Our swizzle lowering optimizations depend on replication of scalar fp16. This
holds on Bifrost (at least for now), but not on Valhall which has proper support
for write masks. For now, enforce Bifrost-compatible behaviour as we do not make
use of the write masks on Valhall yet.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15793>
ins->op = BI_OPCODE_MOV_I32;
ins->src[0].swizzle = BI_SWIZZLE_H01;
}
+
+ /* The above passes rely on replicating destinations. For
+ * Valhall, we will want to optimize this. For now, default
+ * to Bifrost compatible behaviour.
+ */
+ ins->dest[0].swizzle = BI_SWIZZLE_H01;
}
free(replicates_16);