diff options
author | Tobias Burnus <tobias@codesourcery.com> | 2023-04-25 16:29:14 +0200 |
---|---|---|
committer | Tobias Burnus <tobias@codesourcery.com> | 2023-04-25 16:29:14 +0200 |
commit | 1c101fcfaac8f609d618f83b124bd50aea012132 (patch) | |
tree | dd1ac83cab1561d60c15f2083fcc243b452636a8 /libgomp | |
parent | 78aaaf862e70cea45f3a2be7cb855cfe1a4ead21 (diff) | |
download | gcc-1c101fcfaac8f609d618f83b124bd50aea012132.zip gcc-1c101fcfaac8f609d618f83b124bd50aea012132.tar.gz gcc-1c101fcfaac8f609d618f83b124bd50aea012132.tar.bz2 |
'omp scan' struct block seq update for OpenMP 5.x
While OpenMP 5.0 required a single structured block before and after the
'omp scan' directive, OpenMP 5.1 changed this to a 'structured block sequence,
denoting 2 or more executable statements in OpenMP 5.1 (whoops!) and zero or
more in OpenMP 5.2. This commit updates C/C++ to accept zero statements (but
till requires the '{' ... '}' for the final-loop-body) and updates Fortran
to accept zero or more than one statements.
If there is no preceeding or succeeding executable statement, a warning is
shown.
gcc/c/ChangeLog:
* c-parser.cc (c_parser_omp_scan_loop_body): Handle
zero exec statements before/after 'omp scan'.
gcc/cp/ChangeLog:
* parser.cc (cp_parser_omp_scan_loop_body): Handle
zero exec statements before/after 'omp scan'.
gcc/fortran/ChangeLog:
* openmp.cc (gfc_resolve_omp_do_blocks): Handle zero
or more than one exec statements before/after 'omp scan'.
* trans-openmp.cc (gfc_trans_omp_do): Likewise.
libgomp/ChangeLog:
* testsuite/libgomp.c-c++-common/scan-1.c: New test.
* testsuite/libgomp.c/scan-23.c: New test.
* testsuite/libgomp.fortran/scan-2.f90: New test.
gcc/testsuite/ChangeLog:
* g++.dg/gomp/attrs-7.C: Update dg-error/dg-warning.
* gfortran.dg/gomp/loop-2.f90: Likewise.
* gfortran.dg/gomp/reduction5.f90: Likewise.
* gfortran.dg/gomp/reduction6.f90: Likewise.
* gfortran.dg/gomp/scan-1.f90: Likewise.
* gfortran.dg/gomp/taskloop-2.f90: Likewise.
* c-c++-common/gomp/scan-6.c: New test.
* gfortran.dg/gomp/scan-8.f90: New test.
Diffstat (limited to 'libgomp')
-rw-r--r-- | libgomp/testsuite/libgomp.c-c++-common/scan-1.c | 68 | ||||
-rw-r--r-- | libgomp/testsuite/libgomp.c/scan-23.c | 121 | ||||
-rw-r--r-- | libgomp/testsuite/libgomp.fortran/scan-2.f90 | 59 |
3 files changed, 248 insertions, 0 deletions
diff --git a/libgomp/testsuite/libgomp.c-c++-common/scan-1.c b/libgomp/testsuite/libgomp.c-c++-common/scan-1.c new file mode 100644 index 0000000..d1951a3 --- /dev/null +++ b/libgomp/testsuite/libgomp.c-c++-common/scan-1.c @@ -0,0 +1,68 @@ +#define N 30 +#define M 3 + +int a[N][M], b[N][M], c[N][M]; + +int +main() +{ + int x, y, shift; + int j = 0; + for (int i = 0; i < N; i++) + { + a[i][0] = (i+1)*32; + a[i][1] = (i+1)*17; + a[i][2] = (i+1)*11; + b[i][0] = (i+1)*7; + b[i][1] = (i+1)*5; + b[i][2] = (i+1)*3; + } + + x = 0; + #pragma omp parallel for simd collapse(2) reduction(inscan,+: x) private(shift) + for (int i = 0; i < N; i++) + for (int j = 0; j < M; j++) + { + x += a[i][j]; + x += b[i][j]; + #pragma omp scan inclusive(x) + shift = i + 29*j; + c[i][j] = x + shift; + } + + y = 0; + for (int i = 0; i < N; i++) + for (int j = 0; j < M; j++) + { + y += a[i][j] + b[i][j]; + if (c[i][j] != y + i + 29*j) + __builtin_abort (); + } + if (x != y) + __builtin_abort (); + + x = 0; + #pragma omp parallel for simd collapse(2) reduction(inscan,+: x) private(shift) + for (int i = 0; i < N; i++) + for (int j = 0; j < M; j++) + { + shift = i + 29*j; + c[i][j] = x + shift; + #pragma omp scan exclusive(x) + x += a[i][j]; + x += b[i][j]; + } + + y = 0; + for (int i = 0; i < N; i++) + for (int j = 0; j < M; j++) + { + if (c[i][j] != y + i + 29*j) + __builtin_abort (); + y += a[i][j] + b[i][j]; + } + if (x != y) + __builtin_abort (); + + return 0; +} diff --git a/libgomp/testsuite/libgomp.c/scan-23.c b/libgomp/testsuite/libgomp.c/scan-23.c new file mode 100644 index 0000000..e7681ad --- /dev/null +++ b/libgomp/testsuite/libgomp.c/scan-23.c @@ -0,0 +1,121 @@ +/* { dg-require-effective-target size32plus } */ +/* Same as scan-9.c, instead of using { ... } it simply uses multiple + executable stmt before 'omp scan'. */ + +extern void abort (void); +int r, a[1024], b[1024], x, y, z; + +__attribute__((noipa)) void +foo (int *a, int *b) +{ + #pragma omp for reduction (inscan, +:r) lastprivate (conditional: z) firstprivate (x) private (y) + for (int i = 0; i < 1024; i++) + { + y = a[i]; + r += y + x + 12; + #pragma omp scan inclusive(r) + b[i] = r; + if ((i & 1) == 0 && i < 937) + z = r; + } +} + +__attribute__((noipa)) int +bar (void) +{ + int s = 0; + #pragma omp parallel + #pragma omp for reduction (inscan, +:s) firstprivate (x) private (y) lastprivate (z) + for (int i = 0; i < 1024; i++) + { + y = 2 * a[i]; s += y; z = y; + #pragma omp scan inclusive(s) + y = s; b[i] = y + x + 12; + } + return s; +} + +__attribute__((noipa)) void +baz (int *a, int *b) +{ + #pragma omp parallel for reduction (inscan, +:r) firstprivate (x) lastprivate (x) + for (int i = 0; i < 1024; i++) + { + r += a[i] + x + 12; if (i == 1023) x = 29; + #pragma omp scan inclusive(r) + b[i] = r; + } +} + +__attribute__((noipa)) int +qux (void) +{ + int s = 0; + #pragma omp parallel for reduction (inscan, +:s) lastprivate (conditional: x, y) + for (int i = 0; i < 1024; i++) + { + s += 2 * a[i]; if ((a[i] & 1) == 1 && i < 825) x = a[i]; + #pragma omp scan inclusive(s) + b[i] = s; if ((a[i] & 1) == 0 && i < 829) y = a[i]; + } + return s; +} + +int +main () +{ + int s = 0; + x = -12; + for (int i = 0; i < 1024; ++i) + { + a[i] = i; + b[i] = -1; + asm ("" : "+g" (i)); + } + #pragma omp parallel + foo (a, b); + if (r != 1024 * 1023 / 2 || x != -12 || z != b[936]) + abort (); + for (int i = 0; i < 1024; ++i) + { + s += i; + if (b[i] != s) + abort (); + else + b[i] = 25; + } + if (bar () != 1024 * 1023 || x != -12 || z != 2 * 1023) + abort (); + s = 0; + for (int i = 0; i < 1024; ++i) + { + s += 2 * i; + if (b[i] != s) + abort (); + else + b[i] = -1; + } + r = 0; + baz (a, b); + if (r != 1024 * 1023 / 2 || x != 29) + abort (); + s = 0; + for (int i = 0; i < 1024; ++i) + { + s += i; + if (b[i] != s) + abort (); + else + b[i] = -25; + } + if (qux () != 1024 * 1023 || x != 823 || y != 828) + abort (); + s = 0; + for (int i = 0; i < 1024; ++i) + { + s += 2 * i; + if (b[i] != s) + abort (); + } + return 0; +} diff --git a/libgomp/testsuite/libgomp.fortran/scan-2.f90 b/libgomp/testsuite/libgomp.fortran/scan-2.f90 new file mode 100644 index 0000000..2815ec7 --- /dev/null +++ b/libgomp/testsuite/libgomp.fortran/scan-2.f90 @@ -0,0 +1,59 @@ +implicit none +integer, parameter :: N = 30 +integer, parameter :: M = 3 + +integer :: a(M,N), b(M,N), c(M,N) +integer :: x, y, shift +integer :: i, j + +do i = 1, N + a(1,i) = i*32 + a(2,i) = i*17 + a(3,i) = i*11 + b(1,i) = i*7 + b(2,i) = i*5 + b(3,i) = i*3 +end do + +x = 0 +!$omp parallel do simd collapse(2) reduction(inscan,+: x) private(shift) +do i = 1, N + do j = 1, M + x = x + a(j,i) + x = x + b(j,i) + !$omp scan inclusive(x) + shift = i + 29*j + c(j,i) = x + shift; + end do +end do + +y = 0 +do i = 1, N + do j = 1, M + y = y + a(j,i) + b(j,i) + if (c(j,i) /= y + i + 29*j) error stop 1 + end do +end do +if (x /= y) error stop 2 + +x = 0 +!$omp parallel do simd collapse(2) reduction(inscan,+: x) private(shift) +do i = 1, N + do j = 1, M + shift = i + 29*j + c(j,i) = x + shift; + !$omp scan exclusive(x) + x = x + a(j,i) + x = x + b(j,i) + end do +end do + +y = 0 +do i = 1, N + do j = 1, M + if (c(j,i) /= y + i + 29*j) error stop 1 + y = y + a(j,i) + b(j,i) + end do +end do +if (x /= y) error stop 2 +end |