wpan11nv commented on a change in pull request #5226: [CODEGEN][CUDA] Fix vector load URL: https://github.com/apache/incubator-tvm/pull/5226#discussion_r404948586
########## File path: src/target/source/codegen_cuda.cc ########## @@ -591,13 +591,17 @@ void CodeGenCUDA::VisitExpr_(const RampNode* op, std::ostream& os) { } void CodeGenCUDA::VisitExpr_(const BroadcastNode* op, std::ostream& os) { // NOLINT(*) - if (op->dtype.is_int() && op->dtype.bits() == 8 && op->lanes == 4) { + if ((op->dtype.is_int() || op->dtype.is_uint()) && op->dtype.bits() == 8 && op->lanes == 4) { // make_int8x4 const int64_t *p = as_const_int(op->value); CHECK(p); int64_t v = *p & 0xFF; v = (v << 24) | (v << 16) | (v << 8) | v; - os << "(int)" << v; + if (op->dtype.is_uint()) { Review comment: why do we care the signedness? this just downcasts to 32 bits,. ---------------------------------------------------------------- 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 With regards, Apache Git Services