[PATCH] D74705: [mlir][quantizer] Support quantizing sparse tensors

[Alexey Romanov via Phabricator via llvm-commits]

alexeyr created this revision.
alexeyr added reviewers: stellaraccident, liufengdb.
alexeyr added a project: LLVM.
Herald added subscribers: llvm-commits, Joonsoo, lucyrfox, mgester, arpith-jacob, nicolasvasilache, antiagainst, shauheen, burmako, jpienaar, rriddle, mehdi_amini.
Herald added a reviewer: rriddle.

Add sparse tensors support for per-axis uniform quantization


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D74705

Files:
  mlir/include/mlir/Dialect/QuantOps/UniformSupport.h
  mlir/include/mlir/IR/StandardTypes.h
  mlir/lib/Dialect/QuantOps/Utils/UniformSupport.cpp
  mlir/lib/IR/StandardTypes.cpp
  mlir/test/Dialect/QuantOps/convert-const.mlir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D74705.244947.patch
Type: text/x-patch
Size: 12055 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200217/364821dc/attachment.bin>