[PATCH] R600: Do not fold single instruction with more that 3 kcache read

[Vincent Lejeune]

It fixes around 100 tfb piglit tests and 16 glean tests.

NOTE: This is a candidate for the Mesa stable branch.
---
 lib/Target/R600/AMDILISelDAGToDAG.cpp  |  2 ++
 lib/Target/R600/R600LowerConstCopy.cpp |  2 +-
 test/CodeGen/R600/kcache-fold.ll       | 52 ++++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+), 1 deletion(-)
 create mode 100644 test/CodeGen/R600/kcache-fold.ll

diff --git a/lib/Target/R600/AMDILISelDAGToDAG.cpp b/lib/Target/R600/AMDILISelDAGToDAG.cpp
index 2f34fe3..858eb5d 100644
--- a/lib/Target/R600/AMDILISelDAGToDAG.cpp
+++ b/lib/Target/R600/AMDILISelDAGToDAG.cpp
@@ -358,6 +358,8 @@ bool AMDGPUDAGToDAGISel::FoldOperands(unsigned Opcode,
     SDValue Operand = Ops[OperandIdx[i] - 1];
     switch (Operand.getOpcode()) {
     case AMDGPUISD::CONST_ADDRESS: {
+      if (i == 2)
+        break;
       SDValue CstOffset;
       if (!Operand.getValueType().isVector() &&
           SelectGlobalValueConstantOffset(Operand.getOperand(0), CstOffset)) {
diff --git a/lib/Target/R600/R600LowerConstCopy.cpp b/lib/Target/R600/R600LowerConstCopy.cpp
index 2557e8f..c8c27a8 100644
--- a/lib/Target/R600/R600LowerConstCopy.cpp
+++ b/lib/Target/R600/R600LowerConstCopy.cpp
@@ -180,7 +180,7 @@ bool R600LowerConstCopy::runOnMachineFunction(MachineFunction &MF) {
             int ConstMovSel =
                 TII->getOperandIdx(CstMov->getOpcode(), R600Operands::SRC0_SEL);
             unsigned ConstIndex = CstMov->getOperand(ConstMovSel).getImm();
-            if (canFoldInBundle(CP, ConstIndex)) {
+            if (MI->isInsideBundle() && canFoldInBundle(CP, ConstIndex)) {
               TII->setImmOperand(MI, OpTable[SrcOp][1], ConstIndex);
               MI->getOperand(SrcIdx).setReg(AMDGPU::ALU_CONST);
             } else {
diff --git a/test/CodeGen/R600/kcache-fold.ll b/test/CodeGen/R600/kcache-fold.ll
new file mode 100644
index 0000000..382f78c
--- /dev/null
+++ b/test/CodeGen/R600/kcache-fold.ll
@@ -0,0 +1,52 @@
+;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
+
+; CHECK: MOV T{{[0-9]+\.[XYZW], CBuf0\[[0-9]+\]\.[XYZW]}}
+
+define void @main() {
+main_body:
+  %0 = load <4 x float> addrspace(9)* null
+  %1 = extractelement <4 x float> %0, i32 0
+  %2 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 1)
+  %3 = extractelement <4 x float> %2, i32 0
+  %4 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 2)
+  %5 = extractelement <4 x float> %4, i32 0
+  %6 = fcmp ult float %1, 0.000000e+00
+  %7 = select i1 %6, float %3, float %5
+  %8 = load <4 x float> addrspace(9)* null
+  %9 = extractelement <4 x float> %8, i32 1
+  %10 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 1)
+  %11 = extractelement <4 x float> %10, i32 1
+  %12 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 2)
+  %13 = extractelement <4 x float> %12, i32 1
+  %14 = fcmp ult float %9, 0.000000e+00
+  %15 = select i1 %14, float %11, float %13
+  %16 = load <4 x float> addrspace(9)* null
+  %17 = extractelement <4 x float> %16, i32 2
+  %18 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 1)
+  %19 = extractelement <4 x float> %18, i32 2
+  %20 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 2)
+  %21 = extractelement <4 x float> %20, i32 2
+  %22 = fcmp ult float %17, 0.000000e+00
+  %23 = select i1 %22, float %19, float %21
+  %24 = load <4 x float> addrspace(9)* null
+  %25 = extractelement <4 x float> %24, i32 3
+  %26 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 1)
+  %27 = extractelement <4 x float> %26, i32 3
+  %28 = load <4 x float> addrspace(9)* getelementptr ([1024 x <4 x float>] addrspace(9)* null, i64 0, i32 2)
+  %29 = extractelement <4 x float> %28, i32 3
+  %30 = fcmp ult float %25, 0.000000e+00
+  %31 = select i1 %30, float %27, float %29
+  %32 = call float @llvm.AMDIL.clamp.(float %7, float 0.000000e+00, float 1.000000e+00)
+  %33 = call float @llvm.AMDIL.clamp.(float %15, float 0.000000e+00, float 1.000000e+00)
+  %34 = call float @llvm.AMDIL.clamp.(float %23, float 0.000000e+00, float 1.000000e+00)
+  %35 = call float @llvm.AMDIL.clamp.(float %31, float 0.000000e+00, float 1.000000e+00)
+  %36 = insertelement <4 x float> undef, float %32, i32 0
+  %37 = insertelement <4 x float> %36, float %33, i32 1
+  %38 = insertelement <4 x float> %37, float %34, i32 2
+  %39 = insertelement <4 x float> %38, float %35, i32 3
+  call void @llvm.R600.store.swizzle(<4 x float> %39, i32 0, i32 0)
+  ret void
+}
+
+declare float @llvm.AMDIL.clamp.(float, float, float) readnone
+declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32)
-- 
1.8.1.2