AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
![]() The inputs are also assumed to be 32-bit quantities. This instruction operates within a single 32-bit wide SIMD lane. Multiplies together each corresponding pair of unsigned 8-bit int bytes in the two input DWORDs, and sums the results into the 32-bit unsigned integer accumulator. ![]() Shading language intrinsics Unsigned Integer Dot-Product of 4 Elements and Accumulate uint32 dot4add_u8packed(uint32 a, uint32 b, uint32 acc) // ubyte4 a, b Ī 4-dimensional unsigned integer dot-product with add. The minimum supported client for these routines is Windows 10, version 1903. Consequently, no separate capability bit check is required, beyond assuring the use of Shader Model 6.4. These intrinsics are a required/supported feature of Shader model 6.4. Describes the machine learning intrinsics added to HLSL Shader Model 6.4. ![]()
0 Comments
Read More
Leave a Reply. |