2014-07-17 13:59:04 +02:00
|
|
|
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
|
|
|
|
|
; RUN: llc < %s -march=nvptx -mcpu=sm_30 | FileCheck %s --check-prefix=SM30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
target triple = "nvptx-unknown-cuda"
|
|
|
|
|
|
|
|
|
|
declare { float, float, float, float } @llvm.nvvm.tex.unified.1d.v4f32.s32(i64, i32)
|
|
|
|
|
declare i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)*)
|
|
|
|
|
|
|
|
|
|
; SM20-LABEL: .entry foo
|
|
|
|
|
; SM30-LABEL: .entry foo
|
|
|
|
|
define void @foo(i64 %img, float* %red, i32 %idx) {
|
|
|
|
|
; SM20: ld.param.u64 %rd[[TEXREG:[0-9]+]], [foo_param_0];
|
|
|
|
|
; SM20: tex.1d.v4.f32.s32 {%f[[RED:[0-9]+]], %f[[GREEN:[0-9]+]], %f[[BLUE:[0-9]+]], %f[[ALPHA:[0-9]+]]}, [%rd[[TEXREG]], {%r{{[0-9]+}}}]
|
|
|
|
|
; SM30: ld.param.u64 %rd[[TEXREG:[0-9]+]], [foo_param_0];
|
|
|
|
|
; SM30: tex.1d.v4.f32.s32 {%f[[RED:[0-9]+]], %f[[GREEN:[0-9]+]], %f[[BLUE:[0-9]+]], %f[[ALPHA:[0-9]+]]}, [%rd[[TEXREG]], {%r{{[0-9]+}}}]
|
|
|
|
|
%val = tail call { float, float, float, float } @llvm.nvvm.tex.unified.1d.v4f32.s32(i64 %img, i32 %idx)
|
|
|
|
|
%ret = extractvalue { float, float, float, float } %val, 0
|
|
|
|
|
; SM20: st.f32 [%r{{[0-9]+}}], %f[[RED]]
|
|
|
|
|
; SM30: st.f32 [%r{{[0-9]+}}], %f[[RED]]
|
|
|
|
|
store float %ret, float* %red
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@tex0 = internal addrspace(1) global i64 0, align 8
|
|
|
|
|
|
|
|
|
|
; SM20-LABEL: .entry bar
|
|
|
|
|
; SM30-LABEL: .entry bar
|
|
|
|
|
define void @bar(float* %red, i32 %idx) {
|
|
|
|
|
; SM30: mov.u64 %rd[[TEXHANDLE:[0-9]+]], tex0
|
|
|
|
|
%texHandle = tail call i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)* @tex0)
|
|
|
|
|
; SM20: tex.1d.v4.f32.s32 {%f[[RED:[0-9]+]], %f[[GREEN:[0-9]+]], %f[[BLUE:[0-9]+]], %f[[ALPHA:[0-9]+]]}, [tex0, {%r{{[0-9]+}}}]
|
|
|
|
|
; SM30: tex.1d.v4.f32.s32 {%f[[RED:[0-9]+]], %f[[GREEN:[0-9]+]], %f[[BLUE:[0-9]+]], %f[[ALPHA:[0-9]+]]}, [%rd[[TEXHANDLE]], {%r{{[0-9]+}}}]
|
|
|
|
|
%val = tail call { float, float, float, float } @llvm.nvvm.tex.unified.1d.v4f32.s32(i64 %texHandle, i32 %idx)
|
|
|
|
|
%ret = extractvalue { float, float, float, float } %val, 0
|
|
|
|
|
; SM20: st.f32 [%r{{[0-9]+}}], %f[[RED]]
|
|
|
|
|
; SM30: st.f32 [%r{{[0-9]+}}], %f[[RED]]
|
|
|
|
|
store float %ret, float* %red
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
!nvvm.annotations = !{!1, !2, !3}
|
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.
llvm-svn: 224257
2014-12-15 20:07:53 +01:00
|
|
|
!1 = !{void (i64, float*, i32)* @foo, !"kernel", i32 1}
|
|
|
|
|
!2 = !{void (float*, i32)* @bar, !"kernel", i32 1}
|
|
|
|
|
!3 = !{i64 addrspace(1)* @tex0, !"texture", i32 1}
|
