[AMDGPU] Fix handling of FP in cs.chain functions

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

@@ -1828,7 +1828,9 @@ bool SIFrameLowering::hasFPImpl(const MachineFunction &MF) const {
     return MFI.getStackSize() != 0;
   }
 
-  return frameTriviallyRequiresSP(MFI) || MFI.isFrameAddressTaken() ||
+  return (frameTriviallyRequiresSP(MFI) &&
+          !MF.getInfo<SIMachineFunctionInfo>()->isChainFunction()) ||
+         MFI.isFrameAddressTaken() ||
          MF.getSubtarget<GCNSubtarget>().getRegisterInfo()->hasStackRealignment(
              MF) ||
          MF.getTarget().Options.DisableFramePointerElim(MF);

llvm/test/CodeGen/AMDGPU/amdgpu-cs-chain-fp-nosave.ll

@@ -0,0 +1,103 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -o - < %s 2>&1 | FileCheck %s
+
+; These situations are "special" in that they have an alloca not in the entry
+; block, which affects prolog/epilog generation.
+
+declare amdgpu_gfx void @foo()
+
+define amdgpu_cs_chain void @test_alloca() {
+; CHECK-LABEL: test_alloca:
+; CHECK:       ; %bb.0: ; %.entry
+; CHECK-NEXT:    s_wait_loadcnt_dscnt 0x0
+; CHECK-NEXT:    s_wait_expcnt 0x0
+; CHECK-NEXT:    s_wait_samplecnt 0x0
+; CHECK-NEXT:    s_wait_bvhcnt 0x0
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    v_mov_b32_e32 v0, 0
+; CHECK-NEXT:    s_mov_b32 s32, 16
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_mov_b32 s0, s32
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_i32 s32, s0, 0x200
+; CHECK-NEXT:    scratch_store_b32 off, v0, s0
+; CHECK-NEXT:    s_endpgm
+.entry:
+  br label %SW_C
+
+SW_C:                                             ; preds = %.entry
+  %v = alloca i32, i32 1, align 4, addrspace(5)
+  store i32 0, ptr addrspace(5) %v, align 4
+  ret void
+}
+
+define amdgpu_cs_chain void @test_alloca_and_call() {
+; CHECK-LABEL: test_alloca_and_call:
+; CHECK:       ; %bb.0: ; %.entry
+; CHECK-NEXT:    s_wait_loadcnt_dscnt 0x0
+; CHECK-NEXT:    s_wait_expcnt 0x0
+; CHECK-NEXT:    s_wait_samplecnt 0x0
+; CHECK-NEXT:    s_wait_bvhcnt 0x0
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_getpc_b64 s[0:1]
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_sext_i32_i16 s1, s1
+; CHECK-NEXT:    s_add_co_u32 s0, s0, foo@gotpcrel32@lo+12
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_ci_u32 s1, s1, foo@gotpcrel32@hi+24
+; CHECK-NEXT:    v_mov_b32_e32 v0, 0
+; CHECK-NEXT:    s_load_b64 s[0:1], s[0:1], 0x0
+; CHECK-NEXT:    s_mov_b32 s32, 16
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_mov_b32 s2, s32
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_i32 s32, s2, 0x200
+; CHECK-NEXT:    scratch_store_b32 off, v0, s2
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_swappc_b64 s[30:31], s[0:1]
+; CHECK-NEXT:    s_endpgm
+.entry:
+  br label %SW_C
+
+SW_C:                                             ; preds = %.entry
+  %v = alloca i32, i32 1, align 4, addrspace(5)
+  store i32 0, ptr addrspace(5) %v, align 4
+  call amdgpu_gfx void @foo()
+  ret void
+}
+
+define amdgpu_cs_chain void @test_call_and_alloca() {
+; CHECK-LABEL: test_call_and_alloca:
+; CHECK:       ; %bb.0: ; %.entry
+; CHECK-NEXT:    s_wait_loadcnt_dscnt 0x0
+; CHECK-NEXT:    s_wait_expcnt 0x0
+; CHECK-NEXT:    s_wait_samplecnt 0x0
+; CHECK-NEXT:    s_wait_bvhcnt 0x0
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_getpc_b64 s[0:1]
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_sext_i32_i16 s1, s1
+; CHECK-NEXT:    s_add_co_u32 s0, s0, foo@gotpcrel32@lo+12
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_ci_u32 s1, s1, foo@gotpcrel32@hi+24
+; CHECK-NEXT:    s_mov_b32 s32, 16
+; CHECK-NEXT:    s_load_b64 s[0:1], s[0:1], 0x0
+; CHECK-NEXT:    s_mov_b32 s4, s32
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_i32 s32, s4, 0x200
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_swappc_b64 s[30:31], s[0:1]
+; CHECK-NEXT:    v_mov_b32_e32 v0, 0
+; CHECK-NEXT:    scratch_store_b32 off, v0, s4
+; CHECK-NEXT:    s_endpgm
+.entry:
+  br label %SW_C
+
+SW_C:                                             ; preds = %.entry
+  %v = alloca i32, i32 1, align 4, addrspace(5)
+  call amdgpu_gfx void @foo()
+  store i32 0, ptr addrspace(5) %v, align 4
+  ret void
+}