Commit Graph

10 Commits

Author SHA1 Message Date
Chris Lattner b2f232b830 [testsuite] Make testsuite more stable vs canonicalization change. NFC.
Differential Revision: https://reviews.llvm.org/D98998
2021-03-19 18:11:12 -07:00
River Riddle d70185ec48 [mlir][IR] Support parsing hex float values in the DialectSymbolParser
This has been a TODO for a while, and prevents breakages for attributes/types that contain floats that can't roundtrip outside of the hex format.

Differential Revision: https://reviews.llvm.org/D98808
2021-03-17 13:52:32 -07:00
Alex Zinenko 40d8e4d3f9 Revert "[Canonicalizer] Process regions top-down instead of bottom up & reuse existing constants."
This reverts commit b5d9a3c923.

The commit introduced a memory error in canonicalization/operation
walking that is exposed when compiled with ASAN. It leads to crashes in
some "release" configurations.
2021-03-15 10:27:55 +01:00
Chris Lattner b5d9a3c923 [Canonicalizer] Process regions top-down instead of bottom up & reuse existing constants.
Two changes:
 1) Change the canonicalizer to walk the function in top-down order instead of
    bottom-up order.  This composes well with the "top down" nature of constant
    folding and simplification, reducing iterations and re-evaluation of ops in
    simple cases.
 2) Explicitly enter existing constants into the OperationFolder table before
    canonicalizing.  Previously we would "constant fold" them and rematerialize
    them, wastefully recreating a bunch fo constants, which lead to pointless
    memory traffic.

Both changes together provide a 33% speedup for canonicalize on some mid-size
CIRCT examples.

One artifact of this change is that the constants generated in normal pattern
application get inserted at the top of the function as the patterns are applied.
Because of this, we get "inverted" constants more often, which is an aethetic
change to the IR but does permute some testcases.

Differential Revision: https://reviews.llvm.org/D98609
2021-03-14 18:21:42 -07:00
Chris Lattner a44e630353 [AsmParser] Fix support for zero bit integer types.
Zero bit integer types are supported by IntegerType for consistency,
but the asmparser never got updated. Allow them to be parsed, as
required to fix CIRCT issue #316

Differential Revision: https://reviews.llvm.org/D93089
2020-12-12 21:24:18 -08:00
Tei Jeong 760063267c Fix CalibratedQuantizedType's print function to match parser
Reviewed By: liufengdb

Differential Revision: https://reviews.llvm.org/D92034
2020-11-24 09:35:35 -08:00
Tei Jeong 94e4ec6499 Add CalibratedQuantizedType to quant dialect
This type supports a calibrated type with min, max provided.

This will be used for importing calibration values of intermediate tensors (e.g. LSTM) which can't be imported with QuantStats op.

This type was initially suggested in the following RFC: https://llvm.discourse.group/t/rfc-a-proposal-for-implementing-quantization-transformations-in-mlir/655

Reviewed By: stellaraccident

Differential Revision: https://reviews.llvm.org/D91584
2020-11-17 22:14:54 -08:00
Mehdi Amini 95371ce9c2 Enable FileCheck -enable-var-scope by default in MLIR test
This option avoids to accidentally reuse variable across -LABEL match,
it can be explicitly opted-in by prefixing the variable name with $

Differential Revision: https://reviews.llvm.org/D81531
2020-06-12 00:43:09 +00:00
Mehdi Amini bab5bcf8fd Add a flag on the context to protect against creation of operations in unregistered dialects
Differential Revision: https://reviews.llvm.org/D76903
2020-03-30 19:37:31 +00:00
Rob Suderman 363dd3f394 [mlir][NFC] Rename QuantOps to Quant
Summary:
Renamed QuantOps to Quant to avoid the Ops suffix. All dialects will contain
ops, so the Ops suffix is redundant.

Differential Revision: https://reviews.llvm.org/D76318
2020-03-17 15:16:47 -07:00