[Mlir-commits] [mlir] [mlir] [memref] Compile-time memref.alloc Scheduling/Merging optimization (PR #95882)

[Matthias Springer]

================
@@ -0,0 +1,465 @@
+# Compile-time memref.alloc Scheduling and Merging
+
+This document describes a compile-time optimization on `memref.alloc` to reduce
+memory usage and improve memory locality.
+
+## Current status of bufferization and memref pass pipeline
+Bufferization is a process in the current MLIR of converting ops with tensor
+semantics to ops with memref semantics. One-Shot Bufferize is a new tensor
+bufferization pass designed for IR in destination-passing style, and with
+aggressive in-place bufferization. The older/partial bufferization was built
+around multiple dialects. The community is trying to gradually deprecate the
+older bufferization and replace them with one-shot bufferization. The goal of
+bufferization is to use as little memory as possible and copy as little memory
+as possible, as a result, the exsiting focus is to determine in-place or
----------------
matthias-springer wrote:

`existing`

https://github.com/llvm/llvm-project/pull/95882