From d078070f6a76326853885bfa661ff4fa9755e2b8 Mon Sep 17 00:00:00 2001
From: Tom Stellard <thomas.stellard@amd.com>
Date: Thu, 23 May 2013 18:26:42 +0000
Subject: [PATCH] R600: Fix R600ControlFlowFinalizer not considering VTX_READ
 128 bit dst reg

Patch by: Vincent Lejeune

https://bugs.freedesktop.org/show_bug.cgi?id=64877

NOTE: This is a candidate for the 3.3 branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182600 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/R600/R600ControlFlowFinalizer.cpp | 11 ++++++++--
 test/CodeGen/R600/vtx-schedule.ll            | 22 ++++++++++++++++++++
 2 files changed, 31 insertions(+), 2 deletions(-)
 create mode 100644 test/CodeGen/R600/vtx-schedule.ll

diff --git a/lib/Target/R600/R600ControlFlowFinalizer.cpp b/lib/Target/R600/R600ControlFlowFinalizer.cpp
index d447f0842d7..832c375bf5b 100644
--- a/lib/Target/R600/R600ControlFlowFinalizer.cpp
+++ b/lib/Target/R600/R600ControlFlowFinalizer.cpp
@@ -117,8 +117,15 @@ private:
       const MachineOperand &MO = *I;
       if (!MO.isReg())
         continue;
-      if (MO.isDef())
-        DstMI = MO.getReg();
+      if (MO.isDef()) {
+        unsigned Reg = MO.getReg();
+        if (AMDGPU::R600_Reg128RegClass.contains(Reg))
+          DstMI = Reg;
+        else
+          DstMI = TRI.getMatchingSuperReg(Reg,
+              TRI.getSubRegFromChannel(TRI.getHWRegChan(Reg)),
+              &AMDGPU::R600_Reg128RegClass);
+      }
       if (MO.isUse()) {
         unsigned Reg = MO.getReg();
         if (AMDGPU::R600_Reg128RegClass.contains(Reg))
diff --git a/test/CodeGen/R600/vtx-schedule.ll b/test/CodeGen/R600/vtx-schedule.ll
new file mode 100644
index 00000000000..a0c79e36d3c
--- /dev/null
+++ b/test/CodeGen/R600/vtx-schedule.ll
@@ -0,0 +1,22 @@
+; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+; This test is for a scheduler bug where VTX_READ instructions that used
+; the result of another VTX_READ instruction were being grouped in the
+; same fetch clasue.
+
+; CHECK: @test
+; CHECK: Fetch clause
+; CHECK_VTX_READ_32 [[IN0:T[0-9]+\.X]], [[IN0]], 40
+; CHECK_VTX_READ_32 [[IN1:T[0-9]+\.X]], [[IN1]], 44
+; CHECK: Fetch clause
+; CHECK_VTX_READ_32 [[IN0:T[0-9]+\.X]], [[IN0]], 0
+; CHECK_VTX_READ_32 [[IN1:T[0-9]+\.X]], [[IN1]], 0
+define void @test(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in0, i32 addrspace(1)* nocapture %in1) {
+entry:
+  %0 = load i32 addrspace(1)* %in0, align 4
+  %1 = load i32 addrspace(1)* %in1, align 4
+  %cmp.i = icmp slt i32 %0, %1
+  %cond.i = select i1 %cmp.i, i32 %0, i32 %1
+  store i32 %cond.i, i32 addrspace(1)* %out, align 4
+  ret void
+}