maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/NVPTX/surf-read-cuda.ll

54 lines
2.0 KiB
LLVM
Raw Normal View History

[NVPTX] Add more surface/texture intrinsics, including CUDA unified texture fetch This also uses TSFlags to mark machine instructions that are surface/texture accesses, as well as the vector width for surface operations. This is used to simplify some of the switch statements that need to detect surface/texture instructions llvm-svn: 213256
2014-07-17 19:59:04 +08:00
; 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 i32 @llvm.nvvm.suld.1d.i32.trap(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[[SURFREG:[0-9]+]], [foo_param_0];
; SM20: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFREG]], {%r{{[0-9]+}}}]
; SM30: ld.param.u64 %rd[[SURFREG:[0-9]+]], [foo_param_0];
; SM30: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFREG]], {%r{{[0-9]+}}}]
%val = tail call i32 @llvm.nvvm.suld.1d.i32.trap(i64 %img, i32 %idx)
; SM20: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
; SM30: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
%ret = sitofp i32 %val to float
[NVPTX] roll forward r239082 NVPTXISelDAGToDAG translates "addrspacecast to param" to NVPTX::nvvm_ptr_gen_to_param Added an llc test in bug21465. llvm-svn: 239100
2015-06-05 05:28:26 +08:00
; SM20: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
; SM30: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
[NVPTX] Add more surface/texture intrinsics, including CUDA unified texture fetch This also uses TSFlags to mark machine instructions that are surface/texture accesses, as well as the vector width for surface operations. This is used to simplify some of the switch statements that need to detect surface/texture instructions llvm-svn: 213256
2014-07-17 19:59:04 +08:00
store float %ret, float* %red
ret void
}
@surf0 = 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[[SURFHANDLE:[0-9]+]], surf0
%surfHandle = tail call i64 @llvm.nvvm.texsurf.handle.internal.p1i64(i64 addrspace(1)* @surf0)
; SM20: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [surf0, {%r{{[0-9]+}}}]
; SM30: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [%rd[[SURFHANDLE]], {%r{{[0-9]+}}}]
%val = tail call i32 @llvm.nvvm.suld.1d.i32.trap(i64 %surfHandle, i32 %idx)
; SM20: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
; SM30: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
%ret = sitofp i32 %val to float
[NVPTX] roll forward r239082 NVPTXISelDAGToDAG translates "addrspacecast to param" to NVPTX::nvvm_ptr_gen_to_param Added an llc test in bug21465. llvm-svn: 239100
2015-06-05 05:28:26 +08:00
; SM20: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
; SM30: st.global.f32 [%r{{[0-9]+}}], %f[[REDF]]
[NVPTX] Add more surface/texture intrinsics, including CUDA unified texture fetch This also uses TSFlags to mark machine instructions that are surface/texture accesses, as well as the vector width for surface operations. This is used to simplify some of the switch statements that need to detect surface/texture instructions llvm-svn: 213256
2014-07-17 19:59:04 +08:00
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
2014-12-16 03:07:53 +08:00
!1 = !{void (i64, float*, i32)* @foo, !"kernel", i32 1}
!2 = !{void (float*, i32)* @bar, !"kernel", i32 1}
!3 = !{i64 addrspace(1)* @surf0, !"surface", i32 1}
[NVPTX] Add more surface/texture intrinsics, including CUDA unified texture fetch This also uses TSFlags to mark machine instructions that are surface/texture accesses, as well as the vector width for surface operations. This is used to simplify some of the switch statements that need to detect surface/texture instructions llvm-svn: 213256
2014-07-17 19:59:04 +08:00