AMDGPU: Set scratch_en if there is dynamic stack but no fixed stack

[rampitec]

LGTM

[arsenm]

8dfe60c35670a2d6d3017528de95300d797231c0

llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,
   else if (MFI->hasWorkItemIDY())
     TIDIGCompCnt = 1;
 
   // The private segment wave byte offset is the last of the system SGPRs. We
   // initially assumed it was allocated, and may have used it. It shouldn't harm
   // anything to disable it if we know the stack isn't used here. We may still
   // have emitted code reading it to initialize scratch, but if that's unused
   // reading garbage should be OK.
-  const bool EnablePrivateSegment = ProgInfo.ScratchBlocks > 0;
+  const bool EnablePrivateSegment =
+      ProgInfo.ScratchBlocks > 0 || ProgInfo.DynamicCallStack;
   ProgInfo.ComputePGMRSrc2 =
       S_00B84C_SCRATCH_EN(EnablePrivateSegment) |
       S_00B84C_USER_SGPR(MFI->getNumUserSGPRs()) |
       // For AMDHSA, TRAP_HANDLER must be zero, as it is populated by the CP.
       S_00B84C_TRAP_HANDLER(STM.isAmdHsaOS() ? 0 : STM.isTrapHandlerEnabled()) |
       S_00B84C_TGID_X_EN(MFI->hasWorkGroupIDX()) |
       S_00B84C_TGID_Y_EN(MFI->hasWorkGroupIDY()) |
       S_00B84C_TGID_Z_EN(MFI->hasWorkGroupIDZ()) |

llvm/test/CodeGen/AMDGPU/enable-scratch-only-dynamic-stack.ll

+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=5 < %s | FileCheck -check-prefixes=GCN,COV5 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=4 < %s | FileCheck -check-prefixes=GCN,COV4 %s
+
[e-mail]0 = external hidden unnamed_addr addrspace(4) constant ptr, align 4
+
+; No stack objects, only indirect call has to enable scrathch
+; GCN-LABEL: test_indirect_call:
+
+; COV5: .amdhsa_private_segment_fixed_size 0{{$}}
+; COV4: .amdhsa_private_segment_fixed_size 16384{{$}}
+
+; GCN: .amdhsa_user_sgpr_private_segment_buffer 1
+
+; COV5: .amdhsa_uses_dynamic_stack 1
+; GCN: .amdhsa_system_sgpr_private_segment_wavefront_offset 1
+define amdgpu_kernel void @test_indirect_call() {
+  %fptr = load ptr, ptr addrspace(4) @gv.fptr0
+  call void %fptr()
+  ret void
+}