Skip to content

Fix matrix rank #74406

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

Merged
merged 1 commit into from
Aug 5, 2025
Merged

Fix matrix rank #74406

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions paddle/phi/kernels/gpu/matrix_rank_tol_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -634,8 +634,16 @@ void MatrixRankTolKernel(const Context& dev_ctx,

auto dim_x = x.dims();
auto dim_out = out->dims();
int rows = dim_x[dim_x.size() - 2];
int cols = dim_x[dim_x.size() - 1];
int64_t rows = dim_x[dim_x.size() - 2];
int64_t cols = dim_x[dim_x.size() - 1];
// cusolverDn<t>gesvdj() don't support int64_t, so we need to check it.
int64_t numel_single_batch = rows * cols;
PADDLE_ENFORCE_LE(numel_single_batch,
(1LL << 31) - 1,
common::errors::PreconditionNotMet(
"The element size of x should be <= INT_MAX(2147483647)"
", but got %lld",
numel_single_batch));

if (x.numel() == 0) {
dev_ctx.template Alloc<int64_t>(out);
Expand Down
Loading