diff options
| -rw-r--r-- | llvm/include/llvm/IR/IntrinsicsAMDGPU.td | 10 | ||||
| -rw-r--r-- | llvm/lib/Target/AMDGPU/VOP3Instructions.td | 4 | ||||
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/llvm.amdgcn.alignb.ll | 23 |
3 files changed, 35 insertions, 2 deletions
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td index e1928546607..8017223c4ab 100644 --- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td +++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td @@ -703,6 +703,16 @@ def int_amdgcn_readlane : GCCBuiltin<"__builtin_amdgcn_readlane">, Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>; +def int_amdgcn_alignbit : Intrinsic<[llvm_i32_ty], + [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], + [IntrNoMem, IntrSpeculatable] +>; + +def int_amdgcn_alignbyte : Intrinsic<[llvm_i32_ty], + [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], + [IntrNoMem, IntrSpeculatable] +>; + //===----------------------------------------------------------------------===// // CI+ Intrinsics //===----------------------------------------------------------------------===// diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td index 900adb8b536..a8ca593f14e 100644 --- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td +++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td @@ -172,8 +172,8 @@ def V_CUBEMA_F32 : VOP3Inst <"v_cubema_f32", VOP3_Profile<VOP_F32_F32_F32_F32>, def V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_u32>; def V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>; def V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>; -def V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>>; -def V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>>; +def V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbit>; +def V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>; def V_MIN3_F32 : VOP3Inst <"v_min3_f32", VOP3_Profile<VOP_F32_F32_F32_F32>, AMDGPUfmin3>; def V_MIN3_I32 : VOP3Inst <"v_min3_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUsmin3>; def V_MIN3_U32 : VOP3Inst <"v_min3_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUumin3>; diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.alignb.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.alignb.ll new file mode 100644 index 00000000000..873a3f0f368 --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.alignb.ll @@ -0,0 +1,23 @@ +; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s + +declare i32 @llvm.amdgcn.alignbit(i32, i32, i32) #0 +declare i32 @llvm.amdgcn.alignbyte(i32, i32, i32) #0 + +; GCN-LABEL: {{^}}v_alignbit_b32: +; GCN: v_alignbit_b32 {{[vs][0-9]+}}, {{[vs][0-9]+}}, {{[vs][0-9]+}} +define amdgpu_kernel void @v_alignbit_b32(i32 addrspace(1)* %out, i32 %src1, i32 %src2, i32 %src3) #1 { + %val = call i32 @llvm.amdgcn.alignbit(i32 %src1, i32 %src2, i32 %src3) #0 + store i32 %val, i32 addrspace(1)* %out + ret void +} + +; GCN-LABEL: {{^}}v_alignbyte_b32: +; GCN: v_alignbyte_b32 {{[vs][0-9]+}}, {{[vs][0-9]+}}, {{[vs][0-9]+}} +define amdgpu_kernel void @v_alignbyte_b32(i32 addrspace(1)* %out, i32 %src1, i32 %src2, i32 %src3) #1 { + %val = call i32 @llvm.amdgcn.alignbyte(i32 %src1, i32 %src2, i32 %src3) #0 + store i32 %val, i32 addrspace(1)* %out + ret void +} + +attributes #0 = { nounwind readnone } +attributes #1 = { nounwind } |
