1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
! Test OpenACC 'kernels' construct decomposition.
! { dg-additional-options "-fopt-info-omp-all" }
! { dg-additional-options "-fopenacc-kernels=decompose" }
! { dg-additional-options "-O2" } for 'parloops'.
! See also '../../c-c++-common/goacc/kernels-decompose-2.c'.
! It's only with Tcl 8.5 (released in 2007) that "the variable 'varName'
! passed to 'incr' may be unset, and in that case, it will be set to [...]",
! so to maintain compatibility with earlier Tcl releases, we manually
! initialize counter variables:
! { dg-line l_dummy[variable c_loop_i 0 c_loop_j 0 c_loop_k 0 c_part 0] }
! { dg-message "dummy" "" { target iN-VAl-Id } l_dummy } to avoid
! "WARNING: dg-line var l_dummy defined, but not used".
program main
implicit none
integer, external :: f_g
!$acc routine (f_g) gang
integer, external :: f_w
!$acc routine (f_w) worker
integer, external :: f_v
!$acc routine (f_v) vector
integer, external :: f_s
!$acc routine (f_s) seq
integer :: i, j, k
integer :: x, y, z
logical :: y_l
integer, parameter :: N = 10
integer :: a(N), b(N), c(N)
!$acc kernels
x = 0 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
y = 0
y_l = x < 10
z = x
x = x + 1
;
!$acc end kernels
!$acc kernels ! { dg-optimized "assigned OpenACC gang loop parallelism" }
do i = 1, N ! { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" }
a(i) = 0
end do
!$acc end kernels
!$acc kernels loop ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'parloops' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
b(i) = a(N - i + 1)
end do
!$acc kernels
!$acc loop ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'parloops' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
b(i) = a(N - i + 1)
end do
!$acc loop ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'parloops' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
c(i) = a(i) * b(i)
end do
a(z) = 0 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
!$acc loop ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'parloops' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
c(i) = c(i) + a(i)
end do
!$acc loop seq ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1 + 1, N
c(i) = c(i) + c(i - 1)
end do
!$acc end kernels
!$acc kernels
!TODO What does this mean?
!TODO { dg-optimized "assigned OpenACC worker vector loop parallelism" "" { target *-*-* } .-2 }
!$acc loop independent ! { dg-line l_loop_i[incr c_loop_i] }
! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC gang loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
!$acc loop independent ! { dg-line l_loop_j[incr c_loop_j] }
! { dg-optimized "assigned OpenACC worker loop parallelism" "" { target *-*-* } l_loop_j$c_loop_j }
do j = 1, N
!$acc loop independent ! { dg-line l_loop_k[incr c_loop_k] }
! { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } l_loop_k$c_loop_k }
! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_k$c_loop_k }
do k = 1, N
a(1 + mod(i + j + k, N)) &
= b(j) &
+ f_v (c(k)) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
end do
end do
end do
!TODO Should the following turn into "gang-single" instead of "parloops"?
!TODO The problem is that the first STMT is 'if (y <= 4) goto <D.2547>; else goto <D.2548>;', thus "parloops".
if (y < 5) then ! { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" }
!$acc loop independent ! { dg-line l_loop_j[incr c_loop_j] }
! { dg-missed "unparallelized loop nest in OpenACC 'kernels' region: it's executed conditionally" "" { target *-*-* } l_loop_j$c_loop_j }
do j = 1, N
b(j) = f_w (c(j))
end do
end if
!$acc end kernels
!$acc kernels
y = f_g (a(5)) ! { dg-line l_part[incr c_part] }
!TODO If such a construct is placed in its own part (like it is, here), can't this actually use gang paralelism, instead of "gang-single"?
! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" "" { target *-*-* } l_part$c_part }
! { dg-optimized "assigned OpenACC gang worker vector loop parallelism" "" { target *-*-* } l_part$c_part }
!$acc loop independent ! { dg-line l_loop_j[incr c_loop_j] }
! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_j$c_loop_j }
! { dg-optimized "assigned OpenACC gang loop parallelism" "" { target *-*-* } l_loop_j$c_loop_j }
do j = 1, N
b(j) = y + f_w (c(j)) ! { dg-optimized "assigned OpenACC worker vector loop parallelism" }
end do
!$acc end kernels
!$acc kernels
y = 3 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
!$acc loop independent ! { dg-line l_loop_j[incr c_loop_j] }
! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_j$c_loop_j }
! { dg-optimized "assigned OpenACC gang worker loop parallelism" "" { target *-*-* } l_loop_j$c_loop_j }
do j = 1, N
b(j) = y + f_v (c(j)) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
end do
z = 2 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
!$acc end kernels
!$acc kernels ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
!$acc end kernels
end program main
|
