[PATCH] D71367: [AMDGPU] Fold 64 bit immediates

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added reviewers: arsenm, kzhuravl.
Herald added subscribers: hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely.
Herald added a project: LLVM.

64 bit operand folding did not work because these constants
are usually repsresented as a reg_sequence. Also legality checks
were partially missing and partially too restrictive. We can use
a 64 bit immediate if it can be represented by a 32 bit sign
extended integer.


https://reviews.llvm.org/D71367

Files:
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp
  llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
  llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
  llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
  llvm/test/CodeGen/AMDGPU/inline-constraints.ll
  llvm/test/CodeGen/AMDGPU/shl.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D71367.233411.patch
Type: text/x-patch
Size: 11576 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191211/b8f00105/attachment-0001.bin>