nvptx: Support '-mfake-ptx-alloca': defer failure to run-time 'alloca' usage

Follow-up to commit 1146410c0feb0e82c689b1333fdf530a2b34dc2b
"nvptx: Support '-mfake-ptx-alloca'".  '-mfake-ptx-alloca' is applicable only
for configurations where PTX 'alloca' is not supported, where target libraries
are built with it enabled (that is, libstdc++, libgfortran).

This change progresses:

    [-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++17 (test for excess errors)
    [-UNRESOLVED:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++17 [-compilation failed to produce executable-]{+execution test+}
    [-FAIL:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++26 (test for excess errors)
    [-UNRESOLVED:-]{+PASS:+} g++.dg/tree-ssa/pr20458.C  -std=gnu++26 [-compilation failed to produce executable-]{+execution test+}
    UNSUPPORTED: g++.dg/tree-ssa/pr20458.C  -std=gnu++98: exception handling not supported

..., and "enables" a few test cases:

    FAIL: g++.old-deja/g++.other/sibcall1.C  -std=gnu++17 (test for excess errors)
    [Etc.]

    FAIL: g++.old-deja/g++.other/unchanging1.C  -std=gnu++17 (test for excess errors)
    [Etc.]

..., which now (unrelatedly to 'alloca', and in the same way as configurations
where PTX 'alloca' is supported) FAIL due to:

    unresolved symbol _Unwind_DeleteException
    collect2: error: ld returned 1 exit status

Most importantly, it progresses ~830 libstdc++ test cases:

    [-FAIL:-]{+PASS:+} [...] (test for excess errors)

..., with (if applicable, for most of them):

    [-UNRESOLVED:-]{+PASS:+} [...] [-compilation failed to produce executable-]{+execution test+}

..., or just a few 'FAIL: [...] execution test' where these test cases also
FAIL in configurations where PTX 'alloca' is supported, or ~120 instances of
'FAIL: [...]  execution test' due to run-time
'GCC/nvptx: sorry, unimplemented: dynamic stack allocation not supported'.

This change also resolves the cases noted in
commit bac2d8a246892334e24dfa7d62be0cd0648c5606
"nvptx: Build libgfortran with '-mfake-ptx-alloca' [PR107635]":

| With '-mfake-ptx-alloca', libgfortran again succeeds to build, and compared
| to before, we've got only a small number of regressions due to nvptx 'ld'
| complaining about 'unresolved symbol __GCC_nvptx__PTX_alloca_not_supported':
|
|     [-PASS:-]{+FAIL:+} gfortran.dg/coarray/codimension_2.f90 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray/codimension_2.f90 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)

|     [-PASS:-]{+FAIL:+} gfortran.dg/coarray/event_4.f08 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
|     [-PASS:-]{+UNRESOLVED:+} gfortran.dg/coarray/event_4.f08 -fcoarray=lib  -O2  -lcaf_single [-execution test-]{+compilation failed to produce executable+}

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray/event_4.f08 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
    [-UNRESOLVED:-]{+PASS:+} gfortran.dg/coarray/event_4.f08 -fcoarray=lib  -O2  -lcaf_single [-compilation failed to produce executable-]{+execution test+}

|     [-PASS:-]{+FAIL:+} gfortran.dg/coarray/fail_image_2.f08 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
|     [-PASS:-]{+UNRESOLVED:+} gfortran.dg/coarray/fail_image_2.f08 -fcoarray=lib  -O2  -lcaf_single [-execution test-]{+compilation failed to produce executable+}

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray/fail_image_2.f08 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
    [-UNRESOLVED:-]{+PASS:+} gfortran.dg/coarray/fail_image_2.f08 -fcoarray=lib  -O2  -lcaf_single [-compilation failed to produce executable-]{+execution test+}

|     [-PASS:-]{+FAIL:+} gfortran.dg/coarray/proc_pointer_assign_1.f90 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
|     [-PASS:-]{+UNRESOLVED:+} gfortran.dg/coarray/proc_pointer_assign_1.f90 -fcoarray=lib  -O2  -lcaf_single [-execution test-]{+compilation failed to produce executable+}

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray/proc_pointer_assign_1.f90 -fcoarray=lib  -O2  -lcaf_single (test for excess errors)
    [-UNRESOLVED:-]{+PASS:+} gfortran.dg/coarray/proc_pointer_assign_1.f90 -fcoarray=lib  -O2  -lcaf_single [-compilation failed to produce executable-]{+execution test+}

|     [-PASS:-]{+FAIL:+} gfortran.dg/coarray_43.f90   -O  (test for excess errors)

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray_43.f90   -O  (test for excess errors)

..., and further progresses:

    [-FAIL:-]{+PASS:+} gfortran.dg/coarray_lib_comm_1.f90   -O0  (test for excess errors)
    [-UNRESOLVED:-]{+FAIL:+} gfortran.dg/coarray_lib_comm_1.f90   -O0  [-compilation failed to produce executable-]{+execution test+}
    [Etc.]

..., which now (unrelatedly to 'alloca', and in the same way as configurations
where PTX 'alloca' is supported) FAILs due to:

    error   : Prototype doesn't match for '_gfortran_caf_transfer_between_remotes' in 'input file 9 at offset 159897', first defined in 'input file 9 at offset 159897'
    error   : Prototype doesn't match for '_gfortran_caf_stop_numeric' in 'input file 9 at offset 159897', first defined in 'input file 9 at offset 159897'
    nvptx-run: cuLinkAddData failed: device kernel image is invalid (CUDA_ERROR_INVALID_SOURCE, 300)

	gcc/
	* config/nvptx/nvptx.opt (-mfake-ptx-alloca): Update.
	gcc/testsuite/
	* gcc.target/nvptx/alloca-2-O0_-mfake-ptx-alloca.c: Adjust.
	libgcc/
	* config/nvptx/alloca.c: New.
	* config/nvptx/t-nvptx (LIB2ADD): Add it.

diff --git a/gcc/config/nvptx/nvptx.opt b/gcc/config/nvptx/nvptx.opt
index 02d36b33025bfd1b37b736b22308733389b8918e..9be81aecdddfda1b31ad3394cc31cd18fe5d33b5 100644 (file)
--- a/gcc/config/nvptx/nvptx.opt
+++ b/gcc/config/nvptx/nvptx.opt
@@ -173,12 +173,12 @@ Target Var(nvptx_fake_ptx_alloca) Init(0) Undocumented
 ; With '-mfake-ptx-alloca' enabled, the user-visible behavior changes only
 ; for configurations where PTX 'alloca' is not available.  Rather than a
 ; compile-time 'sorry, unimplemented: dynamic stack allocation not supported'
-; in presence of dynamic stack allocation, compilation and assembly then
-; succeeds.  However, attempting to link in such '*.o' files then fails due
-; to unresolved symbol '__GCC_nvptx__PTX_alloca_not_supported'.
+; in presence of dynamic stack allocation, with '-mfake-ptx-alloca' enabled,
+; compilation, assembly, and linking succeeds, as does execution, in case that
+; 'alloca' is not attempted (if only used in error code paths, for example),
+; and a run-time failure only in case that 'alloca' is actually attempted.
 ; 
 ; This is meant to be used in scenarios where large volumes of code are
 ; compiled, a small fraction of which runs into dynamic stack allocation, but
 ; these parts are not important for specific use cases, and we'd thus like the
-; build to succeed, and error out just upon actual, very rare use of the
-; offending '*.o' files.
+; build to succeed, and error out just upon actual, very rare use of 'alloca'.

diff --git a/gcc/testsuite/gcc.target/nvptx/alloca-2-O0_-mfake-ptx-alloca.c b/gcc/testsuite/gcc.target/nvptx/alloca-2-O0_-mfake-ptx-alloca.c
index 4cc4d0c93f2804a035a62206302deeede98c4c4b..92562cde4008fe7223c750144970919745d7089b 100644 (file)
--- a/gcc/testsuite/gcc.target/nvptx/alloca-2-O0_-mfake-ptx-alloca.c
+++ b/gcc/testsuite/gcc.target/nvptx/alloca-2-O0_-mfake-ptx-alloca.c
@@ -1,4 +1,4 @@
-/* { dg-do link } */
+/* { dg-do run } */
 /* { dg-options {-O0 -mno-soft-stack} } */
 /* { dg-additional-options -march=sm_30 } */
 /* { dg-additional-options -mfake-ptx-alloca } */
@@ -13,6 +13,7 @@ main(void)
 
 /* { dg-final { scan-assembler-times {(?n)^\.extern \.func \(\.param\.u64 %value_out\) __GCC_nvptx__PTX_alloca_not_supported \(\.param\.u64 %in_ar0\);$} 1 } } */
 
-/* { dg-message __GCC_nvptx__PTX_alloca_not_supported {unresolved symbol} { target *-*-* } 0 } */
+/* { dg-bogus __GCC_nvptx__PTX_alloca_not_supported {unresolved symbol} { target *-*-* } 0 } */
 
-/* { dg-final output-exists-not } */
+/* { dg-output {GCC/nvptx: sorry, unimplemented: dynamic stack allocation not supported[\r\n]+} }
+   { dg-shouldfail __GCC_nvptx__PTX_alloca_not_supported } */

diff --git a/libgcc/config/nvptx/alloca.c b/libgcc/config/nvptx/alloca.c
new file mode 100644 (file)
index 0000000..09bdeb6
--- /dev/null
+++ b/libgcc/config/nvptx/alloca.c
@@ -0,0 +1,38 @@
+/* Fake 'alloca' implementation.
+
+   Copyright (C) 2025 Free Software Foundation, Inc.
+
+   This file is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the
+   Free Software Foundation; either version 3, or (at your option) any
+   later version.
+
+   This file is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+/* For '-mfake-ptx-alloca', in case real PTX 'alloca' is not available.
+   With this function defined, we don't get a link-time failure
+   (unresolved symbol '__GCC_nvptx__PTX_alloca_not_supported'), but rather:
+   successful execution, in case that 'alloca' is not attempted (if only used
+   in error code paths, for example), and a run-time failure only in case that
+   'alloca' is actually attempted.  */
+
+void *
+__GCC_nvptx__PTX_alloca_not_supported (__SIZE_TYPE__ size __attribute__ ((unused)))
+{
+  __builtin_printf ("GCC/nvptx: sorry, unimplemented:"
+                   " dynamic stack allocation not supported\n");
+  __builtin_abort ();
+  return 0;
+}

diff --git a/libgcc/config/nvptx/t-nvptx b/libgcc/config/nvptx/t-nvptx
index f295898d69fcf0a37fc7bcbdfc1ee2ee7e1f65d3..5e2e27898fd61afcb64a7f6ea2436d4133ec6282 100644 (file)
--- a/libgcc/config/nvptx/t-nvptx
+++ b/libgcc/config/nvptx/t-nvptx
@@ -1,7 +1,8 @@
 LIB2ADD=$(srcdir)/config/nvptx/reduction.c \
        $(srcdir)/config/nvptx/mgomp.c \
        $(srcdir)/config/nvptx/atomic.c \
-       $(srcdir)/config/nvptx/unwind-nvptx.c
+       $(srcdir)/config/nvptx/unwind-nvptx.c \
+       $(srcdir)/config/nvptx/alloca.c
 
 LIB2ADDEH=
 LIB2FUNCS_EXCLUDE=