Merging r275928 and r276438:

------------------------------------------------------------------------
r275928 | arsenm | 2016-07-18 16:09:51 -0700 (Mon, 18 Jul 2016) | 1 line

AMDGPU: Fix test name and broken CHECK-LABEL
------------------------------------------------------------------------

------------------------------------------------------------------------
r276438 | arsenm | 2016-07-22 10:01:33 -0700 (Fri, 22 Jul 2016) | 6 lines

AMDGPU: Fix groupstaticsize for large LDS

The size can exceed s_movk_i32's limit, and we don't
want to use it this early since it inhibits optimizations.

This should probably be merged to the release branch.
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_39@276664 91177308-0d34-0410-b5e6-96231b3b80d8

Author: zmodem

lib/Target/AMDGPU/SIISelLowering.cpp

@@ -1134,9 +1134,9 @@ MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter(
     MachineFunction *MF = BB->getParent();
     SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
     DebugLoc DL = MI.getDebugLoc();
-    BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOVK_I32))
-        .addOperand(MI.getOperand(0))
-        .addImm(MFI->LDSSize);
+    BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOV_B32))
+      .addOperand(MI.getOperand(0))
+      .addImm(MFI->LDSSize);
     MI.eraseFromParent();
     return BB;
   }

test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticgroup.ll renamed to test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll

@@ -2,13 +2,14 @@
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
 
-
 @lds0 = addrspace(3) global [512 x float] undef, align 4
 @lds1 = addrspace(3) global [256 x float] undef, align 4
 
-; FUNC-LABEL: {{^}}groupstaticsize_test0:
-; CHECK: s_movk_i32 s{{[0-9]+}}, 0x800
-define void @get_groupstaticsize_test0(float addrspace(1)* %out, i32 addrspace(1)* %lds_size) #0 {
+@large = addrspace(3) global [4096 x i32] undef, align 4
+
+; CHECK-LABEL: {{^}}groupstaticsize_test0:
+; CHECK: v_mov_b32_e32 v{{[0-9]+}}, 0x800{{$}}
+define void @groupstaticsize_test0(float addrspace(1)* %out, i32 addrspace(1)* %lds_size) #0 {
   %tid.x = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %idx.0 = add nsw i32 %tid.x, 64
   %static_lds_size = call i32 @llvm.amdgcn.groupstaticsize() #1
@@ -20,9 +21,8 @@ define void @get_groupstaticsize_test0(float addrspace(1)* %out, i32 addrspace(1
   ret void
 }
 
-
-; FUNC-LABEL: {{^}}groupstaticsize_test1:
-; CHECK: s_movk_i32 s{{[0-9]+}}, 0xc00
+; CHECK-LABEL: {{^}}groupstaticsize_test1:
+; CHECK: v_mov_b32_e32 v{{[0-9]+}}, 0xc00{{$}}
 define void @groupstaticsize_test1(float addrspace(1)* %out, i32 %cond, i32 addrspace(1)* %lds_size) {
 entry:
   %static_lds_size = call i32 @llvm.amdgcn.groupstaticsize() #1
@@ -48,6 +48,16 @@ endif:                                            ; preds = %else, %if
   ret void
 }
 
+; Exceeds 16-bit simm limit of s_movk_i32
+; CHECK-LABEL: {{^}}large_groupstaticsize:
+; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0x4000{{$}}
+define void @large_groupstaticsize(i32 addrspace(1)* %size, i32 %idx) #0 {
+  %gep = getelementptr inbounds [4096 x i32], [4096 x i32] addrspace(3)* @large, i32 0, i32 %idx
+  store volatile i32 0, i32 addrspace(3)* %gep
+  %static_lds_size = call i32 @llvm.amdgcn.groupstaticsize()
+  store i32 %static_lds_size, i32 addrspace(1)* %size
+  ret void
+}
 
 declare i32 @llvm.amdgcn.groupstaticsize() #1
 declare i32 @llvm.amdgcn.workitem.id.x() #1