fix(gpu): accept PTX compute target aliases

Preserve the source spelling of NVIDIA's documented compute_xx target synonym.

Fixes #6494
This commit is contained in:
morluto
2026-10-23 17:59:09 +08:00
parent 2dfcc6463b
commit f250c8cca5
3 changed files with 22 additions and 1 deletions
+2
View File
@@ -81,6 +81,8 @@ Kernel representations have different meanings:
- PTX reports parameter declarations and virtual registers. Shared bytes cover
supported static declarations inside that entry; they do not establish module
shared memory, dynamic allocation or physical device resources.
A `.target compute_xx` spelling is retained as written; NVIDIA PTX defines it
as a synonym for `.target sm_xx`.
Scalar register declarations count each bare or percent-prefixed name and
each parameterized range. Unsupported declaration forms or overflowing totals
retain an unknown count and partial decoding coverage. Unsupported parameter