void advec_cell_kernel4_xdir_c_wrapper(
double *p_a0,
double *p_a1,
double *p_a2,
double *p_a3,
double *p_a4,
double *p_a5,
double *p_a6,
double *p_a7,
double *p_a8,
double *p_a9,
double *p_a10,
int x_size, int y_size, int z_size) {
#ifdef OPS_GPU
#pragma acc parallel deviceptr(p_a0,p_a1,p_a2,p_a3,p_a4,p_a5,p_a6,p_a7,p_a8,p_a9,p_a10)
#pragma acc loop
#endif
for ( int n_z=0; n_z<z_size; n_z++ ){
#ifdef OPS_GPU
#pragma acc loop
#endif
for ( int n_y=0; n_y<y_size; n_y++ ){
#ifdef OPS_GPU
#pragma acc loop
#endif
for ( int n_x=0; n_x<x_size; n_x++ ){
advec_cell_kernel4_xdir( p_a0 + n_x*1 + n_y*xdim0_advec_cell_kernel4_xdir*1 + n_z*xdim0_advec_cell_kernel4_xdir*ydim0_advec_cell_kernel4_xdir*1,
p_a1 + n_x*1 + n_y*xdim1_advec_cell_kernel4_xdir*1 + n_z*xdim1_advec_cell_kernel4_xdir*ydim1_advec_cell_kernel4_xdir*1,
p_a2 + n_x*1 + n_y*xdim2_advec_cell_kernel4_xdir*1 + n_z*xdim2_advec_cell_kernel4_xdir*ydim2_advec_cell_kernel4_xdir*1,
p_a3 + n_x*1 + n_y*xdim3_advec_cell_kernel4_xdir*1 + n_z*xdim3_advec_cell_kernel4_xdir*ydim3_advec_cell_kernel4_xdir*1,
p_a4 + n_x*1 + n_y*xdim4_advec_cell_kernel4_xdir*1 + n_z*xdim4_advec_cell_kernel4_xdir*ydim4_advec_cell_kernel4_xdir*1,
p_a5 + n_x*1 + n_y*xdim5_advec_cell_kernel4_xdir*1 + n_z*xdim5_advec_cell_kernel4_xdir*ydim5_advec_cell_kernel4_xdir*1,
p_a6 + n_x*1 + n_y*xdim6_advec_cell_kernel4_xdir*1 + n_z*xdim6_advec_cell_kernel4_xdir*ydim6_advec_cell_kernel4_xdir*1,
p_a7 + n_x*1 + n_y*xdim7_advec_cell_kernel4_xdir*1 + n_z*xdim7_advec_cell_kernel4_xdir*ydim7_advec_cell_kernel4_xdir*1,
p_a8 + n_x*1 + n_y*xdim8_advec_cell_kernel4_xdir*1 + n_z*xdim8_advec_cell_kernel4_xdir*ydim8_advec_cell_kernel4_xdir*1,
p_a9 + n_x*1 + n_y*xdim9_advec_cell_kernel4_xdir*1 + n_z*xdim9_advec_cell_kernel4_xdir*ydim9_advec_cell_kernel4_xdir*1,
p_a10 + n_x*1 + n_y*xdim10_advec_cell_kernel4_xdir*1 + n_z*xdim10_advec_cell_kernel4_xdir*ydim10_advec_cell_kernel4_xdir*1 );
}
}
}
}
// host stub function
void ops_par_loop_advec_cell_kernel4_xdir(
char const *name, ops_block block, int dim, int *range, ops_arg arg0,
ops_arg arg1, ops_arg arg2, ops_arg arg3, ops_arg arg4, ops_arg arg5,
ops_arg arg6, ops_arg arg7, ops_arg arg8, ops_arg arg9, ops_arg arg10) {
// Timing
double t1, t2, c1, c2;
char *p_a[11];
int offs[11][3];
ops_arg args[11] = {arg0, arg1, arg2, arg3, arg4, arg5,
arg6, arg7, arg8, arg9, arg10};
#ifdef CHECKPOINTING
if (!ops_checkpointing_before(args, 11, range, 111))
return;
#endif
if (OPS_diags > 1) {
ops_timing_realloc(111, "advec_cell_kernel4_xdir");
OPS_kernels[111].count++;
ops_timers_core(&c2, &t2);
}
// compute locally allocated range for the sub-block
int start[3];
int end[3];
#ifdef OPS_MPI
sub_block_list sb = OPS_sub_block_list[block->index];
#endif
#ifdef OPS_DEBUG
ops_register_args(args, "advec_cell_kernel4_xdir");
#endif
int arg_idx[3];
int arg_idx_base[3];
#ifdef OPS_MPI
if (compute_ranges(args, 11, block, range, start, end, arg_idx) < 0)
return;
#else // OPS_MPI
for (int n = 0; n < 3; n++) {
start[n] = range[2 * n];
end[n] = range[2 * n + 1];
arg_idx[n] = start[n];
}
#endif // OPS_MPI
for (int n = 0; n < 3; n++) {
arg_idx_base[n] = arg_idx[n];
}
offs[0][0] = args[0].stencil->stride[0] * 1; // unit step in x dimension
offs[0][1] =
off3D(1, &start[0], &end[0], args[0].dat->size, args[0].stencil->stride) -
offs[0][0];
offs[0][2] =
off3D(2, &start[0], &end[0], args[0].dat->size, args[0].stencil->stride) -
offs[0][1] - offs[0][0];
offs[1][0] = args[1].stencil->stride[0] * 1; // unit step in x dimension
offs[1][1] =
off3D(1, &start[0], &end[0], args[1].dat->size, args[1].stencil->stride) -
offs[1][0];
offs[1][2] =
off3D(2, &start[0], &end[0], args[1].dat->size, args[1].stencil->stride) -
offs[1][1] - offs[1][0];
offs[2][0] = args[2].stencil->stride[0] * 1; // unit step in x dimension
offs[2][1] =
off3D(1, &start[0], &end[0], args[2].dat->size, args[2].stencil->stride) -
offs[2][0];
offs[2][2] =
off3D(2, &start[0], &end[0], args[2].dat->size, args[2].stencil->stride) -
offs[2][1] - offs[2][0];
offs[3][0] = args[3].stencil->stride[0] * 1; // unit step in x dimension
offs[3][1] =
off3D(1, &start[0], &end[0], args[3].dat->size, args[3].stencil->stride) -
offs[3][0];
offs[3][2] =
off3D(2, &start[0], &end[0], args[3].dat->size, args[3].stencil->stride) -
offs[3][1] - offs[3][0];
offs[4][0] = args[4].stencil->stride[0] * 1; // unit step in x dimension
offs[4][1] =
off3D(1, &start[0], &end[0], args[4].dat->size, args[4].stencil->stride) -
offs[4][0];
offs[4][2] =
off3D(2, &start[0], &end[0], args[4].dat->size, args[4].stencil->stride) -
offs[4][1] - offs[4][0];
offs[5][0] = args[5].stencil->stride[0] * 1; // unit step in x dimension
offs[5][1] =
off3D(1, &start[0], &end[0], args[5].dat->size, args[5].stencil->stride) -
offs[5][0];
offs[5][2] =
off3D(2, &start[0], &end[0], args[5].dat->size, args[5].stencil->stride) -
offs[5][1] - offs[5][0];
offs[6][0] = args[6].stencil->stride[0] * 1; // unit step in x dimension
offs[6][1] =
off3D(1, &start[0], &end[0], args[6].dat->size, args[6].stencil->stride) -
offs[6][0];
offs[6][2] =
off3D(2, &start[0], &end[0], args[6].dat->size, args[6].stencil->stride) -
offs[6][1] - offs[6][0];
offs[7][0] = args[7].stencil->stride[0] * 1; // unit step in x dimension
offs[7][1] =
off3D(1, &start[0], &end[0], args[7].dat->size, args[7].stencil->stride) -
offs[7][0];
offs[7][2] =
off3D(2, &start[0], &end[0], args[7].dat->size, args[7].stencil->stride) -
offs[7][1] - offs[7][0];
offs[8][0] = args[8].stencil->stride[0] * 1; // unit step in x dimension
offs[8][1] =
off3D(1, &start[0], &end[0], args[8].dat->size, args[8].stencil->stride) -
offs[8][0];
offs[8][2] =
off3D(2, &start[0], &end[0], args[8].dat->size, args[8].stencil->stride) -
offs[8][1] - offs[8][0];
offs[9][0] = args[9].stencil->stride[0] * 1; // unit step in x dimension
offs[9][1] =
off3D(1, &start[0], &end[0], args[9].dat->size, args[9].stencil->stride) -
offs[9][0];
offs[9][2] =
off3D(2, &start[0], &end[0], args[9].dat->size, args[9].stencil->stride) -
offs[9][1] - offs[9][0];
offs[10][0] = args[10].stencil->stride[0] * 1; // unit step in x dimension
offs[10][1] = off3D(1, &start[0], &end[0], args[10].dat->size,
args[10].stencil->stride) -
offs[10][0];
offs[10][2] = off3D(2, &start[0], &end[0], args[10].dat->size,
args[10].stencil->stride) -
offs[10][1] - offs[10][0];
int off0_0 = offs[0][0];
int off0_1 = offs[0][1];
int off0_2 = offs[0][2];
int dat0 = (OPS_soa ? args[0].dat->type_size : args[0].dat->elem_size);
int off1_0 = offs[1][0];
int off1_1 = offs[1][1];
int off1_2 = offs[1][2];
int dat1 = (OPS_soa ? args[1].dat->type_size : args[1].dat->elem_size);
int off2_0 = offs[2][0];
int off2_1 = offs[2][1];
int off2_2 = offs[2][2];
int dat2 = (OPS_soa ? args[2].dat->type_size : args[2].dat->elem_size);
int off3_0 = offs[3][0];
int off3_1 = offs[3][1];
int off3_2 = offs[3][2];
int dat3 = (OPS_soa ? args[3].dat->type_size : args[3].dat->elem_size);
int off4_0 = offs[4][0];
int off4_1 = offs[4][1];
int off4_2 = offs[4][2];
int dat4 = (OPS_soa ? args[4].dat->type_size : args[4].dat->elem_size);
int off5_0 = offs[5][0];
int off5_1 = offs[5][1];
int off5_2 = offs[5][2];
int dat5 = (OPS_soa ? args[5].dat->type_size : args[5].dat->elem_size);
int off6_0 = offs[6][0];
int off6_1 = offs[6][1];
int off6_2 = offs[6][2];
int dat6 = (OPS_soa ? args[6].dat->type_size : args[6].dat->elem_size);
int off7_0 = offs[7][0];
int off7_1 = offs[7][1];
int off7_2 = offs[7][2];
int dat7 = (OPS_soa ? args[7].dat->type_size : args[7].dat->elem_size);
int off8_0 = offs[8][0];
int off8_1 = offs[8][1];
int off8_2 = offs[8][2];
int dat8 = (OPS_soa ? args[8].dat->type_size : args[8].dat->elem_size);
int off9_0 = offs[9][0];
int off9_1 = offs[9][1];
int off9_2 = offs[9][2];
int dat9 = (OPS_soa ? args[9].dat->type_size : args[9].dat->elem_size);
int off10_0 = offs[10][0];
int off10_1 = offs[10][1];
int off10_2 = offs[10][2];
int dat10 = (OPS_soa ? args[10].dat->type_size : args[10].dat->elem_size);
// set up initial pointers and exchange halos if necessary
int base0 = args[0].dat->base_offset +
(OPS_soa ? args[0].dat->type_size : args[0].dat->elem_size) *
start[0] * args[0].stencil->stride[0];
base0 = base0 +
(OPS_soa ? args[0].dat->type_size : args[0].dat->elem_size) *
args[0].dat->size[0] * start[1] * args[0].stencil->stride[1];
base0 = base0 +
(OPS_soa ? args[0].dat->type_size : args[0].dat->elem_size) *
args[0].dat->size[0] * args[0].dat->size[1] * start[2] *
args[0].stencil->stride[2];
p_a[0] = (char *)args[0].data + base0;
int base1 = args[1].dat->base_offset +
(OPS_soa ? args[1].dat->type_size : args[1].dat->elem_size) *
start[0] * args[1].stencil->stride[0];
base1 = base1 +
(OPS_soa ? args[1].dat->type_size : args[1].dat->elem_size) *
args[1].dat->size[0] * start[1] * args[1].stencil->stride[1];
base1 = base1 +
(OPS_soa ? args[1].dat->type_size : args[1].dat->elem_size) *
args[1].dat->size[0] * args[1].dat->size[1] * start[2] *
args[1].stencil->stride[2];
p_a[1] = (char *)args[1].data + base1;
int base2 = args[2].dat->base_offset +
(OPS_soa ? args[2].dat->type_size : args[2].dat->elem_size) *
start[0] * args[2].stencil->stride[0];
base2 = base2 +
(OPS_soa ? args[2].dat->type_size : args[2].dat->elem_size) *
args[2].dat->size[0] * start[1] * args[2].stencil->stride[1];
base2 = base2 +
(OPS_soa ? args[2].dat->type_size : args[2].dat->elem_size) *
args[2].dat->size[0] * args[2].dat->size[1] * start[2] *
args[2].stencil->stride[2];
p_a[2] = (char *)args[2].data + base2;
int base3 = args[3].dat->base_offset +
(OPS_soa ? args[3].dat->type_size : args[3].dat->elem_size) *
start[0] * args[3].stencil->stride[0];
base3 = base3 +
(OPS_soa ? args[3].dat->type_size : args[3].dat->elem_size) *
args[3].dat->size[0] * start[1] * args[3].stencil->stride[1];
base3 = base3 +
(OPS_soa ? args[3].dat->type_size : args[3].dat->elem_size) *
args[3].dat->size[0] * args[3].dat->size[1] * start[2] *
args[3].stencil->stride[2];
p_a[3] = (char *)args[3].data + base3;
int base4 = args[4].dat->base_offset +
(OPS_soa ? args[4].dat->type_size : args[4].dat->elem_size) *
start[0] * args[4].stencil->stride[0];
base4 = base4 +
(OPS_soa ? args[4].dat->type_size : args[4].dat->elem_size) *
args[4].dat->size[0] * start[1] * args[4].stencil->stride[1];
base4 = base4 +
(OPS_soa ? args[4].dat->type_size : args[4].dat->elem_size) *
args[4].dat->size[0] * args[4].dat->size[1] * start[2] *
args[4].stencil->stride[2];
p_a[4] = (char *)args[4].data + base4;
int base5 = args[5].dat->base_offset +
(OPS_soa ? args[5].dat->type_size : args[5].dat->elem_size) *
start[0] * args[5].stencil->stride[0];
base5 = base5 +
(OPS_soa ? args[5].dat->type_size : args[5].dat->elem_size) *
args[5].dat->size[0] * start[1] * args[5].stencil->stride[1];
base5 = base5 +
(OPS_soa ? args[5].dat->type_size : args[5].dat->elem_size) *
args[5].dat->size[0] * args[5].dat->size[1] * start[2] *
args[5].stencil->stride[2];
p_a[5] = (char *)args[5].data + base5;
int base6 = args[6].dat->base_offset +
(OPS_soa ? args[6].dat->type_size : args[6].dat->elem_size) *
start[0] * args[6].stencil->stride[0];
base6 = base6 +
(OPS_soa ? args[6].dat->type_size : args[6].dat->elem_size) *
args[6].dat->size[0] * start[1] * args[6].stencil->stride[1];
base6 = base6 +
(OPS_soa ? args[6].dat->type_size : args[6].dat->elem_size) *
args[6].dat->size[0] * args[6].dat->size[1] * start[2] *
args[6].stencil->stride[2];
p_a[6] = (char *)args[6].data + base6;
int base7 = args[7].dat->base_offset +
(OPS_soa ? args[7].dat->type_size : args[7].dat->elem_size) *
start[0] * args[7].stencil->stride[0];
base7 = base7 +
(OPS_soa ? args[7].dat->type_size : args[7].dat->elem_size) *
args[7].dat->size[0] * start[1] * args[7].stencil->stride[1];
base7 = base7 +
(OPS_soa ? args[7].dat->type_size : args[7].dat->elem_size) *
args[7].dat->size[0] * args[7].dat->size[1] * start[2] *
args[7].stencil->stride[2];
p_a[7] = (char *)args[7].data + base7;
int base8 = args[8].dat->base_offset +
(OPS_soa ? args[8].dat->type_size : args[8].dat->elem_size) *
start[0] * args[8].stencil->stride[0];
base8 = base8 +
(OPS_soa ? args[8].dat->type_size : args[8].dat->elem_size) *
args[8].dat->size[0] * start[1] * args[8].stencil->stride[1];
base8 = base8 +
(OPS_soa ? args[8].dat->type_size : args[8].dat->elem_size) *
args[8].dat->size[0] * args[8].dat->size[1] * start[2] *
args[8].stencil->stride[2];
p_a[8] = (char *)args[8].data + base8;
int base9 = args[9].dat->base_offset +
(OPS_soa ? args[9].dat->type_size : args[9].dat->elem_size) *
start[0] * args[9].stencil->stride[0];
base9 = base9 +
(OPS_soa ? args[9].dat->type_size : args[9].dat->elem_size) *
args[9].dat->size[0] * start[1] * args[9].stencil->stride[1];
base9 = base9 +
(OPS_soa ? args[9].dat->type_size : args[9].dat->elem_size) *
args[9].dat->size[0] * args[9].dat->size[1] * start[2] *
args[9].stencil->stride[2];
p_a[9] = (char *)args[9].data + base9;
int base10 = args[10].dat->base_offset +
(OPS_soa ? args[10].dat->type_size : args[10].dat->elem_size) *
start[0] * args[10].stencil->stride[0];
base10 = base10 +
(OPS_soa ? args[10].dat->type_size : args[10].dat->elem_size) *
args[10].dat->size[0] * start[1] * args[10].stencil->stride[1];
base10 = base10 +
(OPS_soa ? args[10].dat->type_size : args[10].dat->elem_size) *
args[10].dat->size[0] * args[10].dat->size[1] * start[2] *
args[10].stencil->stride[2];
p_a[10] = (char *)args[10].data + base10;
// initialize global variable with the dimension of dats
xdim0 = args[0].dat->size[0];
ydim0 = args[0].dat->size[1];
xdim1 = args[1].dat->size[0];
ydim1 = args[1].dat->size[1];
xdim2 = args[2].dat->size[0];
ydim2 = args[2].dat->size[1];
xdim3 = args[3].dat->size[0];
ydim3 = args[3].dat->size[1];
xdim4 = args[4].dat->size[0];
ydim4 = args[4].dat->size[1];
xdim5 = args[5].dat->size[0];
ydim5 = args[5].dat->size[1];
xdim6 = args[6].dat->size[0];
ydim6 = args[6].dat->size[1];
xdim7 = args[7].dat->size[0];
ydim7 = args[7].dat->size[1];
xdim8 = args[8].dat->size[0];
ydim8 = args[8].dat->size[1];
xdim9 = args[9].dat->size[0];
ydim9 = args[9].dat->size[1];
xdim10 = args[10].dat->size[0];
ydim10 = args[10].dat->size[1];
// Halo Exchanges
ops_H_D_exchanges_host(args, 11);
ops_halo_exchanges(args, 11, range);
ops_H_D_exchanges_host(args, 11);
if (OPS_diags > 1) {
ops_timers_core(&c1, &t1);
OPS_kernels[111].mpi_time += t1 - t2;
}
int n_x;
for (int n_z = start[2]; n_z < end[2]; n_z++) {
for (int n_y = start[1]; n_y < end[1]; n_y++) {
#pragma novector
for (n_x = start[0];
n_x < start[0] + ((end[0] - start[0]) / SIMD_VEC) * SIMD_VEC;
n_x += SIMD_VEC) {
// call kernel function, passing in pointers to data -vectorised
#pragma simd
for (int i = 0; i < SIMD_VEC; i++) {
advec_cell_kernel4_xdir(
(double *)p_a[0] + i * 1 * 1, (double *)p_a[1] + i * 1 * 1,
(double *)p_a[2] + i * 1 * 1, (double *)p_a[3] + i * 1 * 1,
(double *)p_a[4] + i * 1 * 1, (double *)p_a[5] + i * 1 * 1,
(double *)p_a[6] + i * 1 * 1, (double *)p_a[7] + i * 1 * 1,
(double *)p_a[8] + i * 1 * 1, (double *)p_a[9] + i * 1 * 1,
(double *)p_a[10] + i * 1 * 1);
}
// shift pointers to data x direction
p_a[0] = p_a[0] + (dat0 * off0_0) * SIMD_VEC;
p_a[1] = p_a[1] + (dat1 * off1_0) * SIMD_VEC;
p_a[2] = p_a[2] + (dat2 * off2_0) * SIMD_VEC;
p_a[3] = p_a[3] + (dat3 * off3_0) * SIMD_VEC;
p_a[4] = p_a[4] + (dat4 * off4_0) * SIMD_VEC;
p_a[5] = p_a[5] + (dat5 * off5_0) * SIMD_VEC;
p_a[6] = p_a[6] + (dat6 * off6_0) * SIMD_VEC;
p_a[7] = p_a[7] + (dat7 * off7_0) * SIMD_VEC;
p_a[8] = p_a[8] + (dat8 * off8_0) * SIMD_VEC;
p_a[9] = p_a[9] + (dat9 * off9_0) * SIMD_VEC;
p_a[10] = p_a[10] + (dat10 * off10_0) * SIMD_VEC;
}
for (int n_x = start[0] + ((end[0] - start[0]) / SIMD_VEC) * SIMD_VEC;
n_x < end[0]; n_x++) {
// call kernel function, passing in pointers to data - remainder
advec_cell_kernel4_xdir(
(double *)p_a[0], (double *)p_a[1], (double *)p_a[2],
(double *)p_a[3], (double *)p_a[4], (double *)p_a[5],
(double *)p_a[6], (double *)p_a[7], (double *)p_a[8],
(double *)p_a[9], (double *)p_a[10]);
// shift pointers to data x direction
p_a[0] = p_a[0] + (dat0 * off0_0);
p_a[1] = p_a[1] + (dat1 * off1_0);
p_a[2] = p_a[2] + (dat2 * off2_0);
p_a[3] = p_a[3] + (dat3 * off3_0);
p_a[4] = p_a[4] + (dat4 * off4_0);
p_a[5] = p_a[5] + (dat5 * off5_0);
p_a[6] = p_a[6] + (dat6 * off6_0);
p_a[7] = p_a[7] + (dat7 * off7_0);
p_a[8] = p_a[8] + (dat8 * off8_0);
p_a[9] = p_a[9] + (dat9 * off9_0);
p_a[10] = p_a[10] + (dat10 * off10_0);
}
// shift pointers to data y direction
p_a[0] = p_a[0] + (dat0 * off0_1);
p_a[1] = p_a[1] + (dat1 * off1_1);
p_a[2] = p_a[2] + (dat2 * off2_1);
p_a[3] = p_a[3] + (dat3 * off3_1);
p_a[4] = p_a[4] + (dat4 * off4_1);
p_a[5] = p_a[5] + (dat5 * off5_1);
p_a[6] = p_a[6] + (dat6 * off6_1);
p_a[7] = p_a[7] + (dat7 * off7_1);
p_a[8] = p_a[8] + (dat8 * off8_1);
p_a[9] = p_a[9] + (dat9 * off9_1);
p_a[10] = p_a[10] + (dat10 * off10_1);
}
// shift pointers to data z direction
p_a[0] = p_a[0] + (dat0 * off0_2);
p_a[1] = p_a[1] + (dat1 * off1_2);
p_a[2] = p_a[2] + (dat2 * off2_2);
p_a[3] = p_a[3] + (dat3 * off3_2);
p_a[4] = p_a[4] + (dat4 * off4_2);
p_a[5] = p_a[5] + (dat5 * off5_2);
p_a[6] = p_a[6] + (dat6 * off6_2);
p_a[7] = p_a[7] + (dat7 * off7_2);
p_a[8] = p_a[8] + (dat8 * off8_2);
p_a[9] = p_a[9] + (dat9 * off9_2);
p_a[10] = p_a[10] + (dat10 * off10_2);
}
if (OPS_diags > 1) {
ops_timers_core(&c2, &t2);
OPS_kernels[111].time += t2 - t1;
}
ops_set_dirtybit_host(args, 11);
ops_set_halo_dirtybit3(&args[0], range);
ops_set_halo_dirtybit3(&args[1], range);
ops_set_halo_dirtybit3(&args[6], range);
ops_set_halo_dirtybit3(&args[7], range);
ops_set_halo_dirtybit3(&args[8], range);
ops_set_halo_dirtybit3(&args[9], range);
if (OPS_diags > 1) {
// Update kernel record
ops_timers_core(&c1, &t1);
OPS_kernels[111].mpi_time += t1 - t2;
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg0);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg1);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg2);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg3);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg4);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg5);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg6);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg7);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg8);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg9);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg10);
}
}
// host stub function
void ops_par_loop_advec_cell_kernel4_xdir(
char const *name, ops_block block, int dim, int *range, ops_arg arg0,
ops_arg arg1, ops_arg arg2, ops_arg arg3, ops_arg arg4, ops_arg arg5,
ops_arg arg6, ops_arg arg7, ops_arg arg8, ops_arg arg9, ops_arg arg10) {
// Timing
double t1, t2, c1, c2;
int offs[11][3];
ops_arg args[11] = {arg0, arg1, arg2, arg3, arg4, arg5,
arg6, arg7, arg8, arg9, arg10};
#ifdef CHECKPOINTING
if (!ops_checkpointing_before(args, 11, range, 111))
return;
#endif
if (OPS_diags > 1) {
ops_timing_realloc(111, "advec_cell_kernel4_xdir");
OPS_kernels[111].count++;
ops_timers_core(&c1, &t1);
}
#ifdef OPS_MPI
sub_block_list sb = OPS_sub_block_list[block->index];
#endif
// compute locally allocated range for the sub-block
int start[3];
int end[3];
int arg_idx[3];
#ifdef OPS_MPI
if (!sb->owned)
return;
for (int n = 0; n < 3; n++) {
start[n] = sb->decomp_disp[n];
end[n] = sb->decomp_disp[n] + sb->decomp_size[n];
if (start[n] >= range[2 * n]) {
start[n] = 0;
} else {
start[n] = range[2 * n] - start[n];
}
if (sb->id_m[n] == MPI_PROC_NULL && range[2 * n] < 0)
start[n] = range[2 * n];
if (end[n] >= range[2 * n + 1]) {
end[n] = range[2 * n + 1] - sb->decomp_disp[n];
} else {
end[n] = sb->decomp_size[n];
}
if (sb->id_p[n] == MPI_PROC_NULL &&
(range[2 * n + 1] > sb->decomp_disp[n] + sb->decomp_size[n]))
end[n] += (range[2 * n + 1] - sb->decomp_disp[n] - sb->decomp_size[n]);
if (end[n] < start[n])
end[n] = start[n];
}
#else
for (int n = 0; n < 3; n++) {
start[n] = range[2 * n];
end[n] = range[2 * n + 1];
}
#endif
#ifdef OPS_DEBUG
ops_register_args(args, "advec_cell_kernel4_xdir");
#endif
offs[0][0] = args[0].stencil->stride[0] * 1; // unit step in x dimension
offs[0][1] =
off3D(1, &start[0], &end[0], args[0].dat->size, args[0].stencil->stride) -
offs[0][0];
offs[0][2] =
off3D(2, &start[0], &end[0], args[0].dat->size, args[0].stencil->stride) -
offs[0][1] - offs[0][0];
offs[1][0] = args[1].stencil->stride[0] * 1; // unit step in x dimension
offs[1][1] =
off3D(1, &start[0], &end[0], args[1].dat->size, args[1].stencil->stride) -
offs[1][0];
offs[1][2] =
off3D(2, &start[0], &end[0], args[1].dat->size, args[1].stencil->stride) -
offs[1][1] - offs[1][0];
offs[2][0] = args[2].stencil->stride[0] * 1; // unit step in x dimension
offs[2][1] =
off3D(1, &start[0], &end[0], args[2].dat->size, args[2].stencil->stride) -
offs[2][0];
offs[2][2] =
off3D(2, &start[0], &end[0], args[2].dat->size, args[2].stencil->stride) -
offs[2][1] - offs[2][0];
offs[3][0] = args[3].stencil->stride[0] * 1; // unit step in x dimension
offs[3][1] =
off3D(1, &start[0], &end[0], args[3].dat->size, args[3].stencil->stride) -
offs[3][0];
offs[3][2] =
off3D(2, &start[0], &end[0], args[3].dat->size, args[3].stencil->stride) -
offs[3][1] - offs[3][0];
offs[4][0] = args[4].stencil->stride[0] * 1; // unit step in x dimension
offs[4][1] =
off3D(1, &start[0], &end[0], args[4].dat->size, args[4].stencil->stride) -
offs[4][0];
offs[4][2] =
off3D(2, &start[0], &end[0], args[4].dat->size, args[4].stencil->stride) -
offs[4][1] - offs[4][0];
offs[5][0] = args[5].stencil->stride[0] * 1; // unit step in x dimension
offs[5][1] =
off3D(1, &start[0], &end[0], args[5].dat->size, args[5].stencil->stride) -
offs[5][0];
offs[5][2] =
off3D(2, &start[0], &end[0], args[5].dat->size, args[5].stencil->stride) -
offs[5][1] - offs[5][0];
offs[6][0] = args[6].stencil->stride[0] * 1; // unit step in x dimension
offs[6][1] =
off3D(1, &start[0], &end[0], args[6].dat->size, args[6].stencil->stride) -
offs[6][0];
offs[6][2] =
off3D(2, &start[0], &end[0], args[6].dat->size, args[6].stencil->stride) -
offs[6][1] - offs[6][0];
offs[7][0] = args[7].stencil->stride[0] * 1; // unit step in x dimension
offs[7][1] =
off3D(1, &start[0], &end[0], args[7].dat->size, args[7].stencil->stride) -
offs[7][0];
offs[7][2] =
off3D(2, &start[0], &end[0], args[7].dat->size, args[7].stencil->stride) -
offs[7][1] - offs[7][0];
offs[8][0] = args[8].stencil->stride[0] * 1; // unit step in x dimension
offs[8][1] =
off3D(1, &start[0], &end[0], args[8].dat->size, args[8].stencil->stride) -
offs[8][0];
offs[8][2] =
off3D(2, &start[0], &end[0], args[8].dat->size, args[8].stencil->stride) -
offs[8][1] - offs[8][0];
offs[9][0] = args[9].stencil->stride[0] * 1; // unit step in x dimension
offs[9][1] =
off3D(1, &start[0], &end[0], args[9].dat->size, args[9].stencil->stride) -
offs[9][0];
offs[9][2] =
off3D(2, &start[0], &end[0], args[9].dat->size, args[9].stencil->stride) -
offs[9][1] - offs[9][0];
offs[10][0] = args[10].stencil->stride[0] * 1; // unit step in x dimension
offs[10][1] = off3D(1, &start[0], &end[0], args[10].dat->size,
args[10].stencil->stride) -
offs[10][0];
offs[10][2] = off3D(2, &start[0], &end[0], args[10].dat->size,
args[10].stencil->stride) -
offs[10][1] - offs[10][0];
int off0_0 = offs[0][0];
int off0_1 = offs[0][1];
int off0_2 = offs[0][2];
int dat0 = (OPS_soa ? args[0].dat->type_size : args[0].dat->elem_size);
int off1_0 = offs[1][0];
int off1_1 = offs[1][1];
int off1_2 = offs[1][2];
int dat1 = (OPS_soa ? args[1].dat->type_size : args[1].dat->elem_size);
int off2_0 = offs[2][0];
int off2_1 = offs[2][1];
int off2_2 = offs[2][2];
int dat2 = (OPS_soa ? args[2].dat->type_size : args[2].dat->elem_size);
int off3_0 = offs[3][0];
int off3_1 = offs[3][1];
int off3_2 = offs[3][2];
int dat3 = (OPS_soa ? args[3].dat->type_size : args[3].dat->elem_size);
int off4_0 = offs[4][0];
int off4_1 = offs[4][1];
int off4_2 = offs[4][2];
int dat4 = (OPS_soa ? args[4].dat->type_size : args[4].dat->elem_size);
int off5_0 = offs[5][0];
int off5_1 = offs[5][1];
int off5_2 = offs[5][2];
int dat5 = (OPS_soa ? args[5].dat->type_size : args[5].dat->elem_size);
int off6_0 = offs[6][0];
int off6_1 = offs[6][1];
int off6_2 = offs[6][2];
int dat6 = (OPS_soa ? args[6].dat->type_size : args[6].dat->elem_size);
int off7_0 = offs[7][0];
int off7_1 = offs[7][1];
int off7_2 = offs[7][2];
int dat7 = (OPS_soa ? args[7].dat->type_size : args[7].dat->elem_size);
int off8_0 = offs[8][0];
int off8_1 = offs[8][1];
int off8_2 = offs[8][2];
int dat8 = (OPS_soa ? args[8].dat->type_size : args[8].dat->elem_size);
int off9_0 = offs[9][0];
int off9_1 = offs[9][1];
int off9_2 = offs[9][2];
int dat9 = (OPS_soa ? args[9].dat->type_size : args[9].dat->elem_size);
int off10_0 = offs[10][0];
int off10_1 = offs[10][1];
int off10_2 = offs[10][2];
int dat10 = (OPS_soa ? args[10].dat->type_size : args[10].dat->elem_size);
// Halo Exchanges
ops_H_D_exchanges_host(args, 11);
ops_halo_exchanges(args, 11, range);
ops_H_D_exchanges_host(args, 11);
#ifdef _OPENMP
int nthreads = omp_get_max_threads();
#else
int nthreads = 1;
#endif
xdim0 = args[0].dat->size[0];
ydim0 = args[0].dat->size[1];
xdim1 = args[1].dat->size[0];
ydim1 = args[1].dat->size[1];
xdim2 = args[2].dat->size[0];
ydim2 = args[2].dat->size[1];
xdim3 = args[3].dat->size[0];
ydim3 = args[3].dat->size[1];
xdim4 = args[4].dat->size[0];
ydim4 = args[4].dat->size[1];
xdim5 = args[5].dat->size[0];
ydim5 = args[5].dat->size[1];
xdim6 = args[6].dat->size[0];
ydim6 = args[6].dat->size[1];
xdim7 = args[7].dat->size[0];
ydim7 = args[7].dat->size[1];
xdim8 = args[8].dat->size[0];
ydim8 = args[8].dat->size[1];
xdim9 = args[9].dat->size[0];
ydim9 = args[9].dat->size[1];
xdim10 = args[10].dat->size[0];
ydim10 = args[10].dat->size[1];
if (OPS_diags > 1) {
ops_timers_core(&c2, &t2);
OPS_kernels[111].mpi_time += t2 - t1;
}
#pragma omp parallel for
for (int thr = 0; thr < nthreads; thr++) {
int z_size = end[2] - start[2];
char *p_a[11];
int start_i = start[2] + ((z_size - 1) / nthreads + 1) * thr;
int finish_i =
start[2] + MIN(((z_size - 1) / nthreads + 1) * (thr + 1), z_size);
// get address per thread
int start0 = start[0];
int start1 = start[1];
int start2 = start_i;
// set up initial pointers
int d_m[OPS_MAX_DIM];
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[0].dat->d_m[d] + OPS_sub_dat_list[args[0].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[0].dat->d_m[d];
#endif
int base0 = dat0 * 1 * (start0 * args[0].stencil->stride[0] -
args[0].dat->base[0] - d_m[0]);
base0 = base0 +
dat0 * args[0].dat->size[0] * (start1 * args[0].stencil->stride[1] -
args[0].dat->base[1] - d_m[1]);
base0 = base0 +
dat0 * args[0].dat->size[0] * args[0].dat->size[1] *
(start2 * args[0].stencil->stride[2] - args[0].dat->base[2] -
d_m[2]);
p_a[0] = (char *)args[0].data + base0;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[1].dat->d_m[d] + OPS_sub_dat_list[args[1].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[1].dat->d_m[d];
#endif
int base1 = dat1 * 1 * (start0 * args[1].stencil->stride[0] -
args[1].dat->base[0] - d_m[0]);
base1 = base1 +
dat1 * args[1].dat->size[0] * (start1 * args[1].stencil->stride[1] -
args[1].dat->base[1] - d_m[1]);
base1 = base1 +
dat1 * args[1].dat->size[0] * args[1].dat->size[1] *
(start2 * args[1].stencil->stride[2] - args[1].dat->base[2] -
d_m[2]);
p_a[1] = (char *)args[1].data + base1;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[2].dat->d_m[d] + OPS_sub_dat_list[args[2].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[2].dat->d_m[d];
#endif
int base2 = dat2 * 1 * (start0 * args[2].stencil->stride[0] -
args[2].dat->base[0] - d_m[0]);
base2 = base2 +
dat2 * args[2].dat->size[0] * (start1 * args[2].stencil->stride[1] -
args[2].dat->base[1] - d_m[1]);
base2 = base2 +
dat2 * args[2].dat->size[0] * args[2].dat->size[1] *
(start2 * args[2].stencil->stride[2] - args[2].dat->base[2] -
d_m[2]);
p_a[2] = (char *)args[2].data + base2;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[3].dat->d_m[d] + OPS_sub_dat_list[args[3].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[3].dat->d_m[d];
#endif
int base3 = dat3 * 1 * (start0 * args[3].stencil->stride[0] -
args[3].dat->base[0] - d_m[0]);
base3 = base3 +
dat3 * args[3].dat->size[0] * (start1 * args[3].stencil->stride[1] -
args[3].dat->base[1] - d_m[1]);
base3 = base3 +
dat3 * args[3].dat->size[0] * args[3].dat->size[1] *
(start2 * args[3].stencil->stride[2] - args[3].dat->base[2] -
d_m[2]);
p_a[3] = (char *)args[3].data + base3;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[4].dat->d_m[d] + OPS_sub_dat_list[args[4].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[4].dat->d_m[d];
#endif
int base4 = dat4 * 1 * (start0 * args[4].stencil->stride[0] -
args[4].dat->base[0] - d_m[0]);
base4 = base4 +
dat4 * args[4].dat->size[0] * (start1 * args[4].stencil->stride[1] -
args[4].dat->base[1] - d_m[1]);
base4 = base4 +
dat4 * args[4].dat->size[0] * args[4].dat->size[1] *
(start2 * args[4].stencil->stride[2] - args[4].dat->base[2] -
d_m[2]);
p_a[4] = (char *)args[4].data + base4;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[5].dat->d_m[d] + OPS_sub_dat_list[args[5].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[5].dat->d_m[d];
#endif
int base5 = dat5 * 1 * (start0 * args[5].stencil->stride[0] -
args[5].dat->base[0] - d_m[0]);
base5 = base5 +
dat5 * args[5].dat->size[0] * (start1 * args[5].stencil->stride[1] -
args[5].dat->base[1] - d_m[1]);
base5 = base5 +
dat5 * args[5].dat->size[0] * args[5].dat->size[1] *
(start2 * args[5].stencil->stride[2] - args[5].dat->base[2] -
d_m[2]);
p_a[5] = (char *)args[5].data + base5;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[6].dat->d_m[d] + OPS_sub_dat_list[args[6].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[6].dat->d_m[d];
#endif
int base6 = dat6 * 1 * (start0 * args[6].stencil->stride[0] -
args[6].dat->base[0] - d_m[0]);
base6 = base6 +
dat6 * args[6].dat->size[0] * (start1 * args[6].stencil->stride[1] -
args[6].dat->base[1] - d_m[1]);
base6 = base6 +
dat6 * args[6].dat->size[0] * args[6].dat->size[1] *
(start2 * args[6].stencil->stride[2] - args[6].dat->base[2] -
d_m[2]);
p_a[6] = (char *)args[6].data + base6;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[7].dat->d_m[d] + OPS_sub_dat_list[args[7].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[7].dat->d_m[d];
#endif
int base7 = dat7 * 1 * (start0 * args[7].stencil->stride[0] -
args[7].dat->base[0] - d_m[0]);
base7 = base7 +
dat7 * args[7].dat->size[0] * (start1 * args[7].stencil->stride[1] -
args[7].dat->base[1] - d_m[1]);
base7 = base7 +
dat7 * args[7].dat->size[0] * args[7].dat->size[1] *
(start2 * args[7].stencil->stride[2] - args[7].dat->base[2] -
d_m[2]);
p_a[7] = (char *)args[7].data + base7;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[8].dat->d_m[d] + OPS_sub_dat_list[args[8].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[8].dat->d_m[d];
#endif
int base8 = dat8 * 1 * (start0 * args[8].stencil->stride[0] -
args[8].dat->base[0] - d_m[0]);
base8 = base8 +
dat8 * args[8].dat->size[0] * (start1 * args[8].stencil->stride[1] -
args[8].dat->base[1] - d_m[1]);
base8 = base8 +
dat8 * args[8].dat->size[0] * args[8].dat->size[1] *
(start2 * args[8].stencil->stride[2] - args[8].dat->base[2] -
d_m[2]);
p_a[8] = (char *)args[8].data + base8;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[9].dat->d_m[d] + OPS_sub_dat_list[args[9].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[9].dat->d_m[d];
#endif
int base9 = dat9 * 1 * (start0 * args[9].stencil->stride[0] -
args[9].dat->base[0] - d_m[0]);
base9 = base9 +
dat9 * args[9].dat->size[0] * (start1 * args[9].stencil->stride[1] -
args[9].dat->base[1] - d_m[1]);
base9 = base9 +
dat9 * args[9].dat->size[0] * args[9].dat->size[1] *
(start2 * args[9].stencil->stride[2] - args[9].dat->base[2] -
d_m[2]);
p_a[9] = (char *)args[9].data + base9;
#ifdef OPS_MPI
for (int d = 0; d < dim; d++)
d_m[d] =
args[10].dat->d_m[d] + OPS_sub_dat_list[args[10].dat->index]->d_im[d];
#else
for (int d = 0; d < dim; d++)
d_m[d] = args[10].dat->d_m[d];
#endif
int base10 = dat10 * 1 * (start0 * args[10].stencil->stride[0] -
args[10].dat->base[0] - d_m[0]);
base10 =
base10 +
dat10 * args[10].dat->size[0] * (start1 * args[10].stencil->stride[1] -
args[10].dat->base[1] - d_m[1]);
base10 = base10 +
dat10 * args[10].dat->size[0] * args[10].dat->size[1] *
(start2 * args[10].stencil->stride[2] - args[10].dat->base[2] -
d_m[2]);
p_a[10] = (char *)args[10].data + base10;
for (int n_z = start_i; n_z < finish_i; n_z++) {
for (int n_y = start[1]; n_y < end[1]; n_y++) {
for (int n_x = start[0];
n_x < start[0] + (end[0] - start[0]) / SIMD_VEC; n_x++) {
// call kernel function, passing in pointers to data -vectorised
#pragma simd
for (int i = 0; i < SIMD_VEC; i++) {
advec_cell_kernel4_xdir(
(double *)p_a[0] + i * 1 * 1, (double *)p_a[1] + i * 1 * 1,
(const double *)p_a[2] + i * 1 * 1,
(const double *)p_a[3] + i * 1 * 1,
(const double *)p_a[4] + i * 1 * 1,
(const double *)p_a[5] + i * 1 * 1,
(double *)p_a[6] + i * 1 * 1, (double *)p_a[7] + i * 1 * 1,
(double *)p_a[8] + i * 1 * 1, (double *)p_a[9] + i * 1 * 1,
(const double *)p_a[10] + i * 1 * 1);
}
// shift pointers to data x direction
p_a[0] = p_a[0] + (dat0 * off0_0) * SIMD_VEC;
p_a[1] = p_a[1] + (dat1 * off1_0) * SIMD_VEC;
p_a[2] = p_a[2] + (dat2 * off2_0) * SIMD_VEC;
p_a[3] = p_a[3] + (dat3 * off3_0) * SIMD_VEC;
p_a[4] = p_a[4] + (dat4 * off4_0) * SIMD_VEC;
p_a[5] = p_a[5] + (dat5 * off5_0) * SIMD_VEC;
p_a[6] = p_a[6] + (dat6 * off6_0) * SIMD_VEC;
p_a[7] = p_a[7] + (dat7 * off7_0) * SIMD_VEC;
p_a[8] = p_a[8] + (dat8 * off8_0) * SIMD_VEC;
p_a[9] = p_a[9] + (dat9 * off9_0) * SIMD_VEC;
p_a[10] = p_a[10] + (dat10 * off10_0) * SIMD_VEC;
}
for (int n_x = start[0] + ((end[0] - start[0]) / SIMD_VEC) * SIMD_VEC;
n_x < end[0]; n_x++) {
// call kernel function, passing in pointers to data - remainder
advec_cell_kernel4_xdir(
(double *)p_a[0], (double *)p_a[1], (const double *)p_a[2],
(const double *)p_a[3], (const double *)p_a[4],
(const double *)p_a[5], (double *)p_a[6], (double *)p_a[7],
(double *)p_a[8], (double *)p_a[9], (const double *)p_a[10]);
// shift pointers to data x direction
p_a[0] = p_a[0] + (dat0 * off0_0);
p_a[1] = p_a[1] + (dat1 * off1_0);
p_a[2] = p_a[2] + (dat2 * off2_0);
p_a[3] = p_a[3] + (dat3 * off3_0);
p_a[4] = p_a[4] + (dat4 * off4_0);
p_a[5] = p_a[5] + (dat5 * off5_0);
p_a[6] = p_a[6] + (dat6 * off6_0);
p_a[7] = p_a[7] + (dat7 * off7_0);
p_a[8] = p_a[8] + (dat8 * off8_0);
p_a[9] = p_a[9] + (dat9 * off9_0);
p_a[10] = p_a[10] + (dat10 * off10_0);
}
// shift pointers to data y direction
p_a[0] = p_a[0] + (dat0 * off0_1);
p_a[1] = p_a[1] + (dat1 * off1_1);
p_a[2] = p_a[2] + (dat2 * off2_1);
p_a[3] = p_a[3] + (dat3 * off3_1);
p_a[4] = p_a[4] + (dat4 * off4_1);
p_a[5] = p_a[5] + (dat5 * off5_1);
p_a[6] = p_a[6] + (dat6 * off6_1);
p_a[7] = p_a[7] + (dat7 * off7_1);
p_a[8] = p_a[8] + (dat8 * off8_1);
p_a[9] = p_a[9] + (dat9 * off9_1);
p_a[10] = p_a[10] + (dat10 * off10_1);
}
// shift pointers to data z direction
p_a[0] = p_a[0] + (dat0 * off0_2);
p_a[1] = p_a[1] + (dat1 * off1_2);
p_a[2] = p_a[2] + (dat2 * off2_2);
p_a[3] = p_a[3] + (dat3 * off3_2);
p_a[4] = p_a[4] + (dat4 * off4_2);
p_a[5] = p_a[5] + (dat5 * off5_2);
p_a[6] = p_a[6] + (dat6 * off6_2);
p_a[7] = p_a[7] + (dat7 * off7_2);
p_a[8] = p_a[8] + (dat8 * off8_2);
p_a[9] = p_a[9] + (dat9 * off9_2);
p_a[10] = p_a[10] + (dat10 * off10_2);
}
}
if (OPS_diags > 1) {
ops_timers_core(&c1, &t1);
OPS_kernels[111].time += t1 - t2;
}
ops_set_dirtybit_host(args, 11);
ops_set_halo_dirtybit3(&args[0], range);
ops_set_halo_dirtybit3(&args[1], range);
ops_set_halo_dirtybit3(&args[6], range);
ops_set_halo_dirtybit3(&args[7], range);
ops_set_halo_dirtybit3(&args[8], range);
ops_set_halo_dirtybit3(&args[9], range);
if (OPS_diags > 1) {
// Update kernel record
ops_timers_core(&c2, &t2);
OPS_kernels[111].mpi_time += t2 - t1;
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg0);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg1);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg2);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg3);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg4);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg5);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg6);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg7);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg8);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg9);
OPS_kernels[111].transfer += ops_compute_transfer(dim, start, end, &arg10);
}
}
