AMDGPU Tests: Change a case to be run with -O0

D40231 requires to run case with -O0 to prevent InstructionSimplify from
transforming an extractelement with undef index.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319907 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll b/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
index b2873402da4360c18d5d96a741bde6381c573fb1..63384f5e445083cef0c57a7831d0e5cac27db966 100644 (file)
--- a/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
+++ b/test/CodeGen/AMDGPU/indirect-addressing-si-noopt.ll
@@ -17,3 +17,48 @@ entry:
   ret void
 }
 
+; Make sure we don't hit use of undefined register errors when expanding an
+; extract with undef index.
+
+; CHECK-LABEL: {{^}}extract_adjacent_blocks:
+; CHECK: s_load_dword [[ARG:s[0-9]+]]
+; CHECK: s_cmp_lg_u32
+; CHECK: s_cbranch_scc1 [[BB4:BB[0-9]+_[0-9]+]]
+
+; CHECK: buffer_load_dwordx4
+; CHECK: s_mov_b32 m0,
+; CHECK: v_movrels_b32_e32
+
+; CHECK: s_branch [[ENDBB:BB[0-9]+_[0-9]+]]
+
+; CHECK: [[BB4]]:
+; CHECK: buffer_load_dwordx4
+; CHECK: s_mov_b32 m0,
+; CHECK: v_movrels_b32_e32
+
+; CHECK: [[ENDBB]]:
+; CHECK: buffer_store_dword
+; CHECK: s_endpgm
+
+define amdgpu_kernel void @extract_adjacent_blocks(i32 %arg) #0 {
+bb:
+  %tmp = icmp eq i32 %arg, 0
+  br i1 %tmp, label %bb1, label %bb4
+
+bb1:
+  %tmp2 = load volatile <4 x float>, <4 x float> addrspace(1)* undef
+  %tmp3 = extractelement <4 x float> %tmp2, i32 undef
+  call void asm sideeffect "; reg use $0", "v"(<4 x float> %tmp2) #0 ; Prevent block optimize out
+  br label %bb7
+
+bb4:
+  %tmp5 = load volatile <4 x float>, <4 x float> addrspace(1)* undef
+  %tmp6 = extractelement <4 x float> %tmp5, i32 undef
+  call void asm sideeffect "; reg use $0", "v"(<4 x float> %tmp5) #0 ; Prevent block optimize out
+  br label %bb7
+
+bb7:
+  %tmp8 = phi float [ %tmp3, %bb1 ], [ %tmp6, %bb4 ]
+  store volatile float %tmp8, float addrspace(1)* undef
+  ret void
+}

diff --git a/test/CodeGen/AMDGPU/indirect-addressing-si.ll b/test/CodeGen/AMDGPU/indirect-addressing-si.ll
index d181d5029efbbbd80926ff7b9917995954922a0a..2b4aca019a391cdc06cb77dddd437acec97f8df4 100644 (file)
--- a/test/CodeGen/AMDGPU/indirect-addressing-si.ll
+++ b/test/CodeGen/AMDGPU/indirect-addressing-si.ll
@@ -469,55 +469,6 @@ bb2:
   ret void
 }
 
-; GCN-LABEL: {{^}}extract_adjacent_blocks:
-; GCN: s_load_dword [[ARG:s[0-9]+]]
-; GCN: s_cmp_lg_u32
-; GCN: s_cbranch_scc0 [[BB4:BB[0-9]+_[0-9]+]]
-
-; GCN: buffer_load_dwordx4
-; MOVREL: s_mov_b32 m0,
-; MOVREL: v_movrels_b32_e32
-
-; IDXMODE: s_set_gpr_idx_on s{{[0-9]+}}, src0
-; IDXMODE: v_mov_b32_e32
-; IDXMODE: s_set_gpr_idx_off
-
-; GCN: s_branch [[ENDBB:BB[0-9]+_[0-9]+]]
-
-; GCN: [[BB4]]:
-; GCN: buffer_load_dwordx4
-; MOVREL: s_mov_b32 m0,
-; MOVREL: v_movrels_b32_e32
-
-; IDXMODE: s_set_gpr_idx_on
-; IDXMODE: v_mov_b32_e32
-; IDXMODE: s_set_gpr_idx_off
-
-; GCN: [[ENDBB]]:
-; GCN: buffer_store_dword
-; GCN: s_endpgm
-define amdgpu_kernel void @extract_adjacent_blocks(i32 %arg) #0 {
-bb:
-  %tmp = icmp eq i32 %arg, 0
-  br i1 %tmp, label %bb1, label %bb4
-
-bb1:
-  %tmp2 = load volatile <4 x float>, <4 x float> addrspace(1)* undef
-  %tmp3 = extractelement <4 x float> %tmp2, i32 undef
-  call void asm sideeffect "; reg use $0", "v"(<4 x float> %tmp2) #0 ; Prevent block optimize out
-  br label %bb7
-
-bb4:
-  %tmp5 = load volatile <4 x float>, <4 x float> addrspace(1)* undef
-  %tmp6 = extractelement <4 x float> %tmp5, i32 undef
-  call void asm sideeffect "; reg use $0", "v"(<4 x float> %tmp5) #0 ; Prevent block optimize out
-  br label %bb7
-
-bb7:
-  %tmp8 = phi float [ %tmp3, %bb1 ], [ %tmp6, %bb4 ]
-  store volatile float %tmp8, float addrspace(1)* undef
-  ret void
-}
 
 ; GCN-LABEL: {{^}}insert_adjacent_blocks:
 ; GCN: s_load_dword [[ARG:s[0-9]+]]