[clang] [NVPTX] Add support for maxclusterrank in launch_bounds (PR #66496)

Jakub Chlanda via cfe-commits cfe-commits at lists.llvm.org
Fri Sep 22 03:05:55 PDT 2023


================
@@ -537,59 +537,46 @@ void NVPTXAsmPrinter::emitKernelFunctionDirectives(const Function &F,
                                                    raw_ostream &O) const {
   // If the NVVM IR has some of reqntid* specified, then output
   // the reqntid directive, and set the unspecified ones to 1.
-  // If none of reqntid* is specified, don't output reqntid directive.
-  unsigned reqntidx, reqntidy, reqntidz;
-  bool specified = false;
-  if (!getReqNTIDx(F, reqntidx))
-    reqntidx = 1;
-  else
-    specified = true;
-  if (!getReqNTIDy(F, reqntidy))
-    reqntidy = 1;
-  else
-    specified = true;
-  if (!getReqNTIDz(F, reqntidz))
-    reqntidz = 1;
-  else
-    specified = true;
-
-  if (specified)
-    O << ".reqntid " << reqntidx << ", " << reqntidy << ", " << reqntidz
+  // If none of Reqntid* is specified, don't output reqntid directive.
+  unsigned Reqntidx, Reqntidy, Reqntidz;
+  Reqntidx = Reqntidy = Reqntidz = 1;
+  bool ReqSpecified = false;
+  ReqSpecified |= getReqNTIDx(F, Reqntidx);
+  ReqSpecified |= getReqNTIDy(F, Reqntidy);
+  ReqSpecified |= getReqNTIDz(F, Reqntidz);
+
+  if (ReqSpecified)
+    O << ".reqntid " << Reqntidx << ", " << Reqntidy << ", " << Reqntidz
       << "\n";
 
   // If the NVVM IR has some of maxntid* specified, then output
   // the maxntid directive, and set the unspecified ones to 1.
   // If none of maxntid* is specified, don't output maxntid directive.
-  unsigned maxntidx, maxntidy, maxntidz;
-  specified = false;
-  if (!getMaxNTIDx(F, maxntidx))
-    maxntidx = 1;
-  else
-    specified = true;
-  if (!getMaxNTIDy(F, maxntidy))
-    maxntidy = 1;
-  else
-    specified = true;
-  if (!getMaxNTIDz(F, maxntidz))
-    maxntidz = 1;
-  else
-    specified = true;
-
-  if (specified)
-    O << ".maxntid " << maxntidx << ", " << maxntidy << ", " << maxntidz
+  unsigned Maxntidx, Maxntidy, Maxntidz;
+  Maxntidx = Maxntidy = Maxntidz = 1;
+  bool MaxSpecified = false;
+  MaxSpecified |= getMaxNTIDx(F, Maxntidx);
+  MaxSpecified |= getMaxNTIDy(F, Maxntidy);
+  MaxSpecified |= getMaxNTIDz(F, Maxntidz);
+
+  if (MaxSpecified)
+    O << ".maxntid " << Maxntidx << ", " << Maxntidy << ", " << Maxntidz
       << "\n";
 
-  unsigned mincta;
-  if (getMinCTASm(F, mincta))
-    O << ".minnctapersm " << mincta << "\n";
+  unsigned Mincta = 0;
+  if (getMinCTASm(F, Mincta))
+    O << ".minnctapersm " << Mincta << "\n";
 
-  unsigned maxnreg;
-  if (getMaxNReg(F, maxnreg))
-    O << ".maxnreg " << maxnreg << "\n";
+  unsigned Maxnreg = 0;
+  if (getMaxNReg(F, Maxnreg))
+    O << ".maxnreg " << Maxnreg << "\n";
+
+  unsigned Maxclusterrank = 0;
----------------
jchlanda wrote:

You are right, `ptxas` reacts to a sample with `.maxclusterrank` with pre SM_90 with a hard error:
```
ptxas --gpu-name sm_75 --output-file cluster_rank.o cluster_rank.s

ptxas cluster_rank.s, line 18; error   : Feature '.maxclusterrank' requires .target sm_90 or higher
ptxas fatal   : Ptx assembly aborted due to errors
```

Do I understand you right, that you'd like to see a [check similar to what we do in SemaDeclAttr](https://github.com/llvm/llvm-project/pull/66496/files#diff-2a5bdb2d9f07f8d77de51d5403d349c22978141b6de6bd87fc5e449f5ed95becR5683) and filter out the directive on targets < SM_90?

https://github.com/llvm/llvm-project/pull/66496


More information about the cfe-commits mailing list