[llvm] r279804 - Replace subregister uses when processing tied operands

[Matt Arsenault via llvm-commits]

Author: arsenm
Date: Fri Aug 26 01:31:32 2016
New Revision: 279804

URL: http://llvm.org/viewvc/llvm-project?rev=279804&view=rev
Log:
Replace subregister uses when processing tied operands

This was for some reason skipping operands that are subregisters
instead of keeping the same subregister index.

v_movreld_b32 expects src0 to be the subregister of the tied
super register use/def.

e.g.

v_movreld_b32 v0, v9, <imp-def, tied3> v[0:3], <imp-use, tied2> v[0:3]

was being replaced with

v[4:7] = copy v[0:3]
v_movreld_b32 v0, v9, <imp-def, tied3> v[4:7], <imp-use, tied2> v[4:7],

which really writes to v[0:3]

Added:
    llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
Modified:
    llvm/trunk/lib/CodeGen/TwoAddressInstructionPass.cpp
    llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si.ll

Modified: llvm/trunk/lib/CodeGen/TwoAddressInstructionPass.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/TwoAddressInstructionPass.cpp?rev=279804&r1=279803&r2=279804&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/TwoAddressInstructionPass.cpp (original)
+++ llvm/trunk/lib/CodeGen/TwoAddressInstructionPass.cpp Fri Aug 26 01:31:32 2016
@@ -1567,14 +1567,14 @@ TwoAddressInstructionPass::processTiedPa
     if (!IsEarlyClobber) {
       // Replace other (un-tied) uses of regB with LastCopiedReg.
       for (MachineOperand &MO : MI->operands()) {
-        if (MO.isReg() && MO.getReg() == RegB && MO.getSubReg() == SubRegB &&
+        if (MO.isReg() && MO.getReg() == RegB &&
             MO.isUse()) {
           if (MO.isKill()) {
             MO.setIsKill(false);
             RemovedKillFlag = true;
           }
           MO.setReg(LastCopiedReg);
-          MO.setSubReg(0);
+          MO.setSubReg(MO.getSubReg());
         }
       }
     }

Added: llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll?rev=279804&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll Fri Aug 26 01:31:32 2016
@@ -0,0 +1,19 @@
+; RUN: llc -O0 -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
+
+; FIXME: Merge into indirect-addressing-si.ll
+
+; Make sure that TwoAddressInstructions keeps src0 as subregister sub0
+; of the tied implicit use and def of the super register.
+
+; CHECK-LABEL: {{^}}insert_wo_offset:
+; CHECK: s_load_dword [[IN:s[0-9]+]]
+; CHECK: s_mov_b32 m0, [[IN]]
+; CHECK: v_movreld_b32_e32 v[[ELT0:[0-9]+]]
+; CHECK-NEXT: buffer_store_dwordx4 v{{\[}}[[ELT0]]:
+define void @insert_wo_offset(<4 x float> addrspace(1)* %out, i32 %in) {
+entry:
+  %ins = insertelement <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, float 5.0, i32 %in
+  store <4 x float> %ins, <4 x float> addrspace(1)* %out
+  ret void
+}
+

Modified: llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si.ll?rev=279804&r1=279803&r2=279804&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/indirect-addressing-si.ll Fri Aug 26 01:31:32 2016
@@ -125,27 +125,32 @@ entry:
 }
 
 ; CHECK-LABEL: {{^}}insert_w_offset:
-; CHECK: s_load_dword [[IN:s[0-9]+]]
-; CHECK: s_mov_b32 m0, [[IN]]
-; CHECK: v_movreld_b32_e32
-define void @insert_w_offset(float addrspace(1)* %out, i32 %in) {
+; CHECK-DAG: s_load_dword [[IN:s[0-9]+]]
+; CHECK-DAG: s_mov_b32 m0, [[IN]]
+; CHECK-DAG: v_mov_b32_e32 v[[ELT0:[0-9]+]], 1.0
+; CHECK-DAG: v_mov_b32_e32 v[[ELT1:[0-9]+]], 2.0
+; CHECK-DAG: v_mov_b32_e32 v[[ELT2:[0-9]+]], 0x40400000
+; CHECK-DAG: v_mov_b32_e32 v[[ELT3:[0-9]+]], 4.0
+; CHECK-DAG: v_mov_b32_e32 v[[INS:[0-9]+]], 0x40a00000
+; CHECK: v_movreld_b32_e32 v[[ELT1]], v[[INS]]
+; CHECK: buffer_store_dwordx4 v{{\[}}[[ELT0]]:[[ELT3]]{{\]}}
+define void @insert_w_offset(<4 x float> addrspace(1)* %out, i32 %in) {
 entry:
   %0 = add i32 %in, 1
   %1 = insertelement <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, float 5.0, i32 %0
-  %2 = extractelement <4 x float> %1, i32 2
-  store float %2, float addrspace(1)* %out
+  store <4 x float> %1, <4 x float> addrspace(1)* %out
   ret void
 }
 
 ; CHECK-LABEL: {{^}}insert_wo_offset:
 ; CHECK: s_load_dword [[IN:s[0-9]+]]
 ; CHECK: s_mov_b32 m0, [[IN]]
-; CHECK: v_movreld_b32_e32
-define void @insert_wo_offset(float addrspace(1)* %out, i32 %in) {
+; CHECK: v_movreld_b32_e32 v[[ELT0:[0-9]+]]
+; CHECK: buffer_store_dwordx4 v{{\[}}[[ELT0]]:
+define void @insert_wo_offset(<4 x float> addrspace(1)* %out, i32 %in) {
 entry:
   %0 = insertelement <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, float 5.0, i32 %in
-  %1 = extractelement <4 x float> %0, i32 2
-  store float %1, float addrspace(1)* %out
+  store <4 x float> %0, <4 x float> addrspace(1)* %out
   ret void
 }