radv: Only use 32 KiB per threadgroup on Stoney.

Causes hangs on some machines.

What works for dEQP-VK.tessellation.shader_input_output.barrier:

- running num_patches = 6 (which limits LDS to 32 KiB)
- running num_patches = 8, and artificially cutting LDS size at 32 KiB.

CC: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
(cherry picked from commit 76b12fa5)