1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-23 04:52:54 +02:00
llvm-mirror/test/CodeGen/AMDGPU/llvm.amdgcn.sdot4.ll
Matt Arsenault 23fa05864d AMDGPU: Add Vega12 and Vega20
Changes by
  Matt Arsenault
  Konstantin Zhuravlyov

llvm-svn: 331215
2018-04-30 19:08:16 +00:00

22 lines
796 B
LLVM

; RUN: llc -march=amdgcn -mcpu=gfx906 -verify-machineinstrs < %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX906
declare i32 @llvm.amdgcn.sdot4(i32 %a, i32 %b, i32 %c)
; GCN-LABEL: {{^}}test_llvm_amdgcn_sdot4
; GFX906: v_dot4_i32_i8
define amdgpu_kernel void @test_llvm_amdgcn_sdot4(
i32 addrspace(1)* %r,
<4 x i8> addrspace(1)* %a,
<4 x i8> addrspace(1)* %b,
i32 addrspace(1)* %c) {
entry:
%a.val = load <4 x i8>, <4 x i8> addrspace(1)* %a
%b.val = load <4 x i8>, <4 x i8> addrspace(1)* %b
%a.val.cast = bitcast <4 x i8> %a.val to i32
%b.val.cast = bitcast <4 x i8> %b.val to i32
%c.val = load i32, i32 addrspace(1)* %c
%r.val = call i32 @llvm.amdgcn.sdot4(i32 %a.val.cast, i32 %b.val.cast, i32 %c.val)
store i32 %r.val, i32 addrspace(1)* %r
ret void
}