |
(555) 0x4fe81 MOV 0x98(%RSP),%RDI |
(555) 0x4fe89 LEA (%RAX,%R11,8),%RAX |
(555) 0x4fe8d VBROADCASTSD %XMM8,%ZMM2 |
(555) 0x4fe93 AND $0x7,%R10D |
(554) 0x4fe97 VMULSD (%RDI),%XMM15,%XMM6 |
(554) 0x4fe9b TEST %R14,%R14 |
(554) 0x4fe9e JE 50193 |
(554) 0x4fea4 CMPQ $0x6,0xa8(%RSP) |
(554) 0x4fead JBE 502a8 |
(554) 0x4feb3 LEA -0x40(%R13),%RSI |
(554) 0x4feb7 LEA (%RAX,%R12,1),%R9 |
(554) 0x4febb VBROADCASTSD %XMM6,%ZMM1 |
(554) 0x4fec1 XOR %R15D,%R15D |
(554) 0x4fec4 SHR $0x6,%RSI |
(554) 0x4fec8 LEA (%R9,%R12,1),%R8 |
(554) 0x4fecc INC %RSI |
(554) 0x4fecf LEA (%R8,%R12,1),%R11 |
(554) 0x4fed3 AND $0x3,%ESI |
(554) 0x4fed6 JE 4ff89 |
(554) 0x4fedc CMP $0x1,%RSI |
(554) 0x4fee0 JE 4ff4c |
(554) 0x4fee2 CMP $0x2,%RSI |
(554) 0x4fee6 JE 4ff18 |
(554) 0x4fee8 VMULPD (%R9),%ZMM4,%ZMM0 |
(554) 0x4feee MOV $0x40,%R15D |
(554) 0x4fef4 VMULPD (%R11),%ZMM2,%ZMM16 |
(554) 0x4fefa VFMADD231PD (%RAX),%ZMM5,%ZMM0 |
(554) 0x4ff00 VFMADD231PD (%R8),%ZMM3,%ZMM16 |
(554) 0x4ff06 VADDPD %ZMM16,%ZMM0,%ZMM0 |
(554) 0x4ff0c VFMADD213PD (%RCX),%ZMM1,%ZMM0 |
(554) 0x4ff12 VMOVUPD %ZMM0,(%RCX) |
(554) 0x4ff18 VMULPD (%R9,%R15,1),%ZMM4,%ZMM0 |
(554) 0x4ff1f VMULPD (%R11,%R15,1),%ZMM2,%ZMM17 |
(554) 0x4ff26 VFMADD231PD (%RAX,%R15,1),%ZMM5,%ZMM0 |
(554) 0x4ff2d VFMADD231PD (%R8,%R15,1),%ZMM3,%ZMM17 |
(554) 0x4ff34 VADDPD %ZMM17,%ZMM0,%ZMM0 |
(554) 0x4ff3a VFMADD213PD (%RCX,%R15,1),%ZMM1,%ZMM0 |
(554) 0x4ff41 VMOVUPD %ZMM0,(%RCX,%R15,1) |
(554) 0x4ff48 ADD $0x40,%R15 |
(554) 0x4ff4c VMULPD (%R9,%R15,1),%ZMM4,%ZMM0 |
(554) 0x4ff53 VMULPD (%R11,%R15,1),%ZMM2,%ZMM18 |
(554) 0x4ff5a VFMADD231PD (%RAX,%R15,1),%ZMM5,%ZMM0 |
(554) 0x4ff61 VFMADD231PD (%R8,%R15,1),%ZMM3,%ZMM18 |
(554) 0x4ff68 VADDPD %ZMM18,%ZMM0,%ZMM0 |
(554) 0x4ff6e VFMADD213PD (%RCX,%R15,1),%ZMM1,%ZMM0 |
(554) 0x4ff75 VMOVUPD %ZMM0,(%RCX,%R15,1) |
(554) 0x4ff7c ADD $0x40,%R15 |
(554) 0x4ff80 CMP %R15,%R13 |
(554) 0x4ff83 JE 5006b |
(557) 0x4ff89 VMULPD (%R9,%R15,1),%ZMM4,%ZMM0 |
(557) 0x4ff90 VMULPD (%R11,%R15,1),%ZMM2,%ZMM19 |
(557) 0x4ff97 VMULPD 0x40(%R11,%R15,1),%ZMM2,%ZMM20 |
(557) 0x4ff9f VMULPD 0x80(%R11,%R15,1),%ZMM2,%ZMM21 |
(557) 0x4ffa7 VMULPD 0xc0(%R11,%R15,1),%ZMM2,%ZMM22 |
(557) 0x4ffaf VFMADD231PD (%RAX,%R15,1),%ZMM5,%ZMM0 |
(557) 0x4ffb6 VFMADD231PD (%R8,%R15,1),%ZMM3,%ZMM19 |
(557) 0x4ffbd VFMADD231PD 0x40(%R8,%R15,1),%ZMM3,%ZMM20 |
(557) 0x4ffc5 VFMADD231PD 0x80(%R8,%R15,1),%ZMM3,%ZMM21 |
(557) 0x4ffcd VFMADD231PD 0xc0(%R8,%R15,1),%ZMM3,%ZMM22 |
(557) 0x4ffd5 VADDPD %ZMM19,%ZMM0,%ZMM0 |
(557) 0x4ffdb VFMADD213PD (%RCX,%R15,1),%ZMM1,%ZMM0 |
(557) 0x4ffe2 VMOVUPD %ZMM0,(%RCX,%R15,1) |
(557) 0x4ffe9 VMULPD 0x40(%R9,%R15,1),%ZMM4,%ZMM0 |
(557) 0x4fff1 VFMADD231PD 0x40(%RAX,%R15,1),%ZMM5,%ZMM0 |
(557) 0x4fff9 VADDPD %ZMM20,%ZMM0,%ZMM0 |
(557) 0x4ffff VFMADD213PD 0x40(%RCX,%R15,1),%ZMM1,%ZMM0 |
(557) 0x50007 VMOVUPD %ZMM0,0x40(%RCX,%R15,1) |
(557) 0x5000f VMULPD 0x80(%R9,%R15,1),%ZMM4,%ZMM0 |
(557) 0x50017 VFMADD231PD 0x80(%RAX,%R15,1),%ZMM5,%ZMM0 |
(557) 0x5001f VADDPD %ZMM21,%ZMM0,%ZMM0 |
(557) 0x50025 VFMADD213PD 0x80(%RCX,%R15,1),%ZMM1,%ZMM0 |
(557) 0x5002d VMOVUPD %ZMM0,0x80(%RCX,%R15,1) |
(557) 0x50035 VMULPD 0xc0(%R9,%R15,1),%ZMM4,%ZMM0 |
(557) 0x5003d VFMADD231PD 0xc0(%RAX,%R15,1),%ZMM5,%ZMM0 |
(557) 0x50045 VADDPD %ZMM22,%ZMM0,%ZMM0 |
(557) 0x5004b VFMADD213PD 0xc0(%RCX,%R15,1),%ZMM1,%ZMM0 |
(557) 0x50053 VMOVUPD %ZMM0,0xc0(%RCX,%R15,1) |
(557) 0x5005b ADD $0x100,%R15 |
(557) 0x50062 CMP %R15,%R13 |
(557) 0x50065 JNE 4ff89 |
(554) 0x5006b TEST %R10D,%R10D |
(554) 0x5006e JE 50193 |
(554) 0x50074 MOV 0xa0(%RSP),%RDX |
(554) 0x5007c MOV %R14,%RSI |
(554) 0x5007f SUB %RDX,%RSI |
(554) 0x50082 LEA -0x1(%RSI),%R9 |
(554) 0x50086 CMP $0x2,%R9 |
(554) 0x5008a JBE 500dc |
(554) 0x5008c LEA (%RBX,%RDX,1),%R9 |
(554) 0x50090 LEA (%RCX,%RDX,8),%R8 |
(554) 0x50094 VBROADCASTSD %XMM6,%YMM0 |
(554) 0x50099 LEA (%RBX,%R9,1),%R11 |
(554) 0x5009d LEA (%RBX,%R11,1),%R15 |
(554) 0x500a1 VMULPD (%RAX,%R11,8),%YMM11,%YMM1 |
(554) 0x500a7 VMULPD (%RAX,%R15,8),%YMM13,%YMM23 |
(554) 0x500ae VFMADD231PD (%RAX,%R9,8),%YMM12,%YMM1 |
(554) 0x500b4 VFMADD231PD (%RAX,%RDX,8),%YMM14,%YMM23 |
(554) 0x500bb VADDPD %YMM23,%YMM1,%YMM1 |
(554) 0x500c1 VFMADD213PD (%R8),%YMM1,%YMM0 |
(554) 0x500c6 VMOVUPD %YMM0,(%R8) |
(554) 0x500cb TEST $0x3,%SIL |
(554) 0x500cf JE 50193 |
(554) 0x500d5 AND $-0x4,%RSI |
(554) 0x500d9 ADD %RSI,%RDX |
(554) 0x500dc LEA (%RBX,%RDX,1),%R11 |
(554) 0x500e0 LEA (,%RDX,8),%R8 |
(554) 0x500e8 LEA (%R11,%RBX,1),%RSI |
(554) 0x500ec LEA (%RCX,%R8,1),%R9 |
(554) 0x500f0 VMULSD (%RAX,%RSI,8),%XMM7,%XMM0 |
(554) 0x500f5 ADD %RBX,%RSI |
(554) 0x500f8 LEA 0x1(%RDX),%R15 |
(554) 0x500fc VMULSD (%RAX,%RSI,8),%XMM8,%XMM1 |
(554) 0x50101 VFMADD231SD (%RAX,%R11,8),%XMM10,%XMM0 |
(554) 0x50107 VFMADD231SD (%RAX,%RDX,8),%XMM9,%XMM1 |
(554) 0x5010d VADDSD %XMM1,%XMM0,%XMM0 |
(554) 0x50111 VFMADD213SD (%R9),%XMM6,%XMM0 |
(554) 0x50116 VMOVSD %XMM0,(%R9) |
(554) 0x5011b CMP %R14,%R15 |
(554) 0x5011e JAE 50193 |
(554) 0x50120 ADD %RBX,%R15 |
(554) 0x50123 LEA 0x8(%RCX,%R8,1),%R11 |
(554) 0x50128 ADD $0x2,%RDX |
(554) 0x5012c LEA (%RBX,%R15,1),%R9 |
(554) 0x50130 VMULSD (%RAX,%R9,8),%XMM7,%XMM0 |
(554) 0x50136 ADD %RBX,%R9 |
(554) 0x50139 VMULSD (%RAX,%R9,8),%XMM8,%XMM1 |
(554) 0x5013f VFMADD231SD (%RAX,%R15,8),%XMM10,%XMM0 |
(554) 0x50145 VFMADD231SD 0x8(%R8,%RAX,1),%XMM9,%XMM1 |
(554) 0x5014c VADDSD %XMM1,%XMM0,%XMM0 |
(554) 0x50150 VFMADD213SD (%R11),%XMM6,%XMM0 |
(554) 0x50155 VMOVSD %XMM0,(%R11) |
(554) 0x5015a CMP %R14,%RDX |
(554) 0x5015d JAE 50193 |
(554) 0x5015f ADD %RBX,%RDX |
(554) 0x50162 LEA 0x10(%RCX,%R8,1),%R15 |
(554) 0x50167 LEA (%RBX,%RDX,1),%RSI |
(554) 0x5016b VMULSD (%RAX,%RSI,8),%XMM7,%XMM0 |
(554) 0x50170 ADD %RBX,%RSI |
(554) 0x50173 VMULSD (%RAX,%RSI,8),%XMM8,%XMM1 |
(554) 0x50178 VFMADD231SD (%RAX,%RDX,8),%XMM10,%XMM0 |
(554) 0x5017e VFMADD231SD 0x10(%R8,%RAX,1),%XMM9,%XMM1 |
(554) 0x50185 VADDSD %XMM1,%XMM0,%XMM0 |
(554) 0x50189 VFMADD213SD (%R15),%XMM6,%XMM0 |
(554) 0x5018e VMOVSD %XMM0,(%R15) |
(554) 0x50193 MOV 0xb8(%RSP),%RDX |
(554) 0x5019b ADD $0x8,%RDI |
(554) 0x5019f ADD %RDX,%RAX |
(554) 0x501a2 CMP %RDI,0xb0(%RSP) |
(554) 0x501aa JNE 4fe97 |
(555) 0x501b0 MOV 0x90(%RSP),%R8 |
(555) 0x501b8 MOV 0x88(%RSP),%R11 |
(555) 0x501c0 MOV 0x80(%RSP),%RDI |
(555) 0x501c8 MOV 0x98(%RSP),%RAX |
(555) 0x501d0 ADD $0x8,%R8 |
(555) 0x501d4 ADD %RDI,%R11 |
(555) 0x501d7 CMP %RAX,%R8 |
(555) 0x501da JNE 4fe50 |
(556) 0x501e0 ADDQ $0x8,0x68(%RSP) |
(556) 0x501e6 ADDQ $0x18,0x58(%RSP) |
(556) 0x501ec MOV 0x68(%RSP),%R10 |
(556) 0x501f1 CMP %R10,0x28(%RSP) |
(556) 0x501f6 JNE 4fb2a |
0x501fc MOV 0x8(%RSP),%RBX |
0x50201 VZEROUPPER |
0x50204 MOV 0x18(%RSP),%RDI |
0x50209 XOR %R14D,%R14D |
0x5020c XOR %R12D,%R12D |
0x5020f CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> |
0x50214 MOV 0x30(%RBX),%ESI |
0x50217 MOV 0x10(%RSP),%R13 |
0x5021c TEST %ESI,%ESI |
0x5021e JLE 5027e |
(553) 0x50220 MOV 0x40(%RBX),%EAX |
(553) 0x50223 MOV %R12D,%R9D |
(553) 0x50226 INC %R12D |
(553) 0x50229 MOV 0x8(%RBX),%ECX |
(553) 0x5022c IMUL %ESI,%R9D |
(553) 0x50230 IMUL %R12D,%EAX |
(553) 0x50234 CMP %ECX,%EAX |
(553) 0x50236 CMOVG %ECX,%EAX |
(553) 0x50239 SUB %R9D,%EAX |
(553) 0x5023c TEST %EAX,%EAX |
(553) 0x5023e JLE 50275 |
(553) 0x50240 MOV 0x18(%R13),%RDX |
(553) 0x50244 MOV 0x300(%RBX),%R8 |
(553) 0x5024b MOVSXD %R9D,%R15 |
(553) 0x5024e CLTQ |
(553) 0x50250 LEA (%RDX,%R15,8),%RDI |
(553) 0x50254 LEA (,%RAX,8),%RDX |
(553) 0x5025c MOV (%R8,%R14,1),%R11 |
(553) 0x50260 CMP $0x8,%RDX |
(553) 0x50264 JE 5035d |
(553) 0x5026a MOV %R11,%RSI |
(553) 0x5026d CALL 8080 <memmove@plt> |
(553) 0x50272 MOV 0x30(%RBX),%ESI |
(553) 0x50275 ADD $0x18,%R14 |
(553) 0x50279 CMP %ESI,%R12D |
(553) 0x5027c JL 50220 |
0x5027e MOV 0x138(%RSP),%RAX |
0x50286 SUB %FS:0x28,%RAX |
0x5028f JNE 5036b |
0x50295 LEA -0x28(%RBP),%RSP |
0x50299 POP %RBX |
0x5029a POP %R12 |
0x5029c POP %R13 |
0x5029e POP %R14 |
0x502a0 POP %R15 |
0x502a2 POP %RBP |
0x502a3 RET |
0x502a4 NOPL (%RAX) |
(554) 0x502a8 XOR %EDX,%EDX |
(554) 0x502aa JMP 5007c |
(556) 0x502af VMOVSD 0x167c9(%RIP),%XMM7 |
(556) 0x502b7 MOV 0x167ca(%RIP),%RSI |
(556) 0x502be MOVQ $0,0x90(%RSP) |
(556) 0x502ca VXORPD %XMM8,%XMM8,%XMM8 |
(556) 0x502cf VMOVQ %RSI,%XMM10 |
(556) 0x502d4 VMOVSD %XMM7,%XMM7,%XMM9 |
(556) 0x502d8 JMP 4fd5d |
(556) 0x502dd MOVQ $0,0xa8(%RSP) |
(556) 0x502e9 VMOVAPD 0x1678f(%RIP),%YMM13 |
(556) 0x502f1 JMP 4fcb2 |
(556) 0x502f6 VMOVAPD 0x16782(%RIP),%YMM12 |
(556) 0x502fe XOR %R12D,%R12D |
(556) 0x50301 JMP 4fc09 |
(556) 0x50306 VMOVAPD 0x16792(%RIP),%YMM12 |
(556) 0x5030e MOVSXD %EDI,%R12 |
(556) 0x50311 JMP 4fc09 |
(556) 0x50316 MOV 0x1676b(%RIP),%RBX |
(556) 0x5031d CLTQ |
(556) 0x5031f VMOVSD 0x16791(%RIP),%XMM8 |
(556) 0x50327 VXORPD %XMM9,%XMM9,%XMM9 |
(556) 0x5032c MOV %RAX,0x90(%RSP) |
(556) 0x50334 VMOVSD 0x1676c(%RIP),%XMM10 |
(556) 0x5033c VMOVQ %RBX,%XMM7 |
(556) 0x50341 JMP 4fd5d |
(556) 0x50346 CLTQ |
(556) 0x50348 VMOVAPD 0x16750(%RIP),%YMM13 |
(556) 0x50350 MOV %RAX,0xa8(%RSP) |
(556) 0x50358 JMP 4fcb2 |
(553) 0x5035d VMOVSD (%R11),%XMM15 |
(553) 0x50362 VMOVSD %XMM15,(%RDI) |
(553) 0x50366 JMP 50275 |
0x5036b CALL 80d0 <__stack_chk_fail@plt> |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►50.00+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:194 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:216 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1123 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►42.50+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:194 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:216 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1123 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►7.50+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:194 | libqmcwfs.so |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:216 | libqmcwfs.so |
○ | main._omp_fn.1 | miniqmc.cpp:486 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | einspline_spo_ref.hpp:172-189 |
Module | libqmcwfs.so |
nb instructions | 83 |
nb uops | 90 |
loop length | 397 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 22.50 cycles |
front end | 22.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.50 | 7.50 | 16.83 | 16.50 | 26.00 | 7.50 | 7.50 | 16.67 |
cycles | 7.50 | 7.50 | 16.83 | 16.50 | 26.00 | 7.50 | 7.50 | 16.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.13 |
Stall cycles | 0.91 |
SB full (events) | 1.45 |
Front-end | 22.50 |
Dispatch | 26.00 |
Overall L1 | 26.00 |
all | 4% |
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) |
other | 14% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 3% |
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 | 14% |
all | 11% |
load | 10% |
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) |
other | 11% |
all | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 11% |
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 | 11% |
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 |
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 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,%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 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x140,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,0x138(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x348(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,0x18(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
LEA 0x48(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x988(%R12),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP 0x984(%R12),%R15D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 4fa61 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5e8(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R15,%R15,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RCX,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0xc0(%RSP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD 0x30(%RBX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 50204 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD 0x40(%RBX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x2e8(%RBX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0xe0(%RSP),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x100(%RSP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x300(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x120(%RSP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0xd0(%RSP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (,%R14,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%R10,%RSI,8),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0xc8(%RSP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
AND $-0x8,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0xc0(%RSP),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R14D,0x74(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SHR $0x3,%R13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R9,0x58(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x6,%R13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R10,0x68(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0x28(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,0x98(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM0,0x38(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM1,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%RSP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV 0x18(%RSP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RSP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 5027e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x138(%RSP),%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 5036b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
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 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 80d0 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
Source file and lines | einspline_spo_ref.hpp:172-189 |
Module | libqmcwfs.so |
nb instructions | 83 |
nb uops | 90 |
loop length | 397 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 3 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 22.50 cycles |
front end | 22.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.50 | 7.50 | 16.83 | 16.50 | 26.00 | 7.50 | 7.50 | 16.67 |
cycles | 7.50 | 7.50 | 16.83 | 16.50 | 26.00 | 7.50 | 7.50 | 16.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.13 |
Stall cycles | 0.91 |
SB full (events) | 1.45 |
Front-end | 22.50 |
Dispatch | 26.00 |
Overall L1 | 26.00 |
all | 4% |
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) |
other | 14% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 3% |
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 | 14% |
all | 11% |
load | 10% |
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) |
other | 11% |
all | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 11% |
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 | 11% |
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 |
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 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSI,%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 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x40,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SUB $0x140,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,0x10(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %FS:0x28,%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,0x138(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x348(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,0x18(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 8460 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
LEA 0x48(%RBX),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x988(%R12),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP 0x984(%R12),%R15D | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 4fa61 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x5e8(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%R15,%R15,2),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RCX,%RDX,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0xc0(%RSP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 123c0 <_ZNK11qmcplusplus14CrystalLatticeIdLj3ELb0EE12toUnit_floorIdEENS_10TinyVectorIdLj3EEERKNS3_IT_Lj3EEE> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD 0x30(%RBX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 50204 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD 0x40(%RBX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x2e8(%RBX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0xe0(%RSP),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x100(%RSP),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x300(%RBX),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x120(%RSP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0xd0(%RSP),%XMM7 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R15,0x20(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R14,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA (,%R14,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%R10,%RSI,8),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD 0xc8(%RSP),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
AND $-0x8,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD 0xc0(%RSP),%XMM1 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R14D,0x74(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,0x60(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SHR $0x3,%R13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R9,0x58(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SAL $0x6,%R13 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R10,0x68(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,0x28(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R12,0xa0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RAX,0xb0(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,0x8(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDX,0x98(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM7,0x40(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM0,0x38(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM1,0x30(%RSP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%RSP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
MOV 0x18(%RSP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R14D,%R14D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 8420 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x30(%RBX),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RSP),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %ESI,%ESI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 5027e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x138(%RSP),%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 5036b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
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 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 80d0 <__stack_chk_fail@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::einspline_spo_ref | 14.65 | 0.2 |
○Loop 553 - einspline_spo_ref.hpp:183-187 - libqmcwfs.so | 0 | 0 |
▼Loop 556 - einspline_spo_ref.hpp:175-176 - libqmcwfs.so– | 0 | 0 |
▼Loop 555 - MultiBsplineRef.hpp:65-74 - libqmcwfs.so– | 0 | 0 |
▼Loop 554 - MultiBsplineRef.hpp:66-74 - libqmcwfs.so– | 0 | 0 |
○Loop 557 - MultiBsplineRef.hpp:72-74 - libqmcwfs.so | 14.65 | 0.2 |