Skip to content

Pytorch3D can build and run on AMD GPUs #2022

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ZJLi2013 wants to merge 2 commits into
base: main
Choose a base branch
from
+4 −1
Open

Pytorch3D can build and run on AMD GPUs #2022

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2f7dadf
Fix float3 operator availability for AMD ROCm support
ZJLi2013 Mar 4, 2026
669eb84
Fix float3 operator ambiguity for ROCm/HIP AMD support
ZJLi2013 Mar 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion pytorch3d/csrc/pulsar/include/math.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,9 @@ IHD float3 outer_product_sum(const float3& a) {
}

// TODO: put intrinsics here.
// On ROCm/HIP, float3 is HIP_vector_type<float, 3> which already provides
// all arithmetic and compound-assignment operators as member functions.
// Defining them here too causes "ambiguous overload" errors. Skip for ROCm.
#if !defined(USE_ROCM)
IHD float3 operator+(const float3& a, const float3& b) {
return make_float3(a.x + b.x, a.y + b.y, a.z + b.z);
Expand Down Expand Up @@ -94,7 +97,7 @@ IHD float3 operator*(const float3& a, const float3& b) {
IHD float3 operator*(const float& a, const float3& b) {
return b * a;
}
#endif //! USE_ROCM
#endif // !USE_ROCM

INLINE DEVICE float length(const float3& v) {
// TODO: benchmark what's faster.
Expand Down