Skip to content

Adapt ifdefs to generic architectures #471

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
Jun 11, 2025
Merged

Adapt ifdefs to generic architectures #471

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 2 additions & 8 deletions library/src/level2/csrmv_device.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -497,10 +497,7 @@ namespace rocsparse
// To force the compiler to stick to the order of operations, we need acquire/release fences.
// Workgroup scope is sufficient for this purpose, to only invalidate L1 and avoid L2
// invalidations.
#if defined(__gfx1200__) || defined(__gfx1201__)
#define __gfx12__
#endif
#if defined(__gfx12__)
#if defined(__GFX12__)
__threadfence();
#else
__builtin_amdgcn_fence(__ATOMIC_RELEASE, "workgroup");
Expand Down Expand Up @@ -1047,10 +1044,7 @@ namespace rocsparse
// To force the compiler to stick to the order of operations, we need acquire/release fences.
// Workgroup scope is sufficient for this purpose, to only invalidate L1 and avoid L2
// invalidations.
#if defined(__gfx1200__) || defined(__gfx1201__)
#define __gfx12__
#endif
#if defined(__gfx12__)
#if defined(__GFX12__)
__threadfence();
#else
__builtin_amdgcn_fence(__ATOMIC_RELEASE, "workgroup");
Expand Down