Use autogenerate, use stdout, add call to entry from another fn

Author: jofrn

llvm/test/CodeGen/AMDGPU/cc-entry.ll

@@ -1,7 +1,68 @@
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s 2>&1 | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck %s
 
 define amdgpu_kernel void @entry_fn() {
-; CHECK-NOT: LLVM ERROR: invalid call to entry function
+; CHECK-LABEL: entry_fn:
+; CHECK:       ; %bb.0: ; %entry
+; CHECK-NEXT:    s_getpc_b64 s[4:5]
+; CHECK-NEXT:    s_sext_i32_i16 s5, s5
+; CHECK-NEXT:    s_add_co_u32 s4, s4, entry_fn@gotpcrel32@lo+8
+; CHECK-NEXT:    s_add_co_ci_u32 s5, s5, entry_fn@gotpcrel32@hi+16
+; CHECK-NEXT:    s_mov_b32 s32, 0
+; CHECK-NEXT:    s_load_b64 s[4:5], s[4:5], 0x0
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_swappc_b64 s[30:31], s[4:5]
+; CHECK-NEXT:    s_endpgm
+entry:
+  call void @entry_fn()
+  ret void
+}
+
+define void @caller() {
+; CHECK-LABEL: caller:
+; 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_mov_b32 s0, s33
+; CHECK-NEXT:    s_mov_b32 s33, s32
+; CHECK-NEXT:    s_or_saveexec_b32 s1, -1
+; CHECK-NEXT:    scratch_store_b32 off, v40, s33 ; 4-byte Folded Spill
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_mov_b32 exec_lo, s1
+; CHECK-NEXT:    s_add_co_i32 s32, s32, 16
+; CHECK-NEXT:    v_writelane_b32 v40, s0, 2
+; CHECK-NEXT:    s_mov_b64 s[0:1], s[4:5]
+; CHECK-NEXT:    s_getpc_b64 s[4:5]
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_sext_i32_i16 s5, s5
+; CHECK-NEXT:    s_add_co_u32 s4, s4, entry_fn@gotpcrel32@lo+12
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_add_co_ci_u32 s5, s5, entry_fn@gotpcrel32@hi+24
+; CHECK-NEXT:    v_mov_b32_e32 v0, v31
+; CHECK-NEXT:    s_load_b64 s[4:5], s[4:5], 0x0
+; CHECK-NEXT:    v_writelane_b32 v40, s30, 0
+; CHECK-NEXT:    s_mov_b64 s[2:3], s[6:7]
+; CHECK-NEXT:    s_mov_b64 s[6:7], s[10:11]
+; CHECK-NEXT:    v_writelane_b32 v40, s31, 1
+; CHECK-NEXT:    s_wait_kmcnt 0x0
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_swappc_b64 s[30:31], s[4:5]
+; CHECK-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; CHECK-NEXT:    v_readlane_b32 s31, v40, 1
+; CHECK-NEXT:    v_readlane_b32 s30, v40, 0
+; CHECK-NEXT:    s_mov_b32 s32, s33
+; CHECK-NEXT:    v_readlane_b32 s0, v40, 2
+; CHECK-NEXT:    s_or_saveexec_b32 s1, -1
+; CHECK-NEXT:    scratch_load_b32 v40, off, s33 ; 4-byte Folded Reload
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_mov_b32 exec_lo, s1
+; CHECK-NEXT:    s_mov_b32 s33, s0
+; CHECK-NEXT:    s_wait_loadcnt 0x0
+; CHECK-NEXT:    s_wait_alu 0xfffe
+; CHECK-NEXT:    s_setpc_b64 s[30:31]
 entry:
   call void @entry_fn()
   ret void