diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll new file mode 100644 index 00000000000..2599305bc8e --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll @@ -0,0 +1,21 @@ +; RUN: llc -march=amdgcn -mcpu=gfx906 -verify-machineinstrs < %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX906 + +declare i32 @llvm.amdgcn.udot8(i32 %a, i32 %b, i32 %c) + +; GCN-LABEL: {{^}}test_llvm_amdgcn_udot8 +; GFX906: v_dot8_u32_u4 +define amdgpu_kernel void @test_llvm_amdgcn_udot8( + i32 addrspace(1)* %r, + <8 x i4> addrspace(1)* %a, + <8 x i4> addrspace(1)* %b, + i32 addrspace(1)* %c) { +entry: + %a.val = load <8 x i4>, <8 x i4> addrspace(1)* %a + %b.val = load <8 x i4>, <8 x i4> addrspace(1)* %b + %a.val.cast = bitcast <8 x i4> %a.val to i32 + %b.val.cast = bitcast <8 x i4> %b.val to i32 + %c.val = load i32, i32 addrspace(1)* %c + %r.val = call i32 @llvm.amdgcn.udot8(i32 %a.val.cast, i32 %b.val.cast, i32 %c.val) + store i32 %r.val, i32 addrspace(1)* %r + ret void +} |
