From 3a4775d4403f2e88b589e88a9937cc1fd45a0e87 Mon Sep 17 00:00:00 2001
From: Thomas Schwinge <tschwinge@baylibre.com>
Date: Wed, 5 Jun 2024 13:13:24 +0200
Subject: [PATCH] nvptx, libgfortran: Switch out of "minimal" mode
..., in order to enable (portions of) Fortran I/O, for example.
libgfortran/
* configure.ac: No longer set 'LIBGFOR_MINIMAL' for nvptx.
* configure: Regenerate.
libgomp/
* libgomp.texi (nvptx): Update.
* testsuite/libgomp.fortran/target-print-1-nvptx.f90: Remove.
* testsuite/libgomp.fortran/target-print-1.f90: Adjust.
* testsuite/libgomp.oacc-fortran/error_stop-2-nvptx.f: New.
* testsuite/libgomp.oacc-fortran/error_stop-2.f: Adjust.
* testsuite/libgomp.oacc-fortran/print-1-nvptx.f90: Adjust.
* testsuite/libgomp.oacc-fortran/print-1.f90: Adjust.
* testsuite/libgomp.oacc-fortran/stop-2-nvptx.f: New.
* testsuite/libgomp.oacc-fortran/stop-2.f: Adjust.
Co-authored-by: Andrew Stubbs <ams@gcc.gnu.org>
---
libgfortran/configure | 21 ++++------
libgfortran/configure.ac | 17 +++-----
libgomp/libgomp.texi | 10 +++--
.../libgomp.fortran/target-print-1-nvptx.f90 | 11 -----
.../libgomp.fortran/target-print-1.f90 | 3 --
.../libgomp.oacc-fortran/error_stop-2-nvptx.f | 39 ++++++++++++++++++
.../libgomp.oacc-fortran/error_stop-2.f | 3 +-
.../libgomp.oacc-fortran/print-1-nvptx.f90 | 40 +++++++++++++++----
.../libgomp.oacc-fortran/print-1.f90 | 4 +-
.../libgomp.oacc-fortran/stop-2-nvptx.f | 36 +++++++++++++++++
.../testsuite/libgomp.oacc-fortran/stop-2.f | 3 +-
11 files changed, 134 insertions(+), 53 deletions(-)
delete mode 100644 libgomp/testsuite/libgomp.fortran/target-print-1-nvptx.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/error_stop-2-nvptx.f
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/stop-2-nvptx.f
@@ -6207,17 +6207,12 @@ else
fi
-# For GPU offloading, not everything in libfortran can be supported.
-# Currently, the only target that has this problem is nvptx. The
-# following is a (partial) list of features that are unsupportable on
-# this particular target:
-# * Constructors
-# * alloca
-# * C library support for I/O, with printf as the one notable exception
-# * C library support for other features such as signal, environment
-# variables, time functions
-
- if test "x${target_cpu}" = xnvptx; then
+# "Minimal" mode is for targets that cannot (yet) support all features of
+# libgfortran. It avoids the need for working constructors, alloca, and C
+# library support for I/O, signals, environment variables, time functions, etc.
+# At present there are no targets that require this mode.
+
+ if false; then
LIBGFOR_MINIMAL_TRUE=
LIBGFOR_MINIMAL_FALSE='#'
else
@@ -12852,7 +12847,7 @@ else
lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
lt_status=$lt_dlunknown
cat > conftest.$ac_ext <<_LT_EOF
-#line 12855 "configure"
+#line 12850 "configure"
#include "confdefs.h"
#if HAVE_DLFCN_H
@@ -12958,7 +12953,7 @@ else
lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
lt_status=$lt_dlunknown
cat > conftest.$ac_ext <<_LT_EOF
-#line 12961 "configure"
+#line 12956 "configure"
#include "confdefs.h"
#if HAVE_DLFCN_H
@@ -209,17 +209,12 @@ AM_CONDITIONAL(LIBGFOR_USE_SYMVER, [test "x$gfortran_use_symver" != xno])
AM_CONDITIONAL(LIBGFOR_USE_SYMVER_GNU, [test "x$gfortran_use_symver" = xgnu])
AM_CONDITIONAL(LIBGFOR_USE_SYMVER_SUN, [test "x$gfortran_use_symver" = xsun])
-# For GPU offloading, not everything in libfortran can be supported.
-# Currently, the only target that has this problem is nvptx. The
-# following is a (partial) list of features that are unsupportable on
-# this particular target:
-# * Constructors
-# * alloca
-# * C library support for I/O, with printf as the one notable exception
-# * C library support for other features such as signal, environment
-# variables, time functions
-
-AM_CONDITIONAL(LIBGFOR_MINIMAL, [test "x${target_cpu}" = xnvptx])
+# "Minimal" mode is for targets that cannot (yet) support all features of
+# libgfortran. It avoids the need for working constructors, alloca, and C
+# library support for I/O, signals, environment variables, time functions, etc.
+# At present there are no targets that require this mode.
+
+AM_CONDITIONAL(LIBGFOR_MINIMAL, false)
# Some compiler target support may have limited support for integer
# or floating point numbers – or may want to reduce the libgfortran size
@@ -6354,7 +6354,7 @@ The used sizes are
The implementation remark:
@itemize
-@item I/O within OpenMP target regions and OpenACC parallel/kernels is supported
+@item I/O within OpenMP target regions and OpenACC compute regions is supported
using the C library @code{printf} functions and the Fortran
@code{print}/@code{write} statements.
@item Reverse offload regions (i.e. @code{target} regions with
@@ -6429,9 +6429,11 @@ CUDA version and hardware.
The implementation remark:
@itemize
-@item I/O within OpenMP target regions and OpenACC parallel/kernels is supported
- using the C library @code{printf} functions. Note that the Fortran
- @code{print}/@code{write} statements are not supported, yet.
+@item I/O within OpenMP target regions and OpenACC compute regions is supported
+ using the C library @code{printf} functions.
+ Additionally, the Fortran @code{print}/@code{write} statements are
+ supported within OpenMP target regions, but not yet OpenACC compute
+ regions. @c The latter needs 'GOMP_NVPTX_NATIVE_GPU_THREAD_STACK_SIZE'.
@item Compilation OpenMP code that contains @code{requires reverse_offload}
requires at least @code{-march=sm_35}, compiling for @code{-march=sm_30}
is not supported.
deleted file mode 100644
@@ -1,11 +0,0 @@
-! Ensure that write on the offload device works, nvptx offloading variant.
-
-! This doesn't compile: for nvptx offloading we're using a minimal libgfortran
-! configuration.
-! { dg-do link } ! ..., but still apply 'dg-do run' options.
-! { dg-xfail-if "minimal libgfortran" { offload_target_nvptx } }
-
-! Skip duplicated testing.
-! { dg-skip-if "separate file" { ! offload_target_nvptx } }
-
-include 'target-print-1.f90'
@@ -3,9 +3,6 @@
! { dg-do run }
! { dg-output "The answer is 42(\n|\r\n|\r)+" }
-! Separate file 'target-print-1-nvptx.f90' for nvptx offloading.
-! { dg-skip-if "separate file" { offload_target_nvptx } }
-
program main
implicit none
integer :: var = 42
new file mode 100644
@@ -0,0 +1,39 @@
+! 'error_stop-2.f' nvptx offloading variant
+
+! { dg-do run { target openacc_nvidia_accel_selected } }
+!
+! The PTX JIT doesn't understand the 'ERROR STOP' call graph, and therefore:
+! warning : Stack size for entry function 'main$_omp_fn$0' cannot be statically determined
+! Running with default 1024-bytes GPU thread stack size overflows the stack,
+! so raise it to an arbitrarily higher value:
+! { dg-set-target-env-var GOMP_NVPTX_NATIVE_GPU_THREAD_STACK_SIZE 3333 }
+
+ PROGRAM MAIN
+ IMPLICIT NONE
+
+! Initialize before the checkpoint, in case this produces any output.
+!$ACC PARALLEL
+!$ACC END PARALLEL
+
+ PRINT *, "CheCKpOInT"
+!$ACC PARALLEL
+ ERROR STOP 35
+!$ACC END PARALLEL
+ PRINT *, "WrONg WAy"
+
+ END PROGRAM MAIN
+
+! { dg-output "CheCKpOInT(\n|\r\n|\r)+" }
+
+! { dg-output "ERROR STOP 35(\n|\r\n|\r)+" }
+!
+! In gfortran's main program, libfortran's set_options is called - which sets
+! compiler_options.backtrace = 1 by default. For an offload libgfortran, this
+! is never called and, hence, "Error termination." is never printed. Thus:
+! { dg-output "Error termination.*" { target { ! { openacc_nvidia_accel_selected || openacc_radeon_accel_selected } } } }
+
+! PR85463. The 'exit' implementation used with nvptx
+! offloading is a little bit different.
+! { dg-output "libgomp: cuStreamSynchronize error.*" { target openacc_nvidia_accel_selected } }
+
+! { dg-shouldfail "" }
@@ -17,7 +17,8 @@
! { dg-output "CheCKpOInT(\n|\r\n|\r)+" }
-! { dg-output "ERROR STOP 35(\n|\r\n|\r)+" }
+! See 'error_stop-2-nvptx.f' regarding the nvptx offloading XFAIL.
+! { dg-output "ERROR STOP 35(\n|\r\n|\r)+" { xfail openacc_nvidia_accel_selected } }
!
! In gfortran's main program, libfortran's set_options is called - which sets
! compiler_options.backtrace = 1 by default. For an offload libgfortran, this
@@ -1,11 +1,37 @@
! Ensure that write on the offload device works, nvptx offloading variant.
-! This doesn't compile: for nvptx offloading we're using a minimal libgfortran
-! configuration.
-! { dg-do link } ! ..., but still apply 'dg-do run' options.
-! { dg-xfail-if "minimal libgfortran" { offload_target_nvptx } }
+! { dg-do run { target openacc_nvidia_accel_selected } }
+! { dg-output "The answer is 42(\n|\r\n|\r)+" }
+!
+! The PTX JIT doesn't understand the 'write' call graph, and therefore:
+! warning : Stack size for entry function 'main$_omp_fn$0' cannot be statically determined
+! Running with default 1024-bytes GPU thread stack size overflows the stack,
+! so raise it to an arbitrarily higher value:
+! { dg-set-target-env-var GOMP_NVPTX_NATIVE_GPU_THREAD_STACK_SIZE 3333 }
-! Skip duplicated testing.
-! { dg-skip-if "separate file" { ! offload_target_nvptx } }
+! { dg-additional-options "-fopt-info-note-omp" }
+! { dg-additional-options "-foffload=-fopt-info-note-omp" }
-include 'print-1.f90'
+! { dg-additional-options "--param=openacc-privatization=noisy" }
+! { dg-additional-options "-foffload=--param=openacc-privatization=noisy" }
+! Prune a few: uninteresting, and potentially varying depending on GCC configuration (data types):
+! { dg-prune-output {note: variable 'D\.[0-9]+' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} } */
+
+! It's only with Tcl 8.5 (released in 2007) that "the variable 'varName'
+! passed to 'incr' may be unset, and in that case, it will be set to [...]",
+! so to maintain compatibility with earlier Tcl releases, we manually
+! initialize counter variables:
+! { dg-line l_dummy[variable c_compute 0] }
+! { dg-message dummy {} { target iN-VAl-Id } l_dummy } to avoid
+! "WARNING: dg-line var l_dummy defined, but not used".
+
+program main
+ implicit none
+ integer :: var = 42
+
+!$acc parallel ! { dg-line l_compute[incr c_compute] }
+ ! { dg-note {variable 'dt_parm\.[0-9]+' declared in block isn't candidate for adjusting OpenACC privatization level: artificial} {} { target *-*-* } l_compute$c_compute }
+ write (0, '("The answer is ", I2)') var
+!$acc end parallel
+
+end program main
@@ -3,8 +3,8 @@
! { dg-do run }
! { dg-output "The answer is 42(\n|\r\n|\r)+" }
-! Separate file 'print-1-nvptx.f90' for nvptx offloading.
-! { dg-skip-if "separate file" { offload_target_nvptx } }
+! See 'print-1-nvptx.f90' regarding the nvptx offloading XFAIL.
+! { dg-xfail-run-if TODO { openacc_nvidia_accel_selected } }
! { dg-additional-options "-fopt-info-note-omp" }
! { dg-additional-options "-foffload=-fopt-info-note-omp" }
new file mode 100644
@@ -0,0 +1,36 @@
+! 'stop-2.f' nvptx offloading variant
+
+! { dg-do run { target openacc_nvidia_accel_selected } }
+!
+! The PTX JIT doesn't understand the 'STOP' call graph, and therefore:
+! warning : Stack size for entry function 'main$_omp_fn$0' cannot be statically determined
+! Running with default 1024-bytes GPU thread stack size overflows the stack,
+! so raise it to an arbitrarily higher value:
+! { dg-set-target-env-var GOMP_NVPTX_NATIVE_GPU_THREAD_STACK_SIZE 3333 }
+
+ PROGRAM MAIN
+ IMPLICIT NONE
+
+! Initialize before the checkpoint, in case this produces any output.
+!$ACC PARALLEL
+!$ACC END PARALLEL
+
+ PRINT *, "CheCKpOInT"
+!$ACC PARALLEL
+ STOP 35
+!$ACC END PARALLEL
+ PRINT *, "WrONg WAy"
+
+ END PROGRAM MAIN
+
+! { dg-output "CheCKpOInT(\n|\r\n|\r)+" }
+
+! { dg-output "STOP 35(\n|\r\n|\r)+" }
+!
+! PR85463. The 'exit' implementation used with nvptx
+! offloading is a little bit different.
+! { dg-output "libgomp: cuStreamSynchronize error.*" { target openacc_nvidia_accel_selected } }
+
+! { dg-output "$" }
+
+! { dg-shouldfail "" }
@@ -17,7 +17,8 @@
! { dg-output "CheCKpOInT(\n|\r\n|\r)+" }
-! { dg-output "STOP 35(\n|\r\n|\r)+" }
+! See 'stop-2-nvptx.f' regarding the nvptx offloading XFAIL.
+! { dg-output "STOP 35(\n|\r\n|\r)+" { xfail openacc_nvidia_accel_selected } }
!
! PR85463. The 'exit' implementation used with nvptx
! offloading is a little bit different.
--
2.34.1