[nvptx] Add uniform_warp_check insn

On a GT 1030, with driver version 470.94 and -mptx=3.1 I run into:
...
FAIL: libgomp.oacc-c/../libgomp.oacc-c-c++-common/parallel-dims.c \
  -DACC_DEVICE_TYPE_nvidia=1 -DACC_MEM_SHARED=0 -foffload=nvptx-none \
  -O2 execution test
...
which minimizes to the same test-case as listed in commit "[nvptx]
Update default ptx isa to 6.3".

The problem is again that the first diverging branch is not handled as such in
SASS, which causes problems with a subsequent shfl insn, but given that we
have -mptx=3.1 we can't use the bar.warp.sync insn.

Given that the default is now -mptx=6.3, and consequently -mptx=3.1 is of a
lesser importance, implement the next best thing: abort when detecting
non-convergence using this insn:
...
  { .reg.b32 act;
    vote.ballot.b32 act,1;
    .reg.pred uni;
    setp.eq.b32 uni,act,0xffffffff;
    @ !uni trap;
    @ !uni exit;
  }
...

Interestingly, the effect of this is that rather than aborting, the test-case
now passes.

Tested on x86_64 with nvptx accelerator.

gcc/ChangeLog:

2022-01-31  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.cc (nvptx_single): Use nvptx_uniform_warp_check.
	* config/nvptx/nvptx.md (define_c_enum "unspecv"): Add
	UNSPECV_UNIFORM_WARP_CHECK.
	(define_insn "nvptx_uniform_warp_check"): New define_insn.

2 files changed, 36 insertions, 4 deletions

diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc
index 1b91990..b3bb97c 100644
--- a/gcc/config/nvptx/nvptx.cc
+++ b/gcc/config/nvptx/nvptx.cc
@@ -4631,15 +4631,29 @@ nvptx_single (unsigned mask, basic_block from, basic_block to)
 	if (tail_branch)
 	  {
 	    label_insn = emit_label_before (label, before);
-	    if (TARGET_PTX_6_0 && mode == GOMP_DIM_VECTOR)
-	      warp_sync = emit_insn_after (gen_nvptx_warpsync (), label_insn);
+	    if (mode == GOMP_DIM_VECTOR)
+	      {
+		if (TARGET_PTX_6_0)
+		  warp_sync = emit_insn_after (gen_nvptx_warpsync (),
+					       label_insn);
+		else
+		  warp_sync = emit_insn_after (gen_nvptx_uniform_warp_check (),
+					       label_insn);
+	      }
 	    before = label_insn;
 	  }
 	else
 	  {
 	    label_insn = emit_label_after (label, tail);
-	    if (TARGET_PTX_6_0 && mode == GOMP_DIM_VECTOR)
-	      warp_sync = emit_insn_after (gen_nvptx_warpsync (), label_insn);
+	    if (mode == GOMP_DIM_VECTOR)
+	      {
+		if (TARGET_PTX_6_0)
+		  warp_sync = emit_insn_after (gen_nvptx_warpsync (),
+					       label_insn);
+		else
+		  warp_sync = emit_insn_after (gen_nvptx_uniform_warp_check (),
+					       label_insn);
+	      }
 	    if ((mode == GOMP_DIM_VECTOR || mode == GOMP_DIM_WORKER)
 		&& CALL_P (tail) && find_reg_note (tail, REG_NORETURN, NULL))
 	      emit_insn_after (gen_exit (), label_insn);
diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index b4c7cd6..92768dd 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -57,6 +57,7 @@
    UNSPECV_XCHG
    UNSPECV_BARSYNC
    UNSPECV_WARPSYNC
+   UNSPECV_UNIFORM_WARP_CHECK
    UNSPECV_MEMBAR
    UNSPECV_MEMBAR_CTA
    UNSPECV_MEMBAR_GL
@@ -1985,6 +1986,23 @@
   "\\tbar.warp.sync\\t0xffffffff;"
   [(set_attr "predicable" "false")])
 
+(define_insn "nvptx_uniform_warp_check"
+  [(unspec_volatile [(const_int 0)] UNSPECV_UNIFORM_WARP_CHECK)]
+  ""
+  {
+    output_asm_insn ("{", NULL);
+    output_asm_insn ("\\t"	 ".reg.b32"	   "\\t" "act;", NULL);
+    output_asm_insn ("\\t"	 "vote.ballot.b32" "\\t" "act,1;", NULL);
+    output_asm_insn ("\\t"	 ".reg.pred"	   "\\t" "uni;", NULL);
+    output_asm_insn ("\\t"	 "setp.eq.b32"	   "\\t" "uni,act,0xffffffff;",
+		     NULL);
+    output_asm_insn ("@ !uni\\t" "trap;", NULL);
+    output_asm_insn ("@ !uni\\t" "exit;", NULL);
+    output_asm_insn ("}", NULL);
+    return "";
+  }
+  [(set_attr "predicable" "false")])
+
 (define_expand "memory_barrier"
   [(set (match_dup 0)
 	(unspec_volatile:BLK [(match_dup 0)] UNSPECV_MEMBAR))]