wpan11nv commented on issue #4983: [CodeGen][CUDA] Enhance CUDA codegen for SelectNode URL: https://github.com/apache/incubator-tvm/pull/4983#issuecomment-594786914 The test fails without this patch. It is also exposed by https://github.com/apache/incubator-tvm/pull/4968, in which a simple kernel fails during the CUDA codegen // attr [iter_var(blockIdx.x, , blockIdx.x)] thread_extent = 98 // attr [iter_var(threadIdx.x, , threadIdx.x)] thread_extent = 1024 T_relu[ramp(((blockIdx.x*2048) + (threadIdx.x*2)), 1, 2)] = max((placeholder[ramp(((blockIdx.x*2048) + (threadIdx.x*2)), 1, 2)] + placeholder[**floordiv(ramp(((blockIdx.x*2048) + (threadIdx.x*2)), 1, 2), x2(3136))**]), x2(0f))
---------------------------------------------------------------- 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