AMDGPU: Fix not preserving CSR VGPR if used for SGPR spills

Before this was not done if the function had no calls in it. This
is still a possible issue with any callable function, regardless
of calls present.

llvm-svn: 328659

diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index 2534ad0..f78578a 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -273,10 +273,9 @@ bool SIMachineFunctionInfo::allocateSGPRSpillToVGPR(MachineFunction &MF,
       }
 
       Optional<int> CSRSpillFI;
-      if (FrameInfo.hasCalls() && CSRegs && isCalleeSavedReg(CSRegs, LaneVGPR)) {
-        // TODO: Should this be a CreateSpillStackObject? This is technically a
-        // weird CSR spill.
-        CSRSpillFI = FrameInfo.CreateStackObject(4, 4, false);
+      if ((FrameInfo.hasCalls() || !isEntryFunction()) && CSRegs &&
+          isCalleeSavedReg(CSRegs, LaneVGPR)) {
+        CSRSpillFI = FrameInfo.CreateSpillStackObject(4, 4);
       }
 
       SpillVGPRs.push_back(SGPRSpillVGPRCSR(LaneVGPR, CSRSpillFI));

diff --git a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
index 14a6193..0d8244e 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
@@ -92,5 +92,36 @@ define void @callee_no_stack_with_call() #0 {
 
 declare void @external_void_func_void() #0
 
+; Make sure if a CSR vgpr is used for SGPR spilling, it is saved and restored
+; GCN-LABEL: {{^}}callee_func_sgpr_spill_no_calls:
+; GCN: buffer_store_dword v32, off, s[0:3], s5 offset:4 ; 4-byte Folded Spill
+; GCN: v_writelane_b32 v32
+; GCN: ;;#ASMSTART
+; GCN: v_readlane_b32 s{{[0-9]+}}, v32
+; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:4 ; 4-byte Folded Reload
+; GCN-NEXT: s_waitcnt
+; GCN-NEXT: s_setpc_b64
+define void @callee_func_sgpr_spill_no_calls(i32 %in) #0 {
+  call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7}"() #0
+  call void asm sideeffect "", "~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15}"() #0
+  call void asm sideeffect "", "~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23}"() #0
+  call void asm sideeffect "", "~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"() #0
+
+  %wide.sgpr0 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr1 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr2 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr5 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr3 = call <8 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr4 = call <2 x i32> asm sideeffect "; def $0", "=s" () #0
+
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr0) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr1) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr2) #0
+  call void asm sideeffect "; use $0", "s"(<8 x i32> %wide.sgpr3) #0
+  call void asm sideeffect "; use $0", "s"(<2 x i32> %wide.sgpr4) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr5) #0
+  ret void
+}
+
 attributes #0 = { nounwind }
 attributes #1 = { nounwind "no-frame-pointer-elim"="true" }