1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/llvm.amdgcn.udot4.ll
Stanislav Mekhanoshin 3e11a165dc [AMDGPU] gfx1011/gfx1012 targets
Differential Revision: https://reviews.llvm.org/D63307

llvm-svn: 363344
2019-06-14 00:33:31 +00:00

44 lines
1.9 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=gfx906 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX906
; RUN: llc -march=amdgcn -mcpu=gfx1011 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
; RUN: llc -march=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
declare i32 @llvm.amdgcn.udot4(i32 %a, i32 %b, i32 %c, i1 %clamp)
; GCN-LABEL: {{^}}test_llvm_amdgcn_udot4_clamp
; GFX906: v_dot4_u32_u8 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} clamp{{$}}
; GFX10: v_dot4_u32_u8 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}} clamp{{$}}
define amdgpu_kernel void @test_llvm_amdgcn_udot4_clamp(
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.udot4(i32 %a.val.cast, i32 %b.val.cast, i32 %c.val, i1 1)
store i32 %r.val, i32 addrspace(1)* %r
ret void
}
; GCN-LABEL: {{^}}test_llvm_amdgcn_udot4_no_clamp
; GFX906: v_dot4_u32_u8 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}{{$}}
; GFX10: v_dot4_u32_u8 v{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
define amdgpu_kernel void @test_llvm_amdgcn_udot4_no_clamp(
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.udot4(i32 %a.val.cast, i32 %b.val.cast, i32 %c.val, i1 0)
store i32 %r.val, i32 addrspace(1)* %r
ret void
}