Orion34C commented on a change in pull request #4546: [CODEGEN] Support cuda
tensorcore subbyte int data type in auto tensorcore
URL: https://github.com/apache/incubator-tvm/pull/4546#discussion_r381993872
##########
File path: include/tvm/runtime/data_type.h
##########
@@ -231,7 +231,15 @@ inline int GetVectorBytes(DataType dtype) {
int data_bits = dtype.bits() * dtype.lanes();
// allow bool to exist
if (dtype == DataType::Bool()) return 1;
- return data_bits;
+ // allow int4/uint4/int1 to exist
+ if (dtype == DataType::Int(4) ||
+ dtype == DataType::UInt(4) ||
+ dtype == DataType::Int(1)) {
+ return data_bits;
Review comment:
Sorry, this is a mistake when merge code to latest code base, for
int1/int4/uint4 1 is a more appropriate return value. I already fix it in my
latest commit.
----------------------------------------------------------------
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
