Searched refs:finalizing (Results 1 – 20 of 20) sorted by relevance
3 // RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linal…12 // RUN: -finalizing-bufferize -convert-linalg-to-loops -convert-scf-to-cf -convert-scf-to-cf \
3 // RUN: -finalizing-bufferize -buffer-deallocation \
3 // RUN: -finalizing-bufferize -buffer-deallocation -convert-linalg-to-llvm \
4 // RUN: -finalizing-bufferize -buffer-deallocation \
2 // RUN: -tensor-bufferize -func-bufferize -finalizing-bufferize -buffer-deallocation -convert-linal…
482 followed by one *finalizing* bufferization pass.498 materializations. The pass `finalizing-bufferize` provides a minimal pass that502 However, it is possible for a finalizing bufferization to do more than just504 would), it is possible for a finalizing bufferization pass to simultaneously543 that the upstream `finalizing-bufferize` pass can be used as the finalizing658 ### How to write a finalizing bufferization pass660 The contract of a finalizing bufferization pass is that all tensors are gone664 MLIR provides a pass `finalizing-bufferize` which eliminates the673 pattern, bug in the code, etc.), `finalizing-bufferize` will emit a nice clean674 error, and the IR seen by `finalizing-bufferize` will only contain only one[all …]
232 bool finalizing() const { in finalizing() function
194 DCHECK(BQ->finalizing()); in fdrIterator()196 if (BQ == nullptr || !BQ->finalizing()) { in fdrIterator()
73 if (!finalizing()) in init()
43 return BQ == nullptr || BQ->finalizing(); in finalized()
422 DCHECK(!BQ->finalizing()); in profilingLoggingInit()
1 // RUN: mlir-opt %s -finalizing-bufferize -split-input-file -verify-diagnostics | FileCheck %s
186 while (!Buffers.finalizing()) { in TEST()
8 // RUN: --tensor-bufferize --finalizing-bufferize | \
199 finalizing the implementation through the ``__xray_log_finalize()`` function.
136 def FinalizingBufferize : Pass<"finalizing-bufferize", "func::FuncOp"> {