Thanks! Sorry for the late reply. I haven't found the workload that slow down the current kernel yet:). What's more, I notice that [AutoTIR](https://github.com/apache/tvm/issues/8473) has been merged to main recently. Since I haven't found the doc for it, I'm curious about its function. And to be specific, is there any optimization for the hand-written kernels?
--- [Visit Topic](https://discuss.tvm.apache.org/t/sparse-opencl-error-scheduling-sparse-computations-that-use-tir-ir-builder/8585/10) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/88805fec8f15bdbc5005b28112b9a6c2f4f1a6f710b54141e93fd72998991396).
