2015-01-06 18:00:21 +00:00
|
|
|
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -strict-whitespace %s
|
2015-01-27 17:27:15 +00:00
|
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -strict-whitespace %s
|
2013-10-13 17:56:28 +00:00
|
|
|
|
2014-10-01 17:15:17 +00:00
|
|
|
; CHECK-LABEL: {{^}}main:
|
2014-11-05 14:50:53 +00:00
|
|
|
; CHECK: s_load_dwordx4
|
|
|
|
; CHECK: s_load_dwordx4
|
|
|
|
; CHECK: s_waitcnt lgkmcnt(0){{$}}
|
|
|
|
; CHECK: s_waitcnt vmcnt(0){{$}}
|
|
|
|
; CHECK: s_waitcnt expcnt(0) lgkmcnt(0){{$}}
|
2014-08-06 00:29:43 +00:00
|
|
|
define void @main(<16 x i8> addrspace(2)* inreg %arg, <16 x i8> addrspace(2)* inreg %arg1, <32 x i8> addrspace(2)* inreg %arg2, <16 x i8> addrspace(2)* inreg %arg3, <16 x i8> addrspace(2)* inreg %arg4, i32 inreg %arg5, i32 %arg6, i32 %arg7, i32 %arg8, i32 %arg9, float addrspace(2)* inreg %constptr) #0 {
|
2013-10-13 17:56:28 +00:00
|
|
|
main_body:
|
2014-08-06 00:29:43 +00:00
|
|
|
%tmp = getelementptr <16 x i8> addrspace(2)* %arg3, i32 0
|
|
|
|
%tmp10 = load <16 x i8> addrspace(2)* %tmp, !tbaa !0
|
|
|
|
%tmp11 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp10, i32 0, i32 %arg6)
|
|
|
|
%tmp12 = extractelement <4 x float> %tmp11, i32 0
|
|
|
|
%tmp13 = extractelement <4 x float> %tmp11, i32 1
|
|
|
|
call void @llvm.AMDGPU.barrier.global() #1
|
|
|
|
%tmp14 = extractelement <4 x float> %tmp11, i32 2
|
|
|
|
; %tmp15 = extractelement <4 x float> %tmp11, i32 3
|
|
|
|
%tmp15 = load float addrspace(2)* %constptr, align 4 ; Force waiting for expcnt and lgkmcnt
|
|
|
|
%tmp16 = getelementptr <16 x i8> addrspace(2)* %arg3, i32 1
|
|
|
|
%tmp17 = load <16 x i8> addrspace(2)* %tmp16, !tbaa !0
|
|
|
|
%tmp18 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp17, i32 0, i32 %arg6)
|
|
|
|
%tmp19 = extractelement <4 x float> %tmp18, i32 0
|
|
|
|
%tmp20 = extractelement <4 x float> %tmp18, i32 1
|
|
|
|
%tmp21 = extractelement <4 x float> %tmp18, i32 2
|
|
|
|
%tmp22 = extractelement <4 x float> %tmp18, i32 3
|
|
|
|
call void @llvm.SI.export(i32 15, i32 0, i32 0, i32 32, i32 0, float %tmp19, float %tmp20, float %tmp21, float %tmp22)
|
|
|
|
call void @llvm.SI.export(i32 15, i32 0, i32 1, i32 12, i32 0, float %tmp12, float %tmp13, float %tmp14, float %tmp15)
|
2013-10-13 17:56:28 +00:00
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
2014-08-06 00:29:43 +00:00
|
|
|
; Function Attrs: noduplicate nounwind
|
|
|
|
declare void @llvm.AMDGPU.barrier.global() #1
|
|
|
|
|
2013-10-13 17:56:28 +00:00
|
|
|
; Function Attrs: nounwind readnone
|
2014-08-06 00:29:43 +00:00
|
|
|
declare <4 x float> @llvm.SI.vs.load.input(<16 x i8>, i32, i32) #2
|
2013-10-13 17:56:28 +00:00
|
|
|
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|
|
|
|
|
|
|
|
attributes #0 = { "ShaderType"="1" }
|
2014-08-06 00:29:43 +00:00
|
|
|
attributes #1 = { noduplicate nounwind }
|
|
|
|
attributes #2 = { nounwind readnone }
|
2013-10-13 17:56:28 +00:00
|
|
|
|
IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224257 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-15 19:07:53 +00:00
|
|
|
!0 = !{!1, !1, i64 0, i32 1}
|
|
|
|
!1 = !{!"const", null}
|