423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-11-04 18:02:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

CUB usage fix for sample_farthest_points

Browse Source 
Summary: Fix for https://github.com/facebookresearch/pytorch3d/issues/1529

Reviewed By: shapovalov

Differential Revision: D45569211

fbshipit-source-id: 8c485f26cd409cafac53d4d982a03cde81a1d853
This commit is contained in:
Jeremy Reizenstein 2023-05-05 05:59:14 -07:00 committed by Facebook GitHub Bot
parent c8d6cd427e
commit b921efae3e
1 changed files with 1 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
pytorch3d/csrc/sample_farthest_points/sample_farthest_points.cu
View File

@ -155,7 +155,7 @@ at::Tensor FarthestPointSamplingCuda(
// Max possible threads per block
const int MAX_THREADS_PER_BLOCK = 1024;
const size_t threads = max(min(1 << points_pow_2, MAX_THREADS_PER_BLOCK), 1);
const size_t threads = max(min(1 << points_pow_2, MAX_THREADS_PER_BLOCK), 2);
// Create the accessors
auto points_a = points.packed_accessor64<float, 3, at::RestrictPtrTraits>();
@ -215,10 +215,6 @@ at::Tensor FarthestPointSamplingCuda(
FarthestPointSamplingKernel<2><<<threads, threads, shared_mem, stream>>>(
points_a, lengths_a, K_a, idxs_a, min_point_dist_a, start_idxs_a);
break;
case 1:
FarthestPointSamplingKernel<1><<<threads, threads, shared_mem, stream>>>(
points_a, lengths_a, K_a, idxs_a, min_point_dist_a, start_idxs_a);
break;
default:
FarthestPointSamplingKernel<1024>
<<<blocks, threads, shared_mem, stream>>>(