As the GPU vendor recommend "Tell the Compiler the Work-Group Size" by
```
__attribute__((reqd_work_group_size(X,Y,Z))).
```
in OpenCL kenrel function.
I can't get the work group size in codegen, Could you share how to get the work
group size?
---
[Visit
Topic](https://discuss.tvm.ai
Now the souce code of vectorize for OpenCL looks like:
```
vstore2((vload2(0, ( half*)compute + (ff * 2)) + (vload2(0,
pad_temp_shared_local_local + 0) * ((half2)(input1_shared_local_local[0],
input1_shared_local_local[0], 0, ( half*)compute + (ff * 2));
```
but i want something like:
```
Can we write schedule for +bias.
Now "+bias" fuse into conv2d, bias is global memory, can't cache_read.
---
[Visit Topic](https://discuss.tvm.ai/t/how-to-write-schedule-for-bias/6100/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these em
