Err no, my mistake.
I will write a backport.
On 5/8/19 10:54 AM, Samuel Pitoiset wrote:
You mean 19.1?
On 5/7/19 8:29 PM, Dylan Baker wrote:
Hi Samuel,
This doesn't apply cleanly on 19.0, and I'm not sure how to resolve
the diff.
Could you provide a packport please?
Thanks,
Dylan
Quoting
You mean 19.1?
On 5/7/19 8:29 PM, Dylan Baker wrote:
Hi Samuel,
This doesn't apply cleanly on 19.0, and I'm not sure how to resolve the diff.
Could you provide a packport please?
Thanks,
Dylan
Quoting Samuel Pitoiset (2019-05-03 02:45:34)
Because the new raw/struct intrinsics are buggy with
Hi Samuel,
This doesn't apply cleanly on 19.0, and I'm not sure how to resolve the diff.
Could you provide a packport please?
Thanks,
Dylan
Quoting Samuel Pitoiset (2019-05-03 02:45:34)
> Because the new raw/struct intrinsics are buggy with LLVM 8
> (they weren't marked as source of divergence),
On Fri, May 3, 2019 at 11:42 AM Samuel Pitoiset
wrote:
>
> Because the new raw/struct intrinsics are buggy with LLVM 8
> (they weren't marked as source of divergence), we fallback to the
> old instrinsics for atomic buffer operations. This means we need
> to apply the indexing workaround for GFX9.
Because the new raw/struct intrinsics are buggy with LLVM 8
(they weren't marked as source of divergence), we fallback to the
old instrinsics for atomic buffer operations. This means we need
to apply the indexing workaround for GFX9.
The fact that we need another workaround is painful but we shoul