mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 04:33:05 +00:00
1ef70ff39b
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
50 lines
2.4 KiB
LLVM
50 lines
2.4 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; The parallel loop has been invalidated by the new memory accesses introduced
|
|
; by reg2mem (Loop::isParallel() starts to return false). Ensure the loop is
|
|
; now non-vectorizable.
|
|
|
|
;CHECK-NOT: <4 x i32>
|
|
define void @parallel_loop(i32* nocapture %a, i32* nocapture %b) nounwind uwtable {
|
|
entry:
|
|
%indvars.iv.next.reg2mem = alloca i64
|
|
%indvars.iv.reg2mem = alloca i64
|
|
%"reg2mem alloca point" = bitcast i32 0 to i32
|
|
store i64 0, i64* %indvars.iv.reg2mem
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body.for.body_crit_edge, %entry
|
|
%indvars.iv.reload = load i64* %indvars.iv.reg2mem
|
|
%arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv.reload
|
|
%0 = load i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
|
|
%arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv.reload
|
|
%1 = load i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
|
|
%idxprom3 = sext i32 %1 to i64
|
|
%arrayidx4 = getelementptr inbounds i32* %a, i64 %idxprom3
|
|
store i32 %0, i32* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !3
|
|
%indvars.iv.next = add i64 %indvars.iv.reload, 1
|
|
; A new store without the parallel metadata here:
|
|
store i64 %indvars.iv.next, i64* %indvars.iv.next.reg2mem
|
|
%indvars.iv.next.reload1 = load i64* %indvars.iv.next.reg2mem
|
|
%arrayidx6 = getelementptr inbounds i32* %b, i64 %indvars.iv.next.reload1
|
|
%2 = load i32* %arrayidx6, align 4, !llvm.mem.parallel_loop_access !3
|
|
store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
|
|
%indvars.iv.next.reload = load i64* %indvars.iv.next.reg2mem
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next.reload to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 512
|
|
br i1 %exitcond, label %for.end, label %for.body.for.body_crit_edge, !llvm.loop !3
|
|
|
|
for.body.for.body_crit_edge: ; preds = %for.body
|
|
%indvars.iv.next.reload2 = load i64* %indvars.iv.next.reg2mem
|
|
store i64 %indvars.iv.next.reload2, i64* %indvars.iv.reg2mem
|
|
br label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
!3 = !{!3}
|