Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding"

    Two issues identified by buildbots were addressed:
    - The pass no longer forwards COPYs to physical register uses, since
      doing so can break code that implicitly relies on the physical
      register number of the use.
    - The pass no longer forwards COPYs to undef uses, since doing so
      can break the machine verifier by creating LiveRanges that don't
      end on a use (since the undef operand is not considered a use).

    [MachineCopyPropagation] Extend pass to do COPY source forwarding

    This change extends MachineCopyPropagation to do COPY source forwarding.

    This change also extends the MachineCopyPropagation pass to be able to
    be run during register allocation, after physical registers have been
    assigned, but before the virtual registers have been re-written, which
    allows it to remove virtual register COPY LiveIntervals that become dead
    through the forwarding of all of their uses.

    Reviewers: qcolombet, javed.absar, MatzeB, jonpa

    Subscribers: jyknight, nemanjai, llvm-commits, nhaehnle, mcrosier, mgorny

    Differential Revision: https://reviews.llvm.org/D30751

llvm-svn: 311135

1 files changed, 8 insertions, 8 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/ret.ll b/llvm/test/CodeGen/AMDGPU/ret.ll
index 831c71dff79..2d673a9b0cd 100644
--- a/llvm/test/CodeGen/AMDGPU/ret.ll
+++ b/llvm/test/CodeGen/AMDGPU/ret.ll
@@ -2,10 +2,10 @@
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}vgpr:
-; GCN: v_mov_b32_e32 v1, v0
-; GCN-DAG: v_add_f32_e32 v0, 1.0, v1
-; GCN-DAG: exp mrt0 v1, v1, v1, v1 done vm
+; GCN-DAG: v_mov_b32_e32 v1, v0
+; GCN-DAG: exp mrt0 v0, v0, v0, v0 done vm
 ; GCN: s_waitcnt expcnt(0)
+; GCN: v_add_f32_e32 v0, 1.0, v0
 ; GCN-NOT: s_endpgm
 define amdgpu_vs { float, float } @vgpr([9 x <16 x i8>] addrspace(2)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 {
 bb:
@@ -204,13 +204,13 @@ bb:
 }
 
 ; GCN-LABEL: {{^}}both:
-; GCN: v_mov_b32_e32 v1, v0
-; GCN-DAG: exp mrt0 v1, v1, v1, v1 done vm
-; GCN-DAG: v_add_f32_e32 v0, 1.0, v1
-; GCN-DAG: s_add_i32 s0, s3, 2
+; GCN-DAG: exp mrt0 v0, v0, v0, v0 done vm
+; GCN-DAG: v_mov_b32_e32 v1, v0
 ; GCN-DAG: s_mov_b32 s1, s2
-; GCN: s_mov_b32 s2, s3
 ; GCN: s_waitcnt expcnt(0)
+; GCN: v_add_f32_e32 v0, 1.0, v0
+; GCN-DAG: s_add_i32 s0, s3, 2
+; GCN-DAG: s_mov_b32 s2, s3
 ; GCN-NOT: s_endpgm
 define amdgpu_vs { float, i32, float, i32, i32 } @both([9 x <16 x i8>] addrspace(2)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 {
 bb: