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: <[email protected]>
Reviewed-by: Samuel Pitoiset <[email protected]>

1 files changed, 10 insertions, 1 deletions

diff --git a/src/amd/vulkan/radv_nir_to_llvm.c b/src/amd/vulkan/radv_nir_to_llvm.c
index cd58167b766..9d0aa411528 100644
--- a/src/amd/vulkan/radv_nir_to_llvm.c
+++ b/src/amd/vulkan/radv_nir_to_llvm.c
@@ -254,7 +254,16 @@ get_tcs_num_patches(struct radv_shader_context *ctx)
 	/* Make sure that the data fits in LDS. This assumes the shaders only
 	 * use LDS for the inputs and outputs.
 	 */
-	hardware_lds_size = ctx->options->chip_class >= CIK ? 65536 : 32768;
+	hardware_lds_size = 32768;
+
+	/* Looks like STONEY hangs if we use more than 32 KiB LDS in a single
+	 * threadgroup, even though there is more than 32 KiB LDS.
+	 *
+	 * Test: dEQP-VK.tessellation.shader_input_output.barrier
+	 */
+	if (ctx->options->chip_class >= CIK && ctx->options->family != CHIP_STONEY)
+		hardware_lds_size = 65536;
+
 	num_patches = MIN2(num_patches, hardware_lds_size / (input_patch_size + output_patch_size));
 	/* Make sure the output data fits in the offchip buffer */
 	num_patches = MIN2(num_patches, (ctx->options->tess_offchip_block_dw_size * 4) / output_patch_size);