mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
1ed64614d6
Summary: NVPTXGenericToNVVM was using target-specific intrinsics to do address space casts. Using the addrspacecast instruction is (a lot) simpler. But it also has the advantage of being understandable to other passes. In particular, InferAddrSpaces is able to understand these address space casts and remove them in most cases. Reviewers: tra Subscribers: jholewinski, sanjoy, hiraditya, llvm-commits Differential Revision: https://reviews.llvm.org/D43914 llvm-svn: 326389
64 lines
2.8 KiB
LLVM
64 lines
2.8 KiB
LLVM
; Verify functionality of NVPTXGenericToNVVM.cpp pass.
|
|
;
|
|
; RUN: opt < %s -march nvptx64 -S -generic-to-nvvm | FileCheck %s
|
|
|
|
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
; Generic space variables should be converted to global space AKA addrspace(1).
|
|
; CHECK-DAG: @static_var = {{.*}}addrspace(1)
|
|
@static_var = externally_initialized global i8 0, align 1, !dbg !4
|
|
; CHECK-DAG: @.str = {{.*}}addrspace(1)
|
|
@.str = private unnamed_addr constant [4 x i8] c"XXX\00", align 1
|
|
|
|
; Function Attrs: convergent
|
|
define void @func() !dbg !8 {
|
|
;CHECK-LABEL: @func()
|
|
;CHECK-SAME: !dbg [[FUNCNODE:![0-9]+]]
|
|
entry:
|
|
; References to the variables must be converted back to generic address space.
|
|
; CHECK-DAG: addrspacecast ([4 x i8] addrspace(1)* @.str to [4 x i8]*)
|
|
%0 = load i8, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), align 1
|
|
call void @extfunc(i8 signext %0)
|
|
; CHECK-DAG: addrspacecast (i8 addrspace(1)* @static_var to i8*)
|
|
%1 = load i8, i8* @static_var, align 1
|
|
call void @extfunc(i8 signext %1)
|
|
ret void
|
|
; CHECK: ret void
|
|
}
|
|
|
|
declare void @extfunc(i8 signext)
|
|
|
|
!llvm.dbg.cu = !{!0}
|
|
; CHECK: !llvm.dbg.cu = !{[[CUNODE:![0-9]+]]}
|
|
!llvm.module.flags = !{!6, !7}
|
|
|
|
!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1,
|
|
producer: "clang version 4.0.0",
|
|
isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, globals: !3)
|
|
; CHECK: [[CUNODE]] = distinct !DICompileUnit({{.*}} globals: [[GLOBALSNODE:![0-9]+]]
|
|
!1 = !DIFile(filename: "foo.cu", directory: "/usr/local/google/home/tra/work/llvm/build/gpu/debug")
|
|
!2 = !{}
|
|
!3 = !{!4}
|
|
; Find list of global variables and make sure it's the one used by DICompileUnit
|
|
; CHECK: [[GLOBALSNODE]] = !{[[GVNODE:![0-9]+]]}
|
|
!4 = !DIGlobalVariableExpression(var: !DIGlobalVariable(name: "static_var", scope: !0, file: !1, line: 2, type: !5, isLocal: false, isDefinition: true), expr: !DIExpression())
|
|
; Debug info must also be updated to reflect new address space.
|
|
; CHECK: [[GVNODE]] = !DIGlobalVariableExpression(var: [[GVVAR:.*]], expr: !DIExpression())
|
|
; CHECK: [[GVVAR]] = !DIGlobalVariable(name: "static_var"
|
|
; CHECK-SAME: scope: [[CUNODE]]
|
|
; CHECK-SAME: type: [[TYPENODE:![0-9]+]]
|
|
!5 = !DIBasicType(name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char)
|
|
; CHECK: [[TYPENODE]] = !DIBasicType(name: "char"
|
|
!6 = !{i32 2, !"Dwarf Version", i32 4}
|
|
!7 = !{i32 2, !"Debug Info Version", i32 3}
|
|
!8 = distinct !DISubprogram(name: "foo", linkageName: "func",
|
|
scope: !1, file: !1, line: 3, type: !9, isLocal: false, isDefinition: true, scopeLine: 3,
|
|
flags: DIFlagPrototyped, isOptimized: false, unit: !0, variables: !2)
|
|
; CHECK: [[FUNCNODE]] = distinct !DISubprogram(name: "foo",
|
|
; CHECK-SAME: type: [[STYPENODE:![0-9]+]]
|
|
; CHECK-SAME: unit: [[CUNODE]],
|
|
!9 = !DISubroutineType(types: !10)
|
|
; CHECK: [[STYPENODE]] = !DISubroutineType
|
|
!10 = !{null}
|