t-vi commented on a change in pull request #5752:
URL: https://github.com/apache/incubator-tvm/pull/5752#discussion_r437993129
##########
File path: topi/python/topi/cuda/batch_matmul.py
##########
@@ -51,55 +62,73 @@ def _schedule(op):
C = s.outputs[0].output(0)
b, y, x = s[C].op.axis
- y_bn = get_max_power2_factor(M, 64)
- x_bn = get_max_power2_factor(N, 64)
- by, y = s[C].split(y, y_bn)
- bx, x = s[C].split(x, x_bn)
- y_nthreads = min(y_bn, 8)
- x_nthreads = min(x_bn, 8)
- ty, yi = s[C].split(y, nparts=y_nthreads)
- tx, xi = s[C].split(x, nparts=x_nthreads)
- thread_x = te.thread_axis((0, x_nthreads), "threadIdx.x")
- thread_y = te.thread_axis((0, y_nthreads), "threadIdx.y")
+
+ cfg.define_split("tile_y", y, num_outputs=3)
+ cfg.define_split("tile_x", x, num_outputs=3)
+ cfg.define_knob("auto_unroll_max_step", [8, 16, 32, 64])
+ target = tvm.target.Target.current()
+ if target.target_name in ['nvptx', 'rocm']:
+ # llvm-based backends cannot do non-explicit unrolling
+ cfg.define_knob("unroll_explicit", [1])
+ else:
+ cfg.define_knob("unroll_explicit", [0, 1])
+
+ if cfg.is_fallback:
Review comment:
What else can I do to make it prettier?
----------------------------------------------------------------
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
