vinx13 commented on a change in pull request #5101: [CodeGen][CUDA]
Vectorization for intrinsics
URL: https://github.com/apache/incubator-tvm/pull/5101#discussion_r395768711
##########
File path: src/target/source/codegen_cuda.cc
##########
@@ -418,6 +419,54 @@ void CodeGenCUDA::VisitExpr_(const CallNode *op,
std::ostream& os) {
this->PrintExpr(op->args[i * 2 + 1], os);
os << "]" << ((i < 3) ? ", ": ")");
}
+ } else if (op->call_type == CallNode::PureExtern && op->dtype.is_vector()) {
+ //
+ // Emit an unsupported vector call
+ //
+ // v = intrin_f((float4*)A[0], (float4*)B[0])
Review comment:
do you mean `intrin_f(((float4*)A)[0], ((float4*)B)[0])`?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
