/* { dg-bogus "warning: region is worker partitioned but does not contain worker partitioned code" "TODO default 'gang' 'vector'" { xfail *-*-* } .+3 }
TODO It's the compiler's own decision to not use 'worker' parallelism here, so it doesn't make sense to bother the user about it. */
int
-routine1 (int n) /* { dg-bogus "region is worker partitioned but does not contain worker partitioned code" "" { xfail *-*-* } } */
+routine1 (int n)
{
int i;
/* { dg-bogus "warning: region is worker partitioned but does not contain worker partitioned code" "TODO default 'gang' 'vector'" { xfail *-*-* } .+3 }
TODO It's the compiler's own decision to not use 'worker' parallelism here, so it doesn't make sense to bother the user about it. */
int
-routine2 (int n) /* { dg-bogus "region is worker partitioned but does not contain worker partitioned code" "" { xfail *-*-* } } */
+routine2 (int n)
{
int i;
;
#pragma acc cache(t[2:5]) /* { dg-error "is threadprivate variable" } */
;
- #pragma acc cache(k[0.5:]) /* { dg-error "low bound \[^\n\r]* of array section does not have integral type" } */
+ #pragma acc cache(k[0.5:]) /* { dg-error "low bound \[^\n\r]* of array section does not have integral type" } */
;
#pragma acc cache(l[:7.5f]) /* { dg-error "length \[^\n\r]* of array section does not have integral type" } */
;
OpenACC 'kernels' with Graphite kernles handling (default). */
/* { dg-additional-options "-O2" }
- { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
{ dg-additional-options "-fopt-info-optimized-omp" }
{ dg-additional-options "-fopt-info-note-omp" }
{ dg-additional-options "-fdump-tree-ompexp" }
void KERNELS ()
{
#pragma acc kernels copyin (a[0:N], b[0:N]) copyout (c[0:N])
- for (unsigned int i = 0; i < N; i++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
+ for (unsigned int i = 0; i < N; i++)
+ /* { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } .-1 } */
/* An "extern"al mapping of loop iterations/array indices makes the loop
unparallelizable. */
c[i] = a[f (i)] + b[f (i)]; /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
'kernels' (parloops version). */
/* { dg-additional-options "-O2" }
- { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
- { dg-additional-options "-fopt-info-note-optimized-omp" }
+ { dg-additional-options "-fopt-info-optimized-omp" }
+ { dg-additional-options "-fopt-info-note-omp" }
{ dg-additional-options "-fdump-tree-ompexp" }
- { dg-additional-options "-fdump-tree-parloops1-all" }
{ dg-additional-options "-fdump-tree-oaccloops1" } */
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
void KERNELS ()
{
-#pragma acc kernels copyin (a[0:N], b[0:N]) copyout (c[0:N]) /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- for (unsigned int i = 0; i < N; i++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels copyin (a[0:N], b[0:N]) copyout (c[0:N])
+ for (unsigned int i = 0; i < N; i++) /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" } */
+ /* { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } .-1 } */
c[i] = a[i] + b[i];
}
-/* Check the offloaded function's attributes.
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels, omp target entrypoint\\)\\)" 1 "ompexp" } } */
-
-/* Check that exactly one OpenACC kernels construct is analyzed, and that it
- can be parallelized.
- { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
- { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
-
/* Check the offloaded function's classification and compute dimensions (will
always be 1 x 1 x 1 for non-offloading compilation).
- { dg-final { scan-tree-dump-times "(?n)Function is parallelized OpenACC kernels offload" 1 "oaccloops1" } }
+ { dg-final { scan-tree-dump-times "(?n)Function is parallel_kernels_graphite OpenACC kernels offload" 1 "oaccloops1" } }
{ dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccloops1" } } */
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 1 "oaccloops1" } } */
/* { dg-additional-options "-O2 -w" }
{ dg-additional-options "-fopt-info-optimized-omp" }
{ dg-additional-options "-fdump-tree-ompexp" }
- { dg-additional-options "-fdump-tree-oaccloops" } */
+ { dg-additional-options "-fdump-tree-oaccloops1" } */
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
aspects of that functionality. */
void SERIAL ()
{
#pragma acc serial loop copyin (a[0:N], b[0:N]) copyout (c[0:N]) /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-bogus "warning: region contains gang partitioned code but is not gang partitioned" "TODO 'serial'" { xfail *-*-* } .-1 }
- { dg-bogus "warning: region contains worker partitioned code but is not worker partitioned" "" { target *-*-* } .-2 }
- { dg-bogus "warning: region contains vector partitioned code but is not vector partitioned" "TODO 'serial'" { xfail *-*-* } .-3 }
+ /* { dg-bogus "warning: region contains worker partitioned code but is not worker partitioned" "" { target *-*-* } .-2 }
TODO Should we really diagnose this if the user explicitly requested 'serial'?
TODO Should we instead diagnose ('-Wextra' category?) that the user may enable use of parallelism if replacing 'serial' with 'parallel', if applicable? */
for (unsigned int i = 0; i < N; i++)
/* Check the offloaded function's classification and compute dimensions (will
always be 1 x 1 x 1 for non-offloading compilation).
- { dg-final { scan-tree-dump-times "(?n)Function is OpenACC serial offload" 1 "oaccloops" } }
- { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
- { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc serial, omp target entrypoint\\)\\)" 1 "oaccloops" } } */
+ { dg-final { scan-tree-dump-times "(?n)Function is OpenACC serial offload" 1 "oaccloops1" } }
+ { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+ { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc serial, omp target entrypoint\\)\\)" 1 "oaccloops1" } } */
#pragma acc kernels if(c) copy(c)
/* { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_kernels map\(tofrom:c \[len: [0-9]+\]\) if\(_[0-9]+\)$} 1 "gimple" } } */
/* { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_data_kernels map\(tofrom:c \[len: [0-9]+\]\) if\(_[0-9]+\)$} 1 "omp_oacc_kernels_decompose" } }
- { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_gang_single async\(-1\) num_gangs\(1\) map\(force_present:c \[len: [0-9]+\]\) if\(_[0-9]+\)$} 1 "omp_oacc_kernels_decompose" } } */
+ { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_graphite async\(-1\) map\(force_present:c \[len: [0-9]+\]\) if\(_[0-9]+\)$} 1 "omp_oacc_kernels_decompose" } } */
++c;
#pragma acc data if(c) copy(c)
/* Test OpenACC 'kernels' construct decomposition. */
+/* { dg-additional-options "-fopt-info-optimized-omp" } */
+/* { dg-additional-options "-O2" } for "Graphite". */
/* { dg-additional-options "-fopt-info-omp-all" } */
/* { dg-additional-options "-fdump-tree-gimple" } */
/* { dg-additional-options "--param=openacc-kernels=decompose" }
- { dg-additional-options "-fdump-tree-omp_oacc_kernels_decompose" } */
+ { dg-additional-options "-fdump-tree-omp_oacc_kernels_decompose-details" } */
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
aspects of that functionality. */
int i;
unsigned int sum = 1;
-#pragma acc kernels copyin(a[0:N]) copy(sum)
- /* { dg-bogus "optimized: assigned OpenACC seq loop parallelism" "TODO" { xfail *-*-* } .-1 }
- TODO Is this maybe the report that belongs to the XFAILed report further down? */
+#pragma acc kernels copyin(a[0:N]) copy(sum) /* { dg-line l_kernels_pragma } */
+ /* { dg-missed {'map\(tofrom:sum \[len: [0-9]+\]\)' not optimized: 'sum' is unsuitable for privatization} "TODO Missing synthetic reduction clause" { target *-*-* } l_kernels_pragma } */
{
#pragma 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 } */
for (i = 0; i < N; ++i)
sum += a[i];
- sum++; /* { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" } */
+ sum++;
a[0]++;
#pragma 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$c_loop_i } */
- /* { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } l_loop_i$c_loop_i } */
+ /* { dg-optimized "assigned OpenACC gang vector loop parallelism" "" {target *-*-* } l_loop_i$c_loop_i } */
+ /* { dg-warning {loop has "independent" clause but data dependences were found.} "" { target *-*-* } l_loop_i$c_loop_i } */
for (i = 0; i < N; ++i)
sum += a[i];
- if (sum > 10) /* { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" } */
+ if (sum > 10)
{
#pragma acc loop /* { dg-line l_loop_i[incr c_loop_i] } */
/* { dg-missed "unparallelized loop nest in OpenACC 'kernels' region: it's executed conditionally" "" { target *-*-* } l_loop_i$c_loop_i } */
- /*TODO { dg-optimized "assigned OpenACC seq loop parallelism" "TODO" { xfail *-*-* } l_loop_i$c_loop_i } */
+ /* { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i } */
for (i = 0; i < N; ++i)
sum += a[i];
}
#pragma acc loop auto /* { 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 } */
for (i = 0; i < N; ++i)
sum += a[i];
sequence of compute constructs.
{ dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_data_kernels map\(tofrom:sum \[len: [0-9]+\]\) map\(to:a\[0\] \[len: [0-9]+\]\)$} 1 "omp_oacc_kernels_decompose" } }
As noted above, we get three "old-style" kernel regions, one gang-single region, and one parallelized loop region.
- { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_kernels async\(-1\) map\(force_present:sum \[len: [0-9]+\]\) map\(force_present:a\[0\] \[len: [0-9]+\]\) map\(firstprivate:a \[pointer assign, bias: 0\]\)$} 3 "omp_oacc_kernels_decompose" } }
- { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_parallelized async\(-1\) map\(force_present:sum \[len: [0-9]+\]\) map\(force_present:a\[0\] \[len: [0-9]+\]\) map\(firstprivate:a \[pointer assign, bias: 0\]\)$} 1 "omp_oacc_kernels_decompose" } }
- { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_gang_single async\(-1\) num_gangs\(1\) map\(force_present:sum \[len: [0-9]+\]\) map\(force_present:a\[0\] \[len: [0-9]+\]\) map\(firstprivate:a \[pointer assign, bias: 0\]\)$} 1 "omp_oacc_kernels_decompose" } }
+ { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_graphite async\(-1\) map\(force_present:sum \[len: [0-9]+\]\) map\(force_present:a\[0\] \[len: [0-9]+\]\) map\(firstprivate:a \[pointer assign, bias: 0\]\)$} 5 "omp_oacc_kernels_decompose" } }
'data' plus five CCs.
{ dg-final { scan-tree-dump-times {(?n)#pragma omp target } 6 "omp_oacc_kernels_decompose" } }
- { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\)$} 2 "omp_oacc_kernels_decompose" } }
+ { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\)$} 1 "omp_oacc_kernels_decompose" } }
{ dg-final { scan-tree-dump-times {(?n)#pragma acc loop independent private\(i\)$} 1 "omp_oacc_kernels_decompose" } }
- { dg-final { scan-tree-dump-times {(?n)#pragma acc loop auto private\(i\)$} 1 "omp_oacc_kernels_decompose" } }
+ { dg-final { scan-tree-dump-times {(?n)#pragma acc loop auto private\(i\)$} 2 "omp_oacc_kernels_decompose" } }
{ dg-final { scan-tree-dump-times {(?n)#pragma acc loop} 4 "omp_oacc_kernels_decompose" } }
Each of the parallel regions is async, and there is a final call to
__builtin_GOACC_wait.
{ dg-final { scan-tree-dump-times "__builtin_GOACC_wait" 1 "omp_oacc_kernels_decompose" } } */
+
/* { dg-additional-options "-fno-openacc-kernels-annotate-loops" } */
/* { dg-additional-options "-fopt-info-omp-all" } */
-/* { dg-additional-options "--param=openacc-kernels=decompose" }
+/* { dg-additional-options "--param=openacc-kernels=decompose-parloops" }
/* { dg-additional-options "-O2" } for 'parloops'. */
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
/* Test OpenACC 'kernels' construct decomposition. */
-/* { dg-additional-options "-fopt-info-omp-all" } */
+/* { dg-additional-options "-fopt-info-omp-optimized" } */
/* { dg-additional-options "-fchecking --param=openacc-kernels=decompose" } */
-/* { dg-ice "TODO" }
- { dg-prune-output "during GIMPLE pass: omplower" } */
+/* { dg-prune-output "during GIMPLE pass: omplower" } */
/* Reduced from 'kernels-decompose-2.c'.
(Hopefully) similar instances:
/* Test OpenACC 'kernels' construct decomposition. */
/* { dg-additional-options "-fchecking --param=openacc-kernels=decompose" } */
-/* { dg-ice "TODO" }
- { dg-prune-output "during GIMPLE pass: omplower" } */
+/* { dg-prune-output "during GIMPLE pass: omplower" } */
/* Reduced from 'kernels-decompose-ice-1.c'. */
-/* { dg-additional-options "--param=openacc-kernels=parloops" } as this is
+/* { dg-additional-options "--param openacc-kernels=decompose-parloops" } as this is
specifically testing "parloops" handling. */
/* { dg-additional-options "-O2" } */
/* { dg-additional-options "-fdump-tree-parloops1-all" } */
-/* { dg-additional-options "--param=openacc-kernels=parloops" } as this is
+/* { dg-additional-options "--param openacc-kernels=decompose-parloops" } as this is
specifically testing "parloops" handling. */
/* { dg-additional-options "-O2" } */
/* { dg-additional-options "-fno-openacc-kernels-annotate-loops" } */
for (j = 0; j < 10; j++)
{ }
}
-#pragma acc loop seq gang // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc loop seq gang // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc loop worker // { dg-error "inner loop uses same" }
for (j = 0; j < 10; j++)
{ }
-#pragma acc loop gang
+#pragma acc loop gang /* { dg-bogus "incorrectly nested OpenACC loop parallelism" "TODO-kernels" { xfail *-*-* } } */
for (j = 0; j < 10; j++)
{ }
}
-#pragma acc loop seq worker // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc loop seq worker // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc loop gang worker
#pragma acc loop vector // { dg-error "inner loop uses same" }
for (j = 1; j < 10; j++)
{ }
-#pragma acc loop worker
+#pragma acc loop worker /* { dg-bogus "incorrectly nested OpenACC loop parallelism" "TODO-kernels" { xfail *-*-* } } */
for (j = 1; j < 10; j++)
{ }
-#pragma acc loop gang
+#pragma acc loop gang /* { dg-bogus "incorrectly nested OpenACC loop parallelism" "TODO-kernels" { xfail *-*-* } } */
for (j = 1; j < 10; j++)
{ }
}
-#pragma acc loop seq vector // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc loop seq vector // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc loop gang vector
#pragma acc loop auto
for (i = 0; i < 10; i++)
{ }
-#pragma acc loop seq auto // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc loop seq auto // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc loop gang auto // { dg-error "'auto' conflicts" }
#pragma acc kernels loop worker(num:5)
for (i = 0; i < 10; i++)
{ }
-#pragma acc kernels loop seq worker // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc kernels loop seq worker // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc kernels loop gang worker
#pragma acc kernels loop vector(length:5)
for (i = 0; i < 10; i++)
{ }
-#pragma acc kernels loop seq vector // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc kernels loop seq vector // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc kernels loop gang vector
#pragma acc kernels loop auto
for (i = 0; i < 10; i++)
{ }
-#pragma acc kernels loop seq auto // { dg-error "'seq' overrides" "TODO" { xfail *-*-* } }
+#pragma acc kernels loop seq auto // { dg-error "'seq' overrides" }
for (i = 0; i < 10; i++)
{ }
#pragma acc kernels loop gang auto // { dg-error "'auto' conflicts" }
}
}
}
+
+/* The same tests as above, but inside a routine construct. */
+#pragma acc routine gang
+void acc_routine (void)
+{
+ int i, j, k, l, sum, diff;
+
+ {
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop collapse(2) // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ for (j = 0; j < 10; j++)
+ for (k = 0; k < 10; k++)
+ #pragma acc loop reduction(+:sum)
+ for (l = 0; l < 10; l++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ // { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ for (k = 0; k < 10; k++)
+ #pragma acc loop reduction(+:sum)
+ for (l = 0; l < 10; l++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(-:sum)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ // { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ for (k = 0; k < 10; k++)
+ #pragma acc loop reduction(*:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (l = 0; l < 10; l++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum) // { dg-warning "conflicting reduction operations for .sum." })
+ // { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ for (k = 0; k < 10; k++)
+ #pragma acc loop reduction(*:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (l = 0; l < 10; l++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum) reduction(-:diff)
+ for (i = 0; i < 10; i++)
+ {
+ #pragma acc loop reduction(-:diff) // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum) // { dg-warning "nested loop in reduction needs reduction clause for .diff." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(-:diff)
+ for (k = 0; k < 10; k++)
+ diff = 1;
+ }
+ }
+}
+
+void acc_kernels (void)
+{
+ int i, j, k, sum, diff;
+
+ /* FIXME: No diagnostics are produced for these loops because reductions
+ in kernels regions are not supported yet. */
+ #pragma acc kernels
+ {
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ for (j = 0; j < 10; j++)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop
+ for (j = 0; j < 10; j++)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:diff)
+ for (j = 0; j < 10; j++)
+ #pragma acc loop
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop // { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum)
+ for (k = 0; k < 10; k++)
+ sum = 1;
+
+ #pragma acc loop reduction(+:sum)
+ for (i = 0; i < 10; i++)
+ #pragma acc loop reduction(-:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (j = 0; j < 10; j++)
+ #pragma acc loop reduction(+:sum) // { dg-warning "conflicting reduction operations for .sum." }
+ for (k = 0; k < 10; k++)
+ sum = 1;
+ }
+}
+++ /dev/null
-/* Test the output of "-fopt-info-optimized-omp" for an OpenACC 'kernels'
- construct containing conditionally executed 'loop' constructs with
- 'independent' or 'seq' clauses. */
-
-/* { dg-additional-options "-fopt-info-all-omp" } */
-
-//TODO update accordingly
-/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
-
-extern int c;
-
-int
-main ()
-{
- int x, y, z;
-
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* Strangely indented to keep this similar to other test cases. */
- if (c) /* { dg-message "optimized: beginning .Graphite. region in OpenACC .kernels. construct" } */
- {
-#pragma acc loop seq
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent gang
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent worker
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent vector
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent gang vector
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent gang worker
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent worker vector
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent gang worker vector
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent gang
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent worker
- for (y = 0; y < 10; y++)
-#pragma acc loop independent vector
- for (z = 0; z < 10; z++)
- ;
-
-#pragma acc loop independent
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
- ;
-
-#pragma acc loop independent
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent
- for (y = 0; y < 10; y++)
- ;
-
-#pragma acc loop independent
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent
- for (y = 0; y < 10; y++)
-#pragma acc loop independent
- for (z = 0; z < 10; z++)
- ;
-
-#pragma acc loop seq
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent
- for (y = 0; y < 10; y++)
-#pragma acc loop independent
- for (z = 0; z < 10; z++)
- ;
-
-#pragma acc loop independent
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop seq
- for (y = 0; y < 10; y++)
-#pragma acc loop independent
- for (z = 0; z < 10; z++)
- ;
-
-#pragma acc loop independent
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent
- for (y = 0; y < 10; y++)
-#pragma acc loop seq
- for (z = 0; z < 10; z++)
- ;
-
-#pragma acc loop seq
- /* { dg-message "missed: unparallelized loop nest in OpenACC .kernels. region: it's executed conditionally" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent
- for (y = 0; y < 10; y++)
-#pragma acc loop seq
- for (z = 0; z < 10; z++)
- ;
- }
-
- return 0;
-}
construct containing 'loop' constructs with explicit or implicit 'auto'
clause. */
+/* { dg-additional-options "-fopt-info-optimized-omp" } */
/* { dg-additional-options "-fopt-info-note-omp" } */
//TODO update accordingly
#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
{
-#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang
+ /* { dg-message "optimized: assigned OpenACC gang loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto worker
+ /* { dg-message "optimized: assigned OpenACC worker loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto vector
+ /* { dg-message "optimized: assigned OpenACC vector loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto gang vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang vector
+ /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto gang worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang worker
+ /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto worker vector
+ /* { dg-message "optimized: assigned OpenACC worker vector loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto gang worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang worker vector
+ /* { dg-message "optimized: assigned OpenACC gang worker vector loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
;
-#pragma acc loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang
+ /* { dg-message "optimized: assigned OpenACC gang loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-3 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
+#pragma acc loop auto worker
+ /* { dg-message "optimized: assigned OpenACC worker loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-2 } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
+#pragma acc loop auto vector
+ /* { dg-message "optimized: assigned OpenACC vector loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-*} .-2 } */
for (z = 0; z < 10; z++)
;
#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop
+#pragma acc loop /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop
+#pragma acc loop /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "optimized: assigned OpenACC seq loop parallelism" "" { target *-*-*} .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop
+#pragma acc loop /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
}
clauses. */
/* { dg-additional-options "-fopt-info-all-omp" } */
+/* { dg-additional-options "-O2" } */
//TODO update accordingly
/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
+/* { dg-prune-output "^.*?loop in .kernels. region has not been analyzed.*?$" } */
+
int
main ()
{
/* Strangely indented to keep this similar to other test cases. */
{
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent vector /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent gang vector /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent gang worker /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent worker vector /* { dg-message "optimized: assigned OpenACC worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent gang worker vector /* { dg-message "optimized: assigned OpenACC gang worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
for (y = 0; y < 10; y++)
construct containing loops. */
/* { dg-additional-options "-fno-openacc-kernels-annotate-loops" } */
-/* { dg-additional-options "-fopt-info-optimized-omp-note" } */
+/* { dg-additional-options "-fopt-info-optimized-note-omp" } */
//TODO update accordingly
/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
/* Strangely indented to keep this similar to other test cases. */
{
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
;
for (x = 0; x < 10; x++)
/* { dg-optimized {'map\(force_tofrom:x \[len: [0-9]+\]\[implicit\]\)' optimized to 'map\(to:x \[len: [0-9]+\]\[implicit\]\)'} "" { target *-*-* } l_pragma_kernels } */
/* { dg-optimized {'map\(to:x \[len: [0-9]+\]\[implicit\]\)' further optimized to 'private\(x\)'} "" { target *-*-* } l_pragma_kernels } */
{
- x = 0; /* { dg-message "note: beginning .gang-single. part in OpenACC .kernels. region" } */
+ x = 0; /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
y = x < 10;
z = x++;
;
-/* Test the output of "-fopt-info-optimized-omp" for combined OpenACC 'kernels
+/* Test the output of "-fopt-info-note-omp" for combined OpenACC 'kernels
loop' constructs with explicit or implicit 'auto' clause. */
/* { dg-additional-options "-fopt-info-note-omp" } */
int x, y, z;
#pragma acc kernels loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto gang vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto gang worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto gang worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop auto
for (y = 0; y < 10; y++)
int x, y, z;
#pragma acc kernels loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent vector /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent gang vector /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent gang worker /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent worker vector /* { dg-message "optimized: assigned OpenACC worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent gang worker vector /* { dg-message "optimized: assigned OpenACC gang worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop independent /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
for (y = 0; y < 10; y++)
-/* Test the output of "-fopt-info-optimized-omp" for OpenACC 'kernels'
+/* Test the output of "-fopt-info-note-omp" for OpenACC 'kernels'
constructs containing conditionally executed 'loop' constructs with
'independent' or 'seq' clauses. */
-/* { dg-additional-options "-fopt-info-all-omp" } */
+/* { dg-additional-options "-fopt-info-note-omp" } */
+/* { dg-additional-options "-fopt-info-missed-omp" } */
+/* { dg-additional-options "--param openacc-kernels=decompose-parloops" } */
//TODO update accordingly
/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
{
int x, y, z;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
;
}
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
+#pragma acc kernels
/* Strangely indented to keep this similar to other test cases. */
if (c) /* { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" } */
{
int x, y, z;
#pragma acc kernels
-#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang /* { dg-optimized "assigned OpenACC gang loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto worker /* { dg-optimized "assigned OpenACC worker loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto vector /* { dg-optimized "assigned OpenACC vector loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto gang vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang vector /* { dg-optimized "assigned OpenACC gang vector loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto gang worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang worker /* { dg-optimized "assigned OpenACC gang worker loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto worker vector /* { dg-optimized "assigned OpenACC worker vector loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto gang worker vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang worker vector /* { dg-optimized "assigned OpenACC gang worker vector loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto gang /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto gang /* { dg-optimized "assigned OpenACC gang loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto worker /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
+#pragma acc loop auto worker /* { dg-optimized "assigned OpenACC worker loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto vector /* { dg-error ".auto. conflicts with other OpenACC loop specifiers" } */
+#pragma acc loop auto vector /* { dg-optimized "assigned OpenACC vector loop parallelism" } */
+ /* { dg-bogus ".auto. conflicts with other OpenACC loop specifiers" "" { xfail *-*-* } .-1 } */
for (z = 0; z < 10; z++)
;
#pragma acc kernels
-#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
-#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
;
#pragma acc kernels
-#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc kernels
-#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc kernels
-#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc kernels
-#pragma acc loop auto
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
#pragma acc kernels
-#pragma acc loop
- /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .parloops. for analysis" "" { target *-*-* } .-1 } */
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
+ /* { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
-#pragma acc loop auto
+#pragma acc loop auto /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
-#pragma acc loop
+#pragma acc loop /* { dg-optimized "assigned OpenACC seq loop parallelism" } */
for (z = 0; z < 10; z++)
;
constructs containing 'loop' constructs with 'independent' or 'seq'
clauses. */
-/* { dg-additional-options "-fopt-info-note-optimized-omp" } */
+/* { dg-additional-options "-fopt-info-optimized-omp" } */
//TODO update accordingly
/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
#pragma acc kernels
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent vector /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent gang vector /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent gang worker /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent worker vector /* { dg-message "optimized: assigned OpenACC worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent gang worker vector /* { dg-message "optimized: assigned OpenACC gang worker vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent gang /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent worker /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
#pragma acc kernels
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
;
#pragma acc kernels
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
#pragma acc kernels
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC worker loop parallelism" } */
for (y = 0; y < 10; y++)
#pragma acc kernels
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
for (y = 0; y < 10; y++)
#pragma acc kernels
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
for (y = 0; y < 10; y++)
#pragma acc kernels
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang worker loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
for (x = 0; x < 10; x++)
#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC vector loop parallelism" } */
for (y = 0; y < 10; y++)
for (z = 0; z < 10; z++)
;
-#pragma acc kernels
-#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- /* { dg-message "note: parallelized loop nest in OpenACC .kernels. region" "" { target *-*-* } .-1 } */
- for (x = 0; x < 10; x++)
-#pragma acc loop independent /* { dg-message "optimized: assigned OpenACC gang vector loop parallelism" } */
- for (y = 0; y < 10; y++)
-#pragma acc loop seq /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (z = 0; z < 10; z++)
- ;
-
return 0;
}
/* Test the output of "-fopt-info-optimized-omp" for an OpenACC 'kernels'
construct containing loops. */
-/* { dg-additional-options "-fno-openacc-kernels-annotate-loops" } */
-/* { dg-additional-options "-fopt-info-note-optimized-omp" } */
+/* { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
+ Normally, loop variables would get (implicit) 'private' clauses on the (implicit) 'loop' directives, but given '-fno-openacc-kernels-annotate-loops' they're (implicit) 'copy' -- which we then see get optimized. */
+/* { dg-additional-options "-fopt-info-optimized-note-omp" } */
//TODO update accordingly
/* See also "../../gfortran.dg/goacc/note-parallelism.f90". */
{
int x, y, z;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
for (y = 0; y < 10; y++)
for (z = 0; z < 10; z++)
;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
for (y = 0; y < 10; y++)
;
-#pragma acc kernels /* { dg-message "optimized: assigned OpenACC seq loop parallelism" } */
- for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. region in OpenACC .kernels. construct" } */
+#pragma acc kernels
+ for (x = 0; x < 10; x++) /* { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" } */
for (y = 0; y < 10; y++)
for (z = 0; z < 10; z++)
;
int main ()
{
-#pragma acc kernels num_gangs (32) num_workers (32) vector_length (32) /* { dg-warning "region contains gang partitioned code but is not gang partitioned" } */
+#pragma acc kernels num_gangs (32) num_workers (32) vector_length (32)
{
gang ();
worker ();
{ dg-warning "region is vector partitioned but does not contain vector partitioned code" "" { target *-*-* } .+1 } */
void g_1 (void)
{
- /* { dg-bogus "region is worker partitioned but does not contain worker partitioned code" "" { xfail *-*-* } .-2 } */
- /* { dg-bogus "region is vector partitioned but does not contain vector partitioned code" "" { xfail *-*-* } .-3 } */
}
#pragma acc routine (g_1) gang
#pragma acc routine (g_1) gang
/* Test the nohost clause for OpenACC routine directive. Exercising different
variants for declaring routines. */
-/* { dg-additional-options "-fdump-tree-oaccloops" } */
+/* { dg-additional-options "-fdump-tree-oaccloops3" } */
#pragma acc routine nohost
int THREE(void)
int i;
#pragma acc kernels
- /* { dg-warning "'i' is used uninitialized in this function" "" { target *-*-* } .-1 } */
- /*TODO With the 'copy' -> 'firstprivate' optimization, the original implicit 'copy(i)' clause gets optimized into a 'firstprivate(i)' clause -- and the expected (?) warning diagnostic appears.
- Have to read up the history behind these test cases.
- Should this test remain here in this file even if now testing 'firstprivate'?
- Or, should the optimization be disabled for such testing?
- Or, the testing be duplicated for both variants? */
{
i = 1;
}
-/* { dg-additional-options "-O2 -fdump-tree-oaccdevlow*" } */
+/* { dg-additional-options "-O2 -fdump-tree-oaccdevlow1" } */
extern int place ();
/* See gcc/testsuite/gfortran.dg/goacc/nested-function-1.f90 for the Fortran
version. */
+/* { dg-excess-errors ".*insufficient partitioning.*" } */
int main ()
{
#define N 100
#pragma acc loop seq tile(*)
for (local_j = 0; local_j < N; ++local_j)
;
-#pragma acc loop auto independent tile(1)
+#pragma acc loop auto tile(1)
for (local_j = 0; local_j < N; ++local_j)
;
}
! OpenACC kernels.
! { dg-additional-options "-O2" }
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
! { dg-additional-options "-fopt-info-note-optimized-omp" }
! { dg-additional-options "-fdump-tree-ompexp" }
-! { dg-additional-options "-fdump-tree-parloops1-all" }
-! { dg-additional-options "-fdump-tree-oaccloops" }
+! { dg-additional-options "-fdump-tree-graphite-all-details" }
+! { dg-additional-options "-fdump-tree-oaccloops1-details" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
integer, dimension (0:n-1) :: a, b, c
integer :: i
- ! An "external" mapping of loop iterations/array indices makes the loop
- ! unparallelizable.
+ ! A function call in a data-reference makes the loop unparallelizable
integer, external :: f
call setup(a, b)
- !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1)) ! { dg-message "optimized: assigned OpenACC seq loop parallelism" }
- do i = 0, n - 1 ! { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" }
+ !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1))
+ do i = 0, n - 1 ! { dg-message "note: beginning .Graphite. part in OpenACC .kernels. region" }
c(i) = a(f (i)) + b(f (i))
end do
!$acc end kernels
end program main
! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels, omp target entrypoint\\)\\)" 1 "ompexp" } }
-
-! Check that exactly one OpenACC kernels construct is analyzed, and that it
-! can't be parallelized.
-! { dg-final { scan-tree-dump-times "FAILED:" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-not "SUCCESS: may be parallelized" "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 1 "ompexp" } }
! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is unparallelized OpenACC kernels offload" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccloops" } }
+! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-not "^assigned OpenACC.*?loop parallelism$" "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 1 "oaccloops1" } }
! kernels.
! { dg-additional-options "-O2" }
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
-! { dg-additional-options "-fopt-info-note-optimized-omp" }
-! { dg-additional-options "-fdump-tree-ompexp" }
-! { dg-additional-options "-fdump-tree-parloops1-all" }
-! { dg-additional-options "-fdump-tree-oaccloops" }
+! { dg-additional-options "-fopt-info-optimized" }
+! { dg-additional-options "-fdump-tree-oaccloops1" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
call setup(a, b)
- !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1)) ! { dg-message "optimized: assigned OpenACC gang loop parallelism" }
- do i = 0, n - 1 ! { dg-message "note: beginning .parloops. part in OpenACC .kernels. region" }
+ !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1))
+ do i = 0, n - 1 ! { dg-optimized "assigned OpenACC gang vector loop parallelism" }
c(i) = a(i) + b(i)
end do
!$acc end kernels
end program main
-! Check the offloaded function's attributes.
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels, omp target entrypoint\\)\\)" 1 "ompexp" } }
-
-! Check that exactly one OpenACC kernels construct is analyzed, and that it
-! can be parallelized.
-! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
-
! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is parallelized OpenACC kernels offload" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccloops" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is parallel_kernels_graphite OpenACC kernels offload" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 1 "oaccloops1" } }
! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc parallel, omp target entrypoint\\)\\)" 1 "oaccloops" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC parallel offload" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc parallel, omp target entrypoint\\)\\)" 1 "oaccloops1" } }
! { dg-additional-options "-O2" }
! { dg-additional-options "-fopt-info-optimized-omp" }
! { dg-additional-options "-fdump-tree-ompexp" }
-! { dg-additional-options "-fdump-tree-oaccloops" }
+! { dg-additional-options "-fdump-tree-oaccloops1" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target \\(worker\\)\\)\\)" 1 "oaccloops" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC routine level 1" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0 1, 1 1, 1 1\\), omp declare target \\(worker\\)\\)\\)" 1 "oaccloops1" } }
! { dg-additional-options "-O2 -w" }
! { dg-additional-options "-fopt-info-optimized-omp" }
! { dg-additional-options "-fdump-tree-ompexp" }
-! { dg-additional-options "-fdump-tree-oaccloops" }
+! { dg-additional-options "-fdump-tree-oaccloops1" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
call setup(a, b)
!$acc serial loop copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1)) ! { dg-message "optimized: assigned OpenACC gang vector loop parallelism" }
- ! { dg-bogus "\[Ww\]arning: region contains gang partitioned code but is not gang partitioned" "TODO 'serial'" { xfail *-*-* } .-1 }
- ! { dg-bogus "\[Ww\]arning: region contains worker partitioned code but is not worker partitioned" "" { target *-*-* } .-2 }
- ! { dg-bogus "\[Ww\]arning: region contains vector partitioned code but is not vector partitioned" "TODO 'serial'" { xfail *-*-* } .-3 }
do i = 0, n - 1
c(i) = a(i) + b(i)
end do
! Check the offloaded function's classification and compute dimensions (will
! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC serial offload" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc serial, omp target entrypoint\\)\\)" 1 "oaccloops" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC serial offload" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc serial, omp target entrypoint\\)\\)" 1 "oaccloops1" } }
!$acc end kernels
end program main
-! { dg-final { scan-tree-dump-times "omp target oacc_parallel .*map\\(tofrom:a \\\[len: 400\\\]\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel .*map\\(tofrom:a \\\[len: 400\\\]\\\)" 1 "omplower" } }
! { dg-final { scan-tree-dump-times "omp target oacc_parallel .*map\\(tofrom:b \\\[len: 400\\\]\\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_parallel .*map\\(tofrom:c \\\[len: 4\\\]\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel .*map\\(tofrom:c \\\[len: 4\\\]\\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_data_kernels .*map\\(tofrom:x \\\[len: 400\\\]\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_data_kernels .*map\\(tofrom:x \\\[len: 400\\\]\\\)" 1 "omplower" } }
! { dg-final { scan-tree-dump-times "omp target oacc_data_kernels .*map\\(tofrom:y \\\[len: 400\\\]\\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_kernels .*map\\(force_present:x \\\[len: 400\\\]\\\[implicit\\\]\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_kernels .*map\\(force_present:y \\\[len: 400\\\]\\\[implicit\\\]\\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_kernels .*map\\(force_tofrom:i \\\[len: 4\\\]\\\[implicit\\\]\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "omp target oacc_kernels .*map\\(force_tofrom:c \\\[len: 4\\\]\\\[implicit\\\]\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel_kernels_graphite .*map\\(force_present:x \\\[len: 400\\\]\\\[implicit\\\]\\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel_kernels_graphite .*map\\(force_present:y \\\[len: 400\\\]\\\[implicit\\\]\\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel_kernels_graphite .*private\\(i\\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "omp target oacc_parallel_kernels_graphite .*map\\(force_tofrom:c \\\[len: 4\\\]\\\[implicit\\\]\\\)" 1 "omplower" } }
! Expecting no mapping of un-referenced common-blocks variables
call test (a, b, 0, n)
- !$acc parallel loop gang (static:1) num_gangs (10)
+ !$acc parallel loop gang (static:1) num_gangs (11)
do i = 1, n
a(i) = b(i) + 1
end do
call test (a, b, 1, n)
- !$acc parallel loop gang (static:2) num_gangs (10)
+ !$acc parallel loop gang (static:2) num_gangs (12)
do i = 1, n
a(i) = b(i) + 2
end do
call test (a, b, 2, n)
- !$acc parallel loop gang (static:5) num_gangs (10)
+ !$acc parallel loop gang (static:5) num_gangs (13)
do i = 1, n
a(i) = b(i) + 5
end do
call test (a, b, 5, n)
- !$acc parallel loop gang (static:20) num_gangs (10)
+ !$acc parallel loop gang (static:20) num_gangs (14)
do i = 1, n
a(i) = b(i) + 20
end do
end do
end subroutine test
-! { dg-final { scan-tree-dump-times "gang\\(static:\\\*\\)" 1 "omplower" } }
! { dg-final { scan-tree-dump-times "gang\\(static:1\\)" 1 "omplower" } }
! { dg-final { scan-tree-dump-times "gang\\(static:2\\)" 1 "omplower" } }
! { dg-final { scan-tree-dump-times "gang\\(static:5\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "gang\\(static:20\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "gang\\(num: 5 static:\\\*\\)" 1 "omplower" } }
-! { dg-final { scan-tree-dump-times "gang\\(num: 30 static:20\\)" 1 "omplower" } }
+! { dg-final { scan-tree-dump-times "gang\\(static:20\\)" 2 "omplower" } }
+! { dg-final { scan-tree-dump-times "gang\\(static:\\\*\\)" 2 "omplower" } }
! Test OpenACC 'kernels' construct decomposition.
-! { dg-additional-options "-fopt-info-omp-all" }
-! { dg-additional-options "-fdump-tree-gimple" }
-! { dg-additional-options "--param=openacc-kernels=decompose" }
-! { dg-additional-options "-fdump-tree-omp_oacc_kernels_decompose" }
-
+! { dg-additional-options "-fopt-info-optimized-note-omp" }
+! { dg-additional-options "-O2" } for "Graphite".
+! { dg-additional-options "-fdump-tree-omp_oacc_kernels_decompose-details -fdump-tree-gimple-details" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
-! See also '../../c-c++-common/goacc/kernels-decompose-1.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] }
-! { 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, parameter :: N = 1024
- integer, dimension (1:N) :: a
- integer :: i, sum
- !$acc kernels copyin(a(1:N)) copy(sum)
- ! { dg-bogus "optimized: assigned OpenACC seq loop parallelism" "TODO" { xfail *-*-* } .-1 }
- !TODO Is this maybe the report that belongs to the XFAILed report further down? */
+ integer, external :: f_g
+ !$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
+ !$acc routine (f_s) seq
+
+ integer :: i, j, k
+ integer :: x, y, z
+ logical :: y_l
+ integer, parameter :: N = 10
+ integer :: a(N), b(N), c(N)
+ integer :: sum
+
+ !$acc kernels
+ ! { dg-optimized {'map\(force_tofrom:x \[len: [0-9]+\]\[implicit\]\)' optimized to 'map\(to:x \[len: [0-9]+\]\[implicit\]\)'} "" { target *-*-* } .-1 }
+ ! { dg-optimized {'map\(to:x \[len: [0-9]+\]\[implicit\]\)' further optimized to 'private\(x\)'} "" { target *-*-* } .-2 }
+ ! { dg-optimized {'map\(force_tofrom:y_l \[len: [0-9]+\]\[implicit\]\)' optimized to 'map\(to:y_l \[len: [0-9]+\]\[implicit\]\)'} "" { target *-*-* } .-3 }
+ ! { dg-optimized {'map\(to:y_l \[len: [0-9]+\]\[implicit\]\)' further optimized to 'private\(y_l\)'} "" { target *-*-* } .-4 }
+ x = 0
+ y = 0
+ y_l = x < 10
+ z = x
+ x = x + 1
+ ;
+ !$acc end kernels
+
+ !$acc kernels
+ do i = 1, N ! { dg-optimized "assigned OpenACC gang vector loop parallelism" }
+ a(i) = 0
+ end do
+ !$acc end kernels
- !$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 }
+ !$acc kernels loop
+ ! { dg-bogus "assigned OpenACC seq loop parallelism" "TODO-kernels Graphite cannot represent access function" { xfail *-*-* } .-1 }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "TODO-kernels Graphite cannot represent access function " { xfail *-*-* } .-2 }
+ ! { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-3 }
do i = 1, N
- sum = sum + a(i)
+ b(i) = a(N - i + 1)
end do
- sum = sum + 1 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
- a(1) = a(1) + 1
+ !$acc kernels ! { dg-optimized {.map\(force_tofrom:sum \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:sum \[len: [0-9]+\]\[implicit\]\).} }
+ !$acc loop
+ ! { dg-bogus "assigned OpenACC seq loop parallelism" "TODO-kernels Graphite cannot represent access function" { xfail *-*-* } .-1 }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "TODO-kernels Graphite cannot represent access function " { xfail *-*-* } .-2 }
+ ! { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-3 }
+ do i = 1, N
+ b(i) = a(N - i + 1)
+ end do
- !$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$c_loop_i }
- ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ !$acc loop
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "TODO-kernels Graphite cannot represent access function " { target *-*-* } .-1 }
+ ! { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-2 }
do i = 1, N
- sum = sum + a(i)
+ c(i) = a(i) * b(i)
end do
- if (sum .gt. 10) then ! { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" }
- !$acc loop ! { dg-line l_loop_i[incr c_loop_i] }
- ! { dg-missed "unparallelized loop nest in OpenACC 'kernels' region: it's executed conditionally" "" { target *-*-* } l_loop_i$c_loop_i }
- !TODO { dg-optimized "assigned OpenACC seq loop parallelism" "TODO" { xfail *-*-* } l_loop_i$c_loop_i }
- do i = 1, N
- sum = sum + a(i)
- end do
- end if
+ a(z) = 0
- !$acc loop auto ! { dg-line l_loop_i[incr c_loop_i] }
- ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'parloops' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
- ! { dg-optimized "assigned OpenACC seq loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ !$acc loop
+ ! { dg-bogus "assigned OpenACC seq loop parallelism" "TODO-kernels missing synth reductions" { xfail *-*-* } .-1 }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "TODO-kernels missing synth reductions" { xfail *-*-* } .-2 }
+ ! { dg-message "note: forwarded loop nest in OpenACC .kernels. region to .Graphite. for analysis" "" { target *-*-* } .-3 }
do i = 1, N
sum = sum + a(i)
end do
+ !$acc loop seq ! { dg-optimized "assigned OpenACC seq loop parallelism" }
+ do i = 1 + 1, N
+ c(i) = c(i) + c(i - 1)
+ end do
!$acc end kernels
-end program main
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_kernels map\(to:a\[_[0-9]+\] \[len: _[0-9]+\]\) map\(alloc:a \[pointer assign, bias: _[0-9]+\]\) map\(tofrom:sum \[len: [0-9]+\]\)$} 1 "gimple" } }
+ !$acc kernels
+ !$acc loop independent ! { dg-optimized "assigned OpenACC gang loop parallelism" }
+ do i = 1, N
+ !$acc loop independent ! { dg-optimized "assigned OpenACC worker loop parallelism" }
+ do j = 1, N
+ !$acc loop independent ! { dg-optimized "assigned OpenACC seq loop parallelism" }
+ ! { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ ! { dg-bogus "optimized: assigned OpenACC vector loop parallelism" "" { target *-*-* } .-2 }
+ do k = 1, N
+ a(1 + mod(i + j + k, N)) &
+ = b(j) &
+ + f_v (c(k)) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
+ end do
+ end do
+ end do
+
+ if (y < 5) then
+ !$acc loop independent ! { dg-optimized "assigned OpenACC gang loop parallelism" }
+ do j = 1, N
+ b(j) = f_w (c(j)) ! { dg-optimized "assigned OpenACC worker vector loop parallelism" }
+ end do
+ end if
+ !$acc end kernels
+
+ !$acc kernels
+ y = f_g (a(5)) ! { dg-optimized "assigned OpenACC gang worker vector loop parallelism" }
+
+ !$acc loop independent ! { dg-optimized "assigned OpenACC gang loop parallelism" }
+ ! { dg-bogus "optimized: assigned OpenACC gang vector loop parallelism" "" { target *-*-* } .-1 }
+ do j = 1, N
+ b(j) = y + f_w (c(j)) ! { dg-optimized "assigned OpenACC worker vector loop parallelism" }
+ end do
+ !$acc end kernels
+
+ !$acc kernels
+ ! { dg-optimized {.map\(force_tofrom:z \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:z \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } .-1 }
+ ! { dg-optimized {.map\(to:z \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(z\).} "" { target *-*-* } .-2 }
+ ! { dg-optimized {.map\(force_tofrom:y \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:y \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } .-3 }
+ ! { dg-optimized {.map\(to:y \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(y\).} "" { target *-*-* } .-4 }
+ y = 3
+
+ !$acc loop independent ! { dg-optimized "assigned OpenACC gang worker loop parallelism" }
+ ! { dg-bogus "optimized: assigned OpenACC gang vector loop parallelism" "" { target *-*-* } .-1 }
+ do j = 1, N
+ b(j) = y + f_v (c(j)) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
+ end do
+
+ z = 2
+ !$acc end kernels
+
+ !$acc kernels
+ !$acc end kernels
+end program main
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\)$} 2 "gimple" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\)$} 4 "gimple" } }
! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\) independent$} 1 "gimple" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\) auto$} 1 "gimple" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop} 4 "gimple" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop auto private\(i\)$} 1 "gimple" } }
! Check that the OpenACC 'kernels' got decomposed into 'data' and an enclosed
! sequence of compute constructs.
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_data_kernels map\(to:a\[_[0-9]+\] \[len: _[0-9]+\]\) map\(tofrom:sum \[len: [0-9]+\]\)$} 1 "omp_oacc_kernels_decompose" } }
-! As noted above, we get three "old-style" kernel regions, one gang-single region, and one parallelized loop region.
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_kernels async\(-1\) map\(force_present:a\[_[0-9]+\] \[len: _[0-9]+\]\) map\(alloc:a \[pointer assign, bias: _[0-9]+\]\) map\(force_present:sum \[len: [0-9]+\]\)$} 3 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_parallelized async\(-1\) map\(force_present:a\[_[0-9]+\] \[len: _[0-9]+\]\) map\(alloc:a \[pointer assign, bias: _[0-9]+\]\) map\(force_present:sum \[len: [0-9]+\]\)$} 1 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_gang_single async\(-1\) num_gangs\(1\) map\(force_present:a\[_[0-9]+\] \[len: _[0-9]+\]\) map\(alloc:a \[pointer assign, bias: _[0-9]+\]\) map\(force_present:sum \[len: [0-9]+\]\)$} 1 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_data_kernels} 8 "omp_oacc_kernels_decompose" } }
!
! 'data' plus five CCs.
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target } 6 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_graphite async\(-1\)} 6 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\)$} 2 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop auto private\(i\)$} 5 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\) seq$} 1 "omp_oacc_kernels_decompose" } }
! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\) independent$} 1 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(i\) auto} 1 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop} 4 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(j\) independent$} 4 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop private\(k\) independent$} 1 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma acc loop} 12 "omp_oacc_kernels_decompose" } }
! Each of the parallel regions is async, and there is a final call to
! __builtin_GOACC_wait.
-! { dg-final { scan-tree-dump-times "__builtin_GOACC_wait" 1 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times "__builtin_GOACC_wait" 4 "omp_oacc_kernels_decompose" } }
! Test OpenACC 'kernels' construct decomposition.
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
+! { dg-additional-options "-fopenacc-kernels-annotate-loops" }
! { dg-additional-options "-fopt-info-omp-all" }
! { dg-additional-options "--param=openacc-kernels=decompose" }
-! { dg-additional-options "-O2" } for 'parloops'.
+! { dg-additional-options "-O2" } for 'Graphite'.
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
integer, parameter :: N = 10
integer :: a(N), b(N), c(N)
- !$acc kernels
- x = 0 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
+ !$acc kernels ! { dg-line l_kernels[incr region] }
+ ! { dg-missed {.map\(force_tofrom:y \[len: [0-9]+\]\[implicit\]\). not optimized: .y. used} "" { target *-*-* } l_kernels$region }
+ ! { dg-optimized {.map\(force_tofrom:y_l \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:y_l \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } l_kernels$region }
+ ! { dg-optimized {.map\(to:y_l \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(y_l\).} "" { target *-*-* } l_kernels$region }
+ ! { dg-optimized {.map\(force_tofrom:x \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:x \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } l_kernels$region }
+ ! { dg-optimized {.map\(to:x \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(x\).} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(force_tofrom:z \[len: [0-9]+\]\[implicit\]\). not optimized: .z. used} "" { target *-*-* } l_kernels$region }
+ x = 0
y = 0
y_l = x < 10
z = x
x = x + 1
+
;
!$acc end kernels
- !$acc kernels ! { dg-optimized "assigned OpenACC gang loop parallelism" }
- do i = 1, N ! { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" }
+ !$acc kernels ! { dg-line l_kernels[incr region] }
+ ! { dg-missed {'map\(tofrom:a \[len: [0-9]+\]\[implicit\]\)' not optimized: 'a' is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ do i = 1, N ! { dg-line l_loop_i[incr c_loop_i] }
+ ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'Graphite' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
a(i) = 0
end do
!$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 gang loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-missed {.map\(tofrom:b \[len: [0-9]+\]\[implicit\]\). not optimized: .b. is unsuitable for privatization} "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-missed {.map\(tofrom:a \[len: [0-9]+\]\[implicit\]\). not optimized: .a. is unsuitable for privatization} "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'Graphite' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-optimized "assigned OpenACC gang loop parallelism" "TODO Graphite cannot represent access function" { xfail *-*-* } l_loop_i$c_loop_i }
+ ! { dg-bogus "assigned OpenACC seq loop parallelism" "TODO Graphite cannot represent access function" { xfail *-*-* } l_loop_i$c_loop_i }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_i$c_loop_i }
do i = 1, N
b(i) = a(N - i + 1)
end do
- !$acc kernels
+ !$acc kernels ! { dg-line l_kernels[incr region] }
+ ! { dg-missed {.map\(force_tofrom:z \[len: [0-9]+\]\[implicit\]\). not optimized: .z. used} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {\.\.\. here} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:c \[len: [0-9]+\]\[implicit\]\). not optimized: .c. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:b \[len: [0-9]+\]\[implicit\]\). not optimized: .b. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:a \[len: [0-9]+\]\[implicit\]\). not optimized: .a. is unsuitable for privatization} "" { target *-*-* } l_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$c_loop_i }
- ! { dg-optimized "assigned OpenACC gang loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'Graphite' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-optimized "assigned OpenACC gang loop parallelism" "" { xfail *-*-* } l_loop_i$c_loop_i }
+ ! { dg-bogus "assigned OpenACC seq loop parallelism" "TODO Graphite cannot represent access function" { xfail *-*-* } l_loop_i$c_loop_i }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_i$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 gang loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'Graphite' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = 1, N
c(i) = a(i) * b(i)
end do
- a(z) = 0 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
+ a(z) = 0
!$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$c_loop_i }
- ! { dg-optimized "assigned OpenACC gang loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-message "note: forwarded loop nest in OpenACC 'kernels' region to 'Graphite' for analysis" "" { target *-*-* } l_loop_i$c_loop_i }
+ ! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$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
- !$acc kernels ! { dg-optimized "assigned OpenACC worker vector loop parallelism" }
+ !$acc kernels ! { dg-line l_kernels[incr region] }
+ ! { dg-missed {.map\(force_tofrom:y \[len: [0-9]+\]\[implicit\]\). not optimized: .y. used} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {\.\.\. here} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:c \[len: [0-9]+\]\[implicit\]\). not optimized: .c. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:b \[len: [0-9]+\]\[implicit\]\). not optimized: .b. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {.map\(tofrom:a \[len: [0-9]+\]\[implicit\]\). not optimized: .a. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+
!$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 }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_i$c_loop_i }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_i$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 }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$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$c_loop_k }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_k$c_loop_k }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_k$c_loop_k }
do k = 1, N
a(1 + mod(i + j + k, N)) &
= b(j) &
end do
end do
- !TODO Should the following turn into "gang-single" instead of "parloops"?
- !TODO The problem is that the first STMT is 'if (y <= 4) goto <D.2547>; else goto <D.2548>;', thus "parloops".
- if (y < 5) then ! { dg-message "note: beginning 'parloops' part in OpenACC 'kernels' region" }
+ if (y < 5) then ! { dg-message "note: beginning 'Graphite' part in OpenACC 'kernels' region" }
!$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$c_loop_j }
+ ! { dg-missed "unparallelized loop nest in OpenACC 'kernels' region: it's executed conditionally" "" { target *-*-* } l_loop_j$c_loop_j } ! TODO-kernels Clarify: should this be unparallelized or should the warning go away?
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
+ ! { dg-optimized "assigned OpenACC gang loop parallelism" "" { target *-*-* } l_loop_j$c_loop_j }
do j = 1, N
- b(j) = f_w (c(j))
+ b(j) = f_w (c(j)) ! { dg-optimized "assigned OpenACC worker vector loop parallelism" }
end do
end if
!$acc end kernels
- !$acc kernels
- ! { dg-bogus "\[Ww\]arning: region contains gang partitioned code but is not gang partitioned" "TODO 'kernels'" { xfail *-*-* } .-1 }
+ !$acc kernels ! { dg-line l_kernels[incr region] }
+ ! { dg-missed {'map\(force_tofrom:y \[len: [0-9]+\]\[implicit\]\)' not optimized: 'y' used} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {'map\(tofrom:c \[len: [0-9]+\]\[implicit\]\)' not optimized: 'c' is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {'map\(tofrom:b \[len: [0-9]+\]\[implicit\]\)' not optimized: 'b' is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+ ! { dg-missed {'map\(tofrom:a \[len: [0-9]+\]\[implicit\]\)' not optimized: 'a' is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
y = f_g (a(5)) ! { dg-line l_part[incr c_part] }
- !TODO If such a construct is placed in its own part (like it is, here), can't this actually use gang paralelism, instead of "gang-single"?
- ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" "" { target *-*-* } l_part$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 }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$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 kernels ! { dg-line l_kernels[incr region] }
+! { dg-optimized {.map\(force_tofrom:z \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:z \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } l_kernels$region }
+! { dg-optimized {.map\(to:z \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(z\).} "" { target *-*-* } l_kernels$region }
+! { dg-optimized {.map\(force_tofrom:y \[len: [0-9]+\]\[implicit\]\). optimized to .map\(to:y \[len: [0-9]+\]\[implicit\]\).} "" { target *-*-* } l_kernels$region }
+! { dg-optimized {.map\(to:y \[len: [0-9]+\]\[implicit\]\). further optimized to .private\(y\).} "" { target *-*-* } l_kernels$region }
+! { dg-missed {\.\.\. here} "" { target *-*-* } l_kernels$region }
+! { dg-missed {.map\(tofrom:c \[len: [0-9]+\]\[implicit\]\). not optimized: .c. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+! { dg-missed {.map\(tofrom:b \[len: [0-9]+\]\[implicit\]\). not optimized: .b. is unsuitable for privatization} "" { target *-*-* } l_kernels$region }
+! { dg-missed {\.\.\. here} "" { target *-*-* } l_kernels[expr {$region - 1}] }
+
+ y = 3
!$acc loop independent ! { dg-line l_loop_j[incr c_loop_j] }
- ! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_j$c_loop_j }
! { dg-optimized "assigned OpenACC gang worker loop parallelism" "" { target *-*-* } l_loop_j$c_loop_j }
+ ! { dg-bogus "missed: .auto. loop has not been analyzed .cf. .graphite. dumps for more information." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
+ ! { dg-bogus "missed: .independent. loop in .kernels. region has not been analyzed .cf. .graphite. dumps for more information.." "TODO Inexact representation of access function in Graphite" { xfail *-*-* } l_loop_j$c_loop_j }
do j = 1, N
b(j) = y + f_v (c(j)) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
end do
- z = 2 ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
+ z = 2
!$acc end kernels
- !$acc kernels ! { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" }
+ !$acc kernels
!$acc end kernels
end program main
-! { dg-additional-options "--param=openacc-kernels=parloops" } as this is
-! specifically testing "parloops" handling.
+! { dg-additional-options "--param openacc-kernels=decompose" } as this is
+! specifically testing "Graphite" handling.
! { dg-additional-options "-O2" }
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
-! { dg-additional-options "-fdump-tree-parloops1-all" }
+! { dg-additional-options "-fdump-tree-graphite-details" }
! { dg-additional-options "-fdump-tree-optimized" }
program main
end program main
! Check that only three loops are analyzed, and that all can be parallelized.
-! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
-! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
+! { dg-final { scan-tree-dump-times "loop has no data-dependences" 6 "graphite" } } ! Two CFG loops per OpenACC loop
+! { dg-final { scan-tree-dump-not "loop has data-dependences" "graphite" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(, , \\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 3 "graphite" } }
! Check that the loop has been split off into a function.
! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
-! { dg-additional-options "--param=openacc-kernels=parloops" } as this is
-! specifically testing "parloops" handling.
+! { dg-additional-options "--param=openacc-kernels=decompose" } as this is
+! specifically testing "Graphite" handling.
! { dg-additional-options "-O2" }
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
-! { dg-additional-options "-fdump-tree-parloops1-all" }
+! { dg-additional-options "-fdump-tree-graphite-details" }
! { dg-additional-options "-fdump-tree-optimized" }
program main
end program main
! Check that only three loops are analyzed, and that all can be parallelized.
-! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
-! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
+
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(, , \\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 3 "graphite" } }
+! { dg-final { scan-tree-dump-times "loop has no data-dependences" 6 "graphite" } } ! Two CFG loops per OpenACC loop
! Check that the loop has been split off into a function.
! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
-! { dg-additional-options "--param=openacc-kernels=parloops" } as this is
+! { dg-additional-options "--param openacc-kernels=decompose-parloops" } as this is
! specifically testing "parloops" handling.
! { dg-additional-options "-O2" }
! { dg-additional-options "-fopt-info-optimized-omp" }
integer :: a(100,100), b(100,100)
integer :: i, j, d
- !$acc kernels ! { dg-message "optimized: assigned OpenACC gang loop parallelism" }
- do i=1,100
+ !$acc kernels
+ do i=1,10 ! { dg-message "optimized: assigned OpenACC seq loop parallelism" }0
do j=1,100
a(i,j) = 1
b(i,j) = 2
-! { dg-additional-options "--param=openacc-kernels=parloops" } as this is
-! specifically testing "parloops" handling.
+! { dg-additional-options "--param openacc-kernels=decompose" } as this is
+! specifically testing "Graphite" handling.
! { dg-additional-options "-O2" }
-! { dg-additional-options "-fno-openacc-kernels-annotate-loops" }
-! { dg-additional-options "-fdump-tree-parloops1-all" }
+! { dg-additional-options "-fdump-tree-graphite-details" }
! { dg-additional-options "-fdump-tree-optimized" }
program main
end program main
! Check that only one loop is analyzed, and that it can be parallelized.
-! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(, , \\), oacc parallel_kernels_graphite, omp target entrypoint\\)\\)" 1 "graphite" } }
+! { dg-final { scan-tree-dump-times "loop has no data-dependences" 2 "graphite" } } ! Two CFG loops per OpenACC loop
! Check that the loop has been split off into a function.
! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
! { dg-final { scan-tree-dump-times "map\\(force_deviceptr:u\\)" 1 "original" } }
! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_data_kernels if\((?:D\.|_)[0-9]+\)$} 1 "omp_oacc_kernels_decompose" } }
-! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_gang_single num_gangs\(1\) if\((?:D\.|_)[0-9]+\) async\(-1\)$} 1 "omp_oacc_kernels_decompose" } }
+! { dg-final { scan-tree-dump-times {(?n)#pragma omp target oacc_parallel_kernels_graphite if\((?:D\.|_)[0-9]+\) async\(-1\)$} 1 "omp_oacc_kernels_decompose" } }
DO j = 1,10
ENDDO
ENDDO
- !$acc loop seq gang ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc loop seq gang ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc loop worker ! { dg-error "inner loop uses same OpenACC parallelism as containing loop" }
DO j = 1,10
ENDDO
- !$acc loop gang ! { dg-error "" "TODO" { xfail *-*-* } }
+ !$acc loop gang ! { dg-error "" }
DO j = 1,10
ENDDO
ENDDO
- !$acc loop seq worker ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc loop seq worker ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc loop gang worker
!$acc loop vector ! { dg-error "inner loop uses same OpenACC parallelism as containing loop" }
DO j = 1,10
ENDDO
- !$acc loop worker ! { dg-error "" "TODO" { xfail *-*-* } }
+ !$acc loop worker ! { dg-error "" }
DO j = 1,10
ENDDO
- !$acc loop gang ! { dg-error "" "TODO" { xfail *-*-* } }
+ !$acc loop gang ! { dg-error "" }
DO j = 1,10
ENDDO
ENDDO
- !$acc loop seq vector ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc loop seq vector ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc loop gang vector
!$acc loop auto
DO i = 1,10
ENDDO
- !$acc loop seq auto ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc loop seq auto ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc loop gang auto ! { dg-error "'auto' conflicts with other OpenACC loop specifiers" }
!$acc kernels loop gang(static:*)
DO i = 1,10
ENDDO
- !$acc kernels loop seq gang ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc kernels loop seq gang ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc kernels loop worker(num:5)
DO i = 1,10
ENDDO
- !$acc kernels loop seq worker ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc kernels loop seq worker ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc kernels loop gang worker
!$acc kernels loop vector(length:5)
DO i = 1,10
ENDDO
- !$acc kernels loop seq vector ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc kernels loop seq vector ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc kernels loop gang vector
!$acc kernels loop auto
DO i = 1,10
ENDDO
- !$acc kernels loop seq auto ! { dg-error "'seq' overrides other OpenACC loop specifiers" "TODO" { xfail *-*-* } }
+ !$acc kernels loop seq auto ! { dg-error "'seq' overrides other OpenACC loop specifiers" }
DO i = 1,10
ENDDO
!$acc kernels loop gang auto ! { dg-error "'auto' conflicts with other OpenACC loop specifiers" }
!$acc parallel loop auto copy(array1, array2) ! { dg-message "assigned OpenACC gang vector loop parallelism" }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-1 }
- ! { dg-message ".auto. loop can be parallel" "" {target *-*-*} .-2 }
do i=1, n
array2(i) = array1(i) ! { dg-message "loop has no data-dependences" }
end do
!$acc parallel loop auto copy(array1, array2) ! { dg-message "assigned OpenACC seq loop parallelism" }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-1 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-2 }
do i=1, n-1
array1(i+1) = array1(i) + 10 ! { dg-message "loop has data-dependences" }
array2(i) = array1(i)
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, m
array (1, i, j) = array(2, i, j) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n) = array(1, i, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, m
array (1, i, j) = array (2, i,j) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do i=1, n-1
array (1, i+1, 1) = array (2, i, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC gang vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, m
array (1, i, j) = array (2, i, j) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n) = array (1, i, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do j=1, m-1
array (1, i, j+1) = array (1, i, j) ! { dg-message "loop has data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
!$acc loop auto
! { dg-message "assigned OpenACC worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do k=1, n
array (1, i, j, k) = array(2, i, j, k) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (1, i, j, k+1) = array(1, i, j, k) ! { dg-message "loop has data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n, n) = array (1, i, n, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n-1
array (2, i, j, n) = array (1, i, j, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (2, i, j, k) = array(1, i, j, k) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n, n) = array (1, i, n, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n-1
array (2, i, j, n) = array (1, i, j, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (1, i, j, k+1) = array(1, i, j, k) ! { dg-message "loop has data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n, n) = array (1, i, n, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do j=1, n-1
array (1, i, j+1, n) = array (1, i, j, n) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (2, i, j, k) = array(1, i, j, k) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC gang vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do i=1, n
array (2, i, n, n) = array (1, i, n, n) ! { dg-message "loop has no data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do j=1, n-1
array (1, i, j+1, n) = array (1, i, j, n) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (1, i, j, k+1) = array(1, i, j, k) ! { dg-message "loop has data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do i=1, n - 1
array (1, i+1, 1, 1) = array (1, i, 1, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC gang worker loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n
!$acc loop auto
! { dg-message "assigned OpenACC vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do k=1, n
array (1, i, j, k) = array(2, i, j, k) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do i=1, n - 1
array (1, i+1, 1, 1) = array (1, i, 1, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC gang vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do j=1, n
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do k=1, n - 1
array (1, i, j, k+1) = array(1, i, j, k) ! { dg-message "loop has data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do i=1, n - 1
array (1, i+1, 1, 1) = array (1, i, 1, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do j=1, n - 1
array (1, i, j+1, 1) = array (1, i, j, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC gang vector loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop can be parallel" "" {target *-*-*} .-3 }
do k=1, n
array (1, i, j, k) = array(2, i, j, k) ! { dg-message "loop has no data-dependences" }
end do
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do i=1, n-1
array (1, i+1, 1, 1) = array (1, i, 1, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do j=1, n-1
array (1, i, j+1, 1) = array (1, i, j, 1) ! { dg-message "loop has data-dependences" }
!$acc loop auto
! { dg-message "assigned OpenACC seq loop parallelism" "" {target *-*-*} .-1 }
! { dg-message "loop has no data-dependences" "OpenACC internal chunking CFG loop can be parallel" {target *-*-*} .-2 }
- ! { dg-message "'auto' loop cannot be parallel" "" {target *-*-*} .-3 }
do k=1, n-1
array (1, i, j, k+1) = array(1, i, j, k) ! { dg-message "loop has data-dependences" }
end do
!$acc exit data copyout(nonlocal_a) delete(nonlocal_i) finalize
end subroutine nonlocal
end program main
+
+! { dg-prune-output ".*insufficient partitioning.*" }
end do
end do
end subroutine acc_parallel_loop_reduction
+
+! The same tests as above, but inside a routine construct.
+subroutine acc_routine ()
+ implicit none (type, external)
+ !$acc routine gang
+ integer :: i, j, k, l, sum, diff
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum)
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop collapse(2) ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ do j = 1, 10
+ do k = 1, 10
+ !$acc loop reduction(+:sum)
+ do l = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ do j = 1, 10
+ !$acc loop ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ ! { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ do k = 1, 10
+ !$acc loop reduction(+:sum)
+ do l = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(-:sum)
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do j = 1, 10
+ !$acc loop ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ ! { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ do k = 1, 10
+ !$acc loop reduction(*:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do l = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ ! { dg-warning "insufficient partitioning available to parallelize loop" "" { target *-*-* } .-1 }
+ do k = 1, 10
+ !$acc loop reduction(*:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do l = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum) reduction(-:diff)
+ do i = 1, 10
+ !$acc loop reduction(-:diff) ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum)
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+
+ !$acc loop reduction(+:sum) ! { dg-warning "nested loop in reduction needs reduction clause for .diff." }
+ do j = 1, 10
+ !$acc loop reduction(-:diff)
+ do k = 1, 10
+ diff = 1
+ end do
+ end do
+ end do
+end subroutine acc_routine
+
+subroutine acc_kernels ()
+ integer :: i, j, k, sum, diff
+
+ ! FIXME: No diagnostics are produced for these loops because reductions
+ ! in kernels regions are not supported yet.
+ !$acc kernels
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ do j = 1, 10
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop
+ do j = 1, 10
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:diff)
+ do j = 1, 10
+ !$acc loop
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop ! { dg-warning "nested loop in reduction needs reduction clause for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum)
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+
+ !$acc loop reduction(+:sum)
+ do i = 1, 10
+ !$acc loop reduction(-:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do j = 1, 10
+ !$acc loop reduction(+:sum) ! { dg-warning "conflicting reduction operations for .sum." }
+ do k = 1, 10
+ sum = 1
+ end do
+ end do
+ end do
+ !$acc end kernels
+end subroutine acc_kernels
IMPLICIT NONE
EXTERNAL :: g_1
!$ACC ROUTINE (g_1) GANG WORKER ! { dg-error "Multiple loop axes" }
- !$ACC ROUTINE (ABORT) SEQ VECTOR ! { dg-error "Multiple loop axes" "" { xfail *-*-* } }
-! { dg-bogus "invalid function name abort" "" { xfail *-*-* } .-1 }
+ !$ACC ROUTINE (ABORT) SEQ VECTOR ! { dg-error "Multiple loop axes" "" }
+! { dg-bogus "invalid function name abort" }
CALL v_1
CALL g_1
IMPLICIT NONE
EXTERNAL :: w_1
!$ACC ROUTINE (w_1) WORKER SEQ ! { dg-error "Multiple loop axes" }
- !$ACC ROUTINE (ABORT) VECTOR GANG ! { dg-error "Multiple loop axes" "" { xfail *-*-* } }
-! { dg-bogus "invalid function name abort" "" { xfail *-*-* } .-1 }
+ !$ACC ROUTINE (ABORT) VECTOR GANG ! { dg-error "Multiple loop axes" }
+! { dg-bogus "invalid function name abort" "" { target *-*-* } .-1 }
CONTAINS
SUBROUTINE sub_2
integer :: i3_5_s, j3_5_s, k3_5_s
!$acc kernels ! Explicit "private(i0_1)" clause cannot be specified here.
- ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:i0_1 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { xfail *-*-* } } } ! PR90067
+ ! The "private" clause gets added in the "omp_data_optimize" pass and is hence
+ ! not there in the "original"
+ ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 0 "original"} }
do i0_1 = 1, 100
end do
!$acc end kernels
!$acc kernels ! Explicit "private(i0_2, j0_2)" clause cannot be specified here.
- ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:j0_2 \\\[len: \[0-9\]+\\\]\\) map\\(force_tofrom:i0_2 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { xfail *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 0 "original" } }
+ ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 0 "original" } }
do i0_2 = 1, 100
do j0_2 = 1, 100
end do
integer :: i3_5_s, j3_5_s, k3_5_s
!$acc kernels
- ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:i0_1 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { xfail *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 0 "original" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(i0_1\\)" 1 "gimple" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:i0_1 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { target *-*-* } } } ! PR90067
do i0_1 = 1, 100
end do
!$acc end kernels
!$acc kernels
- ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 1 "original" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 1 "gimple" { xfail *-*-* } } } ! PR90067
- ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:j0_2 \\\[len: \[0-9\]+\\\]\\) map\\(force_tofrom:i0_2 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { xfail *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 0 "original" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 0 "original" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(i0_2\\)" 1 "gimple" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "private\\(j0_2\\)" 1 "gimple" { target *-*-* } } } ! PR90067
+ ! { dg-final { scan-tree-dump-times "#pragma omp target oacc_kernels map\\(force_tofrom:j0_2 \\\[len: \[0-9\]+\\\]\\) map\\(force_tofrom:i0_2 \\\[len: \[0-9\]+\\\]\\)" 0 "gimple" { target *-*-* } } } ! PR90067
do i0_2 = 1, 100
do j0_2 = 1, 100
end do
! OpenACC 'routine' directives inside a Fortran module.
! { dg-additional-options "-fopt-info-optimized-omp" }
+! { dg-additional-options "-O0" }
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
! aspects of that functionality.
subroutine g_1 ! { dg-warning "region is worker partitioned but does not contain worker partitioned code" }
implicit none
!$acc routine gang
- ! { dg-bogus "\[Ww\]arning: region is worker partitioned but does not contain worker partitioned code" "TODO default 'gang' 'vector'" { xfail *-*-* } .-3 }
integer :: i
integer :: i
!$acc kernels
- ! { dg-warning "'i' is used uninitialized in this function" "" { target *-*-* } .-1 }
- !TODO See discussion in '../../c-c++-common/goacc/uninit-copy-clause.c'.
i = 1
!$acc end kernels
/* { dg-missed {'map\(tofrom:b [^)]+\)' not optimized: 'b' is unsuitable for privatization} "" { target *-*-* } .-1 }
{ dg-missed {'map\(force_tofrom:a [^)]+\)' not optimized: 'a' is unsuitable for privatization} "" { target *-*-* } .-2 } */
{
- int c = 234; /* { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" } */
+ int c = 234; /* { dg-message "note: beginning 'Graphite' part in OpenACC 'kernels' region" } */
/*TODO Hopefully, this is the same issue as '../../../gcc/testsuite/c-c++-common/goacc/kernels-decompose-ice-1.c'. */
(volatile int *) &c;
#pragma acc loop independent gang /* { 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 } */
for (int i = 0; i < N; ++i)
b[i] = c;
- a = c; /* { dg-message "note: beginning 'gang-single' part in OpenACC 'kernels' region" } */
+ a = c; /* { dg-message "note: beginning 'Graphite' part in OpenACC 'kernels' region" } */
}
for (int i = 0; i < N; ++i)
/* { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
aspects of that functionality. */
-/* { dg-additional-options "-O2" } for Graphite/"kernels". */
/* See also '../libgomp.oacc-fortran/parallel-dims.f90'. */
int gangs_min, gangs_max, workers_min, workers_max, vectors_min, vectors_max;
gangs_min = workers_min = vectors_min = INT_MAX;
gangs_max = workers_max = vectors_max = INT_MIN;
-#pragma acc parallel copy (gangs_actual) /* { dg-warning "region contains gang partitioned code but is not gang partitioned" } */ \
- num_gangs (GANGS) /* { dg-warning "'num_gangs' value must be positive" "" { target c++ } } */
- /* { dg-warning "region contains gang partitioned code but is not gang partitioned" "" { target *-*-* } .-2 } */
+#pragma acc parallel copy (gangs_actual) num_gangs (GANGS) /* { dg-warning "'num_gangs' value must be positive" "" { target c++ } } */
+ /* { dg-warning "region contains gang partitioned code but is not gang partitioned" "" { target *-*-* } .-1 } */
{
/* We're actually executing with num_gangs (1). */
gangs_actual = 1;
int gangs_min, gangs_max, workers_min, workers_max, vectors_min, vectors_max;
gangs_min = workers_min = vectors_min = INT_MAX;
gangs_max = workers_max = vectors_max = INT_MIN;
-#pragma acc parallel copy (workers_actual) /* { dg-warning "region contains worker partitioned code but is not worker partitioned" } */ \
- num_workers (WORKERS) /* { dg-warning "'num_workers' value must be positive" "" { target c++ } } */
+#pragma acc parallel copy (workers_actual) \
+ num_workers (WORKERS) /* { dg-warning "'num_workers' value must be positive" "" { target c++ } } */
/* { dg-warning "region contains worker partitioned code but is not worker partitioned" "" { target *-*-* } .-2 } */
{
/* We're actually executing with num_workers (1). */
int gangs_min, gangs_max, workers_min, workers_max, vectors_min, vectors_max;
gangs_min = workers_min = vectors_min = INT_MAX;
gangs_max = workers_max = vectors_max = INT_MIN;
-#pragma acc parallel copy (vectors_actual) /* { dg-warning "region contains vector partitioned code but is not vector partitioned" } */ \
- /* { dg-warning "using vector_length \\(32\\), ignoring 1" "" { target openacc_nvidia_accel_selected } 164 } */ \
+#pragma acc parallel copy (vectors_actual) \
vector_length (VECTORS) /* { dg-warning "'vector_length' value must be positive" "" { target c++ } } */
- /* { dg-warning "region contains vector partitioned code but is not vector partitioned" "" { target *-*-* } .-2 } */
+ /* { dg-warning "using vector_length \\(32\\), ignoring 1" "" { target openacc_nvidia_accel_selected } .-2 } */
+ /* { dg-warning "region contains vector partitioned code but is not vector partitioned" "" { target *-*-* } .-3 } */
{
/* We're actually executing with vector_length (1), just the GCC nvptx
back end enforces vector_length (32). */
#pragma acc parallel copy (gangs_actual) /* { dg-warning "region is gang partitioned but does not contain gang partitioned code" } */ \
reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max) \
num_gangs (gangs)
- /* { dg-bogus "warning: region is gang partitioned but does not contain gang partitioned code" "TODO 'reduction'" { xfail *-*-* } .-3 } */
{
if (acc_on_device (acc_device_host))
{
asm volatile ("" : : : "memory");
#pragma acc loop reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max)
+/* { dg-warning "region is gang partitioned but does not contain gang partitioned code" "" { target *-*-* } .-1 } */
+/* { dg-warning "region is worker partitioned but does not contain worker partitioned code" "" { target *-*-* } .-2 } */
+/* { dg-warning "region is vector partitioned but does not contain vector partitioned code" "" { target *-*-* } .-3 } */
+/* { dg-warning "removed gang worker vector partitioning from 'kernels' region" "" { target *-*-* } .-4 } */
for (int i = 100; i > -100; --i)
- {
- gangs_min = gangs_max = acc_gang ();
- workers_min = workers_max = acc_worker ();
- vectors_min = vectors_max = acc_vector ();
- }
+ {
+ gangs_min = gangs_max = acc_gang ();
+ workers_min = workers_max = acc_worker ();
+ vectors_min = vectors_max = acc_vector ();
+ }
}
if (gangs_min != 0 || gangs_max != 1 - 1
|| workers_min != 0 || workers_max != 1 - 1
/* { dg-bogus "warning: region contains gang partitioned code but is not gang partitioned" "TODO 'serial'" { xfail *-*-* } .-2 }
{ dg-bogus "warning: region contains worker partitioned code but is not worker partitioned" "TODO 'serial'" { xfail *-*-* } .-3 }
{ dg-bogus "warning: region contains vector partitioned code but is not vector partitioned" "TODO 'serial'" { xfail *-*-* } .-4 } */
+ /* { dg-warning "using vector_length \\(32\\), ignoring 1" "" { target openacc_nvidia_accel_selected } .-5 } */
{
if (acc_on_device (acc_device_nvidia))
{
__builtin_abort ();
if (gangs_min != 0 || gangs_max != 1 - 1
|| workers_min != 0 || workers_max != 1 - 1
- || vectors_min != 0 || vectors_max != vectors_actual - 1)
+ || vectors_min != 0 || vectors_max >= vectors_actual)
__builtin_abort ();
}
return i + j;
}
-/* { dg-final { scan-tree-dump-not "if" "cddce2"} } */
return 0;
}
-/* Todo: Boths bar.syncs can be removed.
- Atm we generate this dead code inbetween forked and joining:
+/* All bar.syncs can be removed.
+ Previously, we generated dead code inbetween forked and joining:
mov.u32 %r28, %ntid.y;
mov.u32 %r29, %tid.y;
@%r33 bra $L3;
$L2:
- so the loop is not recognized as empty loop (which we detect by seeing if
+ so the loop was not recognized as empty loop (which we detect by seeing if
joining immediately follows forked). */
-/* { dg-final { scan-offload-rtl-dump-times "nvptx_barsync" 2 "mach" } } */
+/* { dg-final { scan-offload-rtl-dump-times "nvptx_barsync" 0 "mach" } } */
#pragma acc declare create(a)
#pragma acc routine vector
-/* { dg-warning "region is vector partitioned but does not contain vector partitioned code" "" { target *-*-* } .+2 } */
void __attribute__((noinline, noclone))
foo_v (void)
{
}
#pragma acc routine worker
-/* { dg-warning "region is worker partitioned but does not contain worker partitioned code" "" { target *-*-* } .+3 }
- { dg-warning "region is vector partitioned but does not contain vector partitioned code" "" { target *-*-* } .+2 } */
void __attribute__((noinline, noclone))
foo_w (void)
{
{
#pragma acc loop worker
for (int i = 0; i < n; i++)
- ;
+ asm volatile ("");
#pragma acc loop worker
for (int i = 0; i < n; i++)
- ;
+ asm volatile ("");
}
return 0;
#include "pr85486.c"
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow3" } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=32" } */
#include "pr85486.c"
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow3" } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=32" } */
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow3" } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=32" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } *
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=128" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
/* { dg-additional-options "-fopenacc-dim=::128" } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=128" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* We default to warp size 32 for the vector length, so the GOMP_OPENACC_DIM has
no effect. */
/* { dg-set-target-env-var "GOMP_OPENACC_DIM" "::128" } */
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 1, 32\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=1, vectors=32" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=2, vectors=128" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
/* { dg-additional-options "-fopenacc-dim=:2:128" } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 2, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=2, vectors=128" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
/* { dg-set-target-env-var "GOMP_OPENACC_DIM" ":2:" } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=2, vectors=128" } */
/* { dg-do run { target openacc_nvidia_accel_selected } } */
-/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow1" } */
+/* { dg-additional-options "-foffload=-fdump-tree-oaccdevlow" } */
/* { dg-set-target-env-var "GOMP_DEBUG" "1" } */
#include <stdlib.h>
return 0;
}
-/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow1" } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow1" { target { any-opts "-O[123s]"} } } } */
+/* { dg-final { scan-offload-tree-dump "__attribute__\\(\\(oacc function \\(1, 0, 128\\)" "oaccdevlow3" { target { any-opts "-O[0g]"} } } } */
/* { dg-output "nvptx_exec: kernel main\\\$_omp_fn\\\$0: launch gangs=1, workers=8, vectors=128" } */
! { dg-do run }
! { dg-additional-options "-fdump-tree-oaccdevlow-details -Wopenacc-parallelism" }
-! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has gang partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow" } } */
+! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has gang partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow1" { target { any-opts "-O[1,2,3,s]"} } } } */
+! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has gang partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow3" { target { no-opts "-O[1,2,3,s]"} } } } */
program main
integer :: w, arr(0:31)
! { dg-do run }
! { dg-additional-options "-fdump-tree-oaccdevlow-details" }
-! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has worker partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow" } } */
+! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has worker partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow1" { target { any-opts "-O[1,2,3,s]"} } } } */
+! { dg-final { scan-tree-dump-times "Decl UID \[0-9\]+ has worker partitioning: integer\\(kind=4\\) w;" 1 "oaccdevlow3" { target { no-opts "-O[1,2,3,s]"} } } } */
program main
integer :: w, arr(0:31)
! { dg-do run }
-!
+! { dg-xfail-run-if "PR102424" { ! openacc_host_selected } }
+! TODO PR102424 OpenACC 'reduction' with outer 'loop seq', inner 'loop gang'
+
+! { dg-additional-options "-O2" }
+! { dg-additional-options "-fopt-info-omp" }
+
program foo
IMPLICIT NONE
INTEGER :: j,k
!$ACC KERNELS
- !$ACC LOOP REDUCTION(+:vol)
+ ! TODO The "reduction" dependence handling in Graphite should be adjusted to take the outer "reduction" into account correctly
+ !$ACC LOOP REDUCTION(+:vol) ! { dg-bogus "optimized: assigned OpenACC seq loop parallelism" "TODO Suboptimal parallelism assigned" { xfail *-*-* } }
DO k=1,2
- !$ACC LOOP REDUCTION(+:vol)
+ !$ACC LOOP REDUCTION(+:vol) ! { dg-bogus "optimized: assigned OpenACC gang vector loop parallelism" "TODO Suboptimal parallelism assigned" { xfail *-*-* } }
DO j=1,2
vol = vol + 1
ENDDO
+++ /dev/null
-! Check that the Graphite-based "auto" loop and "kernels" handling
-! is able to assign the parallelism dimensions correctly for a simple
-! loop-nest with reductions. All loops should be parallelized.
-
-! { dg-additional-options "-O2 -g" }
-! { dg-additional-options "-foffload=-fdump-tree-oaccloops1-details" }
-! { dg-additional-options "-foffload=-fopt-info-optimized" }
-! { dg-additional-options "-fdump-tree-oaccloops1-details" }
-! { dg-additional-options "-fopt-info-optimized" }
-
-module test
- implicit none
-
- integer, parameter :: n = 10000
- integer :: a(n,n)
- integer :: sums(n,n)
-
-contains
- function sum_loop_auto() result(sum)
- integer :: i, j
- integer :: sum, max_val
-
- sum = 0
- max_val = 0
-
- !$acc parallel copyin (a) reduction(+:sum)
- !$acc loop auto reduction(+:sum) reduction(max:max_val) ! { dg-optimized "assigned OpenACC gang worker loop parallelism" }
- ! { dg-optimized ".auto. loop can be parallel" "" { target *-*-* } .-1 }
- do i = 1,size (a, 1)
- !$acc loop auto reduction(max:max_val) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
- ! { dg-optimized ".auto. loop can be parallel" "" { target *-*-* } .-1 }
- do j = 1,size(a, 2)
- max_val = a(i,j)
- end do
- sum = sum + max_val
- end do
- !$acc end parallel
- end function sum_loop_auto
-
- function sum_kernels() result(sum)
- integer :: i, j
- integer :: sum, max_val
-
- sum = 0
- max_val = 0
-
- !$acc kernels
- ! { dg-optimized {'map\(force_tofrom:max_val [^)]+\)' optimized to 'map\(to:max_val [^)]+\)'} "" { target *-*-* } .-1 }
- !$acc loop reduction(+:sum) reduction(max:max_val) ! { dg-optimized "assigned OpenACC gang worker loop parallelism" }
- ! { dg-optimized ".auto. loop can be parallel" "" { target *-*-* } .-1 }
- ! { dg-optimized "forwarded loop nest in OpenACC .kernels. construct to .Graphite." "" { target *-*-* } .-2 }
- do i = 1,size (a, 1)
- !$acc loop reduction(max:max_val) ! { dg-optimized "assigned OpenACC vector loop parallelism" }
- ! { dg-optimized ".auto. loop can be parallel" "" { target *-*-* } .-1 }
- do j = 1,size(a, 2)
- max_val = a(i,j)
- end do
- sum = sum + max_val
- end do
- !$acc end kernels
- end function sum_kernels
-end module test
-
-program main
- use test
-
- implicit none
-
- integer :: result, i, j
-
- ! We sum the maxima of n rows, each containing numbers
- ! 1..n
- integer, parameter :: expected_sum = n * n
-
- do i = 1, size (a, 1) ! { dg-optimized "loop nest optimized" }
- do j = 1, size (a, 2)
- a(i, j) = j
- end do
- end do
-
-
- result = sum_loop_auto()
- if (result /= expected_sum) then
- write (*, *) "Wrong result:", result
- call abort()
- endif
-
- result = sum_kernels()
- if (result /= expected_sum) then
- write (*, *) "Wrong result:", result
- call abort()
- endif
-end program main
-
-! This ensures that the dg-optimized assertions above hold for both
-! compilers because the output goes to stderr and the dump file.
-! { dg-final { scan-offload-tree-dump-times "optimized: assigned OpenACC .*? parallelism" 4 "oaccloops1" } }
-! { dg-final { scan-tree-dump-times "optimized: assigned OpenACC .*? parallelism" 4 "oaccloops1" } }
! { dg-missed {'map\(tofrom:\*b [^)]+\)' not optimized: '\*b' is unsuitable for privatization} "" { target *-*-* } .-3 }
! { dg-missed {'map\(tofrom:\*a [^)]+\)' not optimized: '\*a' is unsuitable for privatization} "" { target *-*-* } .-4 }
!$acc loop independent ! { dg-line l_loop_i[incr c_loop_i] }
- ! { dg-message "note: parallelized loop nest in OpenACC 'kernels' region" "" { target *-*-* } l_loop_i$c_loop_i }
! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = lo, hi
b(i) = a(i)
end do
!$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$c_loop_i }
! { dg-optimized "assigned OpenACC gang vector loop parallelism" "" { target *-*-* } l_loop_i$c_loop_i }
do i = lo, hi
c(i) = b(i)
projects / thirdparty / gcc.git / commitdiff
