diff options
| author | Rob Suderman <rob.suderman@gmail.com> | 2021-03-19 23:04:39 -0700 |
|---|---|---|
| committer | Rob Suderman <rob.suderman@gmail.com> | 2021-03-22 11:01:35 -0700 |
| commit | d7c44a5c7870f4866f2e0e82c3297ffb7a800013 (patch) | |
| tree | 41e73b44a10a8d9e8e2637491dc696d1164f5ceb /lldb/source/Plugins/ScriptInterpreter/Python/ScriptedProcessPythonInterface.cpp | |
| parent | 5727df2714985f53b2794e9672865554612cc155 (diff) | |
[mlir][tosa] Fix tosa.mul to use tosa.apply_scale
Multiply-shift requires wider compute types or CPU specific code to avoid
premature truncation, apply_shift fixes this issue
Also, Tosa's mul op supports different input / output types. Added path that
sign-extends input values to int-32 values before multiplying.
Differential Revision: https://reviews.llvm.org/D99011
Diffstat (limited to 'lldb/source/Plugins/ScriptInterpreter/Python/ScriptedProcessPythonInterface.cpp')
0 files changed, 0 insertions, 0 deletions