You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ULP comparison support for Float16 was recently added based on the existing pattern in DXC's compareHalfULP function (see issue #81). There will likely be changes to the DXC implementation via PR #7393, which we should also update in our compareFloat16ULP implementation to maintain consistency with DXC.
Changes:
Handling +0 and -0 as equal
ULP differences are calculated with a monotonic ordering
The text was updated successfully, but these errors were encountered:
inbelic
pushed a commit
to inbelic/offload-test-suite
that referenced
this issue
May 23, 2025
Tests GetDimensions method on StructuredBuffer, RWStructuredBuffer,
AppendStructuredBuffer and ConsumeStructuredBuffer.
Test for RasterizerOrderedStructuredBuffer will need to be added later after
the offload-test-suite adds support for pixel shaders.
Closesllvm#202
ULP comparison support for Float16 was recently added based on the existing pattern in DXC's
compareHalfULP
function (see issue #81). There will likely be changes to the DXC implementation via PR #7393, which we should also update in ourcompareFloat16ULP
implementation to maintain consistency with DXC.Changes:
The text was updated successfully, but these errors were encountered: