ICODE-ADC/lammps
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@15246 f3b2605a-c512-4ea7-a41b-209d697bcdaa

Browse Source
This commit is contained in:
sjplimp
2016-07-01 23:23:56 +00:00
parent d11877d5af
commit cedb420ebc
2 changed files with 45 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/USER-INTEL/dihedral_charmm_intel.cpp
View File

@ -178,6 +178,11 @@ void DihedralCharmmIntel::eval(const int vflag,
}
}
#if defined(LMP_SIMD_COMPILER_TEST)
#pragma vector aligned
#pragma simd reduction(+:sedihedral, sevdwl, secoul, sv0, sv1, sv2, \
sv3, sv4, sv5, spv0, spv1, spv2, spv3, spv4, spv5)
#endif
for (int n = nfrom; n < nto; n++) {
const int i1 = dihedrallist[n].a;
const int i2 = dihedrallist[n].b;
@ -237,6 +242,7 @@ void DihedralCharmmIntel::eval(const int vflag,
const flt_t s = rg*rabinv*(ax*vb3x + ay*vb3y + az*vb3z);
// error check
#ifndef LMP_SIMD_COMPILER_TEST
if (c > PTOLERANCE || c < MTOLERANCE) {
int me = comm->me;
@ -258,6 +264,7 @@ void DihedralCharmmIntel::eval(const int vflag,
me,x[i4].x,x[i4].y,x[i4].z);
}
}
#endif
if (c > (flt_t)1.0) c = (flt_t)1.0;
if (c < (flt_t)-1.0) c = (flt_t)-1.0;
@ -337,6 +344,9 @@ void DihedralCharmmIntel::eval(const int vflag,
}
#if defined(LMP_SIMD_COMPILER_TEST)
#pragma simdoff
#endif
{
if (NEWTON_BOND || i2 < nlocal) {
f[i2].x += f2x;
@ -413,6 +423,9 @@ void DihedralCharmmIntel::eval(const int vflag,
}
// apply force to each of 4 atoms
#if defined(LMP_SIMD_COMPILER_TEST)
#pragma simdoff
#endif
{
if (NEWTON_BOND || i1 < nlocal) {
f[i1].x += f1x;
@ -668,7 +681,7 @@ void DihedralCharmmIntel::eval(const int vflag,
const SIMD_flt_t tcos_shift = SIMD_gather(nmask, cos_shift, type);
const SIMD_flt_t tsin_shift = SIMD_gather(nmask, sin_shift, type);
const SIMD_flt_t tk = SIMD_gather(nmask, k, type);
const SIMD_int m = SIMD_gather(nmask, multiplicity, type);
const SIMD_int m = SIMD_gatherz_offset<flt_t>(nmask, multiplicity, type);
SIMD_flt_t p(one);
SIMD_flt_t ddf1(szero);

31
src/USER-INTEL/intel_simd.h
View File

@ -194,6 +194,37 @@ namespace ip_simd {
_MM_SCALE_8);
}
template <typename T>
inline SIMD_int SIMD_gatherz_offset(const SIMD_mask &m, const int *p,
const SIMD_int &i) {
}
template <>
inline SIMD_int SIMD_gatherz_offset<float>(const SIMD_mask &m, const int *p,
const SIMD_int &i) {
return _mm512_mask_i32gather_epi32( _mm512_set1_epi32(0), m, i, p,
_MM_SCALE_4);
}
template <>
inline SIMD_int SIMD_gatherz_offset<double>(const SIMD_mask &m, const int *p,
const SIMD_int &i) {
return _mm512_mask_i32gather_epi32( _mm512_set1_epi32(0), m, i, p,
_MM_SCALE_8);
}
inline SIMD_float SIMD_gatherz(const SIMD_mask &m, const float *p,
const SIMD_int &i) {
return _mm512_mask_i32gather_ps( _mm512_set1_ps((float)0), m, i, p,
_MM_SCALE_4);
}
inline SIMD_double SIMD_gatherz(const SIMD_mask &m, const double *p,
const SIMD_int &i) {
return _mm512_mask_i32logather_pd( _mm512_set1_pd(0.0), m, i, p,
_MM_SCALE_8);
}
// ------- Store Operations
inline void SIMD_store(int *p, const SIMD_int &one) {