| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2025-08-27 | [mlir][amx] Direct AMX data transfers (#154114) | Adam Siemieniuk | |
| Extends Vector to AMX conversion to attempt populating AMX tiles directly from memory. When possible, contraction producers and consumers are replaced by AMX tile data transfer operations. This shortens data path by skipping intermediate register loads and stores. | |||
| 2025-08-13 | [mlir][amx] Vector to AMX conversion pass (#151121) | Adam Siemieniuk | |
| Adds a pass for Vector to AMX operation conversion. Initially, a direct rewrite for vector contraction in packed VNNI layout is supported. Operations are expected to already be in shapes which are AMX-compatible for the rewriting to occur. | |||
 |
index : llvm-project.git | |
| Unnamed repository; edit this file 'description' to name the repository. | thomasg |
| summaryrefslogtreecommitdiff |