[PATCH] D74710: AMDGPU/GlobalISel: Manually select G_BUILD_VECTOR_TRUNC

[Austin Kerbow via Phabricator via llvm-commits]

kerbowa added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp:641
+
+  // With multiple uses of the shift, this will duplicate the shift and
+  // increase register pressure.
----------------
Is there a test with multiple uses of the shift?


================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-build-vector-trunc.v2s16.mir:194
     %0:sgpr(s32) = COPY $sgpr0
 
     %1:sgpr(s32) = G_IMPLICIT_DEF
----------------
Extra newlines


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74710/new/

https://reviews.llvm.org/D74710