[nvptx] Add -mptx=3.1/6.3

Add nvptx option -mptx that sets the ptx ISA version.  This is currently
hardcoded to 3.1.

Tested libgomp on x86_64-linux with nvptx accelerator, both with default set to
3.1 and 6.3.

gcc/ChangeLog:

2021-05-12  Tom de Vries  <tdevries@suse.de>

	PR target/96005
	* config/nvptx/nvptx-opts.h (enum ptx_version): New enum.
	* config/nvptx/nvptx.c (nvptx_file_start): Print .version according
	to ptx_version_option.
	* config/nvptx/nvptx.h (TARGET_PTX_6_3): Define.
	* config/nvptx/nvptx.md (define_insn "nvptx_shuffle<mode>")
	(define_insn "nvptx_vote_ballot"): Use sync variant for
	TARGET_PTX_6_3.
	* config/nvptx/nvptx.opt (ptx_version): Add enum.
	(mptx): Add option.
	* doc/invoke.texi (Nvidia PTX Options): Add mptx item.

6 files changed, 44 insertions, 3 deletions

diff --git a/gcc/config/nvptx/nvptx-opts.h b/gcc/config/nvptx/nvptx-opts.h
index ce88245..bfa926e 100644
--- a/gcc/config/nvptx/nvptx-opts.h
+++ b/gcc/config/nvptx/nvptx-opts.h
@@ -26,5 +26,11 @@ enum ptx_isa
   PTX_ISA_SM35
 };
 
+enum ptx_version
+{
+  PTX_VERSION_3_1,
+  PTX_VERSION_6_3
+};
+
 #endif
 
diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 7a7a913..ebbfa92 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -5309,7 +5309,10 @@ static void
 nvptx_file_start (void)
 {
   fputs ("// BEGIN PREAMBLE\n", asm_out_file);
-  fputs ("\t.version\t3.1\n", asm_out_file);
+  if (TARGET_PTX_6_3)
+    fputs ("\t.version\t6.3\n", asm_out_file);
+  else
+    fputs ("\t.version\t3.1\n", asm_out_file);
   if (TARGET_SM35)
     fputs ("\t.target\tsm_35\n", asm_out_file);
   else
diff --git a/gcc/config/nvptx/nvptx.h b/gcc/config/nvptx/nvptx.h
index 2451703..fdaacdd 100644
--- a/gcc/config/nvptx/nvptx.h
+++ b/gcc/config/nvptx/nvptx.h
@@ -98,6 +98,8 @@
 
 #define TARGET_SM35 (ptx_isa_option >= PTX_ISA_SM35)
 
+#define TARGET_PTX_6_3 (ptx_version_option >= PTX_VERSION_6_3)
+
 /* Registers.  Since ptx is a virtual target, we just define a few
    hard registers for special purposes and leave pseudos unallocated.
    We have to have some available hard registers, to keep gcc setup
diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index 0f15609..00bb8fe 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -1452,14 +1452,24 @@
 		 (match_operand:SI 3 "const_int_operand" "n")]
 		  UNSPEC_SHUFFLE))]
   ""
-  "%.\\tshfl%S3.b32\\t%0, %1, %2, 31;")
+  {
+    if (TARGET_PTX_6_3)
+      return "%.\\tshfl.sync%S3.b32\\t%0, %1, %2, 31, 0xffffffff;";
+    else
+      return "%.\\tshfl%S3.b32\\t%0, %1, %2, 31;";
+  })
 
 (define_insn "nvptx_vote_ballot"
   [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
 	(unspec:SI [(match_operand:BI 1 "nvptx_register_operand" "R")]
 		   UNSPEC_VOTE_BALLOT))]
   ""
-  "%.\\tvote.ballot.b32\\t%0, %1;")
+  {
+    if (TARGET_PTX_6_3)
+      return "%.\\tvote.sync.ballot.b32\\t%0, %1, 0xffffffff;";
+    else
+      return "%.\\tvote.ballot.b32\\t%0, %1;";
+  })
 
 ;; Patterns for OpenMP SIMD-via-SIMT lowering
 
diff --git a/gcc/config/nvptx/nvptx.opt b/gcc/config/nvptx/nvptx.opt
index 51363e4..468c6ca 100644
--- a/gcc/config/nvptx/nvptx.opt
+++ b/gcc/config/nvptx/nvptx.opt
@@ -65,3 +65,17 @@ Enum(ptx_isa) String(sm_35) Value(PTX_ISA_SM35)
 misa=
 Target RejectNegative ToLower Joined Enum(ptx_isa) Var(ptx_isa_option) Init(PTX_ISA_SM35)
 Specify the version of the ptx ISA to use.
+
+Enum
+Name(ptx_version) Type(int)
+Known PTX versions (for use with the -mptx= option):
+
+EnumValue
+Enum(ptx_version) String(3.1) Value(PTX_VERSION_3_1)
+
+EnumValue
+Enum(ptx_version) String(6.3) Value(PTX_VERSION_6_3)
+
+mptx=
+Target RejectNegative ToLower Joined Enum(ptx_version) Var(ptx_version_option) Init(PTX_VERSION_3_1)
+Specify the version of the ptx version to use.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index fddaa8c..5198815 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -26284,6 +26284,12 @@ Generate code for given the specified PTX ISA (e.g.@: @samp{sm_35}).  ISA
 strings must be lower-case.  Valid ISA strings include @samp{sm_30} and
 @samp{sm_35}.  The default ISA is sm_35.
 
+@item -mptx=@var{version-string}
+@opindex mptx
+Generate code for given the specified PTX version (e.g.@: @samp{6.3}).
+Valid version strings include @samp{3.1} and @samp{6.3}.  The default PTX
+version is 3.1.
+
 @item -mmainkernel
 @opindex mmainkernel
 Link in code for a __main kernel.  This is for stand-alone instead of