AMDGPU: Re-do update for branch-relaxation test

Modify the test so that it is still testing something
closer to what it was intended to originally.

I think the original intent was to test the situation where
there was a branch on execz and then unconditional branch
required relaxing.With the change in r296539,
there was no longer and execz branch.

Change the test so that there is now an execz branch inserted.
There is no longer an unconditional branch after the execz branch,
so this might need to be tricked in some other way to keep that
there.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296574 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/AMDGPU/branch-relaxation.ll b/test/CodeGen/AMDGPU/branch-relaxation.ll
index 7ae2e996095828fddc9f67f24750b22ad9e9bb3e..9d3afc2cbaaf8433860839eafb838bfdebd0a425 100644 (file)
--- a/test/CodeGen/AMDGPU/branch-relaxation.ll
+++ b/test/CodeGen/AMDGPU/branch-relaxation.ll
@@ -430,8 +430,16 @@ endif:
 ; GCN-NEXT: s_and_saveexec_b64 [[MASK:s\[[0-9]+:[0-9]+\]]], vcc
 ; GCN-NEXT: s_xor_b64 [[MASK]], exec, [[MASK]]
 ; GCN-NEXT: ; mask branch [[RET:BB[0-9]+_[0-9]+]]
+; GCN-NEXT: s_cbranch_execnz [[LOOP_BODY:BB[0-9]+_[0-9]+]]
+
+; GCN-NEXT: [[BRANCH_SKIP:BB[0-9]+_[0-9]+]]: ; %entry
+; GCN-NEXT: s_getpc_b64 vcc
+; GCN-NEXT: s_add_u32 vcc_lo, vcc_lo, [[RET]]-([[BRANCH_SKIP]]+4)
+; GCN-NEXT: s_addc_u32 vcc_hi, vcc_hi, 0
+; GCN-NEXT: s_setpc_b64 vcc
+
+; GCN-NEXT: [[LOOP_BODY]]: ; %loop_body
 
-; GCN-NEXT: [[LOOP_BODY:BB[0-9]+_[0-9]+]]: ; %loop_body
 ; GCN: ;;#ASMSTART
 ; GCN: v_nop_e64
 ; GCN: v_nop_e64
@@ -448,11 +456,8 @@ endif:
 ; GCN-NEXT: s_subb_u32 vcc_hi, vcc_hi, 0
 ; GCN-NEXT: s_setpc_b64 vcc
 
-; GCN-NEXT: [[RET]]: 
+; GCN-NEXT: BB{{[0-9]+_[0-9]+}}: ; %ret
 ; GCN-NEXT: s_or_b64 exec, exec, [[MASK]]
-; GCN-NEXT: s_mov_b32 s3, 0xf000
-; GCN-NEXT: s_mov_b32 s2, -1
-; GCN-NExt: v_mov_b32_e32 v0, 7
 ; GCN: buffer_store_dword
 ; GCN-NEXT: s_endpgm
 define void @analyze_mask_branch() #0 {
@@ -460,8 +465,14 @@ entry:
   %reg = call float asm sideeffect "v_mov_b32_e64 $0, 0", "=v"()
   %cmp0 = fcmp ogt float %reg, 0.000000e+00
   br i1 %cmp0, label %loop, label %ret
+
 loop:
   %phi = phi float [ 0.000000e+00, %loop_body ], [ 1.000000e+00, %entry ]
+  call void @llvm.amdgcn.s.sleep(i32 0)
+  call void @llvm.amdgcn.s.sleep(i32 0)
+  call void @llvm.amdgcn.s.sleep(i32 0)
+  call void @llvm.amdgcn.s.sleep(i32 0)
+  call void @llvm.amdgcn.s.sleep(i32 0)
   call void asm sideeffect
     "v_nop_e64
      v_nop_e64", ""() #0