diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-01-10 22:02:30 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-01-10 22:02:30 +0000 |
| commit | 0b382a7cb8b0a46fc69f94dd59d83855b72f1277 (patch) | |
| tree | a9d9a5170c5a070a7bc8c835e95676b3283b65e3 /llvm/test/CodeGen/AMDGPU | |
| parent | 7acb42a41a7ed67f19553cd3617aacbca832a458 (diff) | |
| download | bcm5719-llvm-0b382a7cb8b0a46fc69f94dd59d83855b72f1277.tar.gz bcm5719-llvm-0b382a7cb8b0a46fc69f94dd59d83855b72f1277.zip | |
DAG: Avoid OOB when legalizing vector indexing
If a vector index is out of bounds, the result is supposed to be
undefined but is not undefined behavior. Change the legalization
for indexing the vector on the stack so that an out of bounds
index does not create an out of bounds memory access.
llvm-svn: 291604
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll | 8 | ||||
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/local-stack-slot-bug.ll | 7 |
2 files changed, 11 insertions, 4 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll index 7351665f06e..2c538b16e74 100644 --- a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll +++ b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll @@ -207,11 +207,15 @@ define void @dynamic_insertelement_v3i16(<3 x i16> addrspace(1)* %out, <3 x i16> ; GCN: buffer_load_ushort v{{[0-9]+}}, off ; GCN: buffer_load_ushort v{{[0-9]+}}, off +; GCN-DAG: v_mov_b32_e32 [[BASE_FI:v[0-9]+]], 0{{$}} +; GCN-DAG: s_and_b32 [[MASK_IDX:s[0-9]+]], s{{[0-9]+}}, 3{{$}} +; GCN-DAG: v_or_b32_e32 [[IDX:v[0-9]+]], [[MASK_IDX]], [[BASE_FI]]{{$}} + ; GCN-DAG: buffer_store_short v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:6 ; GCN-DAG: buffer_store_short v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:4 ; GCN-DAG: buffer_store_short v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offset:2 -; GCN-DAG: buffer_store_short v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}}{{$}} -; GCN: buffer_store_short v{{[0-9]+}}, v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offen{{$}} +; GCN-DAG: buffer_store_short v{{[0-9]+}}, off, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+$}} +; GCN: buffer_store_short v{{[0-9]+}}, [[IDX]], s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offen{{$}} ; GCN: s_waitcnt diff --git a/llvm/test/CodeGen/AMDGPU/local-stack-slot-bug.ll b/llvm/test/CodeGen/AMDGPU/local-stack-slot-bug.ll index d49fa2bf48a..2ef045dbb8e 100644 --- a/llvm/test/CodeGen/AMDGPU/local-stack-slot-bug.ll +++ b/llvm/test/CodeGen/AMDGPU/local-stack-slot-bug.ll @@ -7,11 +7,14 @@ ; ; CHECK-LABEL: {{^}}main: +; CHECK-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0x200 +; CHECK-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}} ; CHECK-DAG: v_lshlrev_b32_e32 [[BYTES:v[0-9]+]], 2, v0 -; CHECK-DAG: v_add_i32_e32 [[HI_OFF:v[0-9]+]], vcc, 0x200, [[BYTES]] +; CHECK-DAG: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, [[BYTES]] ; TODO: add 0? -; CHECK-DAG: v_add_i32_e32 [[LO_OFF:v[0-9]+]], vcc, 0, [[BYTES]] +; CHECK-DAG: v_or_b32_e32 [[LO_OFF:v[0-9]+]], [[CLAMP_IDX]], [[ZERO]] +; CHECK-DAG: v_or_b32_e32 [[HI_OFF:v[0-9]+]], [[CLAMP_IDX]], [[K]] ; CHECK: buffer_load_dword {{v[0-9]+}}, [[LO_OFF]], {{s\[[0-9]+:[0-9]+\]}}, {{s[0-9]+}} offen ; CHECK: buffer_load_dword {{v[0-9]+}}, [[HI_OFF]], {{s\[[0-9]+:[0-9]+\]}}, {{s[0-9]+}} offen |
