mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-29 13:29:28 +00:00
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
75 lines
2.6 KiB
LLVM
75 lines
2.6 KiB
LLVM
; RUN: opt < %s -O3 -S | FileCheck %s
|
|
|
|
; Make sure the call to syncthreads is not duplicate here by the LLVM
|
|
; optimizations, because it has the noduplicate attribute set.
|
|
|
|
; CHECK: call void @llvm.cuda.syncthreads
|
|
; CHECK-NOT: call void @llvm.cuda.syncthreads
|
|
|
|
; Function Attrs: nounwind
|
|
define void @foo(float* %output) #1 {
|
|
entry:
|
|
%output.addr = alloca float*, align 8
|
|
store float* %output, float** %output.addr, align 8
|
|
%0 = load float** %output.addr, align 8
|
|
%arrayidx = getelementptr inbounds float* %0, i64 0
|
|
%1 = load float* %arrayidx, align 4
|
|
%conv = fpext float %1 to double
|
|
%cmp = fcmp olt double %conv, 1.000000e+01
|
|
br i1 %cmp, label %if.then, label %if.else
|
|
|
|
if.then: ; preds = %entry
|
|
%2 = load float** %output.addr, align 8
|
|
%3 = load float* %2, align 4
|
|
%conv1 = fpext float %3 to double
|
|
%add = fadd double %conv1, 1.000000e+00
|
|
%conv2 = fptrunc double %add to float
|
|
store float %conv2, float* %2, align 4
|
|
br label %if.end
|
|
|
|
if.else: ; preds = %entry
|
|
%4 = load float** %output.addr, align 8
|
|
%5 = load float* %4, align 4
|
|
%conv3 = fpext float %5 to double
|
|
%add4 = fadd double %conv3, 2.000000e+00
|
|
%conv5 = fptrunc double %add4 to float
|
|
store float %conv5, float* %4, align 4
|
|
br label %if.end
|
|
|
|
if.end: ; preds = %if.else, %if.then
|
|
call void @llvm.cuda.syncthreads()
|
|
%6 = load float** %output.addr, align 8
|
|
%arrayidx6 = getelementptr inbounds float* %6, i64 0
|
|
%7 = load float* %arrayidx6, align 4
|
|
%conv7 = fpext float %7 to double
|
|
%cmp8 = fcmp olt double %conv7, 1.000000e+01
|
|
br i1 %cmp8, label %if.then9, label %if.else13
|
|
|
|
if.then9: ; preds = %if.end
|
|
%8 = load float** %output.addr, align 8
|
|
%9 = load float* %8, align 4
|
|
%conv10 = fpext float %9 to double
|
|
%add11 = fadd double %conv10, 3.000000e+00
|
|
%conv12 = fptrunc double %add11 to float
|
|
store float %conv12, float* %8, align 4
|
|
br label %if.end17
|
|
|
|
if.else13: ; preds = %if.end
|
|
%10 = load float** %output.addr, align 8
|
|
%11 = load float* %10, align 4
|
|
%conv14 = fpext float %11 to double
|
|
%add15 = fadd double %conv14, 4.000000e+00
|
|
%conv16 = fptrunc double %add15 to float
|
|
store float %conv16, float* %10, align 4
|
|
br label %if.end17
|
|
|
|
if.end17: ; preds = %if.else13, %if.then9
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: noduplicate nounwind
|
|
declare void @llvm.cuda.syncthreads() #2
|
|
|
|
!0 = !{void (float*)* @foo, !"kernel", i32 1}
|
|
!1 = !{null, !"align", i32 8}
|