R600: Add VTX_READ_* and RAT_WRITE_CACHELESS_* when computing cf addr

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179174 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/R600ControlFlowFinalizer.cpp b/lib/Target/R600/R600ControlFlowFinalizer.cpp
index cfaa36e12275f96caf5383e9015483d2b2307dad..235013088b270c5d590175f61886b53617248fbb 100644 (file)
--- a/lib/Target/R600/R600ControlFlowFinalizer.cpp
+++ b/lib/Target/R600/R600ControlFlowFinalizer.cpp
@@ -67,6 +67,13 @@ private:
     case AMDGPU::TEX_SAMPLE_C_G:
     case AMDGPU::TXD:
     case AMDGPU::TXD_SHADOW:
+    case AMDGPU::VTX_READ_GLOBAL_8_eg:
+    case AMDGPU::VTX_READ_GLOBAL_32_eg:
+    case AMDGPU::VTX_READ_GLOBAL_128_eg:
+    case AMDGPU::VTX_READ_PARAM_8_eg:
+    case AMDGPU::VTX_READ_PARAM_16_eg:
+    case AMDGPU::VTX_READ_PARAM_32_eg:
+    case AMDGPU::VTX_READ_PARAM_128_eg:
      return true;
     default:
       return false;
@@ -207,6 +214,8 @@ public:
         case AMDGPU::EG_ExportSwz:
         case AMDGPU::R600_ExportBuf:
         case AMDGPU::R600_ExportSwz:
+        case AMDGPU::RAT_WRITE_CACHELESS_32_eg:
+        case AMDGPU::RAT_WRITE_CACHELESS_128_eg:
           DEBUG(dbgs() << CfCount << ":"; MI->dump(););
           CfCount++;
           break;
@@ -215,7 +224,7 @@ public:
           MaxStack = std::max(MaxStack, CurrentStack);
           MachineInstr *MIb = BuildMI(MBB, MI, MBB.findDebugLoc(MI),
               getHWInstrDesc(CF_WHILE_LOOP))
-              .addImm(2);
+              .addImm(1);
           std::pair<unsigned, std::set<MachineInstr *> > Pair(CfCount,
               std::set<MachineInstr *>());
           Pair.second.insert(MIb);

diff --git a/test/CodeGen/R600/loop-adress.ll b/test/CodeGen/R600/loop-adress.ll
new file mode 100644 (file)
index 0000000..dc9295e
--- /dev/null
+++ b/test/CodeGen/R600/loop-adress.ll
@@ -0,0 +1,44 @@
+;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+;CHECK: TEX
+;CHECK: ALU_PUSH
+;CHECK: JUMP @4
+;CHECK: ELSE @16
+;CHECK: TEX
+;CHECK: LOOP_START_DX10 @15
+;CHECK: LOOP_BREAK @14
+;CHECK: POP @16
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-v16:16:16-v24:32:32-v32:32:32-v48:64:64-v64:64:64-v96:128:128-v128:128:128-v192:256:256-v256:256:256-v512:512:512-v1024:1024:1024-v2048:2048:2048-n32:64"
+target triple = "r600--"
+
+define void @loop_ge(i32 addrspace(1)* nocapture %out, i32 %iterations) #0 {
+entry:
+  %cmp5 = icmp sgt i32 %iterations, 0
+  br i1 %cmp5, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.body, %entry
+  %i.07.in = phi i32 [ %i.07, %for.body ], [ %iterations, %entry ]
+  %ai.06 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %i.07 = add nsw i32 %i.07.in, -1
+  %arrayidx = getelementptr inbounds i32 addrspace(1)* %out, i32 %ai.06
+  store i32 %i.07, i32 addrspace(1)* %arrayidx, align 4, !tbaa !4
+  %add = add nsw i32 %ai.06, 1
+  %exitcond = icmp eq i32 %add, %iterations
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+attributes #0 = { nounwind "fp-contract-model"="standard" "relocation-model"="pic" "ssp-buffers-size"="8" }
+
+!opencl.kernels = !{!0, !1, !2, !3}
+
+!0 = metadata !{void (i32 addrspace(1)*, i32)* @loop_ge}
+!1 = metadata !{null}
+!2 = metadata !{null}
+!3 = metadata !{null}
+!4 = metadata !{metadata !"int", metadata !5}
+!5 = metadata !{metadata !"omnipotent char", metadata !6}
+!6 = metadata !{metadata !"Simple C/C++ TBAA"}