nvptx: Prevent emitting duplicate declarations for '__nvptx_stacks', '__nvptx_uni'

As I have reported to Nvidia in 2022-12-01 'NVIDIA Incident Report (3891704):
ptxas: Duplicate declaration error: "cannot be resolved by a '.static'"',
'ptxas' has an inscrutable error mode for duplicate declarations:

    ptxas softstack-decl-1.o, line 11; error   : '.extern' variable '__nvptx_stacks' cannot be resolved by a '.static'
    ptxas fatal   : Ptx assembly aborted due to errors
    nvptx-as: ptxas returned 255 exit status

    ptxas uniform-simt-decl-1.o, line 12; error   : '.extern' variable '__nvptx_uni' cannot be resolved by a '.static'
    ptxas fatal   : Ptx assembly aborted due to errors
    nvptx-as: ptxas returned 255 exit status

This is inscrutable, because (a) what is "cannot be resolved by a '.static'"
supposed to tell me (there is no '.static' in PTX?), and (b) why arent't
repeated declaration just verified to match the first, but otherwise a no-op
(like in other programming languages)?

	gcc/
	* config/nvptx/nvptx.cc (nvptx_assemble_undefined_decl): Notice
	'__nvptx_stacks', '__nvptx_uni' declarations.
	(nvptx_file_end): Don't emit duplicate declarations for those.
	gcc/testsuite/
	* gcc.target/nvptx/softstack-decl-1.c: Make 'dg-do assemble',
	adjust.
	* gcc.target/nvptx/uniform-simt-decl-1.c: Likewise.

diff --git a/gcc/ChangeLog.omp b/gcc/ChangeLog.omp
index 382cd5c80c2257a7a5d0dc7032d7aebaf4de3bf4..127b450644b3536403d32cf2a4ed5eb2f1c6d2c2 100644 (file)
--- a/gcc/ChangeLog.omp
+++ b/gcc/ChangeLog.omp
@@ -1,5 +1,9 @@
 2023-01-20  Thomas Schwinge  <thomas@codesourcery.com>
 
+       * config/nvptx/nvptx.cc (nvptx_assemble_undefined_decl): Notice
+       '__nvptx_stacks', '__nvptx_uni' declarations.
+       (nvptx_file_end): Don't emit duplicate declarations for those.
+
        * config/nvptx/nvptx.md (nvptx_uniform_warp_check): Make fit for
        non-full-warp execution.
 

diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc
index da735cf82ff579d7553ac3fdadaf6c67a04ef222..9c284ed5b0105c1ff36ecf17b604d5487a6c4b2d 100644 (file)
--- a/gcc/config/nvptx/nvptx.cc
+++ b/gcc/config/nvptx/nvptx.cc
@@ -181,9 +181,11 @@ static GTY(()) tree global_lock_var;
 
 /* True if any function references __nvptx_stacks.  */
 static bool need_softstack_decl;
+static bool have_softstack_decl;
 
 /* True if any function references __nvptx_uni.  */
 static bool need_unisimt_decl;
+static bool have_unisimt_decl;
 
 static int nvptx_mach_max_workers ();
 
@@ -2572,6 +2574,13 @@ nvptx_assemble_undefined_decl (FILE *file, const char *name, const_tree decl)
                             TREE_TYPE (decl), size ? tree_to_shwi (size) : 0,
                             DECL_ALIGN (decl), true);
   nvptx_assemble_decl_end ();
+
+  static tree softstack_id = get_identifier ("__nvptx_stacks");
+  static tree unisimt_id = get_identifier ("__nvptx_uni");
+  if (DECL_NAME (decl) == softstack_id)
+    have_softstack_decl = true;
+  else if (DECL_NAME (decl) == unisimt_id)
+    have_unisimt_decl = true;
 }
 
 /* Output a pattern for a move instruction.  */
@@ -6052,7 +6061,7 @@ nvptx_file_end (void)
     write_shared_buffer (asm_out_file, gang_private_shared_sym,
                         gang_private_shared_align, gang_private_shared_size);
 
-  if (need_softstack_decl)
+  if (need_softstack_decl && !have_softstack_decl)
     {
       write_var_marker (asm_out_file, false, true, "__nvptx_stacks");
       /* 32 is the maximum number of warps in a block.  Even though it's an
@@ -6061,7 +6070,8 @@ nvptx_file_end (void)
       fprintf (asm_out_file, ".extern .shared .u%d __nvptx_stacks[32];\n",
               POINTER_SIZE);
     }
-  if (need_unisimt_decl)
+
+  if (need_unisimt_decl && !have_unisimt_decl)
     {
       write_var_marker (asm_out_file, false, true, "__nvptx_uni");
       fprintf (asm_out_file, ".extern .shared .u32 __nvptx_uni[32];\n");

diff --git a/gcc/testsuite/ChangeLog.omp b/gcc/testsuite/ChangeLog.omp
index 5b3d9fe416b35571634961a24b906cec8b9cec0a..c942c34dc70060e692e37e76b63cec0c4e1b663a 100644 (file)
--- a/gcc/testsuite/ChangeLog.omp
+++ b/gcc/testsuite/ChangeLog.omp
@@ -1,5 +1,9 @@
 2023-01-20  Thomas Schwinge  <thomas@codesourcery.com>
 
+       * gcc.target/nvptx/softstack-decl-1.c: Make 'dg-do assemble',
+       adjust.
+       * gcc.target/nvptx/uniform-simt-decl-1.c: Likewise.
+
        * gcc.target/nvptx/softstack-decl-1.c: New.
        * gcc.target/nvptx/uniform-simt-decl-1.c: Likewise.
 

diff --git a/gcc/testsuite/gcc.target/nvptx/softstack-decl-1.c b/gcc/testsuite/gcc.target/nvptx/softstack-decl-1.c
index c502eacc1b35a332412a412f1bfbafa2d8795800..2415f6adb1f92c64f5b0ef49aa50a4ed08aaee62 100644 (file)
--- a/gcc/testsuite/gcc.target/nvptx/softstack-decl-1.c
+++ b/gcc/testsuite/gcc.target/nvptx/softstack-decl-1.c
@@ -1,4 +1,4 @@
-/* { dg-do compile } */
+/* { dg-do assemble } */
 /* { dg-options {-save-temps -O0 -msoft-stack} } */
 
 extern void *__nvptx_stacks[32] __attribute__((shared,nocommon));
@@ -14,7 +14,7 @@ void *f()
   return stack_array[5];
 }
 
-/* The implicit (via 'need_softstack_decl') and explicit declarations of
-   '__nvptx_stacks' are both emitted:
-   { dg-final { scan-assembler-times {(?n)\.extern .* __nvptx_stacks\[32\];} 2 } }
+/* Of the implicit (via 'need_softstack_decl') and explicit declarations of
+   '__nvptx_stacks', only one is emitted:
+   { dg-final { scan-assembler-times {(?n)\.extern .* __nvptx_stacks\[32\];} 1 } }
 */

diff --git a/gcc/testsuite/gcc.target/nvptx/uniform-simt-decl-1.c b/gcc/testsuite/gcc.target/nvptx/uniform-simt-decl-1.c
index 486456ab243d03fa82a1e60c851c52e3c41a894c..5a975bdb269bc5827359745523b62a9ef7e11edc 100644 (file)
--- a/gcc/testsuite/gcc.target/nvptx/uniform-simt-decl-1.c
+++ b/gcc/testsuite/gcc.target/nvptx/uniform-simt-decl-1.c
@@ -1,4 +1,4 @@
-/* { dg-do compile } */
+/* { dg-do assemble } */
 /* { dg-options {-save-temps -O0 -muniform-simt} } */
 
 extern unsigned __nvptx_uni[32] __attribute__((shared,nocommon));
@@ -23,7 +23,7 @@ int f (void)
                                      MEMMODEL_RELAXED);
 }
 
-/* The implicit (via 'need_unisimt_decl') and explicit declarations of
-   '__nvptx_uni' are both emitted:
-   { dg-final { scan-assembler-times {(?n)\.extern .* __nvptx_uni\[32\];} 2 } }
+/* Of the implicit (via 'need_unisimt_decl') and explicit declarations of
+   '__nvptx_uni', only one is emitted:
+   { dg-final { scan-assembler-times {(?n)\.extern .* __nvptx_uni\[32\];} 1 } }
 */