AMDGPU/GlobalISel: Fix not constraining result reg of copies to VCC

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@366118 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp b/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
index 0d02e738b4ba54633140e49e004092421f7d7513..f916154c3191197de532dd75dbb47a40f3bd111b 100644 (file)
--- a/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
+++ b/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
@@ -116,6 +116,10 @@ bool AMDGPUInstructionSelector::selectCOPY(MachineInstr &I) const {
       return RBI.constrainGenericRegister(DstReg, *RC, MRI);
     }
 
+    // TODO: Should probably leave the copy and let copyPhysReg expand it.
+    if (!RBI.constrainGenericRegister(DstReg, *TRI.getBoolRC(), MRI))
+      return false;
+
     BuildMI(*BB, &I, DL, TII.get(AMDGPU::V_CMP_NE_U32_e64), DstReg)
       .addImm(0)
       .addReg(SrcReg);

diff --git a/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy.mir b/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy.mir
index 1e20e6c76ebd51229ef241a37cde080d65a6fd11..548dde263fffa6508aaad908ce6eb160d0f9fc90 100644 (file)
--- a/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy.mir
+++ b/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy.mir
@@ -242,3 +242,29 @@ body: |
   bb.1:
 
 ...
+
+---
+
+name:            copy_sgpr_s1_to_vcc_constrain
+legalized:       true
+regBankSelected: true
+
+
+body: |
+  bb.0:
+    liveins: $sgpr0_sgpr1
+    ; WAVE64-LABEL: name: copy_sgpr_s1_to_vcc_constrain
+    ; WAVE64: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr0
+    ; WAVE64: [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_NE_U32_e64 0, [[COPY]], implicit $exec
+    ; WAVE64: S_ENDPGM 0, implicit [[V_CMP_NE_U32_e64_]]
+    ; WAVE32-LABEL: name: copy_sgpr_s1_to_vcc_constrain
+    ; WAVE32: $vcc_hi = IMPLICIT_DEF
+    ; WAVE32: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr0
+    ; WAVE32: [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_32_xm0 = V_CMP_NE_U32_e64 0, [[COPY]], implicit $exec
+    ; WAVE32: S_ENDPGM 0, implicit [[V_CMP_NE_U32_e64_]]
+    %0:sgpr(s32) = COPY $sgpr0
+    %1:sgpr(s1) = G_TRUNC %0
+    %2:vcc(s1) = COPY %1
+    S_ENDPGM 0, implicit %2
+
+...