diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-07-01 22:47:50 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-07-01 22:47:50 +0000 |
| commit | 327bb5ad82328bb92907bb2acf87e2282593e1e4 (patch) | |
| tree | 96f20ec1942050bdab64dc965a2f9f5e292994ce /llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll | |
| parent | 591ff8376bbf3ee0cc6f6006300878ae96475a49 (diff) | |
| download | bcm5719-llvm-327bb5ad82328bb92907bb2acf87e2282593e1e4.tar.gz bcm5719-llvm-327bb5ad82328bb92907bb2acf87e2282593e1e4.zip | |
AMDGPU: Improve load/store of illegal types.
There was a combine before to handle the simple copy case.
Split this into handling loads and stores separately.
We might want to change how this handles some of the vector
extloads, since this can result in large code size increases.
llvm-svn: 274394
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll | 13 |
1 files changed, 3 insertions, 10 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll index 2d1b7f0efa2..93001e4c139 100644 --- a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll +++ b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll @@ -208,10 +208,7 @@ define void @dynamic_insertelement_v3i16(<3 x i16> addrspace(1)* %out, <3 x i16> ; GCN: buffer_load_ushort ; GCN: buffer_load_ushort -; GCN: buffer_store_short v{{[0-9]+}}, off -; GCN: buffer_store_short v{{[0-9]+}}, off -; GCN: buffer_store_short v{{[0-9]+}}, off -; GCN: buffer_store_short v{{[0-9]+}}, off +; GCN: buffer_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, off define void @dynamic_insertelement_v4i16(<4 x i16> addrspace(1)* %out, <4 x i16> %a, i32 %b) nounwind { %vecins = insertelement <4 x i16> %a, i16 5, i32 %b store <4 x i16> %vecins, <4 x i16> addrspace(1)* %out, align 8 @@ -230,8 +227,7 @@ define void @dynamic_insertelement_v4i16(<4 x i16> addrspace(1)* %out, <4 x i16> ; GCN: buffer_load_ubyte ; GCN: buffer_load_ubyte -; GCN: buffer_store_byte v{{[0-9]+}}, off -; GCN: buffer_store_byte v{{[0-9]+}}, off +; GCN: buffer_store_short v{{[0-9]+}}, off define void @dynamic_insertelement_v2i8(<2 x i8> addrspace(1)* %out, <2 x i8> %a, i32 %b) nounwind { %vecins = insertelement <2 x i8> %a, i8 5, i32 %b store <2 x i8> %vecins, <2 x i8> addrspace(1)* %out, align 8 @@ -279,10 +275,7 @@ define void @dynamic_insertelement_v3i8(<3 x i8> addrspace(1)* %out, <3 x i8> %a ; GCN: buffer_load_ubyte ; GCN: buffer_load_ubyte -; GCN: buffer_store_byte v{{[0-9]+}}, off -; GCN: buffer_store_byte v{{[0-9]+}}, off -; GCN: buffer_store_byte v{{[0-9]+}}, off -; GCN: buffer_store_byte v{{[0-9]+}}, off +; GCN: buffer_store_dword v{{[0-9]+}}, off define void @dynamic_insertelement_v4i8(<4 x i8> addrspace(1)* %out, <4 x i8> %a, i32 %b) nounwind { %vecins = insertelement <4 x i8> %a, i8 5, i32 %b store <4 x i8> %vecins, <4 x i8> addrspace(1)* %out, align 4 |
