[PATCH] D32356: AMDGPU: Fix S_PACK_HH_B32_B16

[Konstantin Zhuravlyov via Phabricator via llvm-commits]

kzhuravl created this revision.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng.

We really ought to zero out lower 16 bits


https://reviews.llvm.org/D32356

Files:
  lib/Target/AMDGPU/SIInstrInfo.cpp
  test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll


Index: test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
===================================================================
--- test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
+++ test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
@@ -216,7 +216,7 @@
 ; CIVI-DAG: v_and_b32_e32 [[ELT1:v[0-9]+]], 0xffff0000, [[VEC]]
 ; CIVI: v_or_b32_e32 [[RES:v[0-9]+]], [[ELT0_SHIFT]], [[ELT1]]
 
-; GFX9-DAG: v_mov_b32_e32 [[MASK:v[0-9]+]], 0xffff{{$}}
+; GFX9-DAG: v_mov_b32_e32 [[MASK:v[0-9]+]], 0xffff0000{{$}}
 ; GFX9-DAG: v_lshrrev_b32_e64 [[ELT0_SHIFT:v[0-9]+]], 16, [[ELT0]]
 ; GFX9: v_and_or_b32 [[RES:v[0-9]+]], [[VEC]], [[MASK]], [[ELT0_SHIFT]]
 
Index: lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.cpp
+++ lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -3595,7 +3595,7 @@
       .addImm(16)
       .add(Src0);
     BuildMI(*MBB, Inst, DL, get(AMDGPU::V_MOV_B32_e32), ImmReg)
-      .addImm(0xffff);
+      .addImm(0xffff0000);
     BuildMI(*MBB, Inst, DL, get(AMDGPU::V_AND_OR_B32), ResultReg)
       .add(Src1)
       .addReg(ImmReg, RegState::Kill)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D32356.96156.patch
Type: text/x-patch
Size: 1122 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170421/6ef484ac/attachment.bin>