[GitHub] [incubator-tvm] wpan11nv commented on a change in pull request #5600: [TOPI] Improve CUDA softmax scheduling

[GitBox <gi...@apache.org>]

wpan11nv commented on a change in pull request #5600:
URL: https://github.com/apache/incubator-tvm/pull/5600#discussion_r434689864



##########
File path: src/target/llvm/codegen_llvm.cc
##########
@@ -736,7 +736,40 @@ llvm::Function* CodeGenLLVM::GetIntrinsicDecl(llvm::Intrinsic::ID id, llvm::Type
 #endif  // TVM_LLVM_VERSION
 }
 
+// Check if this is a warp shuffle intrinsic call and match its
+// corresponding nvvm intrinsic. Return true if the match is successful.
+static bool GetWarpShuffleIntrinsic(const CallNode* op, llvm::Intrinsic::ID* id) {
+  // Only 32 bit data type is supported.
+  if (op->dtype.is_vector() || op->dtype.bits() != 32) {

Review comment:
       Sure. I will have a look.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org