wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416246643



##########
File path: src/target/source/codegen_cuda.cc
##########
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
   static const char access[] = {'x', 'y', 'z', 'w'};
   CHECK(i >= 0 && i < (t.is_float16() ? 8 : 4));
   if ((t.is_int()) && t.bits() == 8) {
-    os << "((char)(" << vec << " >> " << i * 8 << "))";
+    if (t.lanes() == 1) {
+      os << vec;
+    } else if (t.lanes() == 2) {
+      os << vec << "." << access[i % 2];
+    } else {
+      os << "((char)(" << vec << " >> " << i * 8 << "))";
+    }
   } else if ((t.is_uint()) && t.bits() == 8) {
-    os << "((unsigned char)(" << vec << " >> " << i * 8 << "))";
+    if (t.lanes() == 1) {

Review comment:
       It should look like:
   
   if lane == 1:
     return vec
   else {
     stored as int and extracted with bit ops. 
   } 




----------------------------------------------------------------
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:
us...@infra.apache.org


Reply via email to