65 use math,
only:
rzero,
rone,
copy,
cmult,
cadd,
cfill,
invcol1,
vdot3,
add2, &
77 use,
intrinsic :: iso_c_binding, only: c_ptr
94 integer,
intent(in),
optional :: n
107 call rzero(a%x, size)
113 integer,
intent(in),
optional :: n
132 integer,
intent(in),
optional :: n
146 call copy(a%x, b%x, size)
152 integer,
intent(in),
optional :: n
154 real(kind=
rp),
intent(in) :: c
166 call cmult(a%x, c, size)
172 integer,
intent(in),
optional :: n
174 real(kind=
rp),
intent(in) :: s
186 call cadd(a%x, s, size)
192 integer,
intent(in),
optional :: n
194 real(kind=
rp),
intent(in) :: c
206 call cfill(a%x, c, size)
212 integer,
intent(in),
optional :: n
232 integer,
intent(in),
optional :: n
247 call invcol3(a%x, b%x, c%x, size)
255 integer,
intent(in),
optional :: n
256 type(
vector_t),
intent(in) :: u1, u2, u3
257 type(
vector_t),
intent(in) :: v1, v2, v3
269 u1%x_d, u2%x_d, u3%x_d, &
270 v1%x_d, v2%x_d, v3%x_d, &
283 integer,
intent(in),
optional :: n
297 call add2(a%x, b%x, size)
304 integer,
intent(in),
optional :: n
318 call add3(a%x, b%x, c%x, size)
325 integer,
intent(in),
optional :: n
327 type(
vector_t),
intent(in) :: b, c, d
339 call add4(a%x, b%x, c%x, d%x, size)
346 integer,
intent(in),
optional :: n
360 call sub2(a%x, b%x, size)
367 integer,
intent(in),
optional :: n
382 call sub3(a%x, b%x, c%x, size)
391 integer,
intent(in),
optional :: n
394 real(kind=
rp),
intent(in) :: c1
406 call add2s1(a%x, b%x, c1, size)
414 integer,
intent(in),
optional :: n
417 real(kind=
rp),
intent(in) :: c1
429 call add2s2(a%x, b%x, c1, size)
436 integer,
intent(in),
optional :: n
439 real(kind=
rp),
intent(in) :: c1
458 integer,
intent(in),
optional :: n
461 real(kind=
rp),
intent(in) :: c
473 call cmult2(a%x, b%x, c, size)
480 integer,
intent(in),
optional :: n
502 integer,
intent(in),
optional :: n
516 call col2(a%x, b%x, size)
523 integer,
intent(in),
optional :: n
538 call col3(a%x, b%x, c%x, size)
545 integer,
intent(in),
optional :: n
560 call subcol3(a%x, b%x, c%x, size)
567 integer,
intent(in),
optional :: n
571 real(kind=
rp),
intent(in) :: c1, c2
583 call add3s2(a%x, b%x, c%x, c1, c2, size)
590 integer,
intent(in),
optional :: n
605 call addcol3(a%x, b%x, c%x, size)
612 integer,
intent(in),
optional :: n
628 call addcol4(a%x, b%x, c%x, d%x, size)
634 integer,
intent(in),
optional :: n
648 sum =
glsum(a%x, size)
654 integer,
intent(in),
optional :: n
656 real(kind=
rp) :: norm
668 norm =
glsc2(a%x, b%x, size)
674 integer,
intent(in),
optional :: n
675 type(
vector_t),
intent(in) :: a, b, c
676 real(kind=
rp) :: norm
688 norm =
glsc3(a%x, b%x, c%x, size)
694 integer,
intent(in),
optional :: n
696 real(kind=
rp) :: norm
722 integer,
intent(in) :: n, n_mask
723 real(kind=
rp),
dimension(n_mask),
intent(inout) :: a
725 integer,
dimension(0:n_mask) ::
mask
726 type(c_ptr) :: mask_d, a_d
747 integer,
intent(in) :: n, n_mask
748 real(kind=
rp),
dimension(n_mask),
intent(in) :: b
750 integer,
dimension(0:n_mask) ::
mask
751 type(c_ptr) :: mask_d, b_d
Return the device pointer for an associated Fortran array.
subroutine, public device_add2s1(a_d, b_d, c1, n, strm)
subroutine, public device_sub3(a_d, b_d, c_d, n, strm)
Vector subtraction .
subroutine, public device_masked_scatter_copy_0(a_d, b_d, mask_d, n, n_mask, strm)
Scatter a masked vector .
subroutine, public device_add2s2(a_d, b_d, c1, n, strm)
Vector addition with scalar multiplication (multiplication on first argument)
subroutine, public device_add2(a_d, b_d, n, strm)
Vector addition .
subroutine, public device_addcol3(a_d, b_d, c_d, n, strm)
Returns .
real(kind=rp) function, public device_glsum(a_d, n, strm)
Sum a vector of length n.
subroutine, public device_invcol1(a_d, n, strm)
Invert a vector .
subroutine, public device_add3s2(a_d, b_d, c_d, c1, c2, n, strm)
Returns .
subroutine, public device_rzero(a_d, n, strm)
Zero a real vector.
subroutine, public device_rone(a_d, n, strm)
Set all elements to one.
subroutine, public device_cmult(a_d, c, n, strm)
Multiplication by constant c .
subroutine, public device_vdot3(dot_d, u1_d, u2_d, u3_d, v1_d, v2_d, v3_d, n, strm)
Compute a dot product (3-d version) assuming vector components etc.
real(kind=rp) function, public device_glsubnorm(a_d, b_d, n, strm)
Returns the norm of the difference of two vectors .
subroutine, public device_sub2(a_d, b_d, n, strm)
Vector substraction .
subroutine, public device_copy(a_d, b_d, n, strm)
Copy a vector .
subroutine, public device_invcol3(a_d, b_d, c_d, n, strm)
Vector division .
subroutine, public device_col2(a_d, b_d, n, strm)
Vector multiplication .
subroutine, public device_add4(a_d, b_d, c_d, d_d, n, strm)
subroutine, public device_subcol3(a_d, b_d, c_d, n, strm)
Returns .
subroutine, public device_masked_gather_copy_0(a_d, b_d, mask_d, n, n_mask, strm)
Gather a masked vector .
subroutine, public device_invcol2(a_d, b_d, n, strm)
Vector division .
subroutine, public device_addsqr2s2(a_d, b_d, c1, n, strm)
Returns .
real(kind=rp) function, public device_glsc3(a_d, b_d, c_d, n, strm)
Weighted inner product .
real(kind=rp) function, public device_glsc2(a_d, b_d, n, strm)
Weighted inner product .
subroutine, public device_cmult2(a_d, b_d, c, n, strm)
Multiplication by constant c .
subroutine, public device_col3(a_d, b_d, c_d, n, strm)
Vector multiplication with 3 vectors .
subroutine, public device_addcol4(a_d, b_d, c_d, d_d, n, strm)
Returns .
subroutine, public device_cfill(a_d, c, n, strm)
Set all elements to a constant c .
subroutine, public device_add3(a_d, b_d, c_d, n, strm)
Vector addition .
Device abstraction, common interface for various accelerators.
Object for handling masks in Neko.
subroutine, public cmult(a, c, n)
Multiplication by constant c .
subroutine, public cmult2(a, b, c, n)
Multiplication by constant c .
subroutine, public invcol2(a, b, n)
Vector division .
real(kind=rp) function, public glsc3(a, b, c, n)
Weighted inner product .
subroutine, public cadd(a, s, n)
Add a scalar to vector .
subroutine, public addsqr2s2(a, b, c1, n)
Returns .
subroutine, public add2s1(a, b, c1, n)
Vector addition with scalar multiplication (multiplication on first argument)
real(kind=rp) function, public glsc2(a, b, n)
Weighted inner product .
subroutine, public masked_scatter_copy_0(a, b, mask, n, n_mask)
Scatter a contigous vector to masked positions in a target array .
subroutine, public subcol3(a, b, c, n)
Returns .
subroutine, public rone(a, n)
Set all elements to one.
subroutine, public add3(a, b, c, n)
Vector addition .
real(kind=rp) function, public glsum(a, n)
Sum a vector of length n.
subroutine, public sub3(a, b, c, n)
Vector subtraction .
subroutine, public addcol4(a, b, c, d, n)
Returns .
subroutine, public add2(a, b, n)
Vector addition .
subroutine, public cfill(a, c, n)
Set all elements to a constant c .
subroutine, public invcol3(a, b, c, n)
Invert a vector .
subroutine, public add3s2(a, b, c, c1, c2, n)
Returns .
subroutine, public masked_gather_copy_0(a, b, mask, n, n_mask)
Gather a masked vector to reduced contigous vector .
subroutine, public addcol3(a, b, c, n)
Returns .
subroutine, public invcol1(a, n)
Invert a vector .
subroutine, public col2(a, b, n)
Vector multiplication .
subroutine, public copy(a, b, n)
Copy a vector .
subroutine, public add4(a, b, c, d, n)
Vector addition .
subroutine, public col3(a, b, c, n)
Vector multiplication with 3 vectors .
subroutine, public vdot3(dot, u1, u2, u3, v1, v2, v3, n)
Compute a dot product (3-d version) assuming vector components etc.
subroutine, public rzero(a, n)
Zero a real vector.
real(kind=rp) function, public glsubnorm(a, b, n)
Returns the norm of the difference of two vectors .
subroutine, public sub2(a, b, n)
Vector substraction .
subroutine, public add2s2(a, b, c1, n)
Vector addition with scalar multiplication (multiplication on second argument)
integer, parameter neko_bcknd_device
integer, parameter, public rp
Global precision used in computations.
subroutine, public vector_masked_gather_copy_0(a, b, mask, n, n_mask)
Gather a vector to reduced contigous array .
real(kind=rp) function, public vector_glsc3(a, b, c, n)
subroutine, public vector_add2(a, b, n)
Vector addition .
subroutine, public vector_vdot3(dot, u1, u2, u3, v1, v2, v3, n)
Compute a dot product (3-d version) assuming vector components etc.
subroutine, public vector_copy(a, b, n)
Copy a vector .
subroutine, public vector_sub3(a, b, c, n)
Vector subtraction .
subroutine, public vector_cmult(a, c, n)
Multiplication by constant c .
subroutine, public vector_invcol1(a, n)
Invert a vector .
subroutine, public vector_add3s2(a, b, c, c1, c2, n)
Returns .
subroutine, public vector_sub2(a, b, n)
Vector substraction .
subroutine, public vector_addsqr2s2(a, b, c1, n)
Returns .
subroutine, public vector_col2(a, b, n)
Vector multiplication .
subroutine, public vector_cfill(a, c, n)
Set all elements to a constant c .
real(kind=rp) function, public vector_glsum(a, n)
real(kind=rp) function, public vector_glsc2(a, b, n)
subroutine, public vector_addcol3(a, b, c, n)
Returns .
real(kind=rp) function, public vector_glsubnorm(a, b, n)
subroutine, public vector_invcol2(a, b, n)
Vector division .
subroutine, public vector_subcol3(a, b, c, n)
Returns .
subroutine, public vector_cadd(a, s, n)
Add a scalar to vector .
subroutine vector_add4(a, b, c, d, n)
Vector addition .
subroutine, public vector_add3(a, b, c, n)
Vector addition .
subroutine, public vector_add2s1(a, b, c1, n)
Vector addition with scalar multiplication (multiplication on first argument)
subroutine, public vector_add2s2(a, b, c1, n)
Vector addition with scalar multiplication (multiplication on second argument)
subroutine, public vector_addcol4(a, b, c, d, n)
Returns .
subroutine, public vector_cmult2(a, b, c, n)
Multiplication by constant c .
subroutine, public vector_rone(a, n)
Set all elements to one.
subroutine, public vector_rzero(a, n)
Zero a real vector.
subroutine, public vector_col3(a, b, c, n)
Vector multiplication with 3 vectors .
subroutine, public vector_masked_scatter_copy_0(a, b, mask, n, n_mask)
Gather a contigous array into a vector .
subroutine, public vector_invcol3(a, b, c, n)
Invert a vector .